CN118213938B - Power supply safety power supply protection method and system based on artificial intelligence - Google Patents
Power supply safety power supply protection method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN118213938B CN118213938B CN202410437435.6A CN202410437435A CN118213938B CN 118213938 B CN118213938 B CN 118213938B CN 202410437435 A CN202410437435 A CN 202410437435A CN 118213938 B CN118213938 B CN 118213938B
- Authority
- CN
- China
- Prior art keywords
- power supply
- electric equipment
- voltage
- power
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 15
- 230000005611 electricity Effects 0.000 claims abstract description 128
- 230000005856 abnormality Effects 0.000 claims abstract description 93
- 230000002159 abnormal effect Effects 0.000 claims abstract description 53
- 238000012544 monitoring process Methods 0.000 claims abstract description 43
- 230000000087 stabilizing effect Effects 0.000 claims abstract description 27
- 238000001514 detection method Methods 0.000 claims description 28
- 238000012545 processing Methods 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 15
- 238000009825 accumulation Methods 0.000 claims description 8
- 238000004146 energy storage Methods 0.000 claims description 2
- 238000006243 chemical reaction Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000009792 diffusion process Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013213 extrapolation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
- H02H3/00—Emergency protective circuit arrangements for automatic disconnection directly responsive to an undesired change from normal electric working condition with or without subsequent reconnection ; integrated protection
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
- H02H1/00—Details of emergency protective circuit arrangements
- H02H1/0007—Details of emergency protective circuit arrangements concerning the detecting means
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
- H02H1/00—Details of emergency protective circuit arrangements
- H02H1/0092—Details of emergency protective circuit arrangements concerning the data processing means, e.g. expert systems, neural networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
- H02H3/00—Emergency protective circuit arrangements for automatic disconnection directly responsive to an undesired change from normal electric working condition with or without subsequent reconnection ; integrated protection
- H02H3/02—Details
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02H—EMERGENCY PROTECTIVE CIRCUIT ARRANGEMENTS
- H02H3/00—Emergency protective circuit arrangements for automatic disconnection directly responsive to an undesired change from normal electric working condition with or without subsequent reconnection ; integrated protection
- H02H3/02—Details
- H02H3/05—Details with means for increasing reliability, e.g. redundancy arrangements
Landscapes
- Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Measurement Of Current Or Voltage (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a power supply safety power supply protection method and system based on artificial intelligence, and relates to the technical field of circuit protection. The method comprises the following steps: detecting a power supply voltage and a power consumption current; determining a supply voltage stability score; under the condition that the stability score of the power supply voltage is lower than the stability threshold value, a first switch between a power supply line and a power grid is controlled to be opened, and a second switch between the power grid and a voltage stabilizing inverter is controlled to be closed; determining the power utilization mode of each electric equipment; determining the power consumption abnormality identification result of each electric equipment through the power consumption abnormality monitoring model; switching off a third switch corresponding to the electric equipment with the abnormal electricity consumption identification result; determining that the electricity utilization abnormality recognition result is a first number of electric equipment with abnormal electricity utilization; and under the condition that the first quantity meets the preset quantity condition, the first switch and the second switch are opened. According to the invention, the abnormal state of the electric equipment can be accurately identified by combining the electric mode of the electric equipment.
Description
Technical Field
The invention relates to the technical field of circuit protection, in particular to a power supply safety power supply protection method and system based on artificial intelligence.
Background
In the related art, CN113572126a discloses an overcurrent protection method, an overcurrent protection device and a power supply circuit, when receiving an overcurrent signal which characterizes that the output current of the overcurrent protection device exceeds the OCP value and is sent by a DC-DC conversion module, the overcurrent protection device does not immediately control the DC-DC conversion module to stop working, but controls the protection module to disconnect, the external equipment to disconnect, so that the on-board circuit is not powered off, then keeps outputting a first enabling signal to the DC-DC conversion module in a third preset time period which is longer than a first preset time period, and judges whether the overcurrent signal sent by the DC-DC conversion module is received again after the first preset time period, if yes, the on-board circuit part is indicated to have overcurrent, and then the on-board circuit is controlled to be powered off, and the on-board circuit is stopped; if not, the control protection module is kept to be disconnected, and power is continuously supplied to the on-board circuit. The scheme solves the problem that the capacitive extrapolation equipment is connected to easily cause the circuit on the board to be powered off, and improves the power supply reliability of the circuit on the board.
CN110994548a provides a protection circuit, a power supply device and a switching power supply protection method, the protection circuit includes: the device comprises a determining unit, a processing unit and an overload protection unit; the determining unit is connected with the switching power supply; the processing unit is respectively connected with the determining unit and the overload protection unit; the determining unit is used for determining a voltage value and a current value of the switching power supply and sending the voltage value and the current value to the processing unit; the processing unit is used for judging whether the switching voltage meets the following conditions: the voltage value is in a preset standard voltage range, the current value is in a preset standard current range, and if not, the overload protection unit is triggered; and the overload protection unit is used for stopping power supply to the electric equipment under the triggering of the processing unit. The method can form overload protection for the switching power supply.
Therefore, in the related art, the protection mode is triggered by the abnormal current and voltage, however, it is difficult to identify the abnormal power consumption when the power consumption modes of the electric devices are different, and thus it is difficult to better protect the power supply system.
The information disclosed in the background section of the application is only for enhancement of understanding of the general background of the application and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.
Disclosure of Invention
The invention provides a power supply safety power supply protection method and system based on artificial intelligence, which can solve the technical problem that the power utilization abnormality is difficult to identify under the condition that the power utilization modes of electric equipment are different.
According to a first aspect of the present invention, there is provided an artificial intelligence-based power supply safety protection method, comprising:
Detecting power supply voltages of a power supply line at a plurality of moments through a first detection device, and detecting power utilization currents of a plurality of electric equipment at a plurality of moments through a plurality of second detection devices;
Determining a power supply voltage stability score through power supply voltages at a plurality of moments in a first preset time period before a current moment, wherein the current moment is the last moment in the first preset time period;
Under the condition that the stability score of the power supply voltage is lower than a stability threshold value, a first switch between a power supply line and a power grid is controlled to be opened, and a second switch between the power grid and a voltage stabilizing inverter is controlled to be closed, wherein the input end of the voltage stabilizing inverter is connected with the second switch, and the output end of the voltage stabilizing inverter is connected with the power supply line;
Determining the power utilization mode of each electric device through the power utilization currents of a plurality of moments in a second preset time period before the current moment of each electric device, wherein the current moment is the last moment in the second preset time period;
processing the power consumption modes of the electric equipment and the power consumption currents at a plurality of moments in a second preset time period through the trained power consumption abnormality monitoring model, and determining power consumption abnormality identification results of the electric equipment;
Disconnecting a third switch corresponding to electric equipment with abnormal electricity consumption identification result, wherein the third switch is positioned between the electric equipment and the power supply line;
determining that the electricity utilization abnormality recognition result is a first number of electric equipment with abnormal electricity utilization;
And under the condition that the first number meets the preset number condition, the first switch and the second switch are disconnected.
According to a second aspect of the present invention, there is provided an artificial intelligence based power supply safety protection system comprising: the device comprises a first detection device, a plurality of second detection devices, a first switch, a second switch, a third switch, a voltage stabilizing inverter and a controller;
The first detection device is used for detecting the power supply voltage of the power supply circuit at a plurality of moments, and the second detection devices are used for detecting the power utilization currents of the electric equipment at a plurality of moments;
the controller is used for:
Determining a power supply voltage stability score through power supply voltages at a plurality of moments in a first preset time period before a current moment, wherein the current moment is the last moment in the first preset time period;
Under the condition that the stability score of the power supply voltage is lower than a stability threshold value, a first switch between a power supply line and a power grid is controlled to be opened, and a second switch between the power grid and a voltage stabilizing inverter is controlled to be closed, wherein the input end of the voltage stabilizing inverter is connected with the second switch, and the output end of the voltage stabilizing inverter is connected with the power supply line;
Determining the power utilization mode of each electric device through the power utilization currents of a plurality of moments in a second preset time period before the current moment of each electric device, wherein the current moment is the last moment in the second preset time period;
processing the power consumption modes of the electric equipment and the power consumption currents at a plurality of moments in a second preset time period through the trained power consumption abnormality monitoring model, and determining power consumption abnormality identification results of the electric equipment;
Disconnecting a third switch corresponding to electric equipment with abnormal electricity consumption identification result, wherein the third switch is positioned between the electric equipment and the power supply line;
determining that the electricity utilization abnormality recognition result is a first number of electric equipment with abnormal electricity utilization;
And under the condition that the first number meets the preset number condition, the first switch and the second switch are disconnected.
The technical effects are as follows: according to the invention, the power supply voltage of the power supply line and the power utilization currents of the electric equipment can be monitored in real time through the first detection device and the second detection device, so that potential problems can be found in time. And judging the stability of the power supply line by scoring the stability of the power supply voltage, and opening the first switch and closing the second switch when the stability of the power supply voltage is lower than a stability threshold. The trained power consumption abnormality monitoring model is used, and the abnormal state of each identified power consumption device can be accurately identified by combining the power consumption modes of the power consumption devices, so that the third switch is automatically disconnected according to the power consumption abnormality identification result, and potential safety risks are prevented. When the first quantity is determined to meet the preset quantity condition, the first switch and the second switch are disconnected, abnormal diffusion and chain reaction are reduced, and stability and safety of the whole power supply system are improved. When determining whether the power supply voltage is stable, the voltage error score can be determined through absolute accumulated errors, so that the error between the actual power supply voltage and the rated voltage can be objectively and accurately expressed, whether the voltage is abnormal due to voltage change can be judged through the magnitude relation between the prediction error and the actual error, and further the moment when the voltage change rate is abnormal can be accurately determined, and the voltage change score can accurately describe the abnormality of the voltage change rate. In the process of training the electricity consumption abnormality monitoring model, errors between a sample electricity consumption mode prediction result and an actual electricity consumption mode can be determined, and a loss function under specific conditions is selected based on the magnitude of the errors, so that the training process using the loss function is more targeted and efficient, the loss function is reduced in the training process, and the accuracy of the electricity consumption abnormality monitoring model is improved more targeted.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention as claimed. Other features and aspects of the present invention will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
In order to more clearly illustrate the embodiments of the invention or the solutions of the prior art, the drawings which are necessary for the description of the embodiments or the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other embodiments may be obtained from these drawings without inventive effort to a person skilled in the art,
FIG. 1 schematically illustrates a flow diagram of an artificial intelligence based power supply security power protection method in accordance with an embodiment of the invention;
FIG. 2 schematically illustrates a block diagram of an artificial intelligence based power safety power protection system in accordance with an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The technical scheme of the invention is described in detail below by specific examples. The following embodiments may be combined with each other, and some embodiments may not be repeated for the same or similar concepts or processes.
FIG. 1 schematically illustrates a flow diagram of an artificial intelligence based power supply safety power protection method according to an embodiment of the invention, the method comprising:
step S101, detecting power supply voltages of a power supply line at a plurality of moments through a first detection device, and detecting power utilization currents of a plurality of electric equipment at a plurality of moments through a plurality of second detection devices;
Step S102, determining a power supply voltage stability score through power supply voltages at a plurality of moments in a first preset time period before a current moment, wherein the current moment is the last moment in the first preset time period;
Step S103, under the condition that the stability score of the power supply voltage is lower than a stability threshold value, a first switch between a power supply line and a power grid is controlled to be opened, and a second switch between the power grid and a voltage stabilizing inverter is controlled to be closed, wherein the input end of the voltage stabilizing inverter is connected with the second switch, and the output end of the voltage stabilizing inverter is connected with the power supply line;
step S104, determining the power consumption mode of each electric device through the power consumption currents of a plurality of moments in a second preset time period before the current moment of each electric device, wherein the current moment is the last moment in the second preset time period;
Step S105, the power consumption mode of each electric equipment and the power consumption currents at a plurality of moments in a second preset time period are processed through the trained power consumption abnormality monitoring model, and power consumption abnormality identification results of each electric equipment are determined;
Step S106, a third switch corresponding to the electric equipment with abnormal electricity consumption identification result is disconnected, wherein the third switch is positioned between the electric equipment and the power supply line;
step S107, determining that the power utilization abnormality recognition result is a first number of electric equipment with abnormal power utilization;
Step S108, when the first number meets a preset number condition, turning off the first switch and the second switch.
According to the power supply safety power supply protection method based on artificial intelligence, provided by the embodiment of the invention, through the first detection device and the second detection device, the power supply voltage of the power supply circuit and the power utilization currents of a plurality of electric equipment can be monitored in real time, so that potential problems can be found in time. And judging the stability of the power supply line by scoring the stability of the power supply voltage, and opening the first switch and closing the second switch when the stability of the power supply voltage is lower than a stability threshold. The trained power consumption abnormality monitoring model is used, and the abnormal state of each identified power consumption device can be accurately identified by combining the power consumption modes of the power consumption devices, so that the third switch is automatically disconnected according to the power consumption abnormality identification result, and potential safety risks are prevented. When the first quantity is determined to meet the preset quantity condition, the first switch and the second switch are disconnected, abnormal diffusion and chain reaction are reduced, and stability and safety of the whole power supply system are improved.
According to an embodiment of the present invention, in step S101, the interval between adjacent moments may be set to 1 minute, 2 minutes, etc., to which the present invention is not limited. The first detection device is used for detecting the power supply line, so that the power supply voltage data of the power supply line at a plurality of moments can be obtained. The first detection device may be a voltage measuring instrument or a sensor, for example a voltmeter, which is capable of measuring the voltage level of the mains supply line at a plurality of moments. And the power utilization currents of the electric equipment are monitored by using a plurality of second detection devices, and the power supply voltages of the power supply lines to the electric equipment are equal to the power supply voltages, so that the power of the electric equipment can be determined by detecting the power utilization currents of the electric equipment. The second detection device may be a sensor or a current measuring device, for example an ammeter, mounted on a different consumer.
According to an embodiment of the present invention, in step S102, the first preset time period may be set to 15 minutes, 30 minutes, etc., which the present invention is not limited to. In this step, the current time is defined as the last time within the first preset time period. And evaluating the stability of the power supply voltage by using the power supply voltage data of a plurality of moments in a first preset time period before the current moment. The supply voltage stability score represents the stability level of the supply voltage.
According to one embodiment of the present invention, step S102 includes: fitting power supply voltages at a plurality of moments in a first preset time period before the current moment to obtain a power supply voltage fitting function; determining the rated voltage of a power supply line of a power supply; obtaining a voltage error score according to the power supply voltage fitting function and the rated voltage; deriving the fitting function of the power supply voltage to obtain a variation function of the power supply voltage; determining voltage change rates at a plurality of moments in the first preset time period according to the power supply voltage change function; determining a voltage change score according to the voltage change rates at a plurality of moments in the first preset time period; and determining a power supply voltage stability score according to the voltage variation score and the voltage error score.
According to one embodiment of the present invention, by fitting power supply voltage data at a plurality of times within a first preset time period before a current time, a power supply voltage fitting function is obtained, and a variation trend of the power supply voltage can be described. The rated voltage of the power supply line can be used as a reference value. And the voltage error score is used for measuring the deviation between the power supply voltage and the rated voltage. And deriving a power supply voltage fitting function to obtain a power supply voltage change function, thereby determining the voltage change rates at a plurality of moments in a first preset time period. And the voltage change score is used for evaluating the change condition of the voltage. And determining a power supply voltage stability score by comprehensively considering deviation and variation conditions of the power supply voltage according to the voltage error score and the voltage variation score. The larger the voltage error score and the voltage variation score, the more unstable the supply voltage, i.e. the lower the supply voltage stability score. The smaller the voltage error score and the voltage variation score, the more stable the supply voltage, i.e. the higher the supply voltage stability score. The supply voltage stability score may reflect the degree of stability of the supply voltage.
According to one embodiment of the invention, obtaining a voltage error score from the supply voltage fitting function and the nominal voltage comprises: subtracting the rated voltage from the power supply voltage fitting function to obtain a power supply voltage error function; determining an absolute value of a supply voltage error function as the supply voltage absolute error function; integrating the absolute error function of the power supply voltage in the first preset time period to obtain an absolute error accumulated value; integrating the rated voltage in the first preset time period to obtain a rated voltage accumulation value; determining a ratio of the absolute error accumulation value to the rated voltage accumulation value as a voltage relative error value; and determining the voltage error score according to the voltage relative error value.
According to one embodiment of the invention, the supply voltage error function describes the difference between the actual supply voltage and the nominal voltage. The absolute value of the power supply voltage error function is taken to obtain the absolute error function of the power supply voltage, so that the underestimation of the error between the power supply voltage fitting function and the rated voltage caused by the offset of the positive and negative errors can be avoided. The cumulative value of the absolute error represents the overall magnitude of the absolute error over a first predetermined period of time, and may be obtained by integrating the supply voltage absolute error function over the first predetermined period of time. The rated voltage is a fixed value, which is integrated over a first preset time period, i.e., the rated voltage is multiplied by the duration of the first preset time period to obtain a rated voltage integrated value. The ratio of the absolute error accumulation value to the rated voltage accumulation value is a relative error value of the voltage, which represents the relative error degree between the actual voltage and the rated voltage, and can be used as a voltage error score. The smaller the voltage relative error value, the smaller the voltage error score.
According to one embodiment of the present invention, determining a voltage variation score according to the voltage variation rates at a plurality of moments within the first preset time period includes: for the ith moment in the first preset time period, determining a power supply voltage predicted value of the (i+1) th moment according to the power supply voltage of the ith moment, the voltage change rate of the ith moment and the time interval between adjacent moments; if i is not equal to n, determining a prediction error between the power supply voltage predicted value at the (i+1) th moment and the rated voltage and an actual error between the power supply voltage at the (i+1) th moment and the rated voltage, wherein n is the number of moments in a first preset time period, the n-th moment in the first preset time period is the current moment, i is not more than n, and both i and n are positive integers; if the prediction error is smaller than or equal to the actual error, determining the ith moment as an abnormal moment of the voltage change rate; if i=n, determining a prediction error between the power supply voltage predicted value at the (i+1) th moment and the rated voltage, and determining the (i) th moment as a voltage change rate abnormal moment under the condition that the prediction error is greater than or equal to a preset prediction error threshold value; counting a second number of abnormal moments of the voltage change rate; and determining the voltage change score according to the second quantity and the moment quantity in the first preset time period.
According to one embodiment of the invention, the predicted value of the supply voltage at the i+1th time is the voltage change rate at the i time multiplied by the time interval between adjacent times plus the supply voltage at the i time. If i is not equal to n (i.e. not the last moment), a prediction error and an actual error can be calculated, wherein the prediction error is the error between the predicted value of the power supply voltage at the (i+1) th moment and the rated voltage, and the actual error is the error between the actually measured power supply voltage at the (i+1) th moment and the rated voltage. If the prediction error is less than or equal to the actual error, i.e., the actual voltage change rate is greater than the voltage change rate at the i-th time in the period from the i-th time to the i+1th time, i.e., the actual voltage change rate exceeds the expectation, the voltage change rate at the i-th time is a part of the actual error, and the i-th time is determined as the voltage change rate abnormality time. If the prediction error is larger than the actual error, it means that the actual error is smaller, and that the voltage change rate at the i-th time is not caused by the larger prediction error, in other words, the smaller actual error is not caused by the voltage change rate at the i-th time but by the smaller voltage change rate in the period from the i-th time to the i+1th time, and therefore, the i-th time is not determined as the abnormal voltage change rate time. If i is equal to n (i.e., the last time), and at the moment, there is no actual error of the (i+1) th time, and when the prediction error is greater than or equal to a preset prediction error threshold, determining the (i) th time as an abnormal time of the voltage change rate. And determining a voltage change score according to the ratio of the second quantity of abnormal moments of the voltage change rate to the quantity of moments in the first preset time period. The score can evaluate whether the voltage change in the power supply system is severe or not, and whether the duty ratio of the moment of voltage instability is high or not, and if the voltage change score is high, the voltage stability is low.
By the method, the voltage error score can be determined through the absolute accumulated error, so that the error between the actual power supply voltage and the rated voltage is objectively and accurately expressed, whether the voltage variation causes the voltage to be abnormal or not can be judged through the magnitude relation between the prediction error and the actual error, the moment when the voltage variation rate is abnormal is accurately determined, and the voltage variation score can accurately describe the abnormality of the voltage variation rate.
According to one embodiment of the present invention, the above voltage variation score and the voltage error score are combined to determine the power supply voltage stability score, for example, a weighted average of 1 minus the voltage variation score and the voltage error score may be used to obtain the power supply voltage stability score, and the higher the voltage variation score and the voltage error score, the worse the stability of the power supply voltage and the lower the power supply voltage stability score.
According to one embodiment of the invention, in step S103, it is determined whether the stability threshold is lower or not based on the supply voltage stability score. If the score is below the stability threshold, an insufficient stability of the supply voltage is indicated. At this time, the first switch between the power supply line and the power grid is controlled to be turned off. The connection between the power supply line and the power grid is cut off, so that unstable voltage is prevented from being used for supplying power to the electric equipment, and the damage probability of the electric equipment is reduced. And meanwhile, a second switch between the power grid and the voltage stabilizing inverter is controlled to be closed. The input end of the voltage stabilizing inverter is connected to the power grid, the output end of the voltage stabilizing inverter is connected to the power supply line, so that the power supply line stably operates, namely, the electric equipment is powered after the voltage stabilizing process of the voltage stabilizing inverter.
According to an embodiment of the present invention, in step S104, the second preset time period may be set to 15 minutes, 30 minutes, etc., which the present invention is not limited to. In this step, the current time is defined as the last time within the second preset time period. And determining the power utilization mode of each electric equipment at the current moment by using the power utilization current data of a plurality of moments in a second preset time period before the current moment. The power consumption mode may relate to information on the working states of different electric equipment, change rules of current and the like.
According to one embodiment of the present invention, step S104 includes: respectively carrying out data fitting on electricity utilization currents of the j-th electric equipment at a plurality of moments in the second preset time period to obtain an electricity utilization current function of the j-th electric equipment, wherein j is a positive integer; acquiring current errors between electricity utilization currents of the jth electric equipment at a plurality of moments and function values of the electricity utilization current function at a plurality of moments; determining an absolute value of the current error as an absolute current error; summing the absolute current errors at a plurality of moments to obtain an absolute accumulated error; and if the absolute accumulated error is smaller than or equal to a preset absolute error threshold value, and the absolute value of the slope of the electricity consumption current function is larger than or equal to a preset slope threshold value, determining the electricity consumption mode of the j-th electricity consumption device as a charging mode, otherwise, determining the electricity consumption mode of the j-th electricity consumption device as a power consumption mode, wherein the charging mode is the electricity consumption mode when the energy storage device is charged, and the power consumption mode is the electricity consumption mode when the electricity consumption device is operated.
According to one embodiment of the invention, the power consumption current function of each electric equipment is obtained by performing data fitting through the power consumption current data at a plurality of moments in the second preset time period. The function may describe the power usage of the device at different points in time. And calculating the current error between the actual electricity utilization current of the j-th electric equipment at a plurality of moments and the function value calculated by the electricity utilization current function at the corresponding moment. The absolute value of the error is the absolute current error. And summing the absolute current errors at a plurality of moments to obtain an absolute accumulated error. The absolute accumulated error represents the accumulated condition of the overall error. In the charging mode, the change of the current is linear or uniformly reduced according to other rules, namely, the power consumption current is gradually changed, so that the error between the power consumption current of the electric equipment in the charging mode and the power consumption current function obtained by fitting is smaller, namely, the absolute accumulated error is smaller than or equal to a preset absolute error threshold value, the absolute value of the slope of the power consumption current function is larger than or equal to a set slope threshold value, namely, the falling speed of the power consumption current is larger than or equal to the set slope threshold value, the power consumption current shows the falling trend along with the time and is not a stable and unchanged current, and if the two conditions are met simultaneously, the power consumption mode of the j electric equipment is determined to be the charging mode.
Conversely, the fitted current function may be a straight line with a low absolute value of slope, in which case the consumer may be in standby. Or when the electric equipment is not in a standby state, the randomness of the electric current value is strong, and the error between the electric current value and the electric current function (for example, a primary function) obtained by fitting is large, so that the phenomenon that the absolute accumulated error is larger than a preset absolute error threshold value can occur. If the electricity consumption current does not simultaneously meet that the absolute accumulated error is smaller than or equal to a preset absolute error threshold value and the absolute value of the slope of the electricity consumption current function is larger than or equal to a preset slope threshold value, the electricity consumption mode of the j-th electric equipment can be determined to be the electricity consumption mode.
According to an embodiment of the present invention, in step S105, the electricity consumption abnormality monitoring model is a neural network model, and the electricity consumption modes of the electric devices are learned by analyzing historical electricity consumption data, so as to identify whether the electric devices are abnormal. Real-time electricity current data of the electric equipment at a plurality of moments in a second preset time period can be input into the model for processing. Based on the processing of the electricity consumption mode and the processing of the electricity consumption current in the second preset time period, the electricity consumption abnormality monitoring model can conduct abnormality identification on each electric equipment. For example, if a device is in a particular power mode, its power current differs significantly from the current in that power mode, this indicates that the device may be faulty or abnormal.
According to one embodiment of the present invention, step S105 includes: inputting the electricity consumption current of each electric equipment at a plurality of moments in a second preset time period into a coding sub-model of the electricity consumption abnormality monitoring model to obtain coding information of each electric equipment; decoding the coding information of each electric equipment through the electric mode decoding sub-model to obtain an electric mode prediction result of each electric equipment; determining the correct rate of the electricity consumption mode prediction result according to the electricity consumption mode prediction result of each electric device and the electricity consumption mode of each electric device; and under the condition that the accuracy is higher than a preset accuracy threshold, inputting the electricity consumption mode of each electric equipment and the coding information of each electric equipment into an anomaly identification decoding sub-model to obtain an electricity consumption anomaly identification result of each electric equipment.
According to one embodiment of the invention, the data of the electricity consumption currents of the electric devices at a plurality of moments in the second preset time period are processed, for example, the data of the plurality of electricity consumption currents of each electric device can form vectors corresponding to each electric device, and the vectors corresponding to the plurality of electric devices can form input quantities in a matrix form so as to input the coding submodel of the electricity consumption abnormality monitoring model for processing. The coding submodel is used for converting the electricity current data in a matrix form into coding information for subsequent processing. And decoding the coding information of each electric equipment through the electric mode decoding submodel, so as to predict the electric mode of each equipment, namely, the prediction result of the electric mode. And calculating the accuracy of the prediction result according to the prediction result of the power consumption mode and the known power consumption mode. When the accuracy is low, the current power consumption abnormality monitoring model is larger in error and needs to be trained continuously. When the accuracy is higher than a preset accuracy threshold, the power consumption mode of each electric equipment and corresponding coding information are input into an anomaly identification decoding sub-model to analyze the information, and whether the electric equipment has an anomaly condition or not is identified, so that a power consumption anomaly identification result of the electric equipment is obtained. Therefore, whether the electricity consumption abnormality monitoring model is suitable for abnormality identification of the electric equipment at the current moment can be judged through the electricity consumption mode prediction result, and if not, the electricity consumption abnormality monitoring model can be continuously trained, so that the accuracy of the electricity consumption abnormality monitoring model is improved. And then, an abnormality identification decoding sub-model of the electricity consumption abnormality monitoring model with higher accuracy can be used for processing the electricity consumption mode of each electric equipment and the coding information of each electric equipment, so that the electricity consumption abnormality identification result of each electric equipment is determined.
According to one embodiment of the present invention, the training step of the electricity consumption abnormality monitoring model includes: sample coding information of each electric equipment is obtained through a coding sub-model of a sample electricity consumption current input electricity consumption abnormality monitoring model of a plurality of electric equipment at a plurality of moments in a historical time period; decoding sample coding information of each electric equipment through the electric mode decoding sub-model to obtain a sample electric mode prediction result of each electric equipment; inputting the sample electricity consumption mode prediction result and the sample coding information into an anomaly identification decoding sub-model to obtain sample electricity consumption anomaly identification results of all electric equipment; obtaining a loss function of an electricity consumption abnormality monitoring model according to the sample electricity consumption mode prediction result, the sample electricity consumption abnormality identification result, the actual abnormal state of each electric equipment and the actual electricity consumption mode of each electric equipment; and training the electricity consumption abnormality monitoring model according to the loss function to obtain the trained electricity consumption abnormality monitoring model.
According to one embodiment of the invention, the loss function of the electricity consumption abnormality monitoring model is used for measuring the difference between the model prediction result and the actual situation, and is a key index of the training model. In the training process, the loss function is counter-propagated, the model parameters are adjusted, and the loss function is minimized, so that the accuracy of the power consumption abnormality monitoring model is improved, and the trained power consumption abnormality monitoring model is obtained.
According to one embodiment of the present invention, obtaining a loss function of an electricity consumption abnormality monitoring model according to the sample electricity consumption mode prediction result, the sample electricity consumption abnormality identification result, the actual abnormal state of each electric device, and the actual electricity consumption mode of each electric device includes: obtaining a loss function L of the electricity consumption abnormality monitoring model according to a formula (1),
（1）；
Wherein,For the probability that the power usage pattern of the kth power consumer is the charging pattern determined based on the actual power usage pattern of the kth power consumer,For the probability that the power mode of the kth power consumer is the charging mode determined based on the sample power mode prediction result of the kth power consumer,For the probability of the power consumption abnormality of the kth power consumption device determined based on the actual abnormal state of the kth power consumption device,For the probability of the electricity utilization abnormality of the kth electric equipment determined based on the sample electricity utilization abnormality identification result of the kth electric equipment, N is the number of the electric equipment, k is less than or equal to N, and k and N are both positive integers,、AndIn order to set the weight of the weight in the preset,。
According to one embodiment of the present invention, in the formula (1), the sample power consumption mode prediction result may be a result in a probability form, for example, may represent a probability that the power consumption mode of the electric device is the charging mode, and the actual power consumption mode may also be a result in a probability form, for example, when the power consumption mode is the charging mode, the actual power consumption mode is 1, otherwise is 0. Similarly, the sample power consumption abnormality identification result may be a probability type result, for example, the sample power consumption abnormality identification result is a probability of power consumption abnormality of the electric equipment, and the actual abnormal state of the electric equipment may also be a probability type result, for example, when the power consumption is abnormal, the actual abnormal state is 1, otherwise, is 0.
In accordance with one embodiment of the present invention,Representing a cross entropy loss function for power mode prediction.Representing a cross entropy loss function for electrical anomaly identification.The difference between the predicted charging mode probability and the actual situation probability is smaller than or equal to 0.5, namely, the power consumption mode prediction result is close to the actual result, the prediction accuracy of the power consumption mode is higher, the power consumption mode prediction result can be adopted to continuously acquire a sample power consumption abnormality identification result, and a cross entropy loss function for power consumption abnormality identification is acquired based on the sample power consumption abnormality identification result. In this case, therefore, the loss function can be calculated by averaging the two weighted sums described above.
In accordance with one embodiment of the present invention,If the difference between the predicted charging mode probability and the actual situation probability is greater than 0.5, that is, the error rate of the power consumption mode prediction result is higher and cannot be used for continuously acquiring the sample power consumption abnormality recognition result, the cross entropy loss function predicted by the power consumption mode is weighted by using a larger weight value, so that the accuracy of the sample power consumption abnormality recognition result is rapidly improved, for example, the weight value in the case is thatIn the case of (a), the sum of the weights of the cross entropy loss function of the electricity consumption mode prediction and the cross entropy loss function of the electricity consumption anomaly identification.
In this way, in the training process, the error between the prediction result of the sample electricity consumption mode and the actual electricity consumption mode can be determined, and the loss function under specific conditions is selected based on the error, so that the training process using the loss function has higher pertinence and efficiency, the loss function is reduced in the training process, and the accuracy of the electricity consumption abnormality monitoring model is improved more pertinently.
According to one embodiment of the present invention, in step S106, a corresponding measure is performed on the powered device with abnormal electricity consumption, i.e. the third switch corresponding to the device is turned off. A third switch is located between the device and the power supply line for directly controlling the power supply of the device.
According to one embodiment of the present invention, in step S107, in the device with the confirmed power consumption abnormality, a first number, that is, the number of electric devices with the power consumption abnormality identification result being the power consumption abnormality, is determined.
According to an embodiment of the present invention, in step S108, if the first number meets the preset number condition, the number of electric devices indicating that the electric abnormality is abnormal in use as a result of the electric abnormality identification is large, and there may be some external faults, for example, damage to the devices caused by natural disasters, or abnormal use of electricity caused by abnormal power supply, etc. At this time, the operation of opening the first switch and the second switch may be performed to protect the electric equipment from further damage, and also to protect the safety of the power supply circuit.
According to the power supply safety power supply protection method based on artificial intelligence, provided by the embodiment of the invention, through the first detection device and the second detection device, the power supply voltage of the power supply circuit and the power utilization currents of a plurality of electric equipment can be monitored in real time, so that potential problems can be found in time. And judging the stability of the power supply line by scoring the stability of the power supply voltage, and opening the first switch and closing the second switch when the stability of the power supply voltage is lower than a stability threshold. The trained power consumption abnormality monitoring model is used, and the abnormal state of each identified power consumption device can be accurately identified by combining the power consumption modes of the power consumption devices, so that the third switch is automatically disconnected according to the power consumption abnormality identification result, and potential safety risks are prevented. When the first quantity is determined to meet the preset quantity condition, the first switch and the second switch are disconnected, abnormal diffusion and chain reaction are reduced, and stability and safety of the whole power supply system are improved. When determining whether the power supply voltage is stable, the voltage error score can be determined through absolute accumulated errors, so that the error between the actual power supply voltage and the rated voltage can be objectively and accurately expressed, whether the voltage is abnormal due to voltage change can be judged through the magnitude relation between the prediction error and the actual error, and further the moment when the voltage change rate is abnormal can be accurately determined, and the voltage change score can accurately describe the abnormality of the voltage change rate. In the process of training the electricity consumption abnormality monitoring model, errors between a sample electricity consumption mode prediction result and an actual electricity consumption mode can be determined, and a loss function under specific conditions is selected based on the magnitude of the errors, so that the training process using the loss function is more targeted and efficient, the loss function is reduced in the training process, and the accuracy of the electricity consumption abnormality monitoring model is improved more targeted.
FIG. 2 schematically illustrates a block diagram of an artificial intelligence based power supply safety power protection system according to an embodiment of the invention, the system comprising: the device comprises a first detection device, a plurality of second detection devices, a first switch, a second switch, a third switch, a voltage stabilizing inverter and a controller;
The first detection device is used for detecting the power supply voltage of the power supply circuit at a plurality of moments, and the second detection devices are used for detecting the power utilization currents of the electric equipment at a plurality of moments;
the controller is used for:
Determining a power supply voltage stability score through power supply voltages at a plurality of moments in a first preset time period before a current moment, wherein the current moment is the last moment in the first preset time period;
Under the condition that the stability score of the power supply voltage is lower than a stability threshold value, a first switch between a power supply line and a power grid is controlled to be opened, and a second switch between the power grid and a voltage stabilizing inverter is controlled to be closed, wherein the input end of the voltage stabilizing inverter is connected with the second switch, and the output end of the voltage stabilizing inverter is connected with the power supply line;
Determining the power utilization mode of each electric device through the power utilization currents of a plurality of moments in a second preset time period before the current moment of each electric device, wherein the current moment is the last moment in the second preset time period;
processing the power consumption modes of the electric equipment and the power consumption currents at a plurality of moments in a second preset time period through the trained power consumption abnormality monitoring model, and determining power consumption abnormality identification results of the electric equipment;
Disconnecting a third switch corresponding to electric equipment with abnormal electricity consumption identification result, wherein the third switch is positioned between the electric equipment and the power supply line;
determining that the electricity utilization abnormality recognition result is a first number of electric equipment with abnormal electricity utilization;
And under the condition that the first number meets the preset number condition, the first switch and the second switch are disconnected.
It will be appreciated by persons skilled in the art that the embodiments of the invention described above and shown in the drawings are by way of example only and are not limiting. The objects of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been shown and described in the examples and embodiments of the invention may be modified or practiced without departing from the principles described.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (2)
1. The power supply safety power supply protection method based on artificial intelligence is characterized by comprising the following steps of:
Detecting power supply voltages of a power supply line at a plurality of moments through a first detection device, and detecting power utilization currents of a plurality of electric equipment at a plurality of moments through a plurality of second detection devices;
Determining a power supply voltage stability score through power supply voltages at a plurality of moments in a first preset time period before a current moment, wherein the current moment is the last moment in the first preset time period;
Under the condition that the stability score of the power supply voltage is lower than a stability threshold value, a first switch between a power supply line and a power grid is controlled to be opened, and a second switch between the power grid and a voltage stabilizing inverter is controlled to be closed, wherein the input end of the voltage stabilizing inverter is connected with the second switch, and the output end of the voltage stabilizing inverter is connected with the power supply line;
Determining the power utilization mode of each electric device through the power utilization currents of a plurality of moments in a second preset time period before the current moment of each electric device, wherein the current moment is the last moment in the second preset time period;
processing the power consumption modes of the electric equipment and the power consumption currents at a plurality of moments in a second preset time period through the trained power consumption abnormality monitoring model, and determining power consumption abnormality identification results of the electric equipment;
Disconnecting a third switch corresponding to electric equipment with abnormal electricity consumption identification result, wherein the third switch is positioned between the electric equipment and the power supply line;
determining that the electricity utilization abnormality recognition result is a first number of electric equipment with abnormal electricity utilization;
opening the first switch and the second switch under the condition that the first number meets the preset number condition;
determining a power supply voltage stability score from power supply voltages at a plurality of times within a first preset time period before a current time, comprising:
Fitting power supply voltages at a plurality of moments in a first preset time period before the current moment to obtain a power supply voltage fitting function;
Determining the rated voltage of a power supply line of a power supply;
Obtaining a voltage error score according to the power supply voltage fitting function and the rated voltage;
deriving the fitting function of the power supply voltage to obtain a variation function of the power supply voltage;
determining voltage change rates at a plurality of moments in the first preset time period according to the power supply voltage change function;
determining a voltage change score according to the voltage change rates at a plurality of moments in the first preset time period;
determining a supply voltage stability score according to the voltage variation score and the voltage error score;
obtaining a voltage error score according to the supply voltage fitting function and the rated voltage, including:
subtracting the rated voltage from the power supply voltage fitting function to obtain a power supply voltage error function;
determining an absolute value of a supply voltage error function as the supply voltage absolute error function;
Integrating the absolute error function of the power supply voltage in the first preset time period to obtain an absolute error accumulated value;
Integrating the rated voltage in the first preset time period to obtain a rated voltage accumulation value;
determining a ratio of the absolute error accumulation value to the rated voltage accumulation value as a voltage relative error value;
determining the voltage error score according to the voltage relative error value;
Determining a voltage change score according to the voltage change rates at a plurality of moments in the first preset time period, including:
for the ith moment in the first preset time period, determining a power supply voltage predicted value of the (i+1) th moment according to the power supply voltage of the ith moment, the voltage change rate of the ith moment and the time interval between adjacent moments;
If i is not equal to n, determining a prediction error between the power supply voltage predicted value at the (i+1) th moment and the rated voltage and an actual error between the power supply voltage at the (i+1) th moment and the rated voltage, wherein n is the number of moments in a first preset time period, the n-th moment in the first preset time period is the current moment, i is not more than n, and both i and n are positive integers;
If the prediction error is smaller than or equal to the actual error, determining the ith moment as an abnormal moment of the voltage change rate;
If i=n, determining a prediction error between the power supply voltage predicted value at the (i+1) th moment and the rated voltage, and determining the (i) th moment as a voltage change rate abnormal moment under the condition that the prediction error is greater than or equal to a preset prediction error threshold value;
counting a second number of abnormal moments of the voltage change rate;
Determining the voltage change score according to the second quantity and the moment quantity in the first preset time period;
determining, by the power consumption currents at a plurality of times in a second preset time period before the current time of each power consumption device, a power consumption mode of each power consumption device, including:
Respectively carrying out data fitting on electricity utilization currents of the j-th electric equipment at a plurality of moments in the second preset time period to obtain an electricity utilization current function of the j-th electric equipment, wherein j is a positive integer;
acquiring current errors between electricity utilization currents of the jth electric equipment at a plurality of moments and function values of the electricity utilization current function at a plurality of moments;
determining an absolute value of the current error as an absolute current error;
summing the absolute current errors at a plurality of moments to obtain an absolute accumulated error;
if the absolute accumulated error is smaller than or equal to a preset absolute error threshold value, and the absolute value of the slope of the electricity consumption current function is larger than or equal to a preset slope threshold value, determining an electricity consumption mode of the j-th electric equipment as a charging mode, otherwise, determining the electricity consumption mode of the j-th electric equipment as a power consumption mode, wherein the charging mode is an electricity consumption mode when the energy storage equipment is charged, and the power consumption mode is an electricity consumption mode when the electric equipment is operated;
the power consumption mode of each electric equipment and the power consumption currents at a plurality of moments in a second preset time period are processed through the trained power consumption abnormality monitoring model, and power consumption abnormality identification results of each electric equipment are determined, wherein the power consumption abnormality identification results comprise:
inputting the electricity consumption current of each electric equipment at a plurality of moments in a second preset time period into a coding sub-model of the electricity consumption abnormality monitoring model to obtain coding information of each electric equipment;
decoding the coding information of each electric equipment through the electric mode decoding sub-model to obtain an electric mode prediction result of each electric equipment;
Determining the correct rate of the electricity consumption mode prediction result according to the electricity consumption mode prediction result of each electric device and the electricity consumption mode of each electric device;
Under the condition that the accuracy is higher than a preset accuracy threshold, inputting the power consumption mode of each electric equipment and the coding information of each electric equipment into an anomaly identification decoding sub-model to obtain a power consumption anomaly identification result of each electric equipment;
The training step of the electricity consumption abnormality monitoring model comprises the following steps:
Sample coding information of each electric equipment is obtained through a coding sub-model of a sample electricity consumption current input electricity consumption abnormality monitoring model of a plurality of electric equipment at a plurality of moments in a historical time period;
Decoding sample coding information of each electric equipment through the electric mode decoding sub-model to obtain a sample electric mode prediction result of each electric equipment;
Inputting the sample electricity consumption mode prediction result and the sample coding information into an anomaly identification decoding sub-model to obtain sample electricity consumption anomaly identification results of all electric equipment;
Obtaining a loss function of an electricity consumption abnormality monitoring model according to the sample electricity consumption mode prediction result, the sample electricity consumption abnormality identification result, the actual abnormal state of each electric equipment and the actual electricity consumption mode of each electric equipment;
training the electricity consumption abnormality monitoring model according to the loss function to obtain the trained electricity consumption abnormality monitoring model;
Obtaining a loss function of an electricity consumption abnormality monitoring model according to the sample electricity consumption mode prediction result, the sample electricity consumption abnormality identification result, the actual abnormal state of each electric equipment and the actual electricity consumption mode of each electric equipment, wherein the loss function comprises the following steps:
According to the formula
；
Obtaining a loss function L of the electricity anomaly monitoring model, wherein,For the probability that the power usage pattern of the kth power consumer is the charging pattern determined based on the actual power usage pattern of the kth power consumer,For the probability that the power mode of the kth power consumer is the charging mode determined based on the sample power mode prediction result of the kth power consumer,For the probability of the power consumption abnormality of the kth power consumption device determined based on the actual abnormal state of the kth power consumption device,For the probability of the electricity utilization abnormality of the kth electric equipment determined based on the sample electricity utilization abnormality identification result of the kth electric equipment, N is the number of the electric equipment, k is less than or equal to N, and k and N are both positive integers,、AndIn order to set the weight of the weight in the preset,。
2. An artificial intelligence based power supply safety protection system for performing the method of claim 1, comprising: the device comprises a first detection device, a plurality of second detection devices, a first switch, a second switch, a third switch, a voltage stabilizing inverter and a controller;
The first detection device is used for detecting the power supply voltage of the power supply circuit at a plurality of moments, and the second detection devices are used for detecting the power utilization currents of the electric equipment at a plurality of moments;
the controller is used for:
Determining a power supply voltage stability score through power supply voltages at a plurality of moments in a first preset time period before a current moment, wherein the current moment is the last moment in the first preset time period;
Under the condition that the stability score of the power supply voltage is lower than a stability threshold value, a first switch between a power supply line and a power grid is controlled to be opened, and a second switch between the power grid and a voltage stabilizing inverter is controlled to be closed, wherein the input end of the voltage stabilizing inverter is connected with the second switch, and the output end of the voltage stabilizing inverter is connected with the power supply line;
Determining the power utilization mode of each electric device through the power utilization currents of a plurality of moments in a second preset time period before the current moment of each electric device, wherein the current moment is the last moment in the second preset time period;
processing the power consumption modes of the electric equipment and the power consumption currents at a plurality of moments in a second preset time period through the trained power consumption abnormality monitoring model, and determining power consumption abnormality identification results of the electric equipment;
Disconnecting a third switch corresponding to electric equipment with abnormal electricity consumption identification result, wherein the third switch is positioned between the electric equipment and the power supply line;
determining that the electricity utilization abnormality recognition result is a first number of electric equipment with abnormal electricity utilization;
And under the condition that the first number meets the preset number condition, the first switch and the second switch are disconnected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410437435.6A CN118213938B (en) | 2024-04-12 | 2024-04-12 | Power supply safety power supply protection method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410437435.6A CN118213938B (en) | 2024-04-12 | 2024-04-12 | Power supply safety power supply protection method and system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118213938A CN118213938A (en) | 2024-06-18 |
| CN118213938B true CN118213938B (en) | 2024-08-30 |
Family
ID=91452066
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410437435.6A Active CN118213938B (en) | 2024-04-12 | 2024-04-12 | Power supply safety power supply protection method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118213938B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117150409A (en) * | 2023-09-14 | 2023-12-01 | 保定市新源绿网电力科技有限公司 | Power consumption abnormality detection method |
| CN117388732A (en) * | 2023-07-07 | 2024-01-12 | 江苏华翊成电气科技有限公司 | High-power density direct-current power supply safety monitoring method and system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP4273564A1 (en) * | 2022-05-02 | 2023-11-08 | Siemens Aktiengesellschaft | Apparatus, system and method for detecting anomalies in a grid |
| EP4297222A1 (en) * | 2022-06-22 | 2023-12-27 | Siemens Aktiengesellschaft | Computer-implemented method and system for anomaly detection and anomaly location in an energy distribution network |
| CN115423003A (en) * | 2022-08-22 | 2022-12-02 | 青岛特来电新能源科技有限公司 | Battery abnormality detection method, battery abnormality detection device, electronic apparatus, and computer storage medium |
| CN117611889A (en) * | 2023-11-22 | 2024-02-27 | 中国电力科学研究院有限公司 | Method and system for detecting abnormality of electric power metering wiring line |
-
2024
- 2024-04-12 CN CN202410437435.6A patent/CN118213938B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117388732A (en) * | 2023-07-07 | 2024-01-12 | 江苏华翊成电气科技有限公司 | High-power density direct-current power supply safety monitoring method and system |
| CN117150409A (en) * | 2023-09-14 | 2023-12-01 | 保定市新源绿网电力科技有限公司 | Power consumption abnormality detection method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118213938A (en) | 2024-06-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114050633B (en) | Dynamic management and control method and device for lithium battery energy storage system and electronic equipment | |
| CN109271741B (en) | Method for predicting residual service life and evaluating health of step-down DC-DC power supply module | |
| CN117007979B (en) | Power output power failure abnormality early warning method based on data driving | |
| CN107942255B (en) | Transformer substation storage battery state evaluation method based on data fusion technology | |
| CN104316879A (en) | Method for forecasting service life of lead-acid storage battery | |
| CN112349988B (en) | Vehicle storage battery online monitoring device and self-adaptive charging method | |
| CN117078113B (en) | Outdoor battery production quality management system based on data analysis | |
| CN112014745A (en) | Three-level fault diagnosis method for power battery | |
| CN118213938B (en) | Power supply safety power supply protection method and system based on artificial intelligence | |
| CN117650611B (en) | Protection method for backup power supply of electricity consumption information acquisition terminal | |
| CN116799899B (en) | Battery safety management method, device, equipment and storage medium | |
| CN117674365B (en) | Battery life cycle management system | |
| CN118444186A (en) | Quick accurate detection device of retired power battery health status | |
| CN116665425B (en) | Monitoring and early warning method and system for power supply | |
| CN117728421A (en) | Micro-grid cluster coordinated scheduling method, system, computer equipment and storage medium | |
| CN115128442B (en) | Dynamic evaluation method for electric life of circuit breaker based on full life operation information | |
| CN112470013B (en) | Electric vehicle charging monitoring device and method | |
| Sun et al. | Diagnosis method for the degradation of lead-acid battery | |
| CN117458572B (en) | Power supply management system for energy storage cabinet BMS | |
| CN117895512B (en) | Intelligent power distribution system and power distribution method | |
| CN111817305B (en) | Power grid operation efficiency post-evaluation method and system for capacity increase of power transmission and transformation equipment | |
| CN118861557A (en) | Health management method and equipment for 5G communication power supply | |
| CN114069640B (en) | Self-adaptive multi-load response controller and control method thereof | |
| CN111129616A (en) | Battery energy storage BMS system based on dual-path information sampling monitoring and protection control | |
| Long et al. | Review on Techniques used in Battery Management System |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |