CN118445736B - Switch cabinet health state monitoring method and equipment - Google Patents
Switch cabinet health state monitoring method and equipment Download PDFInfo
- Publication number
- CN118445736B CN118445736B CN202410903100.9A CN202410903100A CN118445736B CN 118445736 B CN118445736 B CN 118445736B CN 202410903100 A CN202410903100 A CN 202410903100A CN 118445736 B CN118445736 B CN 118445736B
- Authority
- CN
- China
- Prior art keywords
- data
- monitoring data
- health state
- monitoring
- switch cabinet
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 157
- 230000036541 health Effects 0.000 title claims abstract description 121
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000011156 evaluation Methods 0.000 claims abstract description 58
- 230000003862 health status Effects 0.000 claims abstract description 19
- 238000013210 evaluation model Methods 0.000 claims description 24
- 238000012549 training Methods 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 18
- 230000008033 biological extinction Effects 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims 1
- 238000012423 maintenance Methods 0.000 abstract description 11
- 230000000875 corresponding effect Effects 0.000 description 104
- 230000009471 action Effects 0.000 description 12
- 230000002829 reductive effect Effects 0.000 description 7
- 239000002131 composite material Substances 0.000 description 5
- 238000012545 processing Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000004146 energy storage Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012854 evaluation process Methods 0.000 description 2
- 238000011478 gradient descent method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 238000010791 quenching Methods 0.000 description 1
- 230000000171 quenching effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/327—Testing of circuit interrupters, switches or circuit-breakers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2123/00—Data types
- G06F2123/02—Data types in the time domain, e.g. time-series data
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Power Engineering (AREA)
- Probability & Statistics with Applications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application relates to the technical field of switch cabinets, and provides a method and equipment for monitoring the health state of a switch cabinet. A method of health status monitoring comprising: acquiring at least two monitoring data; for each monitoring data, determining a data score of the monitoring data based on a preset evaluation rule; determining a comprehensive score based on the data scores corresponding to the respective monitoring data; determining a target scoring range to which the comprehensive score belongs from at least two preset scoring ranges; and evaluating the health state of the switch cabinet based on the health state evaluation mode corresponding to the target grading range and the data grading corresponding to each monitoring data to obtain the health state of the switch cabinet. By adopting the technical scheme, the proper health state evaluation mode can be determined based on the preset scoring range to which the comprehensive score belongs, and the health state of the switch cabinet is evaluated based on the data scores corresponding to the monitoring data of the health state evaluation mode, so that the guidance of maintenance work of the switch cabinet can be facilitated.
Description
Technical Field
The application relates to the technical field of switch cabinets, in particular to a switch cabinet health state monitoring method and system.
Background
The operation state and maintenance plan of the traditional switch cabinet require operation and maintenance personnel of the switch cabinet to draw up maintenance plans according to operation and maintenance operation guidelines and by combining personal working experience through manual inspection and daily equipment operation state records.
However, the traditional operation and maintenance mode is limited by experience of operation and maintenance personnel and collected equipment state data, so that possible defects of equipment cannot be predicted in advance, a treatment plan of maintenance requirements can be timely made, and maintenance work can only be carried out regularly.
Disclosure of Invention
In order to help to maintain the switch cabinet, the application provides a switch cabinet health state monitoring method and system.
In a first aspect, the application provides a method for monitoring the health state of a switch cabinet, which adopts the following technical scheme:
a method of monitoring the health status of a switchgear, the method comprising:
acquiring at least two monitoring data, wherein the monitoring data are used for indicating the working state of the switch cabinet;
For each piece of monitoring data, determining a data score of the monitoring data based on a preset evaluation rule;
determining a comprehensive score based on the data scores corresponding to the monitoring data;
determining a target scoring range to which the comprehensive score belongs from at least two preset scoring ranges, wherein the preset scoring ranges are obtained by dividing the value range of the comprehensive score;
And evaluating the health state of the switch cabinet based on the health state evaluation mode corresponding to the target score range and the data score corresponding to each monitoring data to obtain the health state of the switch cabinet, wherein the health state evaluation modes corresponding to the preset score range are preset, and the health state evaluation modes corresponding to different preset score ranges are different.
By adopting the technical scheme, the acquired at least two monitoring data can be comprehensively analyzed to obtain the comprehensive score, then the proper health state evaluation mode is determined based on the preset score range to which the comprehensive score belongs, and the health state of the switch cabinet is evaluated based on the data score corresponding to each monitoring data in the proper health state evaluation mode, so that the maintenance work of the switch cabinet can be guided.
Optionally, the monitoring data includes a remaining service life of the circuit breaker, and the acquiring at least two monitoring data includes:
Monitoring the main loop current;
Under the condition that the breaker is monitored to be disconnected, updating a first life parameter based on the magnitude of breaking current, wherein the breaking current is main loop current when the breaker is disconnected;
Under the condition that an arc extinction point is monitored based on the main loop current, performing intercept calculation on arc extinction time based on the fault current extinction characteristic, and estimating damage condition of the contact blade based on the main loop current value actually measured when faults occur and the arc extinction time to update a second life parameter;
The remaining life is determined based on the remaining life indicated by the first life parameter and the remaining life indicated by the second life parameter.
Through adopting above-mentioned technical scheme, can combine breaking current's size and arc extinction to the damage condition of contact piece to renew the remaining life of circuit breaker, so can realize the accurate prediction to the remaining life of circuit breaker, can help accurate prediction switch cabinet's health state.
Optionally, the health state evaluation mode includes a score correspondence rule between the data score and the health state, and the score correspondence rule corresponding to the health state evaluation mode is different; the evaluating the health state of the switch cabinet based on the health state evaluating mode corresponding to the target scoring range and the data scoring corresponding to each monitoring data comprises the following steps:
and determining the health state of the switch cabinet based on the data scores corresponding to the monitoring data and the score corresponding rules corresponding to the target score ranges.
By adopting the technical scheme, the corresponding scoring corresponding rule can be determined based on the preset scoring range to which the comprehensive scoring belongs, so that the scoring rule actually used is more matched with the current monitoring data, and the accuracy of the health state prediction can be improved.
Optionally, the health state evaluation mode includes a first evaluation mode and a second evaluation mode;
the first evaluation mode comprises the step of determining the health state of the switch cabinet by using a preset scoring corresponding rule between the data scoring and the monitoring state;
The second evaluation mode comprises the step of evaluating the health state of the switch cabinet by using a state evaluation model;
The state evaluation model is obtained by training an initial network model by using training data, and each group of training data is determined based on a data score corresponding to the sample monitoring data and a corresponding health state.
By adopting the technical scheme, the method for judging the health state based on the pre-trained state evaluation model can be further introduced on the basis of judging the health state through the preset scoring rule, and different monitoring data can be better considered in the state evaluation model during the evaluation process, so that the method can be beneficial to processing the monitoring data under the condition that some health states are not obvious, and further can be beneficial to improving the accuracy of judging the health state.
Optionally, the evaluating the health state of the switch cabinet based on the health state evaluation mode corresponding to the target scoring range and the data score corresponding to each monitoring data to obtain the health state of the switch cabinet includes:
Performing feature extraction on the monitoring data based on the data score corresponding to the monitoring data for each monitoring data under the condition that the health state evaluation mode corresponding to the target score range is the second evaluation mode, so as to obtain the input parameter corresponding to the monitoring data;
and inputting the input parameters corresponding to the monitoring data into the state evaluation model to obtain the health state of the switch cabinet.
By adopting the technical scheme, the characteristic input state evaluation model with the most information quantity can be extracted, converted and selected from the monitoring data, so that the performance and the prediction capability of the model are improved, and the accuracy of the health state prediction is further improved.
Optionally, the monitoring data includes at least one time deviation data, and the input parameters corresponding to the time deviation data include: a running average of the time offset data;
And/or the number of the groups of groups,
The monitoring data comprise breaker room air pressure data, and input parameters corresponding to the breaker room air pressure data comprise: and the range corresponding to the breaker chamber air pressure data.
By adopting the technical scheme, the sliding average value of the time deviation data can be used as the input parameter, so that the influence of errors of single data points on the judgment of the time deviation condition can be reduced, and the input parameter can accurately reflect the actual time deviation condition.
In addition, the range corresponding to the air pressure data of the breaking chamber can be used as input data, so that the influence of the data acquisition error of the sensing assembly on the air pressure judgment in the breaking chamber can be reduced, and the input data can better reflect the actual air pressure condition in the breaking chamber.
Optionally, the loss function used in the training process of the state evaluation model is a weighted cross entropy function, and the weight of the input data corresponding to each monitoring data in the loss function is set based on the importance degree corresponding to the monitoring data.
According to the technical scheme, the influence of each input parameter can be considered by using the weighted cross entropy loss function, and optimization is performed according to the error classification cost of different states, so that the training process of the model can be better guided, the accuracy of judging the health state is improved, and meanwhile, the robustness of the model is also improved.
Optionally, the loss function further includes a correlation regularization term for capturing correlations between input parameters of the state evaluation model.
In the technical scheme, the redundant influence among parameters can be reduced by adding the associated regularization term, so that the model can learn more independent and diversified characteristics, and the generalization capability of the model is improved.
Optionally, the loss function is represented by:
Wherein, Is a model parameter; n is the number of input parameters; Is the weight coefficient of the ith input parameter; is the real state category corresponding to the ith input parameter; is the model predicting the state class of the ith input parameter as Probability of (2); is a regularization term, used to prevent overfitting, Is thatCorresponding regularized intensities; Is the term of regularization of the association, Is thatThe corresponding strength of the regularization,Represented by the formula:
Wherein, Is the relation coefficient between the input parameter j and the input parameter k; For the weight of the input parameter j, Is the weight of the input parameter k.
In a second aspect, the present application provides an electronic device, which adopts the following technical scheme:
an electronic device, the electronic device comprising:
at least one processor;
A memory;
At least one application program, wherein the at least one application program is stored in the memory and configured to be executed by the at least one processor, the at least one application program configured to: any of the switch cabinet health status monitoring methods provided in the first aspect is performed.
In summary, the present application includes at least one of the following beneficial technical effects:
The health state evaluation mode can be dynamically determined based on comprehensive scores, so that the problem that a scoring rule is not careful and accurate enough when the single health state evaluation mode is used for evaluating the health state of the switch cabinet can be avoided, the actual health state evaluation mode can be matched with current monitoring data more, and further the accuracy of the health state prediction can be improved.
The residual service life of the circuit breaker can be updated by combining the breaking current and the damage condition of the arc extinction to the contact blade, so that the accurate prediction of the residual service life of the circuit breaker can be realized, and the healthy state of the switch cabinet can be accurately predicted.
Drawings
Fig. 1 is a schematic flow chart of a method for monitoring health status of a switch cabinet according to an embodiment of the present application;
FIG. 2 is an example of a scoring rule provided by an embodiment of the present application;
FIG. 3 is an example of a service recommendation generation rule provided by an embodiment of the present application;
FIG. 4 is a flow chart of a remaining service life judging method according to an embodiment of the present application;
Fig. 5 is a schematic diagram of a relationship model of the allowable breaking times and breaking current of a circuit breaker according to an embodiment of the present application;
FIG. 6 is a flowchart of a health status prediction method according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings 1 to 7 and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
The embodiment of the application discloses a method for monitoring the health state of a switch cabinet. Referring to fig. 1, the method for monitoring the health status of a switch cabinet comprises the following steps:
step 101, obtaining at least two monitoring data, wherein the monitoring data are used for indicating the working state of the switch cabinet.
In particular, the monitoring data may be directly collected by sensing components disposed at different locations within the switchgear, such as: the monitoring data comprise the pressure of a breaking chamber, the breaking current and the like; or may be obtained by analyzing and/or calculating data collected by the sensing component, for example: the monitoring data comprise a brake opening action time deviation, a brake closing action time deviation, an energy storage motor action time deviation, a three-station motor action time deviation, the residual service life of the circuit breaker and the like.
In actual implementation, the monitoring data may be set according to actual monitoring requirements, for example: the monitoring data may also include temperature data, humidity data, and the like.
Step 102, for each monitoring data, determining a data score of the monitoring data based on a preset evaluation rule.
Specifically, because different identification modes corresponding to different monitoring data are different, for example: the time deviation is expressed by time, the gas pressure is expressed by pressure, and the remaining life is expressed by percentage, so that in order to help to comprehensively evaluate the state of the switch cabinet by combining different monitoring data, the corresponding expression modes of the monitoring data are necessary to be unified.
Correspondingly, in this embodiment, corresponding scoring rules are set for different monitoring data, so that the corresponding monitoring data can be evaluated based on the scoring rules, thereby obtaining data scores corresponding to the monitoring data.
In one example, the scoring rule includes a base score corresponding to the monitored data and weights corresponding to different numerical ranges, and accordingly, the data score corresponding to the monitored data is a product of the weights corresponding to the numerical ranges to which the detected data belong based on the product.
In one example, the monitoring data includes a brake off action time bias, a brake on action time bias, an energy storage motor action time bias, a three-position motor action time bias, a remaining service life, and a circuit breaker chamber air pressure, and the scoring rules are shown in fig. 2.
In actual implementation, the scoring rule is set reasonably, so that the scoring range of the data can be limited, for example: the value ranges of the data scores corresponding to the monitoring data can be set to be the same, so that the monitoring states of the switch cabinet can be comprehensively analyzed by combining different monitoring data.
And step 103, determining the comprehensive score based on the data scores corresponding to the monitoring data.
Optionally, determining the composite score based on the data score corresponding to each monitored data includes: and determining the weighted sum of the data scores corresponding to the monitoring data as a comprehensive score.
The weight of the data scoring is preset based on the importance degree of the corresponding monitoring data. In one example, the data score weights range from 0 to 1.
In actual implementation, under the condition that the value ranges of the data scores corresponding to the monitoring data are the same, the weighted average value of the data scores of the detection data can be determined to be the comprehensive score, so that the influence of the number of the monitoring data on the value range of the comprehensive score can be avoided, and the number of the monitoring data participating in the monitoring state evaluation can be flexibly adjusted.
And 104, determining a target scoring range to which the comprehensive score belongs from at least two preset scoring ranges.
The preset scoring range is obtained by dividing the value range of the comprehensive score. Specifically, the division manner of the preset scoring range may be set according to actual experience. Such as: the value range of the comprehensive score is divided into four preset score ranges which are less than or equal to 21, more than 24 and less than or equal to 34, more than 34 and less than or equal to 63 and more than 63.
And step 105, evaluating the health state of the switch cabinet based on the health state evaluation mode corresponding to the target grading range and the data grading corresponding to each monitoring data to obtain the health state of the switch cabinet.
The health state evaluation modes corresponding to the preset scoring ranges are preset, and the health state evaluation modes corresponding to different preset scoring ranges are different.
In one example, the health state assessment method includes a score correspondence rule between the data score and the health state, and the score correspondence rules corresponding to different health state assessment methods are different.
Correspondingly, the evaluation of the health state of the switch cabinet based on the health state evaluation mode corresponding to the target scoring range and the data scoring corresponding to each monitoring data comprises the following steps: and determining the health state of the switch cabinet based on the data score corresponding to each monitoring data and the score corresponding rule corresponding to the target score range.
According to the technical scheme, when the single scoring rule is used for evaluating the health state of the switch cabinet, the problem that the scoring rule is not fine enough and accurate is solved, and the corresponding scoring corresponding rule can be determined based on the preset scoring range to which the comprehensive scoring belongs, so that the scoring rule in actual use is matched with the current monitoring data, and the accuracy of the prediction of the health state can be improved.
In one example, health status is categorized into health, pre-alarm and fault alarm conditions. The preset scoring range comprises: less than or equal to 21, greater than 24 and less than or equal to 34, greater than 34 and less than or equal to 63, and greater than 63. Wherein, the scoring correspondence rule of a part of the preset scoring ranges is as follows:
score correspondence rules when the composite score is less than or equal to 21 are: if the maximum value of the data scores corresponding to the monitoring data is smaller than 9, determining that the health state is healthy; if the maximum value of the data scores corresponding to the monitoring data is greater than or equal to 9 and less than or equal to 16, determining that the health state is a pre-alarm; and if the maximum value of the data scores corresponding to the monitoring data is greater than 16, determining that the health state is a fault alarm.
Score correspondence rules when the composite score is greater than 34 and less than or equal to 63 are: if the maximum value of the data scores corresponding to the monitoring data is smaller than 16, determining that the health state is a pre-alarm; and if the maximum value of the data scores corresponding to the detection data is greater than or equal to 16, determining that the health state is a fault alarm.
The score correspondence rule when the composite score is greater than 63 is: and determining the health state as a fault alarm.
In some embodiments, further, in the case that the health state is determined to be a pre-alarm or a fault alarm, the alarm reason is determined based on the monitoring data with the abnormality, and corresponding overhaul advice is output, so that the method can help guide staff to process the abnormality.
In one example, the alarm cause and corresponding service advice refer to FIG. 3.
The implementation principle of the switch cabinet health state monitoring method provided by the embodiment of the application is as follows: acquiring at least two monitoring data, wherein the monitoring data are used for indicating the working state of the switch cabinet; for each monitoring data, determining a data score of the monitoring data based on a preset evaluation rule; determining a comprehensive score based on the data scores corresponding to the respective monitoring data; determining a target scoring range to which the comprehensive score belongs from at least two preset scoring ranges, wherein the preset scoring ranges are obtained by dividing the value range of the comprehensive score; and evaluating the health state of the switch cabinet based on the health state evaluation mode corresponding to the target scoring range and the data scoring corresponding to each monitoring data to obtain the health state of the switch cabinet, wherein the health state evaluation modes corresponding to the preset scoring range are preset, and the health state evaluation modes corresponding to different preset scoring ranges are different. By adopting the technical scheme, the acquired at least two monitoring data can be comprehensively analyzed to obtain the comprehensive score, then the proper health state evaluation mode is determined based on the preset score range to which the comprehensive score belongs, and the health state of the switch cabinet is evaluated based on the data score corresponding to each monitoring data in the proper health state evaluation mode, so that the maintenance work of the switch cabinet can be guided.
Meanwhile, the health state evaluation mode can be dynamically determined based on the comprehensive score, so that the problem that a scoring rule is not careful and accurate enough when the single health state evaluation mode is used for evaluating the health state of the switch cabinet can be avoided, the health state evaluation mode in actual use can be matched with current monitoring data more, and further the accuracy of the health state prediction can be improved.
In some embodiments, referring to fig. 4, the monitoring data includes a remaining life of the circuit breaker, step 101, acquiring at least two monitoring data includes:
in step 201, the main loop current is monitored.
Step 202, updating a first life parameter based on the magnitude of breaking current when the breaker is detected to be open.
The breaking current is the main loop current when the breaker is opened.
The first life parameter is the number of remaining breaks of the circuit breaker. Correspondingly, in the initial state, the first life parameter is the designed breaking times of the circuit breaker, and in the use process, the first life parameter is continuously reduced. It should be noted that, since the degree of influence of different breaking currents on the life of the circuit breaker is different, there may be a difference in the magnitude of reduction of the first life parameter at different breaking currents.
Optionally, updating the first lifetime parameter based on the magnitude of the breaking current includes: updating the first life parameter in a first updating manner when the segmented current is less than the rated current; under the condition that the breaking current is larger than the rated current and smaller than the rated short-circuit current, updating the first life parameter in a second updating mode; and under the condition that the breaking current is larger than the rated short-circuit current, updating the first life parameter in a third updating mode.
In one example, the first update is a decrease in the first life parameter by a preset value, such as: subtracting 1 from the first life parameter; the second updating mode is that the first life parameter is decreased based on the equal proportion of the proportion corresponding to the reference current corresponding to the circuit breaking current; the third updating mode is that the first life parameter is decreased based on the corresponding proportion of rated short-circuit current in equal proportion.
Further, in the above example, the reduction ratio in the second updating manner and the third updating manner may be determined based on a vacuum circuit breaker allowable breaking number (N) and breaking current (kA) relation model. In one example, the circuit breaker allowable number of breaks versus breaking current relationship model refers to fig. 5, where the ratio is the slope of the corresponding curve in fig. 5.
And 203, under the condition that the arc extinction point is detected based on the main loop current, calculating arc extinction time based on the fault current extinction characteristic, and estimating the damage condition of the contact blade based on the main loop current value and the arc extinction time which are actually measured when the fault occurs to update the second life parameter.
Wherein the second life parameter is used to indicate the state of the contact blade. The state of the contact blade needs to be adjusted at this time, since the contact blade may be damaged in the case of arc extinction.
In one example, the manner in which the arc-out point is detected based on the main loop current includes: and searching for the arc extinction point through an adaptive threshold arc extinction point searching algorithm based on the current variation.
Optionally, estimating the damage condition of the contact blade based on the main loop current value and the arc extinguishing time actually measured when the fault occurs includes: determining an arc-extinguishing heat based on the main loop current value and the arc-extinguishing time; and reducing the second life parameter based on the loss value corresponding to the quenching heat.
The calculation mode of the arc extinguishing heat is the product of the square of the current value of the main loop and the arc extinguishing time; the correspondence between the heat and the loss value is preset.
Step 204, determining a remaining service life based on the remaining life indicated by the first life parameter and the remaining life indicated by the second life parameter.
The corresponding relation between the first life parameter and the residual life and the corresponding relation between the second life parameter and the residual life are preset. In one example, the first life parameter is the number of remaining disconnection times, and at this time, the remaining life corresponding to the first life parameter is the ratio of the first life parameter to the number of designed disconnection times; the second life parameter is the residual heat bearing value of the contact blade, and the residual life corresponding to the second life parameter is the ratio of the second life parameter to the designed maximum accumulated heat bearing value.
In one example, determining the remaining useful life based on the remaining life indicated by the first life parameter and the remaining life indicated by the second life parameter includes: a weighted average of the remaining life indicated by the first life parameter and the remaining life indicated by the second life parameter is determined as the remaining life.
In another example, determining the remaining useful life based on the remaining life indicated by the first life parameter and the remaining life indicated by the second life parameter includes: of the remaining lives indicated by the first life parameter and the remaining life indicated by the second life parameter, a relatively small one is determined as the remaining life.
According to the technical scheme, the first life parameter can be updated based on the breaking current of the circuit breaker under the condition that the circuit breaker is broken, the second life parameter is updated based on the main loop current value and the arc extinguishing time under the condition that the arc extinguishing point is monitored, and the residual service life of the circuit breaker is determined based on the first life parameter and the second life parameter, so that the accurate prediction of the residual service life of the circuit breaker can be realized, and the accurate prediction of the health state of the switch cabinet can be facilitated.
It should be noted that, in actual implementation, the remaining service life of the circuit breaker may be predicted based on only the first service life parameter or the second service life parameter, or may be predicted in combination with other parameters (such as a change condition of an operating temperature of the circuit breaker).
In some embodiments, the health status assessment means comprises a first assessment means and a second assessment means. Specifically, the first evaluation mode includes determining a health state of the switch cabinet by using a score correspondence rule between a preset data score and a monitoring state; the second evaluation mode comprises the use of a state evaluation model for evaluating the state of health of the switch cabinet.
The specific implementation of the first evaluation manner is analogous to the embodiment corresponding to step 105, and the specific implementation of the second evaluation manner is described below.
The state evaluation model used in the second evaluation mode is obtained by training the initial network model by using training data, and each set of training data is determined based on the data score corresponding to the sample monitoring data and the corresponding health state.
In the practical process, the fact that the dimension of information reflected by different monitoring data is different is found, so that the data corresponding to the monitoring data is scored and judged by using a preset scoring rule, when the health state of the switch cabinet is obvious (for example, all monitoring data are excellent in performance or at least one monitoring data are extremely poor in performance), the accuracy is good, and when the health state of the switch cabinet is not obvious (for example, most of monitoring data are general and monitoring data which are extremely poor in performance are not present), the judging result may deviate, and particularly, some health risks caused by multi-dimensional factors together may be omitted.
Based on the above problems, in this embodiment, on the basis of health status judgment by a preset scoring rule, a mode of health status judgment based on a pre-trained status evaluation model is further introduced, and different monitoring data can be better considered in the evaluation process by the status evaluation model, so that the processing of monitoring data under the condition that some health status is not obvious can be facilitated, and further the accuracy of health status judgment can be improved. In addition, for the situation that the health state is obvious, the health state judgment can be carried out through the preset grading rule, so that the calculation resources required by the health state monitoring can be saved, and meanwhile, the efficiency of the health state judgment can be improved.
In actual implementation, the selection of the first evaluation mode and the second evaluation mode may be set by a worker according to actual experience, and may be adjusted according to actual effects. Such as: in the case of dividing the value ranges of the composite score into four preset score ranges of less than or equal to 21, greater than 24 and less than or equal to 24, greater than 34 and less than or equal to 63 and greater than 63, three ranges of less than or equal to 21, greater than 34 and less than or equal to 63 and greater than 63 may employ the first evaluation method, and greater than 24 and less than or equal to 34 may employ the second evaluation method.
Further, referring to fig. 6, step 105, evaluating the health status of the switch cabinet based on the health status evaluation mode corresponding to the target score range and the data scores corresponding to the respective monitoring data, to obtain the health status of the switch cabinet, includes:
step 301, in the case that the health state evaluation mode corresponding to the target score range is the second evaluation mode, for each monitoring data, feature extraction is performed on the monitoring data based on the data score corresponding to the monitoring data, so as to obtain the input parameter corresponding to the monitoring data.
Specifically, feature extraction of the monitored data means: and analyzing the change condition of the monitoring data in a period of time or a preset quantity to obtain the characteristics of the monitoring data.
In one example, the monitoring data includes at least one time deviation data, and the manner in which the time deviation data is characterized includes: a running average of the time offset data is calculated. Correspondingly, the input parameters corresponding to the time judgment data comprise a sliding average value corresponding to the time deviation data. Therefore, the influence of errors of single data points on time deviation condition judgment can be reduced, and the input parameters can accurately reflect the actual time deviation condition.
The time deviation data can be at least one of opening action time deviation, closing action time deviation, energy storage motor action time deviation and three-station motor action time deviation.
In actual implementation, the input parameters corresponding to the time deviation data may include other data, such as: standard deviation of time deviation data.
In another example, monitoring data packet breaker chamber pressure data, the manner in which the breaker chamber pressure data is data extracted, includes: and calculating the corresponding range of the breaker chamber air pressure data. The input parameters corresponding to the corresponding breaker chamber pressure data include the range corresponding to the breaker chamber pressure data. Therefore, the influence of the data acquisition error of the sensing assembly on the judgment of the air pressure in the breaking chamber can be reduced, and the actual air pressure condition in the breaking chamber can be better reflected by inputting data.
In actual implementation, the input parameters corresponding to the air pressure data of the breaking chamber may further include other data, such as: minimum value of the breaking chamber air pressure data.
It should be noted that, the manner of extracting the data from the monitoring data may be flexibly set according to the actual needs, that is, each monitoring data needs to correspond to at least one input parameter, if necessary, some monitoring data may correspond to a plurality of input parameters, or some monitoring data associated with each other may commonly correspond to one input parameter.
Step 302, inputting the input parameters corresponding to each monitoring data into a state evaluation model to obtain the health state of the switch cabinet.
Accordingly, in the training of the state evaluation model, the training data used is also obtained by processing the sample monitoring data in the same manner as in step 301.
In the above embodiment, before the state evaluation model is used for prediction, feature extraction is performed on the monitoring data to obtain the input parameters corresponding to the monitoring data, and then the input parameters are input into the state evaluation model, so that the feature input state evaluation model with the most information can be extracted, converted and selected from the monitoring data, thereby improving the performance and the prediction capability of the model, and further improving the accuracy of the health state prediction.
In some embodiments, the loss function used in the training process of the state evaluation model is a weighted cross entropy function, specifically, the weight of the input data corresponding to each monitoring data in the loss function is set based on the importance degree corresponding to the monitoring data.
In one example, the loss function is represented by:
Wherein, Is a model parameter; n is the number of input parameters; Is the weight coefficient of the ith input parameter; is the real state category corresponding to the ith input parameter; is the model predicting the state class of the ith input parameter as Probability of (2); is a regularization term to prevent overfitting, such as: l1 or L2 regularization, Is thatCorresponding regularized intensities.
According to the technical scheme, the influence of each input parameter can be considered by using the weighted cross entropy loss function, and optimization is performed according to the error classification cost of different states, so that the training process of the model can be better guided, the accuracy of judging the health state is improved, and meanwhile, the robustness of the model is also improved.
Further, the loss function also includes an associated regularization term for capturing an association between input parameters of the state evaluation model.
In one example, the loss function is represented by:
Wherein, Is a model parameter; n is the number of input parameters; Is the weight coefficient of the ith input parameter; is the real state category corresponding to the ith input parameter; is the model predicting the state class of the ith input parameter as Probability of (2); is a regularization term, used to prevent overfitting, Is thatCorresponding regularized intensities; Is an associated regularization term that is associated with the regularization term, Is thatThe corresponding strength of the regularization,Represented by the formula:
Wherein, Is the relation coefficient between the input parameter j and the input parameter k; For the weight of the input parameter j, Is the weight of the input parameter k.
In actual implementation, the relationship coefficient between different input parameters (i.e) The input monitoring data may be analyzed in advance, or may be empirically set, and the setting manner of the relationship coefficient between the input parameters is not limited in this embodiment.
In the above technical solution, the redundant influence between parameters can be reduced by adding the associated regularization term, in particular, if two parameters are highly correlated, they may carry similar information, and the regularization term will encourage the model not to depend excessively on any one of the parameters. Therefore, the model can learn more independent and diversified characteristics, and the generalization capability of the model is improved.
While when the model knows that there are associations between certain parameters, it is encouraged to find features that are not directly caused by those associations. This may facilitate model discovery of more diverse patterns that are capable of capturing different aspects of the data. Such as: in the judgment of the health state of the switch cabinet, besides independently monitoring each parameter, the model can learn the special modes of certain parameter combinations, so that the advantage of error judgment through the model can be fully exerted.
Further, the association relation coefficientCan be learned during model training. Specifically, an initial association coefficient is set before training is startedIn the process of each iteration, the association relation coefficientAnd updating. In one example, the gradient descent method may be used to correlate the relationship coefficientsAnd updating. The specific implementation mode is as follows:
Wherein, Is the updated association relation coefficient; is the association relation coefficient before updating; Is the learning rate used for controlling the size of the updating step; Is a loss function Relative toIs a gradient of (a).
Accordingly, in each training iteration, the method comprises the following steps:
First, the gradient of the loss function L with respect to the model parameter θ is calculated, and the loss function L with respect to the model parameter Is a gradient of (a).
Then, updating the model parameters θ based on using a gradient descent method or other optimization algorithm, and updating the model parameters using the above。
By adopting the technical scheme, the association relation coefficient between the parameters can be dynamically adjusted in the model training process, so that the nonlinear relation between the parameters is better captured, the model is encouraged to learn more robust and generalized characteristic representation, and the accuracy of the prediction result can be improved.
The embodiment of the application also provides electronic equipment. As shown in fig. 7, the electronic device 400 shown in fig. 7 includes: a processor 401 and a memory 403. Processor 401 is connected to memory 403, such as via bus 402. Optionally, the electronic device 400 may also include a transceiver 404. It should be noted that, in practical applications, the transceiver 404 is not limited to one, and the structure of the electronic device 400 is not limited to the embodiment of the present application.
The Processor 401 may be a CPU (Central Processing Unit ), general purpose Processor, DSP (DIGITAL SIGNAL Processor, data signal Processor), ASIC (Application SPECIFIC INTEGRATED Circuit) or other programmable logic device, transistor logic device, hardware component, or any combination thereof. Which may implement or perform the various exemplary logic blocks, modules and circuits described in connection with this disclosure. Processor 401 may also be a combination that implements computing functionality, such as a combination comprising one or more microprocessors, a combination of a DSP and a microprocessor, or the like.
Bus 402 may include a path to transfer information between the components. Bus 402 may be a PCI (PERIPHERAL COMPONENT INTERCONNECT, peripheral component interconnect standard) bus, or an EISA (Extended Industry Standard Architecture ) bus, or the like. Bus 402 may be divided into an address bus, a data bus, and the like. For ease of illustration, only one thick line is shown in fig. 7, but not only one bus or one type of bus.
Memory 403 may be, but is not limited to, a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory ) or other type of dynamic storage device that can store information and instructions, an EEPROM (ELECTRICALLY ERASABLE PROGRAMMABLE READ ONLY MEMORY ), magnetic disk storage or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
The memory 403 is used for storing application program codes for executing the inventive arrangements and is controlled to be executed by the processor 401. The processor 401 is arranged to execute application code stored in the memory 403 for implementing what is shown in the foregoing method embodiments.
Among them, electronic devices include, but are not limited to: mobile terminals such as mobile phones, notebook computers, PDAs (personal digital assistants), PADs (tablet computers), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. And may also be a server, etc. The electronic device shown in fig. 7 is only an example and should not be construed as limiting the functionality and scope of use of the embodiments of the application.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when executed in a computer, causes the computer to execute the switch cabinet health status monitoring method provided by the embodiment.
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein.
The foregoing is only a partial embodiment of the present application, and it should be noted that it will be apparent to those skilled in the art that modifications and adaptations can be made without departing from the principles of the present application, and such modifications and adaptations should and are intended to be comprehended within the scope of the present application.
Claims (9)
1. A method of monitoring the health status of a switchgear, the method comprising:
acquiring at least two monitoring data, wherein the monitoring data are used for indicating the working state of the switch cabinet;
For each piece of monitoring data, determining a data score of the monitoring data based on a preset evaluation rule;
determining a comprehensive score based on the data scores corresponding to the monitoring data;
Determining a target scoring range to which the comprehensive score belongs from at least two preset scoring ranges, wherein the preset scoring ranges are obtained by dividing the value range of the comprehensive score, the health state evaluation modes corresponding to the preset scoring ranges are preset, and the health state evaluation modes corresponding to different preset scoring ranges are different;
The health state of the switch cabinet is evaluated based on the health state evaluation mode corresponding to the target scoring range and the data scoring corresponding to each monitoring data, so that the health state of the switch cabinet is obtained;
under the condition that the health state of the switch cabinet is determined to be a pre-alarm or a fault alarm, determining a reason corresponding to the pre-alarm or the fault alarm based on abnormal monitoring data, and outputting a corresponding overhaul suggestion;
The health state evaluation mode comprises the step of evaluating the health state of the switch cabinet by using a state evaluation model, wherein a loss function used in the training process of the state evaluation model is represented by the following formula:
，
Wherein, Is a model parameter; n is the number of input parameters; Is the weight coefficient of the ith input parameter; is the real state category corresponding to the ith input parameter; is the model predicting the state class of the ith input parameter as Probability of (2); is a regularization term, used to prevent overfitting, Is thatCorresponding regularized intensities; Is an associated regularization term that is associated with the regularization term, Is thatThe corresponding strength of the regularization,Represented by the formula:
，
Wherein, Is the relation coefficient between the input parameter j and the input parameter k; For the weight of the input parameter j, Is the weight of the input parameter k.
2. The method of claim 1, wherein the monitoring data comprises a remaining life of the circuit breaker, and wherein the obtaining at least two monitoring data comprises:
Monitoring the main loop current;
updating a first life parameter based on the magnitude of breaking current under the condition that the breaker is monitored to be opened; the first life parameter comprises the number of remaining disconnection times; the breaking current is the main loop current when the breaker is opened;
Under the condition that an arc extinction point is monitored based on the main loop current, performing intercept calculation on arc extinction time based on the fault current extinction characteristic, and estimating damage condition of the contact blade based on the main loop current value actually measured when faults occur and the arc extinction time to update a second life parameter; the second life parameter comprises a residual heat tolerance value of the contact blade;
The remaining life is determined based on the remaining life indicated by the first life parameter and the remaining life indicated by the second life parameter.
3. The method for monitoring the health state of a switch cabinet according to claim 1, wherein the health state evaluation mode further comprises a score correspondence rule between the data score and the health state, and the score correspondence rule corresponding to the health state evaluation mode is different;
The evaluating the health state of the switch cabinet based on the health state evaluating mode corresponding to the target scoring range and the data scoring corresponding to each monitoring data comprises the following steps:
and determining the health state of the switch cabinet based on the data scores corresponding to the monitoring data and the score corresponding rules corresponding to the target score ranges.
4. The method of claim 1, wherein the state of health assessment further comprises determining the state of health of the switchgear using a pre-set rule of score correspondence between the data score and a monitored state.
5. The method for monitoring the health status of a switchgear cabinet according to claim 1, wherein,
The state evaluation model is obtained by training an initial network model by using training data, and each group of training data is determined based on a data score corresponding to sample monitoring data and a corresponding health state;
Under the condition that the state evaluation model is used for evaluating the health state of the switch cabinet, for each piece of monitoring data, carrying out feature extraction on the monitoring data based on the data score corresponding to the monitoring data to obtain the input parameters corresponding to the monitoring data; and inputting the input parameters corresponding to the monitoring data into the state evaluation model to obtain the health state of the switch cabinet.
6. The method of claim 5, wherein the monitoring data includes at least one time offset data, and the input parameters corresponding to the time offset data include: a running average of the time offset data;
And/or the number of the groups of groups,
The monitoring data comprise breaker room air pressure data, and input parameters corresponding to the breaker room air pressure data comprise: and the range corresponding to the breaker chamber air pressure data.
7. The method according to claim 5, wherein the weight of the input data corresponding to each monitoring data in the loss function is set based on the importance level corresponding to the monitoring data.
8. The switchgear health status monitoring method of claim 7, wherein the association regularization term is used to capture associations between input parameters of the status assessment model.
9. An electronic device, the electronic device comprising:
at least one processor;
A memory;
At least one application program, wherein the at least one application program is stored in the memory and configured to be executed by the at least one processor, the at least one application program configured to: a method of monitoring the health of a switchgear cabinet according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410903100.9A CN118445736B (en) | 2024-07-08 | 2024-07-08 | Switch cabinet health state monitoring method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410903100.9A CN118445736B (en) | 2024-07-08 | 2024-07-08 | Switch cabinet health state monitoring method and equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118445736A CN118445736A (en) | 2024-08-06 |
| CN118445736B true CN118445736B (en) | 2024-09-17 |
Family
ID=92320008
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410903100.9A Active CN118445736B (en) | 2024-07-08 | 2024-07-08 | Switch cabinet health state monitoring method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118445736B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105699889A (en) * | 2016-03-17 | 2016-06-22 | 国网四川省电力公司电力科学研究院 | Method of evaluating intelligent substation circuit breaker electrical life loss and arc extinguishing ability |
| CN113327049A (en) * | 2021-06-17 | 2021-08-31 | 通号（长沙）轨道交通控制技术有限公司 | Method and device for identifying health grade of GIS switch cabinet and storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114997051B (en) * | 2022-05-30 | 2023-05-09 | 浙大城市学院 | Aero-engine life prediction and health assessment method based on transfer learning |
| CN117435969A (en) * | 2023-09-06 | 2024-01-23 | 北京理工大学珠海学院 | Switch cabinet health state assessment method, device, equipment and storage medium |
| CN118070007A (en) * | 2024-02-04 | 2024-05-24 | 杭州经纬信息技术股份有限公司 | Method and system for measuring and calculating service life of switch cabinet |
-
2024
- 2024-07-08 CN CN202410903100.9A patent/CN118445736B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105699889A (en) * | 2016-03-17 | 2016-06-22 | 国网四川省电力公司电力科学研究院 | Method of evaluating intelligent substation circuit breaker electrical life loss and arc extinguishing ability |
| CN113327049A (en) * | 2021-06-17 | 2021-08-31 | 通号（长沙）轨道交通控制技术有限公司 | Method and device for identifying health grade of GIS switch cabinet and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118445736A (en) | 2024-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xiao et al. | Decentralized PCA modeling based on relevance and redundancy variable selection and its application to large-scale dynamic process monitoring | |
| CN108445410A (en) | A kind of method and device of monitoring accumulator group operating status | |
| JP2011181070A (en) | System and method for monitoring asset condition in electric power substation device | |
| CN114386537B (en) | Lithium battery fault diagnosis method and device based on Catboost and electronic equipment | |
| Li et al. | Residual useful life estimation by a data‐driven similarity‐based approach | |
| CN116070802B (en) | Intelligent monitoring operation and maintenance method and system based on data twinning | |
| CN116823227A (en) | Intelligent equipment management system and method based on Internet of things | |
| Tang et al. | Rolling bearing remaining useful life prediction via weight tracking relevance vector machine | |
| CN113837596A (en) | Fault determination method and device, electronic equipment and storage medium | |
| Duan | Dynamic Bayesian monitoring and detection for partially observable machines under multivariate observations | |
| CN115856613A (en) | Circuit breaker state evaluation method | |
| CN118445736B (en) | Switch cabinet health state monitoring method and equipment | |
| CN115600879A (en) | Circuit breaker abnormity early warning method, system and related device | |
| KR20210083418A (en) | Fire predictive analysis device and method of building | |
| CN118521159A (en) | Deep learning-based power consumption information acquisition terminal quality detection method and system | |
| Lv et al. | General log‐linear Weibull model combining vibration and temperature characteristics for remaining useful life prediction of rolling element bearings | |
| CN114528914B (en) | Method, terminal and storage medium for monitoring state of cold water host in loop | |
| Elgohary et al. | Transfer of learning in convolutional neural networks for thermal image classification in Electrical Transformer Rooms | |
| CN117742303B (en) | Production automation equipment detection method, system and medium | |
| CN118623517B (en) | Refrigerating unit control method and system based on data monitoring | |
| Bai et al. | Abnormal Detection Scheme of Substation Equipment based on Intelligent Fusion Terminal | |
| CN117875945B (en) | Power grid equipment maintenance prediction method, system and medium | |
| CN118520377B (en) | Acquisition method, application method and device of instrument control card health prediction model | |
| CN118329128B (en) | Method for monitoring running state of electromechanical equipment for remote intelligent processing | |
| CN114692743A (en) | Failure prediction method, failure prediction device and storage medium |
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 |