CN117970211A - Self-adaptive deep learning transformer test instrument calibration system - Google Patents
Self-adaptive deep learning transformer test instrument calibration system Download PDFInfo
- Publication number
- CN117970211A CN117970211A CN202311566368.XA CN202311566368A CN117970211A CN 117970211 A CN117970211 A CN 117970211A CN 202311566368 A CN202311566368 A CN 202311566368A CN 117970211 A CN117970211 A CN 117970211A
- Authority
- CN
- China
- Prior art keywords
- module
- test
- data
- calibration
- self
- 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.)
- Pending
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 188
- 238000013135 deep learning Methods 0.000 title claims abstract description 37
- 238000004164 analytical calibration Methods 0.000 title claims description 28
- 230000003044 adaptive effect Effects 0.000 claims description 31
- 238000012545 processing Methods 0.000 claims description 30
- 238000001514 detection method Methods 0.000 claims description 29
- 238000000034 method Methods 0.000 claims description 25
- 238000004088 simulation Methods 0.000 claims description 18
- 238000005457 optimization Methods 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000012544 monitoring process Methods 0.000 claims description 14
- 230000006978 adaptation Effects 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 11
- 230000007423 decrease Effects 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 7
- 230000008859 change Effects 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 238000013136 deep learning model Methods 0.000 claims description 6
- 230000005672 electromagnetic field Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 230000002452 interceptive effect Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 230000007613 environmental effect Effects 0.000 claims description 5
- 230000000694 effects Effects 0.000 claims description 4
- 238000012423 maintenance Methods 0.000 claims description 4
- 230000002829 reductive effect Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 125000004122 cyclic group Chemical group 0.000 claims description 3
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 230000003631 expected effect Effects 0.000 claims description 3
- 238000011990 functional testing Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 238000009413 insulation Methods 0.000 claims description 3
- 230000003993 interaction Effects 0.000 claims description 3
- 238000013450 outlier detection Methods 0.000 claims description 3
- 238000011056 performance test Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000003449 preventive effect Effects 0.000 claims description 3
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 claims description 3
- 238000013112 stability test Methods 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims description 3
- 230000008646 thermal stress Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 8
- 230000007246 mechanism Effects 0.000 abstract description 3
- 238000004891 communication Methods 0.000 description 4
- 238000007796 conventional method Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000000053 physical method Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000000528 statistical test Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R35/00—Testing or calibrating of apparatus covered by the other groups of this subclass
- G01R35/005—Calibrating; Standards or reference devices, e.g. voltage or resistance standards, "golden" references
-
- 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
- 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
- G01R31/40—Testing power supplies
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Pure & Applied Mathematics (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Algebra (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses a calibration system of a self-adaptive deep learning transformer testing instrument, which relates to the technical field of transformers and comprises a self-adaptive input module, wherein the self-adaptive input module is used for automatically detecting and adapting to different power supply conditions and testing environments through a sensor. And the modularized test module is used for selecting a required test module according to actual requirements. And the real-time calibration and feedback module is used for comparing the test data with cloud standard data in real time, and if data deviation occurs. And the self-learning and optimizing module is used for receiving the data provided by the self-adaptive input module and the modularized test module. And the virtual simulation module is used for creating a digital twin model, namely a virtual transformer model, for each tested transformer. The invention introduces a self-adaptive deep learning mechanism and a virtual simulation technology, realizes intelligent calibration of the transformer testing instrument, improves the accuracy and efficiency of calibration, optimizes in real time and learns by oneself, so that the transformer can maintain the optimal performance under various working conditions.
Description
Technical Field
The invention relates to the technical field of inverter maintenance, in particular to a calibration system of a self-adaptive deep learning transformer test instrument.
Background
In the modern power industry, transformers are critical electrical devices that play a critical role in power transmission and distribution. To ensure the performance and safe operation of the transformer, it is necessary to perform tests and calibrations periodically. Currently, testing and calibration of transformers relies primarily on traditional physical methods and instrumentation, which often require specialized technicians to operate, and in some cases may require downtime. Furthermore, these conventional methods generally provide limited information, such as a single performance index or parameter.
However, these conventional test and calibration methods have some technical problems. First, they are often time consuming and can result in downtime of the equipment and loss of production. Second, since these methods generally rely on manual operations, there may be operational errors or inconsistencies. Furthermore, conventional approaches may not be able to capture certain complex or implicit equipment problems, which may lead to potential equipment failure or performance degradation. Therefore, there is a need to develop a new, more efficient, more accurate transformer testing and calibration technique.
Disclosure of Invention
The present invention has been made in view of the above-mentioned or existing problems occurring in the prior art.
It is therefore an object of the present invention to provide an adaptive deep learning transformer test instrument calibration system.
In order to solve the technical problems, the invention provides the following technical scheme:
In a first aspect, an embodiment of the present invention provides a calibration system for a testing apparatus of a self-adaptive deep learning transformer, which includes a self-adaptive input module, a power quality analyzer, a sensor, a modular testing module, and a self-learning and optimizing module, wherein the self-adaptive input module detects a power condition and a testing environment through the power quality analyzer, and transmits a detection result to the modular testing module and the self-learning and optimizing module; the modularized test module is used for testing according to the detection result of the self-adaptive input module and transmitting test data to the real-time calibration and feedback module and the virtual simulation module; the real-time calibration and feedback module is used for comparing the test data with cloud standard data in real time, and if data deviation occurs, the real-time calibration is automatically carried out and real-time feedback is provided; the real-time calibration and feedback module receives the test data provided by the modularized test module, calibrates the test data according to the suggestion of the self-learning and optimization module, and feeds back the calibration result to the user; the self-learning and optimizing module is used for receiving the data provided by the self-adaptive input module and the modularized test module, learning and optimizing the data and providing a calibration suggestion for the real-time calibration and feedback module; the virtual simulation module is used for creating a digital twin model, namely a virtual transformer model, for each tested transformer; and receiving test data provided by the modularized test module, performing virtual simulation, comparing a simulation result with a real test result, and providing feedback for the self-learning and optimizing module.
As a preferable scheme of the self-adaptive deep learning transformer test instrument calibration system, the invention comprises the following steps: the sensor comprises a temperature sensor, a humidity sensor and an electromagnetic field sensor; the self-adaptive input module comprises a power parameter detection sub-module, an environment parameter detection sub-module, a data processing sub-module and a parameter adaptation sub-module; the power supply parameter detection submodule monitors power supply fluctuation, voltage V and current I through the power supply quality analyzer; the environment parameter detection submodule detects temperature T in real time through the temperature sensor, detects humidity H in real time through the humidity sensor and detects electromagnetic interference EMI in real time through the electromagnetic field sensor; the data processing sub-module performs data processing on the data detected by the power parameter detection sub-module and the environment parameter detection sub-module, wherein the data processing comprises noise filtering and normalization processing, and the formula is as follows:
Where x is the original data and x min is the minimum value of the original data; x max is the maximum value of the raw data.
The parameter adaptation submodule analyzes the data processed by the data processing submodule in real time by using the adaptive filter so as to identify and adapt to the change of the environment and the power supply condition, and the method comprises the following specific steps of: selecting a least mean square error (LMS) algorithm to adapt to filtering and prediction in a non-static environment; the formula of the LMS algorithm is as follows:
wn＝wo+μ·e(t)·x(t)
Wherein w n and w o respectively represent weight vectors before and after updating, μ is a step size parameter, and the learning rate is controlled; e (t) is the prediction error and x (t) is the input signal.
Dynamically adjusting the step size parameter mu according to the change of the real-time data stream: if the prediction error increases, decreasing mu to decrease the weight adjustment amplitude; if the prediction error decreases, μ is increased to increase the learning speed.
Continuously monitoring a prediction error e (t) and performing real-time feedback adjustment according to the error magnitude; periodically monitoring the stability and consistency of the input signal x (t) to ensure filter performance; statistical testing is used to ensure that the input signal varies within a reasonable range.
As a preferable scheme of the self-adaptive deep learning transformer test instrument calibration system, the invention comprises the following steps: the power parameter detection sub-module and the environment parameter detection sub-module both transmit the detected data to the data processing sub-module, the data processing sub-module processes the detected data and transmits the processed data to the parameter adaptation sub-module, and the parameter adaptation sub-module selects the optimal test parameters according to the processed data and transmits the optimal test parameters to the modularized test module.
As a preferable scheme of the self-adaptive deep learning transformer test instrument calibration system, the invention comprises the following steps: the modularized test module comprises a test sequence which is automatically selected and generated according to the data provided by the self-adaptive input module, and a condition logic is implemented; monitoring in real time during the test, and if an abnormal value is detected, immediately adjusting test parameters or suspending the test; the implementation condition logic comprises automatically including a thermal stress test if the temperature exceeds a preset threshold; if the temperature is lower than 0 ℃, adding a cold start test; if the humidity exceeds the threshold, performing a reinforced insulation test; if the humidity is lower than 30%, the performance test in a dry environment is increased; if the power supply fluctuation exceeds the standard range of +/-5%, reducing the test load to avoid damaging equipment; if the power supply is stable, a load test is added to evaluate the maximum bearing capacity; if the current or voltage exceeds 95% of the specification of the equipment, an overload protection test is executed; if the current or voltage is lower than a specified minimum operation threshold, checking the low load performance of the device; if the historical test data show a performance decline trend, increasing a performance decline test; if the historical test data show abnormal fluctuation, performing fault detection and stability test; if a record of maintaining or replacing the parts is recently available, performing a full functional test to ensure that all the parts work normally; maintenance is not performed for a long time, and comprehensive inspection and preventive testing are added.
As a preferable scheme of the self-adaptive deep learning transformer test instrument calibration system, the invention comprises the following steps: the real-time calibration and feedback module is used for receiving test data from the modularized test module and synchronizing the test data with standard data in the cloud database; comparing the received test data with the standard data of the cloud by using a real-time data processing algorithm; calculating a deviation by using a difference analysis formula; defining a deviation threshold, and triggering a calibration procedure when the deviation exceeds the threshold; automatically adjusting calibration settings of the test equipment according to the suggestions of the self-learning and optimization module; creating a detailed calibration report, including data before and after calibration, adjustments made and suggestions; transmitting feedback to a user or technician via a user interface or telecommunications system; and continuously monitoring the calibration effect and adjusting according to the subsequent test data.
As a preferable scheme of the self-adaptive deep learning transformer test instrument calibration system, the invention comprises the following steps: the self-learning and optimizing module comprises a self-adaptive input module and a modularized test module, wherein the self-learning and optimizing module receives environmental parameters, power supply conditions and test result data; denoising, outlier detection and normalization are carried out on the received data; the principal component analysis PCA is used for reducing the data dimension and improving the processing efficiency; selecting a convolutional neural network CNN or a cyclic neural network RNN, processing a target according to data characteristics, and training a model by using a large amount of historical data so as to learn complex modes and correlations in the data; extracting key features by using the trained model, and identifying an abnormal mode in calibration; according to the model output, an optimization algorithm is applied to automatically formulate a calibration strategy; generating specific calibration suggestions according to an optimization strategy, wherein the calibration suggestions comprise adjustment parameters and expected effects; providing clear guidelines and predictive results.
As a preferable scheme of the self-adaptive deep learning transformer test instrument calibration system, the invention comprises the following steps: the virtual simulation module comprises an environment building sub-module, a simulation engine sub-module, a result analysis sub-module and an interaction interface sub-module; the environment building module is responsible for creating and maintaining a virtual environment model of the transformer and storing the model in a database; the simulation engine submodule loads a model from the database and executes simulation according to a strategy; the result analysis submodule analyzes the simulation result and adjusts the strategy according to the analysis result; the interactive interface sub-module provides an interactive interface for a user to view the simulation environment and the result.
In a second aspect, an embodiment of the present invention provides a method for calibrating a testing instrument of an adaptive deep learning transformer, including: the adaptive input module is used for monitoring the test environment and the power supply condition in real time through the sensor, and preprocessing and standardizing the data. In the modularized test module, a test sequence for the transformer is automatically generated and executed according to the monitored environment and power supply data, and a test result is recorded. The self-learning and optimization module uses a deep learning model to analyze the collected test data, identify patterns and potential calibration deviations. Based on the analysis result of the deep learning model, the self-learning and optimizing module formulates a calibration strategy and generates specific calibration suggestions. And the real-time calibration and feedback module compares the test data with cloud standard data, automatically executes calibration, and feeds back a calibration result and advice to a user.
In a third aspect, embodiments of the present invention provide a computer apparatus comprising a memory and a processor, the memory storing a computer program, wherein: the processor performs any step of the adaptive deep learning transformer test instrument calibration method described above when executing the computer program.
In a fourth aspect, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: the computer program when executed by the processor implements any of the steps of the adaptive deep learning transformer test instrument calibration method described above.
The invention has the beneficial effects that: according to the invention, by introducing the self-adaptive deep learning mechanism and the virtual simulation technology, the intelligent calibration of the transformer testing instrument is realized, the accuracy and the efficiency of the calibration are greatly improved, the real-time optimization and self-learning are also realized, the transformer can maintain the optimal performance under various working conditions, meanwhile, the human operation errors and the equipment shutdown time are reduced, and obvious economic and technical benefits are brought to the power industry.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. Wherein:
FIG. 1 is a block diagram of an adaptive deep learning transformer test instrument calibration system.
Fig. 2 is an overall flowchart of an adaptive deep learning transformer test instrument calibration method.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to specific embodiments thereof which are illustrated in the appended drawings.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways other than those described herein, and persons skilled in the art will readily appreciate that the present invention is not limited to the specific embodiments disclosed below.
Further, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic can be included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
Example 1
Referring to fig. 1 and 2, a first embodiment of the present invention provides a calibration system for a testing instrument of an adaptive deep learning transformer, which is composed of an adaptive input module, a modularized testing module, a real-time calibration and feedback module, a self-learning and optimization module and a virtual simulation module.
The self-adaptive input module detects power supply conditions through a power supply quality analyzer and a testing environment through a sensor, and transmits detection results to the modularized testing module and the self-learning and optimizing module. The sensors include temperature sensors, humidity sensors, and electromagnetic field sensors.
Specifically, the self-adaptive input module mainly comprises a power parameter detection sub-module, an environment parameter detection sub-module, a data processing sub-module and a parameter adaptation sub-module. The power parameter detection submodule monitors power supply fluctuation, voltage V and current I through a power supply quality analyzer. The environment parameter detection submodule detects temperature T in real time through a temperature sensor, detects humidity H in real time through the humidity sensor and detects electromagnetic interference EMI in real time through the electromagnetic field sensor. The parameter adaptation submodule automatically selects optimal test parameters according to the processed data; specifically, a preset rule or machine learning model is used, and optimal test parameters are selected according to input parameters such as voltage, current, frequency, temperature, humidity and the like.
Further, the data processing sub-module performs noise filtering and normalization processing on the detected parameter values, and the processing steps are as follows: the formula is as follows:
Where x is the original data and x min is the minimum value of the original data; x max is the maximum value of the raw data.
The parameter adaptation sub-module analyzes the data processed by the data processing sub-module in real time by using the adaptive filter to identify and adapt to the change of the environment and the power supply condition, and the specific steps are as follows:
Selecting a least mean square error (LMS) algorithm to adapt to filtering and prediction in a non-static environment; the formula of the LMS algorithm is as follows:
wn＝wo+μ·e(t)·x(t)
Wherein w n and w o respectively represent weight vectors before and after updating, μ is a step size parameter, and the learning rate is controlled; e (t) is the prediction error and x (t) is the input signal.
The step size parameter mu is dynamically adjusted according to the change of the real-time data stream. If the prediction error increases, decreasing mu to decrease the weight adjustment amplitude; if the prediction error decreases, μ is increased to increase the learning speed.
Continuously monitoring a prediction error e (t) and carrying out real-time feedback adjustment according to the error size, wherein the error e (t) has the formula:
e(t)＝d(t)-y(t)
wherein d (t) is the desired output; y (t) is the current output.
The stability and consistency of the input signal x (t) is monitored periodically to ensure filter performance.
Using statistical tests to ensure that the input signal varies within a reasonable range; the overall performance of the system, including response time, accuracy and stability, is periodically assessed. And adjusting algorithm parameters according to the evaluation result, and optimizing performance.
Furthermore, the modularized test module is used for testing according to the detection result of the self-adaptive input module, and transmitting test data to the real-time calibration and feedback module and the virtual simulation module, and the specific process is as follows:
automatically selecting and generating a test sequence according to the data provided by the self-adaptive input module, and implementing conditional logic; monitoring in real time during the test, and if an abnormal value is detected, immediately adjusting the test parameters or suspending the test.
Implementing the conditional logic includes: if the temperature exceeds the preset threshold, automatically testing the thermal stress; if the temperature is lower than 0 ℃, adding a cold start test; if the humidity exceeds the threshold, performing a reinforced insulation test; if the humidity is lower than 30%, the performance test in a dry environment is increased; if the power supply fluctuation exceeds the standard range of +/-5%, reducing the test load to avoid damaging equipment; if the power supply is stable, a load test is added to evaluate the maximum bearing capacity; if the current or voltage exceeds 95% of the specification of the equipment, an overload protection test is executed; if the current or voltage is lower than a specified minimum operation threshold, checking the low load performance of the device; if the historical test data show a performance decline trend, increasing a performance decline test; if the historical test data show abnormal fluctuation, performing fault detection and stability test; if a record of maintaining or replacing the parts is recently available, performing a full functional test to ensure that all the parts work normally; maintenance is not performed for a long time, and comprehensive inspection and preventive testing are added.
Further, the real-time calibration and feedback module specifically includes: receiving test data from the modularized test module and synchronizing the test data with standard data in a cloud database; comparing the received test data with the standard data of the cloud by using a real-time data processing algorithm; calculating a deviation by using a difference analysis formula; defining a deviation threshold, and triggering a calibration procedure when the deviation exceeds the threshold; automatically adjusting calibration settings of the test equipment according to the suggestions of the self-learning and optimization module; according to the equipment characteristics and deviation types, a detailed calibration report is created through a linear or nonlinear adjustment formula, wherein the detailed calibration report comprises data before and after calibration, and adjustments and suggestions made; transmitting feedback to a user or technician via a user interface or telecommunications system; continuously monitoring the calibration effect and adjusting according to the subsequent test data; cloud standard data is updated periodically to reflect the latest industry standards and technological advances.
Further, the self-learning and optimizing module receives environmental parameters, power supply conditions and test result data transmitted by the adaptive input module and the modularized test module; receiving environmental parameters, power supply conditions and test result data from the adaptive input module and the modular test module; denoising, outlier detection and normalization are carried out on the received data; the principal component analysis PCA is used for reducing the data dimension and improving the processing efficiency; selecting a convolutional neural network CNN or a cyclic neural network RNN, processing a target according to data characteristics, and training a model by using a large amount of historical data so as to learn complex modes and correlations in the data; extracting key features by using the trained model, and identifying an abnormal mode in calibration; according to the model output, an optimization algorithm (such as a genetic algorithm) is applied to automatically formulate a calibration strategy; generating specific calibration suggestions according to an optimization strategy, wherein the calibration suggestions comprise adjustment parameters and expected effects; providing clear guidelines and predictive results. New test data and calibration feedback are continuously collected for continuous optimization and tuning of the model. Ensuring continuous adaptation and promotion of models over time and development of technology.
And the virtual simulation module is used for creating a digital twin model, namely a virtual transformer model, for each tested transformer. And receiving test data provided by the modularized test module, performing virtual simulation, comparing a simulation result with a real test result, and providing feedback for the self-learning and optimizing module. The virtual simulation module comprises an environment building sub-module, a simulation engine sub-module, a result analysis sub-module and an interaction interface sub-module. The environment modeling submodule is responsible for creating and maintaining a virtual environment model of the transformer and storing the model in a database. The simulation engine sub-module loads the model from the database and performs the simulation according to the strategy. The result analysis sub-module analyzes the simulation result and adjusts the strategy according to the analysis result. The interactive interface sub-module provides an interactive interface for a user to view the simulation environment and the result.
In summary, the intelligent calibration of the transformer testing instrument is realized by introducing the self-adaptive deep learning mechanism and the virtual simulation technology, the accuracy and the efficiency of the calibration are greatly improved, the real-time optimization and the self-learning are also realized, the transformer can maintain the optimal performance under various working conditions, meanwhile, the human operation errors and the equipment shutdown time are reduced, and remarkable economic and technical benefits are brought to the power industry. The invention obviously improves the calibration precision and efficiency of the transformer testing instrument. The self-learning and optimizing module of the system is used for self-adaptive adjustment according to the continuously changing test data and environmental conditions, so that human errors are reduced, and the reliability of test results is enhanced. In addition, the combination of the real-time calibration and feedback functions and the virtual simulation module provides deep insight and improvement suggestions for users, and further enhances the overall performance of the system. In summary, the present invention brings innovative and efficient solutions to transformer test instrument calibration by utilizing advanced techniques and algorithms.
Example 2
Referring to fig. 1 and 2, in order to provide a second embodiment of the present invention, based on the first embodiment, the present invention further provides a calibration method for a testing instrument of an adaptive deep learning transformer, including:
S1: the adaptive input module is used for monitoring the test environment and the power supply condition in real time through the sensor, and preprocessing and standardizing the data.
S2: in the modularized test module, a test sequence for the transformer is automatically generated and executed according to the monitored environment and power supply data, and a test result is recorded.
S3: the self-learning and optimization module uses a deep learning model to analyze the collected test data, identify patterns and potential calibration deviations.
S4: based on the analysis result of the deep learning model, the self-learning and optimizing module formulates a calibration strategy and generates specific calibration suggestions.
S5: and the real-time calibration and feedback module compares the test data with cloud standard data, automatically executes calibration, and feeds back a calibration result and advice to a user.
The embodiment also provides a computer device, which is suitable for the situation of the self-adaptive deep learning transformer test instrument calibration method, and comprises a memory and a processor; the memory is used for storing computer executable instructions, and the processor is used for executing the computer executable instructions to realize the calibration method of the adaptive deep learning transformer test instrument according to the embodiment.
The computer device may be a terminal comprising a processor, a memory, a communication interface, a display screen and input means connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless mode can be realized through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer equipment can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment can be a touch layer covered on the display screen, can also be keys, a track ball or a touch pad arranged on the shell of the computer equipment, and can also be an external keyboard, a touch pad or a mouse and the like.
The present embodiment also provides a storage medium, on which a computer program is stored, which when executed by a processor, implements a method for implementing multi-source power grid information fusion based on the internet of things as set forth in the foregoing embodiment.
The storage medium according to the present embodiment belongs to the same inventive concept as the data storage method according to the above embodiment, and technical details not described in detail in the present embodiment can be seen in the above embodiment, and the present embodiment has the same advantageous effects as the above embodiment.
Example 3
Referring to fig. 1, a third embodiment of the present invention is shown, which is different from the first two embodiments: also included. In the above embodiment, the adaptive deep learning transformer test instrument calibration system comprises
The experimental steps are as follows: 10 transformers with the same model are selected as test objects; the 10 transformers were calibrated using conventional techniques and the required time, accuracy and stability were recorded; the technical scheme is used for calibrating 10 transformers and recording the same parameters; the results of the two techniques are compared.
Table 1: transformer calibration technology contrast analysis table
The calibration time of the calibration system of the transformer test instrument by using the self-adaptive deep learning is generally 40% -50% shorter than that of the calibration system of the transformer test instrument by using the traditional technology, which shows that the efficiency of the system is obviously improved. In terms of accuracy, the novel technical scheme is improved by about 4% on average compared with the traditional technology. In addition, the stability score also shows that the new solution has a higher stability, with an average score of 9.2, whereas the conventional technique has an average score of 6.8. These data clearly demonstrate that the adaptive deep learning transformer test instrument calibration system of the present invention is superior to conventional techniques in terms of efficiency, accuracy and stability.
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, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (10)
1. The utility model provides a self-adaptation degree of depth study transformer test instrument calibration system which characterized in that: comprising the steps of (a) a step of,
The self-adaptive input module is used for detecting power supply conditions through a power supply quality analyzer and detecting a test environment through a sensor, and transmitting a detection result to the modularized test module and the self-learning and optimizing module;
The modularized test module is used for testing according to the detection result of the self-adaptive input module and transmitting test data to the real-time calibration and feedback module and the virtual simulation module;
The real-time calibration and feedback module is used for comparing the test data with cloud standard data in real time, and if data deviation occurs, the real-time calibration is automatically carried out and real-time feedback is provided; the real-time calibration and feedback module receives the test data provided by the modularized test module, calibrates the test data according to the suggestion of the self-learning and optimization module, and feeds back the calibration result to the user;
the self-learning and optimizing module is used for receiving the data provided by the self-adaptive input module and the modularized test module, learning and optimizing the data and providing a calibration suggestion for the real-time calibration and feedback module;
The virtual simulation module is used for creating a digital twin model, namely a virtual transformer model, for each tested transformer; and receiving test data provided by the modularized test module, performing virtual simulation, comparing a simulation result with a real test result, and providing feedback for the self-learning and optimizing module.
2. The adaptive deep learning transformer test instrument calibration system of claim 1, wherein: the sensor comprises a temperature sensor, a humidity sensor and an electromagnetic field sensor; the self-adaptive input module comprises a power parameter detection sub-module, an environment parameter detection sub-module, a data processing sub-module and a parameter adaptation sub-module;
The power supply parameter detection submodule monitors power supply fluctuation, voltage V and current I through the power supply quality analyzer;
The environment parameter detection submodule detects temperature T in real time through the temperature sensor, detects humidity H in real time through the humidity sensor and detects electromagnetic interference EMI in real time through the electromagnetic field sensor;
The data processing sub-module performs data processing on the data detected by the power parameter detection sub-module and the environment parameter detection sub-module, wherein the data processing comprises noise filtering and normalization processing, and the formula is as follows:
Where x is the original data and x min is the minimum value of the original data; x max is the maximum value of the raw data;
The parameter adaptation submodule analyzes the data processed by the data processing submodule in real time by using the adaptive filter so as to identify and adapt to the change of the environment and the power supply condition, and the method comprises the following specific steps of:
Selecting a least mean square error (LMS) algorithm to adapt to filtering and prediction in a non-static environment; the formula of the LMS algorithm is as follows:
wn＝wo+μ·e(t)·x(t)
Wherein w n and w o respectively represent weight vectors before and after updating, μ is a step size parameter, and the learning rate is controlled; e (t) is the prediction error, x (t) is the input signal;
dynamically adjusting the step size parameter mu according to the change of the real-time data stream:
If the prediction error increases, decreasing mu to decrease the weight adjustment amplitude;
if the prediction error is reduced, mu is increased to accelerate the learning speed;
Continuously monitoring a prediction error e (t) and performing real-time feedback adjustment according to the error magnitude; periodically monitoring the stability and consistency of the input signal x (t) to ensure filter performance;
statistical testing is used to ensure that the input signal varies within a reasonable range.
3. The adaptive deep learning transformer test instrument calibration system of claim 2, wherein: the power parameter detection sub-module and the environment parameter detection sub-module both transmit the detected data to the data processing sub-module, the data processing sub-module processes the detected data and transmits the processed data to the parameter adaptation sub-module, and the parameter adaptation sub-module selects the optimal test parameters according to the processed data and transmits the optimal test parameters to the modularized test module.
4. The adaptive deep learning transformer test instrument calibration system of claim 3, wherein: the modular test module comprises a plurality of modules,
Automatically selecting and generating a test sequence according to the data provided by the self-adaptive input module, and implementing conditional logic;
Monitoring in real time during the test, and if an abnormal value is detected, immediately adjusting test parameters or suspending the test;
The implementation condition logic includes:
if the temperature exceeds the preset threshold, automatically testing the thermal stress; if the temperature is lower than 0 ℃, adding a cold start test;
if the humidity exceeds the threshold, performing a reinforced insulation test; if the humidity is lower than 30%, the performance test in a dry environment is increased;
if the power supply fluctuation exceeds the standard range of +/-5%, reducing the test load to avoid damaging equipment; if the power supply is stable, a load test is added to evaluate the maximum bearing capacity;
If the current or voltage exceeds 95% of the specification of the equipment, an overload protection test is executed; if the current or voltage is lower than a specified minimum operation threshold, checking the low load performance of the device;
if the historical test data show a performance decline trend, increasing a performance decline test; if the historical test data show abnormal fluctuation, performing fault detection and stability test;
If a record of maintaining or replacing the parts is recently available, performing a full functional test to ensure that all the parts work normally; maintenance is not performed for a long time, and comprehensive inspection and preventive testing are added.
5. The adaptive deep learning transformer test instrument calibration system of claim 4, wherein: the real-time calibration and feedback module includes,
Receiving test data from the modularized test module and synchronizing the test data with standard data in a cloud database;
comparing the received test data with the standard data of the cloud by using a real-time data processing algorithm;
Calculating a deviation by using a difference analysis formula;
defining a deviation threshold, and triggering a calibration procedure when the deviation exceeds the threshold;
Automatically adjusting calibration settings of the test equipment according to the suggestions of the self-learning and optimization module;
Creating a detailed calibration report, including data before and after calibration, adjustments made and suggestions;
transmitting feedback to a user or technician via a user interface or telecommunications system;
And continuously monitoring the calibration effect and adjusting according to the subsequent test data.
6. The adaptive deep learning transformer test instrument calibration system of claim 5, wherein: the self-learning and optimizing module comprises a self-learning and optimizing module,
Receiving environmental parameters, power supply conditions and test result data from the adaptive input module and the modular test module;
denoising, outlier detection and normalization are carried out on the received data;
The principal component analysis PCA is used for reducing the data dimension and improving the processing efficiency;
Selecting a convolutional neural network CNN or a cyclic neural network RNN, processing a target according to data characteristics, and training a model by using a large amount of historical data so as to learn complex modes and correlations in the data;
extracting key features by using the trained model, and identifying an abnormal mode in calibration;
according to the model output, an optimization algorithm is applied to automatically formulate a calibration strategy;
generating specific calibration suggestions according to an optimization strategy, wherein the calibration suggestions comprise adjustment parameters and expected effects;
providing clear guidelines and predictive results.
7. The adaptive deep learning transformer test instrument calibration system of claim 6, wherein: the virtual simulation module comprises an environment building sub-module, a simulation engine sub-module, a result analysis sub-module and an interaction interface sub-module;
The environment building module is responsible for creating and maintaining a virtual environment model of the transformer and storing the model in a database; the simulation engine submodule loads a model from the database and executes simulation according to a strategy; the result analysis submodule analyzes the simulation result and adjusts the strategy according to the analysis result; the interactive interface sub-module provides an interactive interface for a user to view the simulation environment and the result.
8. An adaptive deep learning transformer test instrument calibration method based on the adaptive deep learning transformer test instrument calibration system of any one of claims 1-7, characterized in that: comprising the steps of (a) a step of,
Monitoring test environment and power supply conditions in real time through a sensor by using an adaptive input module, and preprocessing and standardizing the data;
in the modularized test module, automatically generating and executing a test sequence for the transformer according to the monitored environment and power supply data, and recording a test result;
The self-learning and optimizing module uses a deep learning model to analyze the collected test data, and identifies patterns and potential calibration deviations;
Based on the analysis result of the deep learning model, the self-learning and optimizing module formulates a calibration strategy and generates specific calibration suggestions;
And the real-time calibration and feedback module compares the test data with cloud standard data, automatically executes calibration, and feeds back a calibration result and advice to a user.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that: the processor, when executing the computer program, implements the steps of the adaptive deep learning transformer test instrument calibration method of claim 8.
10. A computer-readable storage medium having stored thereon a computer program, characterized by: the computer program when executed by a processor implements the steps of the adaptive deep learning transformer test instrument calibration method of claim 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311566368.XA CN117970211A (en) | 2023-11-23 | 2023-11-23 | Self-adaptive deep learning transformer test instrument calibration system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311566368.XA CN117970211A (en) | 2023-11-23 | 2023-11-23 | Self-adaptive deep learning transformer test instrument calibration system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117970211A true CN117970211A (en) | 2024-05-03 |
Family
ID=90846749
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311566368.XA Pending CN117970211A (en) | 2023-11-23 | 2023-11-23 | Self-adaptive deep learning transformer test instrument calibration system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117970211A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118330447A (en) * | 2024-06-13 | 2024-07-12 | 深圳市晶凯电子技术有限公司 | Semiconductor integrated circuit test system |
| CN118797246A (en) * | 2024-09-13 | 2024-10-18 | 中海石油技术检测有限公司 | An intelligent method and system for instrument calibration |
| CN119291356A (en) * | 2024-12-10 | 2025-01-10 | 国网浙江省电力有限公司营销服务中心 | Automatic test management method and system for electrostatic discharge immunity |
-
2023
- 2023-11-23 CN CN202311566368.XA patent/CN117970211A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118330447A (en) * | 2024-06-13 | 2024-07-12 | 深圳市晶凯电子技术有限公司 | Semiconductor integrated circuit test system |
| CN118330447B (en) * | 2024-06-13 | 2024-09-03 | 深圳市晶凯电子技术有限公司 | Semiconductor integrated circuit test system |
| CN118797246A (en) * | 2024-09-13 | 2024-10-18 | 中海石油技术检测有限公司 | An intelligent method and system for instrument calibration |
| CN119291356A (en) * | 2024-12-10 | 2025-01-10 | 国网浙江省电力有限公司营销服务中心 | Automatic test management method and system for electrostatic discharge immunity |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117970211A (en) | Self-adaptive deep learning transformer test instrument calibration system | |
| CN114430199A (en) | Cubical switchboard operation supervisory systems based on big data | |
| CN114326594B (en) | Machine tool performance evaluation system based on machine tool data and evaluation method thereof | |
| CN113485268B (en) | Industrial Internet of things-based multi-scene distributed information control system | |
| CN117891688B (en) | Operation and maintenance management system and method for generated AI (advanced technology attachment) equipment | |
| CN117038048B (en) | Remote fault processing method and system for medical instrument | |
| CN116388402B (en) | Abnormality alarm analysis method applied to power transformation equipment | |
| CN118211837A (en) | A performance evaluation method and device for smart electric meter | |
| CN117498814B (en) | Power amplifier protection method and system based on temperature real-time monitoring | |
| CN116915535A (en) | Wireless communication's intelligent home systems | |
| CN116805068A (en) | Fault monitoring and early warning system and method based on big data | |
| CN118586874A (en) | An integrated management and optimization system for high-strength cable production | |
| CN116107369A (en) | Explosion-proof frequency converter control system | |
| CN111523662A (en) | Dynamic process control limit determination method and device based on ADALINE neural network | |
| CN118207587B (en) | Remote monitoring, regulating and controlling system for hydrogen production by alkaline water electrolysis | |
| CN110045699A (en) | Data center's power manages system and method | |
| CN117783795B (en) | Comprehensive analysis method and system for insulation state of converter transformer valve side sleeve by edge analysis | |
| CN118777926A (en) | An intelligent power supply monitoring method for a high-speed digital storage oscilloscope | |
| CN118801759A (en) | Methods for improving the anti-interference ability of motor drive chips | |
| CN118011926A (en) | Device and method for realizing remote monitoring and adjustment of rotational molding machine by utilizing Internet of things technology | |
| CN116679139A (en) | Cable replacement monitoring system and method | |
| CN118332484B (en) | Resonance pressure sensor detection system and method for auxiliary signal conditioning | |
| CN119027034B (en) | AI-based tobacco storage optimization system | |
| CN119001377B (en) | A capacitor bank insulation status monitoring system and method | |
| CN119148664B (en) | Intelligent factory management platform and management method based on digital twinning |
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 |