CN114065623A - IGBT remaining life prediction method and related device - Google Patents
IGBT remaining life prediction method and related device Download PDFInfo
- Publication number
- CN114065623A CN114065623A CN202111342562.0A CN202111342562A CN114065623A CN 114065623 A CN114065623 A CN 114065623A CN 202111342562 A CN202111342562 A CN 202111342562A CN 114065623 A CN114065623 A CN 114065623A
- Authority
- CN
- China
- Prior art keywords
- turn
- igbt
- spike voltage
- voltage
- neural network
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
Abstract
The application discloses a method and a related device for predicting the residual life of an IGBT, wherein the method comprises the following steps: extracting the current turn-off peak voltage of the IGBT from the preset turn-off voltage, wherein the current turn-off peak voltage comprises gate emitter turn-off peak voltage and emitter turn-off peak voltage; and inputting the current turn-off spike voltage into a preset BP neural network model for result prediction to obtain a service life prediction result, wherein the preset BP neural network model comprises a cost function consisting of root mean square errors. Selecting gate emitter turn-off peak voltage and emitter turn-off peak voltage as prediction indexes of the residual life of the IGBT with pertinence; the BP neural network model is a model for error feedback training, can ensure the reliability of results, and has strong generalization capability and applicability. Therefore, the method and the device solve the technical problems that in the prior art, the selected data indexes are lack of pertinence, the use of the model is limited, and the generalization capability of the model is poor, so that the error of the prediction result is large.
Description
Technical Field
The application relates to the technical field of service life estimation of electronic devices, in particular to a method and a related device for predicting the residual service life of an IGBT.
Background
Insulated Gate Bipolar Transistor (IGBT) is used as a core device of a power electronic device, and the normal operation of the whole power system is directly affected by the operating life length, the operating stability, fault factors and the like of the IGBT. The IGBT can be aged or failed gradually due to the high load of a power transmission and distribution system, the severe environment in which the IGBT operates, factors such as overvoltage, high temperature and circulating power, and the like, so that a fault problem is caused, and great loss is caused to national economy. In the face of the situation, how to effectively predict the faults of the IGBTs has important significance for reducing the maintenance cost of the power system and improving the running stability of the power system.
In the existing IGBT service life prediction method, prediction models are established from the perspective of a mechanism model and a probability model, the prediction error is relatively small in an experimental result, but a large error occurs in a working condition environment. The reasons for the large errors include that the research parameter selection lacks pertinence, or the data acquisition period is long, so that the model is limited, or the generalization capability of the selected model is poor, and the like.
Disclosure of Invention
The application provides a method and a related device for predicting the residual life of an IGBT (insulated gate bipolar transistor), which are used for solving the technical problems that the data indexes selected in the prior art lack pertinence, the use of a model is limited, and the generalization capability of the model is poor, so that the error of the prediction result is large.
In view of this, the first aspect of the present application provides a method for predicting a remaining lifetime of an IGBT, including:
extracting a current turn-off spike voltage of the IGBT from preset turn-off voltages, wherein the current turn-off spike voltage comprises a gate emitter turn-off spike voltage and an emitter turn-off spike voltage;
and inputting the current turn-off spike voltage into a preset BP neural network model for result prediction to obtain a life prediction result, wherein the preset BP neural network model comprises a cost function consisting of root mean square errors.
Preferably, the extracting, in the preset turn-off voltage, a current turn-off spike voltage of the IGBT, where the current turn-off spike voltage includes a gate emitter turn-off spike voltage and an emitter turn-off spike voltage, and then further includes:
and smoothing the current turn-off peak voltage by adopting a wavelet algorithm, and then carrying out standardization processing.
Preferably, the step of inputting the current turn-off spike voltage into a preset BP neural network model for result prediction to obtain a life prediction result further includes:
inputting the turn-off spike voltage training set into an initial BP neural network model for prediction training to obtain a pre-training BP neural network model;
verifying the pre-trained BP neural network model by cutting off a peak voltage verification set to obtain a verification prediction result, and calculating a corresponding prediction error according to the verification prediction result;
and taking the pre-training BP neural network model with the minimum prediction error value as a preset BP neural network model.
Preferably, the inputting the off spike voltage training set into the initial BP neural network model for prediction training to obtain a pre-trained BP neural network model, before further comprising:
carrying out an IGBT aging test by circularly applying a modulation PWM alternating voltage to an IGBT grid to obtain a test turn-off spike voltage set, wherein the test turn-off spike voltage set comprises a test gate emitter turn-off spike voltage and a test set emitter turn-off spike voltage;
and dividing the test turn-off spike voltage set into a turn-off spike voltage training set and a turn-off spike voltage verification set according to a preset proportion.
The present application provides in a second aspect an IGBT remaining life prediction apparatus, including:
the data extraction module is used for extracting the current turn-off spike voltage of the IGBT from preset turn-off voltage, wherein the current turn-off spike voltage comprises gate emitter turn-off spike voltage and emitter turn-off spike voltage;
and the service life prediction module is used for inputting the current turn-off spike voltage into a preset BP neural network model for result prediction to obtain a service life prediction result, and the preset BP neural network model comprises a cost function consisting of root mean square error.
Preferably, the method further comprises the following steps:
and the preprocessing module is used for smoothing the current turn-off spike voltage by adopting a wavelet algorithm and then carrying out standardization processing.
Preferably, the method further comprises the following steps:
the pre-training module is used for inputting the turn-off spike voltage training set into the initial BP neural network model for prediction training to obtain a pre-training BP neural network model;
the model verification module is used for verifying the pre-training BP neural network model by cutting off a peak voltage verification set to obtain a verification prediction result and calculating a corresponding prediction error according to the verification prediction result;
and the model screening module is used for taking the pre-training BP neural network model with the minimum prediction error value as a preset BP neural network model.
Preferably, the method further comprises the following steps:
the aging test module is used for carrying out an IGBT aging test in a mode of applying modulated PWM alternating voltage to an IGBT grid in a circulating mode to obtain a test turn-off peak voltage set, and the test turn-off peak voltage set comprises a test gate emitter turn-off peak voltage and a test set emitter turn-off peak voltage;
and the data dividing module is used for dividing the test turn-off spike voltage set into the turn-off spike voltage training set and the turn-off spike voltage verification set according to a preset proportion.
A third aspect of the present application provides an IGBT remaining life predicting device, the device including a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is configured to execute the method for predicting the remaining lifetime of the IGBT according to the first aspect according to instructions in the program code.
A fourth aspect of the present application provides a computer-readable storage medium for storing program code for executing the method for predicting the remaining lifetime of an IGBT according to the first aspect.
According to the technical scheme, the embodiment of the application has the following advantages:
the application provides a method for predicting the residual life of an IGBT, which comprises the following steps: extracting the current turn-off peak voltage of the IGBT from the preset turn-off voltage, wherein the current turn-off peak voltage comprises gate emitter turn-off peak voltage and emitter turn-off peak voltage; and inputting the current turn-off spike voltage into a preset BP neural network model for result prediction to obtain a service life prediction result, wherein the preset BP neural network model comprises a cost function consisting of root mean square errors.
According to the method for predicting the residual life of the IGBT, the gate emitter turn-off peak voltage and the emitter turn-off peak voltage are selected as prediction index data of the residual life of the IGBT, index selection is targeted, and the accuracy of a prediction result can be improved to a certain extent; the BP neural network model is a model for error feedback training, so that the reliability of a result can be guaranteed by adopting the BP neural network model for life prediction, and the model for life prediction is obtained by training specific related data and has stronger generalization capability and applicability. Therefore, the method and the device can solve the technical problems that the data indexes selected in the prior art lack pertinence, the use of the model is limited, and the generalization capability of the model is poor, so that the error of the prediction result is large.
Drawings
Fig. 1 is a schematic flowchart of a method for predicting the remaining life of an IGBT according to an embodiment of the present application;
fig. 2 is another schematic flow chart of an IGBT remaining life prediction method provided in the embodiment of the present application
Fig. 3 is a schematic structural diagram of an IGBT remaining life prediction apparatus provided in an embodiment of the present application;
FIG. 4 is a graph showing a test gate emitter turn-off spike voltage waveform of an accelerated aging test provided by an embodiment of the present application;
fig. 5 is a schematic diagram of a test collector-emitter turn-off spike voltage waveform of an accelerated aging test provided in an embodiment of the present application.
Detailed Description
In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
For convenience of understanding, referring to fig. 1, a first embodiment of a method for predicting the remaining life of an IGBT provided by the present application includes:
The preset turn-off voltage generally refers to a current value obtained in an actual working condition environment, and the predicting task is to predict the residual service life of the IGBT device in current operation and accurately estimate the current working time of the IGBT. An insulated Gate bipolar transistor (igbt) is an insulated Gate bipolar transistor (igbt), and is a composite fully-controlled voltage-driven power semiconductor device composed of a Bipolar Junction Transistor (BJT) and an insulated Gate field effect transistor (MOS). An IGBT specifically includes a source (i.e., emitter E), a drain (i.e., base or collector N), and a gate (i.e., gate G) that is located in a control region of the device, referred to as the gate region. The gate emitter turn-off spike voltage and the emitter turn-off spike voltage in this embodiment are the gate and collector turn-off spike voltages, respectively.
And 102, inputting the current turn-off spike voltage into a preset BP neural network model for result prediction to obtain a life prediction result, wherein the preset BP neural network model comprises a cost function consisting of root mean square errors.
The preset BP neural network model is a trained model which can be directly used for IGBT service life prediction, the received data is the current turn-off spike voltage, and the output result is the residual service life of the IGBT. The preset BP neural network model is obtained by training according to a cost function, the cost function is used for calculating the root mean square error between the predicted life value and the true value, the prediction performance of the model is judged according to the error, and then the excellent model is screened and used in the subsequent prediction work.
According to the method for predicting the residual life of the IGBT, the gate emitter turn-off peak voltage and the emitter turn-off peak voltage are selected as prediction index data of the residual life of the IGBT, index selection is targeted, and the accuracy of a prediction result can be improved to a certain extent; the BP neural network model is a model for error feedback training, so that the reliability of a result can be guaranteed by adopting the BP neural network model for life prediction, and the model for life prediction is obtained by training specific related data and has stronger generalization capability and applicability. Therefore, the method and the device for predicting the data indexes can solve the technical problems that the data indexes selected in the prior art are lack of pertinence, the use of the model is limited, and the generalization capability of the model is poor, so that the error of the prediction result is large.
For easy understanding, please refer to fig. 2, the present application provides a second embodiment of a method for predicting a remaining lifetime of an IGBT, including:
The preset turn-off voltage of the operating IGBT is acquired, and then the current turn-off spike voltage is extracted from the preset turn-off voltage and used as current prediction preparation data.
The smoothing and standardization processing of the data is helpful for improving the accuracy of the prediction result, so that some necessary processing can be performed on the acquired data by some means according to actual conditions, so as to ensure the data quality. The normalization process may be in accordance with the following equation:
wherein, x is the data to be processed, mu is the mean value corresponding to the data to be processed, and sigma is the standard deviation corresponding to the data to be processed.
And 203, carrying out an IGBT aging test by circularly applying a modulation PWM alternating voltage to the gate of the IGBT to obtain a test turn-off spike voltage set, wherein the test turn-off spike voltage set comprises a test gate emitter turn-off spike voltage and a test set emitter turn-off spike voltage.
Carrying out accelerated aging test on the IGBTs of the same type or batch of the IGBT to be predicted, and collecting gate emitter turn-off peak voltage and emitter turn-off peak voltage of the IGBT; the specific accelerated aging test process is as follows: and applying the modulated PWM alternating current to the grid electrode of the IGBT device to enable the device to be frequently switched on and off and the temperature to rise, controlling the device to start cooling after the temperature is maximum preset value, and reapplying the PWM alternating current when the temperature is reduced to a preset minimum value, so that the aging fault failure of the device is accelerated in a circulating manner. In the process of accelerating power aging, the cyclic process of applying power is approximately uniform, so that the service life of the IGBT can be uniformly distributed in the whole process of accelerating aging, and finally, the test gate emitter turn-off peak voltage and the test collector emitter turn-off peak voltage in the process of accelerated aging test can be obtained, specifically refer to fig. 4 and 5.
And 204, dividing the test turn-off spike voltage set into a turn-off spike voltage training set and a turn-off spike voltage verification set according to a preset proportion.
Before the data set is divided, the preprocessing operation, namely filtering smoothing, standardization processing and the like, can be performed on the test turn-off spike voltage set, the quality of test data can be improved, and the training effect of the model is guaranteed. The proportion of the divided data sets can be set according to actual conditions, and in the embodiment, the test turn-off spike voltage set is divided into the training set and the verification set according to the proportion of 8: 2.
And 205, inputting the shut-off spike voltage training set into the initial BP neural network model for prediction training to obtain a pre-training BP neural network model.
And in the training process, a cost function is adopted for model optimization, the prediction error is calculated according to the predicted value, and the prediction error is transmitted back to be used for training the excitation model, so that the model is continuously adapted to the characteristics of the index data. And the turn-off spike voltage training set comprises a basic training set and a test set, so that the model can be continuously perfected in the training process according to the cost function.
And step 206, verifying the pre-trained BP neural network model by cutting off the peak voltage verification set to obtain a verification prediction result, and calculating a corresponding prediction error according to the verification prediction result.
The verification aims to obtain the prediction errors of all the pre-trained BP neural network models and determine the prediction performance of all the pre-trained models.
And step 207, taking the pre-trained BP neural network model with the minimum prediction error value as a preset BP neural network model.
The minimum prediction error value shows that the prediction performance of the pre-training BP neural network model is optimal, and the accuracy of the obtained result is highest.
And 208, inputting the current turn-off spike voltage into a preset BP neural network model for result prediction to obtain a life prediction result, wherein the preset BP neural network model comprises a cost function consisting of root mean square errors.
According to the method for predicting the residual life of the IGBT, the gate emitter turn-off peak voltage and the emitter turn-off peak voltage are selected as prediction index data of the residual life of the IGBT, index selection is targeted, and the accuracy of a prediction result can be improved to a certain extent; the BP neural network model is a model for error feedback training, so that the reliability of a result can be guaranteed by adopting the BP neural network model for life prediction, and the model for life prediction is obtained by training specific related data and has stronger generalization capability and applicability. Therefore, the method and the device for predicting the data indexes can solve the technical problems that the data indexes selected in the prior art are lack of pertinence, the use of the model is limited, and the generalization capability of the model is poor, so that the error of the prediction result is large.
For ease of understanding, referring to fig. 3, the present application provides an embodiment of an IGBT remaining life prediction apparatus, including:
the data extraction module 301 is configured to extract a current turn-off spike voltage of the IGBT from a preset turn-off voltage, where the current turn-off spike voltage includes a gate emitter turn-off spike voltage and an emitter turn-off spike voltage;
and the life prediction module 302 is configured to input the current turn-off spike voltage into a preset BP neural network model for result prediction to obtain a life prediction result, where the preset BP neural network model includes a cost function formed by a root mean square error.
Further, still include:
the preprocessing module 303 is configured to perform smoothing processing on the current turn-off peak voltage by using a wavelet algorithm, and then perform normalization processing.
Further, still include:
a pre-training module 304, configured to input the turn-off spike voltage training set into the initial BP neural network model for predictive training, so as to obtain a pre-training BP neural network model;
the model verification module 305 is configured to verify the pre-trained BP neural network model by turning off the spike voltage verification set to obtain a verification prediction result, and calculate a corresponding prediction error according to the verification prediction result;
and the model screening module 306 is configured to use the pre-trained BP neural network model with the smallest prediction error value as the preset BP neural network model.
Further, still include:
the aging test module 307 is used for performing an IGBT aging test by cyclically applying a modulated PWM alternating voltage to an IGBT gate to obtain a test turn-off spike voltage set, where the test turn-off spike voltage set includes a test gate emitter turn-off spike voltage and a test set emitter turn-off spike voltage;
and the data dividing module 308 is configured to divide the test turn-off spike voltage set into a turn-off spike voltage training set and a turn-off spike voltage verification set according to a preset ratio.
The application also provides IGBT residual life prediction equipment, which comprises a processor and a memory;
the memory is used for storing the program codes and transmitting the program codes to the processor;
the processor is used for executing the IGBT remaining life prediction method in the method embodiment according to the instructions in the program codes.
The present application also provides a computer-readable storage medium for storing program code for executing the IGBT remaining life prediction method in the above method embodiment.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for executing all or part of the steps of the method described in the embodiments of the present application through a computer device (which may be a personal computer, a server, or a network device). And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.
Claims (10)
1. An IGBT remaining life prediction method is characterized by comprising the following steps:
extracting a current turn-off spike voltage of the IGBT from preset turn-off voltages, wherein the current turn-off spike voltage comprises a gate emitter turn-off spike voltage and an emitter turn-off spike voltage;
and inputting the current turn-off spike voltage into a preset BP neural network model for result prediction to obtain a life prediction result, wherein the preset BP neural network model comprises a cost function consisting of root mean square errors.
2. The IGBT remaining life prediction method according to claim 1, wherein the extracting a current turn-off spike voltage of the IGBT in a preset turn-off voltage, the current turn-off spike voltage including a gate emitter turn-off spike voltage and an emitter turn-off spike voltage, and thereafter further comprising:
and smoothing the current turn-off peak voltage by adopting a wavelet algorithm, and then carrying out standardization processing.
3. The method for predicting the remaining life of the IGBT according to claim 1, wherein the step of inputting the current turn-off spike voltage into a preset BP neural network model for result prediction to obtain a life prediction result further comprises:
inputting the turn-off spike voltage training set into an initial BP neural network model for prediction training to obtain a pre-training BP neural network model;
verifying the pre-trained BP neural network model by cutting off a peak voltage verification set to obtain a verification prediction result, and calculating a corresponding prediction error according to the verification prediction result;
and taking the pre-training BP neural network model with the minimum prediction error value as a preset BP neural network model.
4. The method for predicting the remaining life of the IGBT according to claim 3, wherein the step of inputting the turn-off spike voltage training set into an initial BP neural network model for prediction training to obtain a pre-trained BP neural network model further comprises:
carrying out an IGBT aging test by circularly applying a modulation PWM alternating voltage to an IGBT grid to obtain a test turn-off spike voltage set, wherein the test turn-off spike voltage set comprises a test gate emitter turn-off spike voltage and a test set emitter turn-off spike voltage;
and dividing the test turn-off spike voltage set into a turn-off spike voltage training set and a turn-off spike voltage verification set according to a preset proportion.
5. An IGBT remaining life prediction apparatus, characterized by comprising:
the data extraction module is used for extracting the current turn-off spike voltage of the IGBT from preset turn-off voltage, wherein the current turn-off spike voltage comprises gate emitter turn-off spike voltage and emitter turn-off spike voltage;
and the service life prediction module is used for inputting the current turn-off spike voltage into a preset BP neural network model for result prediction to obtain a service life prediction result, and the preset BP neural network model comprises a cost function consisting of root mean square error.
6. The IGBT remaining life prediction device according to claim 5, further comprising:
and the preprocessing module is used for smoothing the current turn-off spike voltage by adopting a wavelet algorithm and then carrying out standardization processing.
7. The IGBT remaining life prediction device according to claim 5, further comprising:
the pre-training module is used for inputting the turn-off spike voltage training set into the initial BP neural network model for prediction training to obtain a pre-training BP neural network model;
the model verification module is used for verifying the pre-training BP neural network model by cutting off a peak voltage verification set to obtain a verification prediction result and calculating a corresponding prediction error according to the verification prediction result;
and the model screening module is used for taking the pre-training BP neural network model with the minimum prediction error value as a preset BP neural network model.
8. The IGBT remaining life prediction device according to claim 7, further comprising:
the aging test module is used for carrying out an IGBT aging test in a mode of applying modulated PWM alternating voltage to an IGBT grid in a circulating mode to obtain a test turn-off peak voltage set, and the test turn-off peak voltage set comprises a test gate emitter turn-off peak voltage and a test set emitter turn-off peak voltage;
and the data dividing module is used for dividing the test turn-off spike voltage set into the turn-off spike voltage training set and the turn-off spike voltage verification set according to a preset proportion.
9. An IGBT remaining life prediction device is characterized by comprising a processor and a memory;
the memory is used for storing program codes and transmitting the program codes to the processor;
the processor is used for executing the IGBT remaining life prediction method according to any one of claims 1-4 according to instructions in the program code.
10. A computer-readable storage medium for storing program code for executing the IGBT remaining life prediction method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111342562.0A CN114065623A (en) | 2021-11-12 | 2021-11-12 | IGBT remaining life prediction method and related device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111342562.0A CN114065623A (en) | 2021-11-12 | 2021-11-12 | IGBT remaining life prediction method and related device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114065623A true CN114065623A (en) | 2022-02-18 |
Family
ID=80271933
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111342562.0A Pending CN114065623A (en) | 2021-11-12 | 2021-11-12 | IGBT remaining life prediction method and related device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114065623A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114447900A (en) * | 2022-02-28 | 2022-05-06 | 河南嘉晨智能控制股份有限公司 | Method for actively suppressing peak voltage of power device |
| CN117590190A (en) * | 2024-01-18 | 2024-02-23 | 国网山东省电力公司营销服务中心(计量中心) | Photovoltaic inverter IGBT aging fault prediction method and system |
-
2021
- 2021-11-12 CN CN202111342562.0A patent/CN114065623A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114447900A (en) * | 2022-02-28 | 2022-05-06 | 河南嘉晨智能控制股份有限公司 | Method for actively suppressing peak voltage of power device |
| CN114447900B (en) * | 2022-02-28 | 2024-02-09 | 河南嘉晨智能控制股份有限公司 | Method for actively suppressing spike voltage of power device |
| CN117590190A (en) * | 2024-01-18 | 2024-02-23 | 国网山东省电力公司营销服务中心(计量中心) | Photovoltaic inverter IGBT aging fault prediction method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114065623A (en) | IGBT remaining life prediction method and related device | |
| CN107015875B (en) | Method and device for evaluating storage life of electronic complete machine | |
| CN110852509A (en) | Fault prediction method and device of IGBT module and storage medium | |
| CN108448566B (en) | Online hybrid simulation method and system for power system | |
| Huda et al. | Distribution system reliability assessment using sequential multilevel Monte Carlo method | |
| CN111914000B (en) | Server power capping method and system based on power consumption prediction model | |
| CN112072715B (en) | Method and device for determining new energy acceptance of power grid in consideration of transient voltage constraint | |
| CN107544008B (en) | Vehicle-mounted IGBT state monitoring method and device | |
| CN110797865B (en) | Data-driven power supply weak link identification method and system | |
| CN116611011A (en) | Transient overvoltage amplitude prediction method, system, terminal and medium | |
| CN107612290B (en) | Optimization control method and system for capacitor voltage sequencing frequency of current converter | |
| CN107785875B (en) | Method and system for calculating line operation overvoltage generated in case of single-pole ground fault | |
| Davoodi et al. | System-level reliability analysis of a repairable power electronic-based power system considering non-constant failure rates | |
| CN110148065B (en) | Short-circuit current calculation processing method and system considering flexible and direct influence | |
| CN114725887A (en) | Overcurrent protection method, device, equipment and storage medium | |
| CN108629093B (en) | Noise-aware dynamic voltage frequency regulation transition sequence design method | |
| CN112712443A (en) | Event analysis method and analysis device for converter station | |
| CN115858324B (en) | AI-based IT equipment fault processing method, apparatus, equipment and medium | |
| CN110365234B (en) | Modular multi-level converter valve submodule switching method and device | |
| CN113065762B (en) | Rapid solving method, system, equipment and storage medium for new energy power rejection rate of electric power system | |
| CN112467782B (en) | Operation safety checking method and device of water-light complementary system and electronic equipment | |
| CN112417643B (en) | Thermal power generating unit maximum output real-time evaluation method and system based on blower current | |
| CN117514730B (en) | Water pump power adjusting method and system based on MPPT of photovoltaic inverter | |
| CN117335416B (en) | Method, device, equipment and storage medium for optimizing power load | |
| CN117314683B (en) | Power operation and maintenance method, device, equipment and 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 |