CN112485630A - IGBT health state monitoring method based on parameter transformation - Google Patents
IGBT health state monitoring method based on parameter transformation Download PDFInfo
- Publication number
- CN112485630A CN112485630A CN202011351857.XA CN202011351857A CN112485630A CN 112485630 A CN112485630 A CN 112485630A CN 202011351857 A CN202011351857 A CN 202011351857A CN 112485630 A CN112485630 A CN 112485630A
- Authority
- CN
- China
- Prior art keywords
- igbt
- health
- parameter
- characteristic
- amplitude
- 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
- 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
- G01R31/26—Testing of individual semiconductor devices
- G01R31/2642—Testing semiconductor operation lifetime or reliability, e.g. by accelerated life tests
Abstract
The invention discloses an IGBT health state monitoring method based on parametric transformation, which comprises the following steps: s1, characteristic data acquisition: establishing an aging data acquisition platform, and acquiring a voltage value Vce between a collector and an emitter of the IGBT with the same specification as the target IGBT under different working conditions; s2, data processing: selecting Vce time domain characteristics which represent IGBT degradation behaviors with the same specification as the target IGBT, and performing dimension reduction and simplification on the selected characteristics by using a principal component analysis algorithm; s3, obtaining a new parameter: selecting the first characteristic quantity after the principal component analysis processing as a new health index parameter I; s4, establishing an aging characteristic database: establishing a database about the health condition of the target IGBT and the parameter I amplitude according to the parameter I amplitude of the collected IGBT with the same specification as the target IGBT under different health conditions; s5, health state monitoring: and acquiring the parameter I amplitude of the target IGBT, comparing the parameter I amplitude with the built aging characteristic database, and judging the health condition of the IGBT. The invention provides an IGBT health state monitoring method based on parameter transformation, which is characterized in that a new IGBT health index is obtained by reducing the dimension of a feature space through a principal component analysis algorithm, and the problem of selection of IGBT operation degradation trend parameters is solved.
Description
Technical Field
The invention relates to the field of semiconductors, in particular to an IGBT health state monitoring method based on parameter transformation.
Background
With the gradual attention on the environmental problems, people are more and more favored to select low-carbon and environment-friendly production and living modes, and under the large environment, the development of global renewable energy sources is pushing a wind energy system to become a mainstream energy source. As is known from the wind energy systems currently in use, the availability of wind energy systems is extremely high, the energy utilization of which depends on the turbine, and can reach an average of 96%. Although the energy efficiency of a wind energy system is high, it is still subject to mechanical and electrical failures. According to investigations, it is known that in wind energy systems the electrical failure rate is much higher than the mechanical failure rate. The electrical part of the wind energy system consists of a doubly-fed induction generator, a power converter and a transformer.
At present, the actual service life of the power converter is smaller than that of other subsystems, and the power converter failure accounts for about 20% of all failures of the wind energy system counted by taking years as a time scale. According to a recent investigation, the power semiconductor device is the weakest component in the power converter, which becomes the most important component in the power converter due to the large number of semiconductors in the power converter. The IGBTs in turn account for 42% of the power semiconductor switches in the wind energy system. Therefore, a system is needed that can achieve accurate state of health monitoring and operational condition management for IGBTs that can prevent shutdown of the wind energy system due to IGBT failure.
As is known, health status monitoring methods can be divided into three different types, respectively: physical-based, data-based, and hybrid approaches. Each method utilizes different information. In data-based methods, the starting point for research is almost always to find out what parameters are the most suitable ones for characterizing the health of the IGBT, and the selection of suitable data depends on many factors, such as noise and fluctuations.
Disclosure of Invention
The invention provides a parameter transformation-based IGBT health state monitoring method, aiming at the problem that IGBT component health state monitoring parameters are difficult to select.
In order to achieve the purpose of the invention, the invention adopts the technical scheme that:
the IGBT health state monitoring method based on parametric transformation comprises the following steps:
s1, characteristic data acquisition: establishing an aging data acquisition platform, and acquiring a voltage value Vce between a collector and an emitter of the IGBT with the same specification as the target IGBT under different working conditions;
s2, data processing: selecting Vce time domain characteristics which represent IGBT degradation behaviors with the same specification as the target IGBT, and performing dimension reduction and simplification on the selected characteristics by using a principal component analysis algorithm;
s3, obtaining a new parameter: selecting the first characteristic quantity after the principal component analysis processing as a new health index parameter I;
s4, establishing an aging characteristic database: establishing a database about the health condition of the target IGBT and the parameter I amplitude according to the parameter I amplitude of the collected IGBT with the same specification as the target IGBT under different health conditions;
s5, health state monitoring: and acquiring the parameter I amplitude of the target IGBT, comparing the parameter I amplitude with the built aging characteristic database, and judging the health condition of the IGBT.
Further, in step S1, the operating conditions include a gate voltage between the gate and the emitter, a collector current, and a case temperature.
Further, in step S2, the time domain characteristics such as the standard deviation, peak-to-peak value, and average value of Vce are selected as the original characteristics for health status monitoring.
Further, in step S2, the feature space obtained in the feature extraction is subjected to dimensionality reduction, a new spatial dimension is estimated by using a correlation dimension estimation algorithm, and the extracted features are converted into a low-dimensional space by using a principal component analysis technique.
Further, in step S3, since the first feature has the highest feature value in the new feature space, it is selected to estimate the operation degradation condition of the IGBT.
The invention has the beneficial effects that: the invention provides an IGBT health state monitoring method based on parameter transformation. The feature space is subjected to dimensionality reduction through a principal component analysis algorithm to obtain a new IGBT health index parameter I, the problem of selection of IGBT operation degradation trend parameters is solved, and the health state monitoring of the IGBT is achieved through better parameters.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
The following description of the embodiments of the present invention is provided to facilitate the understanding of the present invention by those skilled in the art, but it should be understood that the present invention is not limited to the scope of the embodiments, and it will be apparent to those skilled in the art that various changes may be made without departing from the spirit and scope of the invention as defined and defined in the appended claims, and all matters produced by the invention using the inventive concept are protected.
As shown in fig. 1, the IGBT health state monitoring method based on parametric transformation includes the following steps:
s1, characteristic data acquisition: establishing an aging data acquisition platform, and acquiring a voltage value Vce between a collector and an emitter of the IGBT with the same specification as the target IGBT under different working conditions;
s2, data processing: selecting Vce time domain characteristics which represent IGBT degradation behaviors with the same specification as the target IGBT, and performing dimension reduction and simplification on the selected characteristics by using a principal component analysis algorithm;
s3, obtaining a new parameter: selecting the first characteristic quantity after the principal component analysis processing as a new health index parameter I;
s4, establishing an aging characteristic database: establishing a database about the health condition of the target IGBT and the parameter I amplitude according to the parameter I amplitude of the collected IGBT with the same specification as the target IGBT under different health conditions;
s5, health state monitoring: and acquiring the parameter I amplitude of the target IGBT, comparing the parameter I amplitude with the built aging characteristic database, and judging the health condition of the IGBT.
The invention solves the problem of selection of trend parameters, provides a new IGBT equipment health indication parameter I by using a characteristic reduction technology, and adopts a principal component analysis technology to perform dimension reduction processing on original characteristics extracted from measured data.
In step S1, the operating conditions include gate voltage between the gate and the emitter, collector current, and case temperature.
In step S2, the time domain features such as the standard deviation, peak-to-peak value, and average value of Vce are selected as the original features for health status monitoring, so as to summarize the degradation rule, and normalize the features by linear transformation.
In step S2, the feature space obtained in the feature extraction is subjected to dimensionality reduction, and a new spatial dimension is estimated by using a correlation dimension estimation algorithm, where the estimated spatial dimension in one specific example is 1.38, so that the dimension is fixed to one dimension. The features extracted in step S2 are then transformed into a low-dimensional space using principal component analysis techniques.
In step S3, since the first feature has the highest feature value in the new feature space, it is selected to estimate the operation degradation condition of the IGBT.
In summary, the present invention provides a method for monitoring the health status of an IGBT based on parametric transformation. The feature space is subjected to dimensionality reduction through a principal component analysis algorithm to obtain a new IGBT health index, the problem of selection of IGBT operation degradation trend parameters is solved, and the health state monitoring of the IGBT is achieved through more optimal parameters.
Claims (4)
1. A method for monitoring the health state of an IGBT (insulated gate bipolar transistor) based on parametric transformation is characterized by comprising the following steps of:
s1, characteristic data acquisition: establishing an aging data acquisition platform, and acquiring a voltage value Vce between a collector and an emitter of the IGBT with the same specification as the target IGBT under different working conditions; the working conditions comprise gate voltage between the gate and the emitter, collector current and temperature of the tube shell;
s2, data processing: selecting Vce time domain characteristics which represent IGBT degradation behaviors with the same specification as the target IGBT, and performing dimension reduction and simplification on the selected characteristics by using a principal component analysis algorithm;
s3, obtaining a new parameter: selecting the first characteristic quantity after the principal component analysis processing as a new health index parameter I;
s4, establishing an aging characteristic database: establishing a database about the health condition of the target IGBT and the parameter I amplitude according to the parameter I amplitude of the collected IGBT with the same specification as the target IGBT under different health conditions;
s5, health state monitoring: and acquiring the parameter I amplitude of the target IGBT, comparing the parameter I amplitude with the built aging characteristic database, and judging the health condition of the IGBT.
2. The method for monitoring the state of health of the IGBT based on parametric inversion according to claim 1, wherein in step S2, a time domain characteristic such as a standard deviation, a peak-to-peak value, an average value, etc. of Vce is selected as an original characteristic for monitoring the state of health.
3. The method for monitoring the state of health of the IGBT based on parametric transformation according to claim 1, wherein in step S2, the dimension of the feature space obtained in the feature extraction is reduced, a new spatial dimension is estimated by using a correlation dimension estimation algorithm, and then the extracted features are converted into a low-dimensional space by using a principal component analysis technique.
4. The parametric inversion-based IGBT health monitoring method of claim 1, wherein in step S3, the first characteristic in the new characteristic space is selected to estimate the IGBT operation degradation condition because it has the highest characteristic value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011351857.XA CN112485630A (en) | 2020-11-26 | 2020-11-26 | IGBT health state monitoring method based on parameter transformation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011351857.XA CN112485630A (en) | 2020-11-26 | 2020-11-26 | IGBT health state monitoring method based on parameter transformation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112485630A true CN112485630A (en) | 2021-03-12 |
Family
ID=74935395
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011351857.XA Pending CN112485630A (en) | 2020-11-26 | 2020-11-26 | IGBT health state monitoring method based on parameter transformation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112485630A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113884851A (en) * | 2021-10-26 | 2022-01-04 | 电子科技大学 | IGBT health monitoring method based on Kelvin emitter voltage change |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109359873A (en) * | 2018-10-24 | 2019-02-19 | 哈工大机器人（山东）智能装备研究院 | One kind being based on PCA-T2Ball screw assembly, health evaluating method |
| CN109948860A (en) * | 2019-03-26 | 2019-06-28 | 哈工大机器人（合肥）国际创新研究院 | A kind of mechanical system method for predicting residual useful life and system |
| CN110262458A (en) * | 2019-06-28 | 2019-09-20 | 佛山科学技术学院 | Fault characteristic information extracts the method and system with initial failure early warning |
| CN110717379A (en) * | 2019-08-28 | 2020-01-21 | 南京康尼机电股份有限公司 | Health assessment method for subway car door key components based on feature fusion |
| CN111007379A (en) * | 2019-12-27 | 2020-04-14 | 电子科技大学 | Self-correcting IGBT health monitoring method |
| CN111190088A (en) * | 2019-12-30 | 2020-05-22 | 西安电子科技大学 | Method for extracting characteristic parameters of IGBT (insulated Gate Bipolar transistor) performance degradation |
-
2020
- 2020-11-26 CN CN202011351857.XA patent/CN112485630A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109359873A (en) * | 2018-10-24 | 2019-02-19 | 哈工大机器人（山东）智能装备研究院 | One kind being based on PCA-T2Ball screw assembly, health evaluating method |
| CN109948860A (en) * | 2019-03-26 | 2019-06-28 | 哈工大机器人（合肥）国际创新研究院 | A kind of mechanical system method for predicting residual useful life and system |
| CN110262458A (en) * | 2019-06-28 | 2019-09-20 | 佛山科学技术学院 | Fault characteristic information extracts the method and system with initial failure early warning |
| CN110717379A (en) * | 2019-08-28 | 2020-01-21 | 南京康尼机电股份有限公司 | Health assessment method for subway car door key components based on feature fusion |
| CN111007379A (en) * | 2019-12-27 | 2020-04-14 | 电子科技大学 | Self-correcting IGBT health monitoring method |
| CN111190088A (en) * | 2019-12-30 | 2020-05-22 | 西安电子科技大学 | Method for extracting characteristic parameters of IGBT (insulated Gate Bipolar transistor) performance degradation |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113884851A (en) * | 2021-10-26 | 2022-01-04 | 电子科技大学 | IGBT health monitoring method based on Kelvin emitter voltage change |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | Design for reliability of power electronic systems | |
| CN106532719B (en) | Based on electric current second harmonic and idle non-frequency air-conditioning non-intrusion type discrimination method | |
| CN107508281B (en) | Dynamic reliability assessment method for power flow controller of in-phase power supply system | |
| Ma et al. | Evaluation and design tools for the reliability of wind power converter system | |
| Vernica et al. | Optimal derating strategy of power electronics converter for maximum wind energy production with lifetime information of power devices | |
| Yuan et al. | Open-circuit fault diagnosis of NPC inverter based on improved 1-D CNN network | |
| CN108767847B (en) | Non-invasive electric load decomposition method and device | |
| Emmanuel et al. | Net electricity clustering at different temporal resolutions using a SAX-based method for integrated distribution system planning | |
| CN112485630A (en) | IGBT health state monitoring method based on parameter transformation | |
| CN108595376A (en) | A kind of non-intruding load discrimination method for distinguishing fixed frequency air conditioner and impact drill | |
| CN110618394A (en) | Fault diagnosis method for photovoltaic microgrid direct current and alternating current converter power supply based on current average value | |
| Zhou et al. | Monitoring chip fatigue in an IGBT module based on grey relational analysis | |
| CN108471137B (en) | Wind power prediction wind speed power probabilistic mapping method | |
| CN111639852B (en) | Real-time evaluation method and system for vibration state of hydroelectric generating set based on wavelet singular value | |
| CN113128153B (en) | Active frequency conversion fault recording method triggered by composite threshold in photovoltaic power station | |
| CN117200241A (en) | New forms of energy intelligent voltage regulation system that is incorporated into power networks | |
| Abdelkader et al. | Three-phase inverters open-circuit faults diagnosis using an enhanced variational mode decomposition, wavelet packet analysis, and scalar indicators | |
| CN111914000B (en) | Server power capping method and system based on power consumption prediction model | |
| CN109546188B (en) | Flow battery energy storage multi-attribute comprehensive evaluation method | |
| CN109510243B (en) | Global MPPT control method and system for photovoltaic system of micro inverter | |
| CN106845799B (en) | Evaluation method for typical working condition of battery energy storage system | |
| CN115034472A (en) | Distributed photovoltaic operation intelligent prediction management system | |
| CN110197012A (en) | Consider the Support Capacitor lifetime estimation method that traction drive failure influences | |
| Ghosh et al. | Wavelet-based rapid identification of IGBT switch breakdown in voltage source converter | |
| Zhou et al. | Design of power converter in DFIG wind turbine with enhanced system-level reliability |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210312 |