Adaptive Residual Useful Life Prediction for the Insulated-Gate Bipolar Transistors with Pulse-Width Modulation Based on Multiple Modes and Transfer Learning
Currently, residual useful life (RUL) prediction models for insulated-gate bipolar transistors (IGBT) do not focus on the multi-modal characteristics caused by the pulse-width modulation (PWM). To fill this gap, the Markovian stochastic process is proposed to model the mode transition process, due t...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Fractal and Fractional |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-3110/7/8/614 |
| _version_ | 1797584694824402944 |
|---|---|
| author | Wujin Deng Yan Gao Wanqing Song Enrico Zio Gaojian Li Jin Liu Aleksey Kudreyko |
| author_facet | Wujin Deng Yan Gao Wanqing Song Enrico Zio Gaojian Li Jin Liu Aleksey Kudreyko |
| author_sort | Wujin Deng |
| collection | DOAJ |
| description | Currently, residual useful life (RUL) prediction models for insulated-gate bipolar transistors (IGBT) do not focus on the multi-modal characteristics caused by the pulse-width modulation (PWM). To fill this gap, the Markovian stochastic process is proposed to model the mode transition process, due to the memoryless properties of the grid operation. For the estimation of the mode transition probabilities, transfer learning is utilized between different control signals. With the continuous mode switching, fractional Weibull motion (fWm) of multiple modes is established to model the stochasticity of the multi-modal IGBT degradation. The drift and diffusion coefficients are adaptively updated in the proposed RUL prediction model. In the case study, two sets of the real thermal-accelerated IGBT aging data are used. Different degradation modes are extracted from the meta degradation data, and then fused to be a complex health indicator (CHI) via a multi-sensor fusion algorithm. The RUL prediction model based on the fWm of multiple modes can reach a maximum relative prediction error of 2.96% and a mean relative prediction error of 1.78%. The proposed RUL prediction model with better accuracy can reduce the losses of the power grid caused by the unexpected IGBT failures. |
| first_indexed | 2024-03-10T23:55:23Z |
| format | Article |
| id | doaj.art-7651e29654f9426faccd617d6ddc20f4 |
| institution | Directory Open Access Journal |
| issn | 2504-3110 |
| language | English |
| last_indexed | 2024-03-10T23:55:23Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Fractal and Fractional |
| spelling | doaj.art-7651e29654f9426faccd617d6ddc20f42023-11-19T01:11:35ZengMDPI AGFractal and Fractional2504-31102023-08-017861410.3390/fractalfract7080614Adaptive Residual Useful Life Prediction for the Insulated-Gate Bipolar Transistors with Pulse-Width Modulation Based on Multiple Modes and Transfer LearningWujin Deng0Yan Gao1Wanqing Song2Enrico Zio3Gaojian Li4Jin Liu5Aleksey Kudreyko6School of Electronic & Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaSchool of Electronic & Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaSchool of Electronic and Electrical Engineering, Minnan University of Science and Technology, Quanzhou 362700, ChinaThe Centre for Research on Risk and Crises (CRC) of Ecole de Mines, Paris Sciences & Lettres (PSL) University, 06904 Paris, FranceSchool of Electronic & Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaSchool of Electronic & Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, ChinaDepartment of General Physics, Ufa University of Science and Technology, Zaki Valedi 32, Ufa 450076, RussiaCurrently, residual useful life (RUL) prediction models for insulated-gate bipolar transistors (IGBT) do not focus on the multi-modal characteristics caused by the pulse-width modulation (PWM). To fill this gap, the Markovian stochastic process is proposed to model the mode transition process, due to the memoryless properties of the grid operation. For the estimation of the mode transition probabilities, transfer learning is utilized between different control signals. With the continuous mode switching, fractional Weibull motion (fWm) of multiple modes is established to model the stochasticity of the multi-modal IGBT degradation. The drift and diffusion coefficients are adaptively updated in the proposed RUL prediction model. In the case study, two sets of the real thermal-accelerated IGBT aging data are used. Different degradation modes are extracted from the meta degradation data, and then fused to be a complex health indicator (CHI) via a multi-sensor fusion algorithm. The RUL prediction model based on the fWm of multiple modes can reach a maximum relative prediction error of 2.96% and a mean relative prediction error of 1.78%. The proposed RUL prediction model with better accuracy can reduce the losses of the power grid caused by the unexpected IGBT failures.https://www.mdpi.com/2504-3110/7/8/614fractional Weibull motionmulti-sensor fusionmulti-modal characteristicsMarkovian mode transition stochastic processtransfer learningpulse-width modulation |
| spellingShingle | Wujin Deng Yan Gao Wanqing Song Enrico Zio Gaojian Li Jin Liu Aleksey Kudreyko Adaptive Residual Useful Life Prediction for the Insulated-Gate Bipolar Transistors with Pulse-Width Modulation Based on Multiple Modes and Transfer Learning Fractal and Fractional fractional Weibull motion multi-sensor fusion multi-modal characteristics Markovian mode transition stochastic process transfer learning pulse-width modulation |
| title | Adaptive Residual Useful Life Prediction for the Insulated-Gate Bipolar Transistors with Pulse-Width Modulation Based on Multiple Modes and Transfer Learning |
| title_full | Adaptive Residual Useful Life Prediction for the Insulated-Gate Bipolar Transistors with Pulse-Width Modulation Based on Multiple Modes and Transfer Learning |
| title_fullStr | Adaptive Residual Useful Life Prediction for the Insulated-Gate Bipolar Transistors with Pulse-Width Modulation Based on Multiple Modes and Transfer Learning |
| title_full_unstemmed | Adaptive Residual Useful Life Prediction for the Insulated-Gate Bipolar Transistors with Pulse-Width Modulation Based on Multiple Modes and Transfer Learning |
| title_short | Adaptive Residual Useful Life Prediction for the Insulated-Gate Bipolar Transistors with Pulse-Width Modulation Based on Multiple Modes and Transfer Learning |
| title_sort | adaptive residual useful life prediction for the insulated gate bipolar transistors with pulse width modulation based on multiple modes and transfer learning |
| topic | fractional Weibull motion multi-sensor fusion multi-modal characteristics Markovian mode transition stochastic process transfer learning pulse-width modulation |
| url | https://www.mdpi.com/2504-3110/7/8/614 |
| work_keys_str_mv | AT wujindeng adaptiveresidualusefullifepredictionfortheinsulatedgatebipolartransistorswithpulsewidthmodulationbasedonmultiplemodesandtransferlearning AT yangao adaptiveresidualusefullifepredictionfortheinsulatedgatebipolartransistorswithpulsewidthmodulationbasedonmultiplemodesandtransferlearning AT wanqingsong adaptiveresidualusefullifepredictionfortheinsulatedgatebipolartransistorswithpulsewidthmodulationbasedonmultiplemodesandtransferlearning AT enricozio adaptiveresidualusefullifepredictionfortheinsulatedgatebipolartransistorswithpulsewidthmodulationbasedonmultiplemodesandtransferlearning AT gaojianli adaptiveresidualusefullifepredictionfortheinsulatedgatebipolartransistorswithpulsewidthmodulationbasedonmultiplemodesandtransferlearning AT jinliu adaptiveresidualusefullifepredictionfortheinsulatedgatebipolartransistorswithpulsewidthmodulationbasedonmultiplemodesandtransferlearning AT alekseykudreyko adaptiveresidualusefullifepredictionfortheinsulatedgatebipolartransistorswithpulsewidthmodulationbasedonmultiplemodesandtransferlearning |