Lifetime Estimation of Discrete IGBT Devices Based on Gaussian Process

IEEE Trans. Power Electron.

2021

510

This paper gives an overview of the Artificial Intelligence (AI) applications for power electronic systems. The three distinctive life-cycle phases, design, control, and maintenance are correlated with one or more tasks to be addressed by AI, including optimization, classification, regression, and data structure exploration. The applications of four categories of AI are discussed, which are expert system, fuzzy logic, metaheuristic method, and machine learning. More than 500 publications have been reviewed to identify the common understandings, practical implementation challenges, and research opportunities in the application of AI for power electronics. This paper is accompanied by an Excel file listing the relevant publications for statistical analytics.

Section: Machine Learningmentioning

confidence: 99%

“…In [119], Gaussian processes regression is applied to the RUL prediction of IGBTs. For the degradation modeling, the nonlinear relationship between the decrement of on-state collector-emitter voltage ∆V ce,on and the condition monitoring time is established by the Gaussian processes regression.…”

Section: Remaining Useful Life Predictionmentioning

confidence: 99%

An Overview of Artificial Intelligence Applications for Power Electronics

Zhao

Blaabjerg

IEEE Trans. Power Electron.

2021

510

IEEE Trans. on Ind. Applicat.

“…The interfacing voltage and flowing current of the RSC are heavily dependent on the inherent parameters of the DFIG. Neglecting the stator resistance and the rotor resistance, and together with the help of DFIG modeling in the dq reference frame [9], the relationship between the rotor-side voltage ur and current ir and the stator-side voltage us and current is are,…”

Section: Electrical Stresses and Selected Power Devicesmentioning

confidence: 99%

“…The stress is related to the environmental loads (like thermal, mechanical, humidity, etc. ), or the functional loads (such as user profiles, electrical operation) [9]- [12]. On the other hand, the strength means the ability to endure such stressors before fatigue occurs (e.g.…”

Section: Introductionmentioning

confidence: 99%

Optimal Selection of Power Converter in DFIG Wind Turbine With Enhanced System-Level Reliability

Zhou

Zhang

Blaabjerg

2018

With the increasing penetration of wind power, reliable and cost-effective wind energy production is of more and more importance. As one of the common configurations, the doubly-fed induction generator based partial-scale wind power converter is still dominating in the existing wind farms, and its reliability assessment is studied considering the annual wind profile. According to an electro-thermal stress evaluation, the time-to-failure of the key power semiconductors is predicted by using lifetime models and Monte Carlo based variation analysis. Aiming for the system-level reliability analysis, a reliability block diagram can be used based on Weibull distributed component-level reliability. A case study of a 2 MW wind power converter shows that the optimal selection of power module may be different seen from the reliability perspective compared to the electrical stress margin. It can also be seen that the B1 lifetimes of the grid-side converter and the rotor-side converter deviate a lot by considering the electrical stresses, while they become more balanced by using an optimized design strategies. Thus, the systemlevel lifetime increases significantly with an appropriate design of the back-to-back power converters.

“…For example, Mukhopadhyay et al proposed a Bayesian method for reliability estimation using multi‐stress accelerated life testing of series systems. Ali et al combined Gaussian process modeling and Bayesian inference method to estimate the remaining useful life of insulated‐gate bipolar transistor devices.…”

Section: Introductionmentioning

confidence: 99%

Ensemble learning for predicting degradation under time‐varying environment

Lu²,

Quality & Reliability Eng

et al. 2020

Product lifetime prediction is challenging when the product is subject to a time-varying operational environment. Most of the existing studies use some functions to explicitly specify the relationship between degradation parameters and environmental conditions so as to reveal how the degradation process evolves over time. However, in many applications, the assumptions needed for establishing these functions cannot be validated in engineering practice or they cannot accurately model the entire underlying degradation mechanism. In contrast to previous work, the focus of our study is placed on product degradation prognosis by implementing an ensemble learning method. This method combines the stochastic process modeling approach and the machine learning approach, taking advantage of these approaches to gain a more accurate and stable degradation prediction. The proposed method is demonstrated by some simulation examples and by a case study of lithium-ion battery accelerated degradation test. Both the simulation study and the real case verify the superiority of the proposed method. The case study indicates that the ensemble learning method can further help to effectively manage the energy storage and energy distribution of battery packs. K E Y W O R D Sdegradation process, ensemble model, Li-ion battery, machine learning, stochastic process