Predicting Power Electronics Device Reliability under Extreme Conditions with Machine Learning Algorithms
This addresses the need for cost-effective reliability prediction in power systems and sensing infrastructures, though it appears incremental by applying existing ML methods to this domain.
The paper tackled the problem of predicting power electronics device reliability under extreme conditions to reduce expensive experimental validation, achieving high accuracy with Gradient Boosting and LSTM encoder-decoder models on a dataset of 224 devices from 10 manufacturers.
Power device reliability is a major concern during operation under extreme environments, as doing so reduces the operational lifetime of any power system or sensing infrastructure. Due to a potential for system failure, devices must be experimentally validated before implementation, which is expensive and time-consuming. In this paper, we have utilized machine learning algorithms to predict device reliability, significantly reducing the need for conducting experiments. To train the models, we have tested 224 power devices from 10 different manufacturers. First, we describe a method to process the data for modeling purposes. Based on the in-house testing data, we implemented various ML models and observed that computational models such as Gradient Boosting and LSTM encoder-decoder networks can predict power device failure with high accuracy.