Ensemble learning for predicting degradation under time‐varying environment

Abstract

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

A novel deep time‐index framework with limited data and feature extraction for battery capacity degradation prediction

“…The existing health feature extraction methods generally used in many literature have their limitations that they focused on a specific experiment scenario. 37 For instance, Dataset 1 was utilized to examine the correlation between the voltage curve after a full charge and capacity, necessitating data collected during a 30-min relaxation process. However, the method falters with Dataset 2, where the relationship was derived from the relaxation voltage curve and capacity.…”

Calibration and frequency estimation in sensors for electrical parameter measurement using regression and metaheuristic based models

“…Relevant Vector Machine Ensemble (RVME) is implemented and tested in a gas sensor for health prediction (Peng et al, 2011). Similarly, the life span of a product is statistically predicted in (Wang et al, 2020) based on an ensemble learning method that adopts stochastic process modelling and a machine learning approach. A term regarded as the Health Reliability Degree (HRD) is defined in this literature to estimate the accuracy of the measured signal.…”

Enhanced semi‐supervised ensemble machine learning approach for earthwork construction simulation activity sequence automatically updating driven by weather data

“…This situation limits the application of semi‐supervised learning methods in practice (Xu & Saleh, 2021). Ensemble learning combines the results of two or more individually trained classifiers to outperform single classifiers (Dong et al, 2020; Wang, Lu, et al, 2020; Zhang, Gu, et al, 2022; Zhang, Li, et al, 2022). To build a more accurate semi‐supervised model of activity sequence classification, this study adopts Dempster–Shafer (DS) evidence theory with a safety filtering mechanism to ensemble three heterogeneous classifiers with complementary characteristics, and the max‐relevance and min‐redundancy (MRMR) method is implemented to perform feature selection and improve computational efficiency.…”

“…Ensemble learning combines the results of two or more individually trained classifiers to outperform single classifiers (Dong et al, 2020;Wang, Lu, et al, 2020;Zhang, Gu, et al, 2022;Zhang, Li, et al, 2022).…”