Accurate life prediction and reliability evaluation of lithium-ion batteries are of great significance for predictive maintenance. In the whole life cycle of a battery, the accurate description of the dynamic and stochastic characteristics of life has always been a key problem. In this paper, the concept of the digital twin is introduced, and a digital twin for reliability based on remaining useful cycle life prediction is proposed for lithium-ion batteries. The capacity degradation model, stochastic degradation model, life prediction, and reliability evaluation model are established to describe the randomness of battery degradation and the dispersion of the life of multiple cells. Based on the Bayesian algorithm, an adaptive evolution method for the model of the digital twin is proposed to improve prediction accuracy, followed by experimental verification. Finally, the life prediction, reliability evaluation, and predictive maintenance of the battery based on the digital twin are implemented. The results show the digital twin for reliability has good accuracy in the whole life cycle. The error can be controlled at about 5% with the adaptive evolution algorithm. For battery L1 and L6 in this case, predictive maintenance costs are expected to decrease by 62.0% and 52.5%, respectively.

This paper presents an empirical study on the impact of maintenance function on more sustainable manufacturing processes. The work methodology comprises four stages. At first, ten factors of maintenance activities from a sustainable manufacturing point of view were identified. Then, in the second stage, the matrix of crossed impact multiplications applied to a classification (MICMAC) was carried out to categorize these factors based on their influence and dependence values. In the third stage, the criteria for evaluation of maintenance factors were defined, then the fuzzy analytic hierarchy process (F-AHP) was applied to determine their relative weights. In the last stage, the results of MICMAC and F-AHP analyses were used as inputs for the fuzzy technique for order preference by similarity to ideal solution (F-TOPIS) to generate aggregate scores and selection of the most important maintenance factors that have an impact on sustainable manufacturing processes. A numerical example is provided to demonstrate the applicability of the approach. It was observed that factors “Implementation of preventive and prognostic service strategies”, “The usage of M&O data collection and processing systems”, and “Modernization of machines and devices” are the major factors that support the realization of sustainable manufacturing process challenges.