Battery lifetime prediction is crucial in industrial applications. However, the lack of diversity in training data often poses challenges regarding the robustness and generalization of lifetime predictions for batteries from different batches. Motivated by the early cycle data from lithium-ion batteries, this article proposes a robust transfer learning method by employing a model average framework, where the weights are determined based on the distance between the source domain and the target domain. Kernel regression is used to build the prediction of battery lifetime using early cycle data, and transfer component analysis is utilized to transfer knowledge between different domains. The case study on lithium-ion phosphate/graphite cells demonstrates that the proposed method can mitigate the impact of negative transfer and has superior performance compared to traditional methods.

As technology advances, more industrial devices are achieving higher reliability and longer lifespans. However, challenges such as limited sample sizes of experimental data and the complexity of factors influencing device degradation are becoming increasingly prevalent. Simultaneously, abundant degradation information from other data sources, including data from other components, historical batches, and different experimental stress levels, is available. Thus, there is an urgent need to find ways to fully utilize these multi-source data for industrial device reliability analysis. Therefore, this thesis proposes several data fusion methods to perform the reliability analysis of industrial devices that collect degradation data from different sources. The research addresses three primary research objectives: developing a data fusion-based framework for predicting the remaining useful life (RUL) of industrial devices that collect multivariate sensor data, formulating reliability analysis methods for degradation data from different batches of industrial devices, and establishing a framework for analyzing degradation data under varying experimental stresses and stress levels....

The Gamma constant-stress accelerated degradation model is a natural model for monotonous degradation processes. However, unit heterogeneity often exists in practice, necessitating a more realistic model. This study develops a Gamma process with random effects to accurately capture accelerated degradation data for reliability analysis, encompassing both point and interval estimation. First, the Expectation-Maximization (EM) algorithm is developed to obtain point estimates of the proposed model. Since these estimates are sensitive to initial values, potentially impacting the outcomes, an improved EM algorithm is proposed, which iteratively refines the estimation quality by executing two different M-steps, thereby enhancing overall estimation accuracy. Secondly, given the complexity of the model and the constraint of small sample sizes and limited stress levels, a three-step interval estimation method is devised. This method segregates the parameters into three distinct parts and addresses them individually using the generalized pivotal quantity method, which simplifies the parameter interval estimation process and enhances the estimation accuracy. Finally, simulation studies and a real example of O-rings are presented to demonstrate the effectiveness of the proposed method.

The prediction of remaining useful life (RUL) is a critical component of prognostic and health management for industrial systems. In recent decades, there has been a surge of interest in RUL prediction based on degradation data of a well-defined degradation index (DI). However, in many real-world applications, the DI may not be readily available and must be constructed from complex source data, rendering many existing methods inapplicable. Motivated by multivariate sensor data from industrial induction motors, this paper proposes a novel prognostic framework that develops a nonlinear DI, serving as an ensemble of representative features, and employs a similarity-based method for RUL prediction. The proposed framework enables online prediction of RUL by dynamically updating information from the in-service unit. Simulation studies and a case study on three-phase industrial induction motors demonstrate that the proposed framework can effectively extract reliability information from various channels and predict RUL with high accuracy.