Transfer learning-motivated intelligent fault diagnosis framework for cross-domain knowledge distillation.

Abstract

Transfer learning, as a transformative learning paradigm, has revolutionized the application of artificial intelligence (AI) frameworks, garnering widespread adoption across diverse fields over the past decade. Intelligent fault diagnosis (IFD) methods based on transfer learning have substantially improved the stability and reliability of industrial automation processes. In this study, a transfer learning-based methodology tailored is proposed for nonlinear system fault diagnosis. The framework integrates cross-domain knowledge distillation into an IFD scheme, further embedding a twin-spiking neural networks (SNNs) to enhance temporal sequence analysis capabilities. By transforming the prior knowledge learned within the feature extraction backbone network and transferring it to the twin SNNs, this integration facilitates the reconstruction of residual generators for IFD. Experimental evaluations on nonlinear systems in high-energy vehicle lithium batteries demonstrate the effectiveness and practicality of the proposed approach.