1 results about "Component Load" patented technology

This application relates to an intelligent fault diagnosis and management system and method for rail transit control consoles. The method includes: constructing a fault prediction probability model and an adaptive dynamic diagnostic threshold adjustment model; constructing a causal intensity quantification model based on fault features corresponding to the fault prediction probability; inputting potential root causes, fault features, and root cause contribution; and outputting a causal intensity score to classify fault root causes and obtain fault level coefficients; and constructing a dynamic parameter adaptive adjustment model based on the fault level coefficients, outputting component dynamic load parameters for dynamic adaptation of component loads. This invention supports zero-sample / small-sample fault detection, solving the problem of scarce fault samples. It adopts a fusion framework of unsupervised contrastive learning and cross-domain transfer learning, achieving anomaly identification without relying on a large number of real fault samples. By combining digital twins to generate high-fidelity virtual fault samples and optimizing their weights, it fundamentally solves the industry problem of few fault samples and difficulty in modeling in rail transit.