Research on Online Condition Monitoring for Complex System Based on Broad Learning System

Abstract

Broad learning system (BLS), which expands the single-hidden-layer neural network by enriching the number of hidden-layer nodes, can greatly improve the model training efficiency. But, the randomly generated hidden-layer nodes make BLSs performing poorly in some high-dimensional data classification tasks. This paper focuses on providing some ideas to tackle this problem by optimizing the generation of initial nodes to compact the BLS hidden-layer structure. Specifically, the logical regression and causal structural model are considered to replace the random generation of the initial node groups in the hidden-layer. The proposed methods are expected to improve the feature extraction effectiveness, to simplify the network structure, and to reduce the computational burden. With real data from a high-speed train brake control system, the effectiveness of the proposed system monitoring framework is verified in comparative experiments. It is also shown that the proposed methods are efficient in generalizing to new operation environments.

Keywords: Broad Learning System, Causality, complex system, High-speed train, condition monitoring