Hierarchical tree-structured belief rule base for fault diagnosis of complex electromechanical systems

Fault diagnosis of complex electromechanical systems is critical for ensuring safe operation of industrial equipment. Belief Rule Base (BRB) demonstrates significant advantages in small-sample and uncertain environments by combining expert knowledge with data-driven modeling. However, it faces the challenge of combinatorial explosion in high-dimensional feature scenarios. The number of rules grows exponentially. This severely limits its engineering applications. To address this challenge, this paper proposes a Hierarchical Tree-Structured BRB (HTS-BRB) method. It breaks the constraint of full rule combinations through hierarchical decomposition strategy. The proposed method first employs mutual information-based quantification integrated with expert knowledge to rank feature importance and select critical feature subsets. Subsequently, it constructs a hierarchical tree based on feature ranking. It employs an evolutionary algorithm to generate a high-quality sub-BRB set. Finally, it introduces the MAKER framework to model correlation coefficients for non-independent evidence fusion. The effectiveness of the proposed method is validated through permanent magnet synchronous motor fault diagnosis experiments.