Hierarchical knowledge guided fault intensity diagnosis of complex industrial systems

2025-08-17

AI Summary

Existing fault intensity diagnosis (FID) methods predominantly rely on chain-of-reasoning paradigms, neglecting hierarchical dependencies among fault categories—leading to limited diagnostic accuracy in complex industrial systems. To address this, we propose HKG, a hierarchical knowledge-guided diagnostic framework. HKG constructs a tree-structured reasoning architecture to explicitly model inter-category hierarchical relationships and introduces a re-weightable hierarchical knowledge correlation matrix (Re-HKCM), which injects prior hierarchical knowledge into a data-driven correlation matrix. By jointly leveraging graph convolutional networks and representation learning, HKG enables end-to-end fault intensity diagnosis while effectively mitigating the over-smoothing problem inherent in graph neural networks. Extensive experiments on four real-world industrial datasets demonstrate that HKG significantly outperforms state-of-the-art methods, achieving superior generalization capability and practical applicability.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Fault intensity diagnosis (FID) plays a pivotal role in monitoring and maintaining mechanical devices within complex industrial systems. As current FID methods are based on chain of thought without considering dependencies among target classes. To capture and explore dependencies, we propose a hierarchical knowledge guided fault intensity diagnosis framework (HKG) inspired by the tree of thought, which is amenable to any representation learning methods. The HKG uses graph convolutional networks to map the hierarchical topological graph of class representations into a set of interdependent global hierarchical classifiers, where each node is denoted by word embeddings of a class. These global hierarchical classifiers are applied to learned deep features extracted by representation learning, allowing the entire model to be end-to-end learnable. In addition, we develop a re-weighted hierarchical knowledge correlation matrix (Re-HKCM) scheme by embedding inter-class hierarchical knowledge into a data-driven statistical correlation matrix (SCM) which effectively guides the information sharing of nodes in graphical convolutional neural networks and avoids over-smoothing issues. The Re-HKCM is derived from the SCM through a series of mathematical transformations. Extensive experiments are performed on four real-world datasets from different industrial domains (three cavitation datasets from SAMSON AG and one existing publicly) for FID, all showing superior results and outperform recent state-of-the-art FID methods.

Problem

• Diagnosing fault intensity in complex industrial systems
• Capturing dependencies among target fault classes
• Avoiding over-smoothing in graph convolutional networks

Innovation

• Hierarchical knowledge framework with graph networks
• Re-weighted correlation matrix embedding inter-class knowledge
• End-to-end learnable global hierarchical classifiers