A multi-granularity cause-effect graph learning method for tracing the causes of industrial equipment operation and maintenance failures

By constructing a multi-granularity hierarchical system and a causal structure learning method that combines a large language model with Bayesian information criteria, the problems of instability and high computational cost in causal structure learning in complex industrial systems are solved, and highly accurate fault tracing and propagation path analysis are achieved.

CN122311468APending Publication Date: 2026-06-30NAT UNIV OF DEFENSE TECH
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
NAT UNIV OF DEFENSE TECH
Filing Date
2026-05-19
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

Existing technologies struggle to effectively integrate multi-granularity data and textual knowledge in complex industrial systems, resulting in unstable causal structure learning, high computational overhead, and insufficient interpretability, failing to meet the high-precision and high-efficiency requirements for industrial fault tracing.

Method used

A multi-granularity hierarchical system is constructed, causal statements are extracted and weighted using a large language model, causal structure learning is performed by combining the scoring-search algorithm of Bayesian information criterion, and the macroscopic credible causal edges are transformed into search space constraints of micro-indicator layers through a projection mechanism, forming an accurate directed acyclic causal graph.

Benefits of technology

It enables the structured transformation and effective utilization of causal knowledge in the industrial field, improves the accuracy and efficiency of causal structure learning, and can accurately locate the root cause and propagation path of faults, adapting to the needs of high-dimensional and low-sample scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122311468A_ABST
    Figure CN122311468A_ABST
Patent Text Reader

Abstract

This application relates to a multi-granularity causal graph learning method for fault tracing in industrial equipment operation and maintenance. The method includes: constructing a three-layer system of macro-mechanism, meso-process, and micro-indicators, obtaining the mapping relationship between the node sets and hierarchical variables at each layer; acquiring domain text corpus, extracting and granularly labeling causal statements using a large language model, and mapping and weighting them to form a set of weighted language candidate edges at each layer; using a scoring-search algorithm based on the Bayesian information criterion to learn the macro-layer causal structure, obtaining macro-level reliable causal edges consistent with the language and data; transforming these edges into micro-layer cross-cluster candidate edges and directional constraints through a projection mechanism, forming a micro-level search space constraint; learning the micro-layer causal structure under this constraint, obtaining a directed acyclic causal graph to realize fault tracing and propagation path analysis. This method can meet the practical needs of complex industrial system fault tracing for high-precision and high-efficiency causal structure learning.
Need to check novelty before this filing date? Find Prior Art