Fault Cause Identification across Manufacturing Lines through Ontology-Guided and Process-Aware FMEA Graph Learning with LLMs

2025-10-17

AI Summary

In heterogeneous manufacturing lines, fault cause identification from Failure Mode and Effects Analysis (FMEA) knowledge suffers from poor cross-line transferability due to inconsistent terminology and process variations. Method: This paper proposes an ontology-guided framework integrating large language models (LLMs) with process-aware graph neural networks. First, domain ontologies constrain LLMs to extract structured action–state–component triples from heterogeneous FMEA documents. Second, a unified knowledge graph is constructed, and a process-flow-aware Relational Graph Convolutional Network (RGCN), coupled with a tailored link prediction scoring function, enables cross-line fault causal reasoning. Contribution/Results: The framework introduces an ontology–LLM co-driven knowledge standardization mechanism and a process-aware graph learning paradigm. Evaluated on an automotive pressure sensor assembly line, it achieves F1@20 = 0.523—significantly outperforming RAG and standard RGCN baselines—demonstrating strong generalizability and practical efficacy.

Technology Category

• Knowledge Representation and Reasoning: Ontologies
• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion

Application Category

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

Abstract

Fault cause identification in automated manufacturing lines is challenging due to the system's complexity, frequent reconfigurations, and the limited reusability of existing Failure Mode and Effects Analysis (FMEA) knowledge. Although FMEA worksheets contain valuable expert insights, their reuse across heterogeneous lines is hindered by natural language variability, inconsistent terminology, and process differences. To address these limitations, this study proposes a process-aware framework that enhances FMEA reusability by combining manufacturing-domain conceptualization with graph neural network (GNN) reasoning. First, FMEA worksheets from multiple manufacturing lines are transformed into a unified knowledge graph through ontology-guided large language model (LLM) extraction, capturing domain concepts such as actions, states, components, and parameters. Second, a Relational Graph Convolutional Network (RGCN) with the process-aware scoring function learns embeddings that respect both semantic relationships and sequential process flows. Finally, link prediction is employed to infer and rank candidate fault causes consistent with the target line's process flow. A case study on automotive pressure sensor assembly lines demonstrates that the proposed method outperforms a state-of-the-art retrieval-augmented generation (RAG) baseline (F1@20 = 0.267) and an RGCN approach (0.400), achieving the best performance (0.523) in fault cause identification. Ablation studies confirm the contributions of both LLM-driven domain conceptualization and process-aware learning. These results indicate that the proposed framework significantly improves the transferability of FMEA knowledge across heterogeneous lines, thereby supporting operators in diagnosing failures more reliably and paving the way for future domain-adaptive LLM applications in smart manufacturing.

Problem

• Identifying fault causes in complex automated manufacturing systems
• Overcoming FMEA knowledge reuse barriers across heterogeneous production lines
• Enhancing fault diagnosis through ontology-guided graph learning with LLMs

Innovation

• Ontology-guided LLM extraction creates unified knowledge graph
• Process-aware RGCN learns semantic and sequential embeddings
• Link prediction ranks fault causes consistent with process flow