Maintenance planning recommendation of complex industrial equipment based on knowledge graph and graph neural network

• Published in: Reliability engineering & system safety Vol. 232; p. 109068
• Main Authors: Xia, Liqiao, Liang, Yongshi, Leng, Jiewu, Zheng, Pai
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.04.2023
• Subjects: Graph neural network; Knowledge graph; Link prediction; Maintenance management; Predictive maintenance; Link prediction; Graph neural network; Knowledge graph; Maintenance management; Predictive maintenance
• ISSN: 0951-8320; 1879-0836
• DOI: 10.1016/j.ress.2022.109068

Maintenance planning is a significant part of predictive maintenance, which involves task planning, resource scheduling, and prevention. With large-scale sensor systems in modern factories, much data will be captured during monitoring and maintenance of complex industrial equipment. Accumulated data facilitates maintenance planning becomes more thorough and timely. Recently, a knowledge graph (KG) was offered to handle large-scale, unorganized maintenance data semantically, resulting in better data usage. Some prior studies have utilized KG for maintenance planning with semantic searching or graph structure-based algorithms, nevertheless neglecting the prediction of potential linkage. To fill this gap, a maintenance-oriented KG is established firstly based on a well-defined domain-specific ontology schema and accumulated maintenance data. Then, an Attention-Based Compressed Relational Graph Convolutional Network is proposed to predict potential solutions and explain fault in maintenance tasks. Lastly, a maintenance case of oil drilling equipment is carried out, where the proposed model is compared with other cutting-edge models to demonstrate its effectiveness in link prediction. This research is anticipated to shed light on future adoption of KG in maintenance planning recommendations. •A Manufacturing Knowledge Graph’s schema is proposed in light of the low efficiency of knowledge use and the absence of uniform standards in maintenance scenarios.•A link prediction model, ACRGCN, is proposed, which is tailored for the sparsity and imbalance node types characteristics of Manufacturing Knowledge Graph.•A question-and-answer system is provided to reduce the operational difficulty of knowledge graph search reasoning, satisfying convenient and user-friendly purposes.