Knowledge Graph Construction and Application for Elevator Diagnosis Based on Large Language Models

Zhao Ziyu; Deng Haodong; Tang Simin; Liao Feiyu; Zheng Qiang; He Zuen

doi:10.13206/j.gjgS26041001

Volume 41 Issue 6

Jun. 2026

Turn off MathJax

Article Contents

Article Navigation > STEEL CONSTRUCTION(Chinese & English) > 2026 > 41(6): 20-29

Zhao Ziyu, Deng Haodong, Tang Simin, Liao Feiyu, Zheng Qiang, He Zuen. Knowledge Graph Construction and Application for Elevator Diagnosis Based on Large Language Models[J]. STEEL CONSTRUCTION(Chinese & English), 2026, 41(6): 20-29. doi: 10.13206/j.gjgS26041001

Citation:

Zhao Ziyu, Deng Haodong, Tang Simin, Liao Feiyu, Zheng Qiang, He Zuen. Knowledge Graph Construction and Application for Elevator Diagnosis Based on Large Language Models[J]. STEEL CONSTRUCTION(Chinese & English), 2026, 41(6): 20-29. doi: 10.13206/j.gjgS26041001

Citation:

PDF( 2468 KB)

Knowledge Graph Construction and Application for Elevator Diagnosis Based on Large Language Models

doi: 10.13206/j.gjgS26041001

1. School of Transportation and Civil Engineering, Fujian Agriculture and Forestry University, Fuzhou 350108, China;
2. Fujian Special Equipment Inspection and Research Institute, Fuzhou 350008, China

Received Date: 2026-04-10
Available Online: 2026-07-06

Abstract

Abstract

As critical special equipment， elevators heavily rely on periodic inspection reports for fault diagnosis and risk assessment. Existing approaches primarily focus on sensor and time-series data while overlooking the rich knowledge embedded in textual inspection reports. To address this limitation， this paper proposes a large language model （LLM）-based method for constructing an elevator inspection and diagnostic knowledge graph. Based on elevator inspection technical specifications， an ontology for elevator inspection and diagnosis is first developed. On this basis， contextual prompt learning is employed to automatically extract entities and relationships from inspection reports. This method addresses challenges such as limited domain-specific semantic representation and reasoning capability， and mitigates the limitations of general-purpose LLMs. Subsequently， entity alignment is performed through predefined rules， and a high-quality building elevator diagnostic knowledge graph is constructed. The proposed method requires neither manual annotation nor model training， and can efficiently process multi-source heterogeneous elevator inspection data. Experimental results demonstrate that LLM-based prompt learning under domain ontology constraints significantly improves knowledge graph coverage and accuracy. Compared with zero-shot learning， few-shot learning improves entity recognition precision， recall， and F₁-score by 6.1 percentage point， 27.20 percentage point， and 17.61 percentage point， respectively， thereby providing effective data support for downstream intelligent fault diagnosis.
- knowledge graph,
- large language model,
- prompt learning,
- ontology construction,
- fault diagnosis

FullText(HTML)

References(24)

References

[1]	Hou J, Qiu R, Xue J, et al. Failure prediction of elevator running system based on knowledge graph[C]// Proceedings of the 3rd International Conference on Data Science and Information Technology, ser. DSIT 2020. New York:Association for Computing Machinery, 2020:53-58.
[2]	Du X Q, Yao Z H, Chen Z C. Wavelet denoising of the horizontal vibration signal for identification of the guide rail irregularity in elevator[J]. Key Engineering Materials, 2007, 353-358:2794-2797.
[3]	Xu S, Huang Y J. The fault diagnosis of elevator based on the autoregressive model and the support vector machine[J]. Applied Mechanics and Materials, 2013（271/272）:1689-1694.
[4]	Yi J Y, Huang Y J. Fault diagnosis of elevator based AR bi-spectrum[J]. Advanced Materials Research, 2012, 468-471:1743-1748.
[5]	Wen P, Zhi M, Zhang G, et al. Fault prediction of elevator door system based on PSO-BP neural network[J]. Engineering, 2016, 8（11）:761-766.
[6]	Sun W, Shao S, Zhao R, et al. A sparse auto-encoder-based deep neural network approach for induction motor faults classification[J]. Measurement, 2016, 89:171-178.
[7]	Wen L, Li X, Gao L, et al. A new convolutional neural network-based data-driven fault diagnosis method[J]. IEEE Transactions on Industrial Electronics, 2018, 65（7）:5990-5998.
[8]	Mishra K M, Huhtala K. Elevator fault detection using profile extraction and deep autoencoder feature extraction for acceleration and magnetic signals[J]. Applied Sciences, 2019, 9（15）:2990.
[9]	Zhao R, Yan R, Chen Z, et al. Deep learning and its applications to machine health monitoring[J]. Mechanical Systems and Signal Processing, 2019, 115:213-237.
[10]	Zhu Z, Peng G, Chen Y, et al. A convolutional neural network based on a capsule network with strong generalization for bearing fault diagnosis[J]. Neurocomputing, 2019, 323:62-75.
[11]	Shao S, Wang P, Yan R. Generative adversarial networks for data augmentation in machine fault diagnosis[J]. Computers in Industry, 2019, 106:85-93.
[12]	Jia M, Gao X, Li H, et al. Elevator running fault monitoring method based on vibration signal[J]. Shock and Vibration, 2021, 2021（1）:4547030.
[13]	Li C, Mo L, Yan R. Fault diagnosis of rolling bearing based on WHVG and GCN[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70:1-11.
[14]	Yang C, Liu J, Zhou K, et al. An improved multi-channel graph convolutional network and its applications for rotating machinery diagnosis[J]. Measurement, 2022, 190:110720.
[15]	Sun K, Huang Z, Mao H, et al. Multi-scale cluster-graph convolution network with multi-channel residual network for intelligent fault diagnosis[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71:1-12.
[16]	Feng J, Bao S, Xu X, et al. Rotating machinery fault diagnosis based on feature extraction via an unsupervised graph neural network[J]. Applied Intelligence, 2023, 53（18）:21211-21226.
[17]	Ji S, Pan S, Cambria E, et al. A survey on knowledge graphs:representation, acquisition, and applications[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33（2）:494-514.
[18]	Hogan A, Blomqvist E, Cochez M, et al. Knowledge graphs[J]. ACM Computing Surveys, 2022, 54（4）:1-37.
[19]	Wei J, Wang X, Schuurmans D, et al. Chain-of-thought prompting elicits reasoning in large language models[J]. Advances in Neural Information Processing Systems, 2022, 35:24824-24837.
[20]	陈囿任, 李勇, 温明, 等. 多模态知识图谱融合技术研究综述[J]. 计算机工程与应用, 2024, 60（13）:36-50.
[21]	Fang W, Ma L, Love E P, et al. Knowledge graph for identifying hazards on construction sites:integrating computer vision with ontology[J]. Automation in Construction, 2020, 119:103310.
[22]	Chen Q H, Long D B, Yang C, et al. Knowledge graph improved dynamic risk analysis method for behavior-based safety management on a construction site[J]. Journal of Management in Engineering, 2023, 39（4）:04023023.
[23]	冯钧, 畅阳红, 陆佳民, 等. 基于大语言模型的水工程调度知识图谱的构建与应用[J]. 计算机科学与探索, 2024, 18（6）:1637-1647.
[24]	Wu H K, Yin L, Chen Y F, et al. Elevator fault diagnosis based on a graph attention recurrent network[J]. Electronics, 2025, 14（11）:2308.