Integrated modeling of commercial aircraft maintenance plan recommendation system based on knowledge graph

doi:10.3785/j.issn.1008-973X.2023.03.009

Journal of ZheJiang University (Engineering Science)

2023, Vol. 57

Issue (3): 512-521 DOI: 10.3785/j.issn.1008-973X.2023.03.009

Integrated modeling of commercial aircraft maintenance plan recommendation system based on knowledge graph

Xue-qi XING1,2(

),Yu-tong DING1,Tang-bin XIA1,2,*(

),Er-shun PAN1,2,Li-feng XI1,2

1. Department of Industrial Engineering and Management, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
2. Chinese Institute for Quality Research, Shanghai Jiao Tong University, Shanghai 200240, China

Download:

HTML

PDF(2093KB) HTML
Export: BibTeX | EndNote (RIS)

Abstract

Aiming at the requirements of intelligent maintenance and digital diagnosis of commercial aircraft in China, a novel Boyer-Moore long short-term memory network (BM LSTM) algorithm was proposed for unstructured fault isolation manual. A majority voting method was used to fuse three entity recognition algorithms including conditional random fields (CRF), bi-directional long short-term memory (BiLSTM) and BiLSTM CRF. The accuracy of entity recognition was effectively improved by the proposed BM LSTM algorithm. On this basis, a maintenance scheme knowledge graph was constructed for the commercial aircraft maintenance fault diagnosis manual. A commercial aircraft maintenance scheme recommendation system was designed by combining term frequency-inverse document frequency (TF-IDF) similarity algorithm with BM LSTM. Maintenance schemes can be matched accurately with this recommendation system by retrieving the unstructured fault description texts. Experimental results show that the proposed knowledge graph and the maintenance scheme recommendation system can effectively ensure the accurate matching of maintenance information, and the efficiency of maintenance scheme formation is significantly improved.

Key words： commercial aircraft fault isolation manual Boyer-Moore long short-term memory network (BM LSTM) knowledge graph term frequency-inverse document frequency (TF-IDF) similarity

Received: 12 July 2022 Published: 31 March 2023

CLC:

TH 183

Fund: 国家自然科学基金资助项目(51875359)；上海市“科技创新行动计划”自然科学基金资助项目(20ZR1428600)；上海商用飞机系统工程科创中心联合研究基金资助项目(FASE-2021-M7)；教育部-中国移动联合基金资助项目(MCM20180703)；上海交通大学深蓝计划基金资助项目(SL2021MS008)；中船-交大海洋装备前瞻创新联合基金资助项目(22B010432)

Corresponding Authors: Tang-bin XIA E-mail: xingxueqi@sjtu.edu.cn;xtbxtb@sjtu.edu.cn

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Xue-qi XING
	Yu-tong DING
	Tang-bin XIA
	Er-shun PAN
	Li-feng XI

Cite this article:

Xue-qi XING,Yu-tong DING,Tang-bin XIA,Er-shun PAN,Li-feng XI. Integrated modeling of commercial aircraft maintenance plan recommendation system based on knowledge graph. Journal of ZheJiang University (Engineering Science), 2023, 57(3): 512-521.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2023.03.009 OR https://www.zjujournals.com/eng/Y2023/V57/I3/512

基于知识图谱的商用飞机维修方案推荐系统集成建模

针对我国商用飞机智能维修和数字化诊断的需求,面向非结构化故障隔离手册，提出新型BM长短期记忆网络（BM LSTM）算法. 运用多数投票法融合条件随机场（CRF）、双向长短期记忆网络（BiLSTM）、BiLSTM CRF 3种实体识别算法，有效提高实体识别精度. 基于商用飞机维修故障诊断手册构建维修方案知识图谱，结合词频-逆向文件频率（TF-IDF）相似度算法与BM LSTM算法，设计商用飞机维修方案推荐系统，实现通过检索非结构化故障描述文本准确匹配到维修方案的功能. 实验结果表明，利用商用飞机故障隔离手册构建知识图谱、基于所提创新方法开发的维修方案推荐系统，能够有效保证维修信息精确匹配，显著提高维修方案形成效率.

关键词： 商用飞机, 故障隔离手册, BM长短期记忆网络（BM LSM）, 知识图谱, 词频-逆向文件频率（TF-IDF）相似度

Fig.1 Example of fault isolation manual

Fig.2 Knowledge graph interface based on Neo4j graph knowledge base storage

Fig.3 Commercial aircraft maintenance scheme recommendation system process

Fig.4 Framework of text similarity matching module

Fig.5 Framework of entity recognition matching module

Fig.6 Example of service manual data in SQL format

Fig.7 Examples of fault description data encoded by BIOES

Fig.8 Ontology design of knowledge graph in field of commercial aircraft maintenance

Fig.9 Chinese named entity recognition results of different algorithms

Fig.10 Three-dimensional graph of integrated algorithm parameter tuning

Fig.11 Two-dimensional graph of integrated algorithm parameter tuning

Fig.12 Example of knowledge graph in field of commercial aircraft maintenance

Fig.13 Performance of maintenance scheme recommendation system under different thresholds

Fig.14 Effect test of maintenance scheme recommendation model


[1]	WU G A trio of commercial aircraft developments in China[J]. Engineering, 2021, 7 (4): 424- 426 doi: 10.1016/j.eng.2020.07.033

[2]	姚明, 李君成, 陈龙边缘计算智能装备技术在飞机检修行为识别领域的应用[J]. 航空维修与工程, 2022, (2): 29- 31 YAO Ming, LI Jun-cheng, CHEN Long Edge computing intelligent equipment technology and its application for aircraft maintenance and inspection behavior recognition[J]. Aviation Maintenance and Engineering, 2022, (2): 29- 31

[3]	厦门航空有限公司维修高质量发展项目组厦航维修系统高质量发展指标框架体系[J]. 航空维修与工程, 2022, (6): 11- 13 High-quality Development Group of Xiamen Air The high quality development index framework of Xiamen Airlines maintenance system[J]. Aviation Maintenance and Engineering, 2022, (6): 11- 13

[4]	王锐光, 吴际, 刘超, 等基于维修日志的飞机设备故障原因判别方法[J]. 软件学报, 2019, 30 (5): 1375- 1385 WANG Rui-guang, WU Ji, LIU Chao, et al Fault cause identification method for aircraft equipment based on maintenance log[J]. Journal of Software, 2019, 30 (5): 1375- 1385

[5]	STEPHEN B, JIANG X, MCARTHUR S D J Extracting distribution network fault semantic labels from free text incident tickets[J]. IEEE Transactions on Power Delivery, 2020, 35 (3): 1610- 1613 doi: 10.1109/TPWRD.2019.2947784

[6]	贾宝惠, 姜番, 王玉鑫, 等基于民机维修文本数据的故障诊断方法研究[J]. 航空学报, 2022, 43: 1- 15 JIA Bao-hui, JIANG Fan, WANG Yu-xin, et al Research on fault diagnosis method based on civil Aircraft maintenance text data[J]. Acta Aeronautica et Astronautica Sinica, 2022, 43: 1- 15 doi: 10.7527/j.issn.1000-6893.2022.7.hkxb202207001

[7]	WANG F, XU T, TANG T, et al Bilevel feature extraction-based text mining for fault diagnosis of railway systems[J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 18 (1): 49- 58 doi: 10.1109/TITS.2016.2521866

[8]	BHARDWAJ A S, DEEP A, VEERAMANI D, et al A custom word embedding model for clustering of maintenance records[J]. IEEE Transactions on Industrial Informatics, 2022, 18 (2): 816- 826 doi: 10.1109/TII.2021.3079521

[9]	EBRAHIMIPOUR V, YACOUT S Ontology-based schema to support maintenance knowledge representation with a case study of a pneumatic valve[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2015, 45 (4): 702- 712 doi: 10.1109/TSMC.2014.2383361

[10]	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 doi: 10.1109/TNNLS.2021.3070843

[11]	陶家琦, 李心雨, 郑湃, 等制造领域知识图谱的应用研究现状与前沿[J]. 计算机集成制造系统, 2022, 28 (12): 3720- 3736 TAO Jia-qi, LI Xin-yu, ZHENG Pai, et al State-of-the-art and frontier of manufacturing knowledge graph application[J]. Computer Integrated Manufacturing Systems, 2022, 28 (12): 3720- 3736

[12]	陈成, 张皞, 李永强, 等关系生成图注意力网络的知识图谱链接预测[J]. 浙江大学学报: 工学版, 2022, 56 (5): 1025- 1034 CHEN Cheng, ZHANG Hao, LI Yong-qiang, et al Knowledge graph link prediction based on relational generative graph attention network[J]. Journal of Zhejiang University: Engineering Science, 2022, 56 (5): 1025- 1034

[13]	LOURENÇO V, PAES A Learning attention-based representations from multiple patterns for relation prediction in knowledge graphs[J]. Knowledge-Based Systems, 2022, 251: 109232 doi: 10.1016/j.knosys.2022.109232

[14]	MA R, GUO F, LI Z, et al Knowledge graph random neural networks for recommender systems[J]. Expert Systems with Applications, 2022, 201: 117120 doi: 10.1016/j.eswa.2022.117120

[15]	宋邓强, 周彬, 申兴旺, 等面向船舶分段制造过程的动态知识图谱建模方法[J]. 上海交通大学学报, 2021, 55 (5): 544- 556 SONG Deng-qiang, ZHOU Bin, SHEN Xing-wang, et al Dynamic knowledge graph modeling for ship block manufacturing process[J]. Journal of Shanghai Jiao Tong University, 2021, 55 (5): 544- 556

[16]	REN H, CHEN Z, JIANG Z, et al An industrial multilevel knowledge graph-based local–global monitoring for plant-wide processes[J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70: 3526715

[17]	郭恒, 黎荣, 张海柱, 等多域融合的高速列车维修性设计知识图谱构建[J]. 中国机械工程, 2022, 33 (24): 3015- 3023 GUO Heng, LI Rong, ZHANG Hai-zhu, et al Construction of knowledge graph of maintainability design based on multi-domain fusion of high-speed trains[J]. China Mechanical Engineering, 2022, 33 (24): 3015- 3023

[18]	欧一鸣, 苏雍贺, 靳健, 等基于知识图谱的分布式光伏运维方案匹配方法[J]. 计算机集成制造系统, 2021, 27 (7): 1860- 1870 OU Yi-ming, SU Yong-he, JIN Jian, et al Matching method for distributed photovoltaic maintenance scheme based on knowledge graph[J]. Computer Integrated Manufacturing Systems, 2021, 27 (7): 1860- 1870

[19]	田嘉鹏, 宋辉, 陈立帆, 等面向知识图谱构建的设备故障文本实体识别方法[J]. 电网技术, 2021, 46 (10): 3913- 3922 TIAN Jia-peng, SONG Hui, CHEN Li-fan, et al Entity recognition approach of equipment failure text for knowledge graph construction[J]. Power System Technology, 2021, 46 (10): 3913- 3922

[20]	张亮, 吴闯, 唐希浪, 等航空发动机故障实体识别方法及应用[J]. 空军工程大学学报: 自然科学版, 2022, 23 (2): 1- 6 ZHANG Liang, WU Chuang, TANG Xi-lang, et al A method of recognizing aero-engine fault entity and its application[J]. Journal of Air Force Engineering University: Natural Science Edition, 2022, 23 (2): 1- 6

[21]	MOUHCINE R, MUSTAPHA A, ZOUHIR M Recognition of cursive Arabic handwritten text using embedded training based on HMMs[J]. Journal of Electrical System and Information Technology, 2018, 5 (2): 245- 251 doi: 10.1016/j.jesit.2017.02.001

[22]	LI M, SHI L, WANG Y, et al Automated data function extraction from textual requirements by leveraging semi-supervised CRF and language model[J]. Information and Software Technology, 2022, 143: 106770 doi: 10.1016/j.infsof.2021.106770

[23]	陈岳林, 田文靖, 蔡晓东, 等基于密集连接网络和多维特征融合的文本匹配模型[J]. 浙江大学学报: 工学版, 2021, 55 (12): 2352- 2358 CHEN Yue-lin, TIAN Wen-jing, CAI Xiao-dong, et al Text matching model based on dense connection network and multi-dimensional feature fusion[J]. Journal of Zhejiang University: Engineering Science, 2021, 55 (12): 2352- 2358

[24]	农元君, 王俊杰, 陈红, 等基于注意力机制和编码-解码架构的施工场景图像描述方法[J]. 浙江大学学报: 工学版, 2022, 56 (2): 236- 244 NONG Yuan-jun, WANG Jun-jie, CHEN Hong, et al A image caption method of construction scene based on attention mechanism and encoding-decoding architecture[J]. Journal of Zhejiang University: Engineering Science, 2022, 56 (2): 236- 244

[25]	于军琪, 杨思远, 赵安军, 等基于神经网络的建筑能耗混合预测模型[J]. 浙江大学学报: 工学版, 2022, 56 (6): 1220- 1231 YU Jun-qi, YANG Si-yuan, ZHAO An-jun, et al Hybrid prediction model of building energy consumption based on neural network[J]. Journal of Zhejiang University: Engineering Science, 2022, 56 (6): 1220- 1231

[26]	LI Z, LI Q, ZOU X, et al Causality extraction based on self-attentive BiLSTM-CRF with transferred embeddings[J]. Neurocomputing, 2021, 423: 207- 219 doi: 10.1016/j.neucom.2020.08.078

[27]	李广龙, 申德荣, 聂铁铮, 等数据库外基于多模型的学习式查询优化方法[J]. 浙江大学学报: 工学版, 2022, 56 (2): 288- 296 LI Guang-long, SHEN De-rong, NIE Tie-zheng, et al Learning query optimization method based on multi model outside database[J]. Journal of Zhejiang University: Engineering Science, 2022, 56 (2): 288- 296

[1]	Feng-long SU,Ning JING. Temporal knowledge graph representation learning based on relational aggregation[J]. Journal of ZheJiang University (Engineering Science), 2023, 57(2): 235-242.

[2]	Li-zhou FENG,Yang YANG,You-wei WANG,Gui-jun YANG. New method for news recommendation based on Transformer and knowledge graph[J]. Journal of ZheJiang University (Engineering Science), 2023, 57(1): 133-143.

[3]	Cheng CHEN,Hao ZHANG,Yong-qiang LI,Yuan-jing FENG. Knowledge graph link prediction based on relational generative graph attention network[J]. Journal of ZheJiang University (Engineering Science), 2022, 56(5): 1025-1034.

Viewed

Full text

Abstract

Cited

Shared

Discussed