PCB工艺FMEA领域知识图谱构建与应用

doi:10.3778/j.issn.1002-8331.2403-0143

摘要/Abstract

摘要： 随着电子产品的快速发展，产业链厂商对印制电路板（PCB）的失效模式和影响分析（FMEA）提出了更高水平要求，传统的FMEA分析方法已经不能满足复杂电子产品的需求。为此提出了一套PCB工艺FMEA知识图谱构建与应用框架，实现端到端的FMEA分析新模式。在图谱构建过程中，针对大量实体为复杂句子的特点，训练了一个加入PCB与FMEA特征词典的FLEBERT NER模型，实现对失效数据的实体识别，实验对比证明效果良好；对识别的实体采用Sentence-BERT结合FLEBERT预训练模型进行实体对齐，提升知识的质量；通过Neo4j进行知识存储完成知识图谱构建。基于已构建的知识图谱，搭建了FMEA知识图谱平台，初步实现了知识探索、知识问答和知识推荐的应用，展示了知识图谱技术在PCB工艺FMEA分析领域具备良好的应用前景。

关键词: 知识图谱, 印制电路板（PCB）, 失效模式和影响分析（FMEA）, 命名实体识别（NER）, BERT

Abstract: With the rapid development of electronic products, industrial chain manufacturers have put forward higher requirements for the failure mode and effect analysis (FMEA) of printed circuit boards (PCB), and the traditional FMEA analysis method can no longer meet the needs of complex electronic products. This paper proposes a set of PCB process FMEA knowledge graph construction and application frameworks to realize a novel end-to-end FMEA analysis model. During the graph construction, given the characteristics of a large number of entities in complex sentences, a named entity recognition (NER) model of FLEBERT with PCB and FMEA feature dictionaries added is trained to recognize the failed data, and the experimental comparison proves that the effect is good. The entities after recognition use Sentence-BERT combined with the FLEBERT pre-training model for entity alignment to improve the quality of knowledge. Finally, Neo4j is used for knowledge storage to complete the construction of the knowledge graph. Based on the constructed knowledge graph, this paper builds the FMEA knowledge graph platform, and initially realizes the application of knowledge exploration, knowledge Q&A and knowledge recommendation, demonstrating that knowledge graph technology has good application prospects in the PCB process FMEA analysis field.

Key words: knowledge graph, printed circuit boards(PCB), failure mode and effect analysis(FMEA), named entity recognition (NER), BERT

叶进, 林琦越, 唐欣, 王秋祥, 胡宁. PCB工艺FMEA领域知识图谱构建与应用[J]. 计算机工程与应用, 2025, 61(11): 227-237.

YE Jin, LIN Qiyue, TANG Xin, WANG Qiuxiang, HU Ning. Construction and Application of Knowledge Graph in PCB Process FMEA Field[J]. Computer Engineering and Applications, 2025, 61(11): 227-237.

参考文献

[1] 张家亮. 2022年全球PCB发展现状及未来趋势[J]. 印制电路资讯, 2023(2): 27-34.
ZHANG J L. Global PCB development and future trends in 2022[J]. Printed Circuit Board Information, 2023(2): 27-34.
[2] 吴一全, 赵朗月, 苑玉彬, 等. 基于机器视觉的PCB缺陷检测算法研究现状及展望[J]. 仪器仪表学报, 2022, 43(8): 1-17.
WU Y Q, ZHAO L Y, YUAN Y B, et al. Research status and the prospect of PCB defect detection algorithm based on machine vision[J]. Chinese Journal of Scientific Instrument, 2022, 43(8): 1-17.
[3] AIAG, VDA. AIAG&VDA Failure mode and effects analysis (FMEA) handbook[M]. Michigan: America Automotive Industry Action Group, 2019.
[4] SINGHAL A. Introducing the knowledge graph: things, not strings[EB/OL]. (2012-05-16) [2024-03-04]. https://www. blog.google/products/search/introducing-knowledge-graph-things-not/.
[5] EHRMANN M, HAMDI A, LINHARES PONTES E, et al. Named entity recognition and classification in historical documents: a survey[J]. ACM Computing Surveys, 2023, 56(2): 1-47.
[6] DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019: 4171-4186.
[7] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017: 6000-6010.
[8] LIU W, FU X Y, ZHANG Y, et al. Lexicon enhanced Chinese sequence labeling using BERT adapter[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, 2021: 5847-5858.
[9] LI Z W, GUO B, HU Y C, et al. BERT-based Chinese NER with lexicon and position enhanced information adapter[C]//Proceedings of the IEEE 24th International Conference on High Performance Computing & Communications, 2023: 1618-1624.
[10] YU J Y, FENG X Y, LI J, et al. Named entity recognition in classical Chinese by lexicon enhancement[C]//Proceedings of the IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology, 2023: 463-468.
[11] MUTINDA J, MWANGI W, OKEYO G. Sentiment analysis of text reviews using lexicon-enhanced BERT embedding (LeBERT) model with convolutional neural network[J]. Applied Sciences, 2023, 13(3): 1445.
[12] 许驹雄, 李敏波, 刘孟珂, 等. 发动机故障领域知识图谱构建与应用[J]. 计算机系统应用, 2022, 31(7): 66-76.
XU J X, LI M B, LIU M K, et al. Construction and application of knowledge graph in diesel engine fault field[J]. Computer Systems & Applications, 2022, 31(7): 66-76.
[13] ZHOU B X, GAO D Q, YAN L C, et al. Research on key technologies for fault knowledge acquisition of power communication equipment[J]. Procedia Computer Science, 2021, 183: 479-485.
[14] 邱凌, 张安思, 张羽, 等. 面向无人机故障诊断的知识图谱构建应用方法[J]. 计算机工程与应用, 2023, 59(9): 280-288.
QIU L, ZHANG A S, ZHANG Y, et al. Application method of knowledge graph construction for UAV fault diagnosis[J]. Computer Engineering and Applications, 2023, 59(9): 280-288.
[15] 胡杰, 李源洁, 耿號, 等. 基于深度学习的汽车故障知识图谱构建[J]. 汽车工程, 2023, 45(1): 52-60.
HU J, LI Y, GENG H, et al. Construction of vehicle fault knowledge graph based on deep learning[J]. Automotive Engineering, 2023, 45(1): 52-60.
[16] 邓健峰, 王涛, 程良伦. 机器人故障诊断事理逻辑知识图谱构建研究[J]. 计算机工程与应用, 2023, 59(13): 139-148.
DENG J F, WANG T, CHENG L L. Research on construction of event logic knowledge graph of robot fault diagnosis[J]. Computer Engineering and Applications, 2023, 59(13): 139-148.
[17] 乔骥, 王新迎, 闵睿, 等. 面向电网调度故障处理的知识图谱框架与关键技术初探[J]. 中国电机工程学报, 2020, 40(18): 5837-5849.
QIAO J, WANG X Y, MIN R, et al. Framework and key technologies of knowledge-graph-based fault handling system in power grid[J]. Proceedings of the CSEE, 2020, 40(18): 5837-5849.
[18] 武杰, 张安思, 吴茂东, 等. 知识图谱在装备故障诊断领域的研究与应用综述[J]. 计算机应用, 2024, 44(9): 2651-2659.
WU J, ZHANG A S, WU M D, et al. Overview of research and application of knowledge graph in equipment fault diagnosis[J]. Journal of Computer Applications, 2024, 44(9): 2651-2659.
[19] MA X Z, HOVY E. End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, 2016: 1064-1074.
[20] REIMERS N, GUREVYCH I. Sentence-BERT: sentence embeddings using siamese BERT-networks[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019: 3982-3992.
[21] WU W, JING X Y, DU W C. Learning dynamics of gradient descent optimization in deep neural networks[J]. Science China Information Sciences, 2021(64): 150102.
[22] SUN C, QIU X P, XU Y G, et al. How to fine-tune BERT for text classification?[C]//Proceedings of the 18th China National Conference on Chinese Computational Linguistics, 2019: 194-206.
[23] GOWRI K, SUNIL M, YADAV R K. Explore deep learning trends by decoding activated networks[C]//Proceedings of the International Conference on Advances in Computation, Communication and Information Technology, 2023: 778-783.