基于本体引导的注塑知识图谱构建及缺陷溯因应用

王雅琳; 邹江枫; 王凯; 袁小锋; 谢胜利

doi:10.11999/JEIT211416

基于本体引导的注塑知识图谱构建及缺陷溯因应用

doi: 10.11999/JEIT211416

1.
中南大学自动化学院长沙 410083
2.
广东工业大学广州 510006

基金项目: 国家自然科学基金(U1911401)，国家重点研发计划(2020YFB1713800)，湖南省科技创新计划(2021RC4054)，中南大学中央高校基本科研业务费专项资金(2021zzts0711)

详细信息

作者简介:
王雅琳：女，1973年生，教授，研究方向为复杂工业过程建模与优化、模式识别与智能优化、工业大数据解析

邹江枫：女，2000年生，硕士生，研究方向为工业知识图谱

王凯：男，1992年生，副教授，研究方向为工业大数据分析与建模、数据驱动的过程监测、工业智能与机器学习

袁小锋：男，1988年生，教授，研究方向为工业大数据和智能制造、机器学习与模式识别、过程监测与软测量建模

谢胜利：男，1959年生，教授，研究方向为自适应信号处理、无线通信与网络、物联网信息技术

通讯作者:
王凯　kaiwang@csu.edu.cn

中图分类号: TP274
计量
- 文章访问数: 886
- HTML全文浏览量: 524
- PDF下载量: 110
- 被引次数: 0
出版历程
- 收稿日期: 2021-12-02
- 修回日期: 2022-04-14
- 网络出版日期: 2022-04-24
- 刊出日期: 2022-05-25

Injection Molding Knowledge Graph Based on Ontology Guidance and its Application to Quality Diagnosis

1.
School of Automation, Central South University, Changsha 410083, China
2.
School of Automation, Guangdong University of Technology, Guangzhou 510006, China

Funds: The National Natural Science Foundation of China (U1911401), The National Key Research and Development Program of China (2020YFB1713800), The Science and Technology Innovation Program of Hunan Province in China (2021RC4054), The Fundamental Research Funds for the Central Universities of Central South University (2021zzts0711)

摘要

摘要: 针对大型注塑图谱缺失、成熟标注语料匮乏等导致的工业知识图谱构建代价高昂、质量不高等问题，该文提出一种基于本体引导的注塑知识图谱构建方法。首先，设计以缺陷-表观-原因-方案为导向的注塑本体，指导注塑网页的搜集；其次将本体信息融入至触发词中，以提升对半结构化网页的知识抽取性能；然后，结合本体中的属性相似度进行两级实体对齐，综合提高冗余知识的发现率。最后与已有方法对比，图谱知识正确率高于95%，可快速实现缺陷溯因。
- 注塑成型 /
- 知识图谱 /
- 本体工程 /
- 实体对齐
Abstract: Due to the lack of mature labeled corpus and large-scale injection molding knowledge graphs for defection diagnosis, industrial knowledge graphs are constructed with high cost and low quality. A framework for constructing industrial knowledge graph based on ontology guidance is developed in this paper. Firstly, the injection molding ontology guided by defect-appearance-cause-scheme chain is designed to limit the collection of web pages. Then, the ontology information is sequentially integrated into the trigger thesaurus to improve the knowledge extraction performance of unstructured web text. Finally, the two-level entity merging method is carried out by combining with the attribute similarity in ontology, which realized the fusion of redundant knowledge. Compared with the existing methods, the accuracy of domain knowledge is higher than 95%, which can be used for tracing the defect quickly.
- Injection molding /
- Knowledge graph /
- Ontology engineering /
- Entity merging

HTML全文

图 1 注塑知识图谱构建框架图

下载: 全尺寸图片幻灯片

图 2 注塑缺陷诊断本体概况(部分)

下载: 全尺寸图片幻灯片

图 3 基于本体引导的领域知识发现方法

下载: 全尺寸图片幻灯片

图 4 基于触发词的语料知识抽取方法

下载: 全尺寸图片幻灯片

图 5 基于多重属性的两级实体对齐架构

下载: 全尺寸图片幻灯片

图 6 采用不同知识抽取方案的效果对比

下载: 全尺寸图片幻灯片

图 7 知识3元组随抽取网页数目的增长曲线

下载: 全尺寸图片幻灯片

图 8 采用不同知识融合方案的效果对比

下载: 全尺寸图片幻灯片

图 9 实体对齐前的知识图谱可视化示例结果

下载: 全尺寸图片幻灯片

图 10 实体对齐后的知识图谱可视化示例结果

下载: 全尺寸图片幻灯片

表 1 注塑知识3元组的置信度评估

图谱组成专家编号	实体属性 A	原因3元组 A/B/C	方案3元组 A/B/C
书籍重合	284	108/83/111	143/87/143
新增知识	284	41/73/38	39/98/38
争议知识	0	11/3/11	5/1/5
错误知识	5	3/4/3	9/10/10
总准确率	0.98	0.91/0.96/0.91	0.93/0.94/0.92

下载: 导出CSV

参考文献(29)

[1]	田书竹. 注塑产品缺陷图析[M]. 北京: 化学工业出版社, 2019: 1–10. TIAN Shuzhu. Defect Analysis of Injection Molding Product[M]. Beijing: Chemical Industry Press, 2019: 1–10.
[2]	ZHAO Peng, ZHANG Jianfeng, DONG Zhengyang, et al. Intelligent injection molding on sensing, optimization, and control[J]. Advances in Polymer Technology, 2020, 2020: 7023616. doi: 10.1155/2020/7023616
[3]	KASHYAP S and DATTA D. Process parameter optimization of plastic injection molding: A review[J]. International Journal of Plastics Technology, 2015, 19(1): 1–18. doi: 10.1007/s12588-015-9115-2
[4]	GIM J, HAN E, RHEE B, et al. Causes of the gloss transition defect on high-gloss injection-molded surfaces[J]. Polymers, 2020, 12(9): 2100. doi: 10.3390/polym12092100
[5]	HENTATI F, HADRICHE I, MASMOUDI N, et al. Optimization of the injection molding process for the PC/ABS parts by integrating Taguchi approach and CAE simulation[J]. The International Journal of Advanced Manufacturing Technology, 2019, 104(9): 4353–4363. doi: 10.1007/s00170-019-04283-z
[6]	MUKRAS S M S, OMAR H M, and AL-MUFADI F A. Experimental-based multi-objective optimization of injection molding process parameters[J]. Arabian Journal for Science and Engineering, 2019, 44(9): 7653–7665. doi: 10.1007/s13369-019-03855-1
[7]	KUMAR S and SINGH A K. Warpage and shrinkage analysis and optimization of rapid tooling molded thin wall component using modified particle swarm algorithm[J]. Journal of Advanced Manufacturing Systems, 2019, 18(1): 85–102. doi: 10.1142/S0219686719500045
[8]	陶显, 侯伟, 徐德. 基于深度学习的表面缺陷检测方法综述[J]. 自动化学报, 2021, 47(5): 1017–1034. doi: 10.16383/j.aas.c190811 TAO Xian, HOU Wei, and XU De. A survey of surface defect detection methods based on deep learning[J]. Acta Automatica Sinica, 2021, 47(5): 1017–1034. doi: 10.16383/j.aas.c190811
[9]	BANG H T, PARK S, and JEON H. Defect identification in composite materials via thermography and deep learning techniques[J]. Composite Structures, 2020, 246: 112405. doi: 10.1016/j.compstruct.2020.112405
[10]	XU Xiaojian, YAN Xinping, SHENG Chenxing, et al. A belief rule-based expert system for fault diagnosis of marine diesel engines[J]. IEEE Transactions on Systems, Man, and Cybernetics:Systems, 2020, 50(2): 656–672. doi: 10.1109/TSMC.2017.2759026
[11]	PAULHEIM H. Knowledge graph refinement: A survey of approaches and evaluation methods[J]. Semantic Web, 2017, 8(3): 489–508. doi: 10.3233/SW-160218
[12]	WANG Quan, MAO Zhendong, WANG Bin, et al. Knowledge graph embedding: A survey of approaches and applications[J]. IEEE Transactions on Knowledge and Data Engineering, 2017, 29(12): 2724–2743. doi: 10.1109/TKDE.2017.2754499
[13]	CHEN Xiaojun, JIA Shengbin, and XIANG Yang. A review: Knowledge reasoning over knowledge graph[J]. Expert Systems with Applications, 2020, 141: 112948. doi: 10.1016/j.eswa.2019.112948
[14]	刘淞华, 何冰冰, 郎恂, 等. 中值互补集合经验模态分解[J]. 自动化学报, 2021, 47: 1–13. doi: 10.16383/j.aas.c201031 LIU Songhua, HE Bingbing, LANG Xun, et al. Median complementary ensemble empirical mode decomposition[J]. Acta Automatica Sinica, 2021, 47: 1–13. doi: 10.16383/j.aas.c201031
[15]	DUAN Linbo, QIN Ping, QIAN Lingfei, et al. Research on domain ontology construction based on thesaurus of geographical science[C]. The 2017 2nd International Conference on Automation, Mechanical Control and Computational Engineering, Beijing, China, 2017: 15–23.
[16]	ZHITOMIRSKY-GEFFET M, EREZ E S, and JUDIT B I. Toward multiviewpoint ontology construction by collaboration of non-experts and crowdsourcing: The case of the effect of diet on health[J]. Journal of the Association for Information Science and Technology, 2017, 68(3): 681–694. doi: 10.1002/asi.23686
[17]	AL-ASWADI F N, CHAN H Y, and GAN K H. Automatic ontology construction from text: A review from shallow to deep learning trend[J]. Artificial Intelligence Review, 2020, 53(6): 3901–3928. doi: 10.1007/s10462-019-09782-9
[18]	MAO Shuai, ZHAO Yunmeng, CHEN Jinhe, et al. Development of process safety knowledge graph: A case study on delayed coking process[J]. Computers & Chemical Engineering, 2020, 143: 107094. doi: 10.1016/j.compchemeng.2020.107094
[19]	XIONG Ziqi, KONG Dezhi, XIA Zhichao, et al. Automated construction technology of the government agencies knowledge graph based on the topical crawler[J]. Journal of Physics:Conference Series, 2020, 1656(1): 012016. doi: 10.1088/1742-6596/1656/1/012016
[20]	SOBHANA N V, MITRA P, and GHOSH S K. Conditional random field based named entity recognition in geological text[J]. International Journal of Computer Applications, 2010, 1(3): 119–126. doi: 10.5120/72-166
[21]	EKBAL A and BANDYOPADHYAY S. Named entity recognition using support vector machine: A language independent approach[J]. International Journal of Electrical, Computer, and Systems Engineering, 2010, 4(2): 155–170.
[22]	MA Jianxia and YUAN Hui. Bi-LSTM+CRF-based named entity recognition in scientific papers in the field of ecological restoration technology[J]. The Association for Information Science and Technology, 2019, 56(1): 186–195. doi: 10.1002/pra2.16
[23]	GENG Zhiqiang, ZHANG Yanhui, and HAN Yongming. Joint entity and relation extraction model based on rich semantics[J]. Neurocomputing, 2021, 429: 132–140. doi: 10.1016/j.neucom.2020.12.037
[24]	LIN B Y, LEE D H, SHEN Ming, et al. TriggerNER: Learning with entity triggers as explanations for named entity recognition[C]. The 58th Annual Meeting of the Association for Computational Linguistics, Jacksonville, USA, 2020: 8503–8511.
[25]	VIDANAGE K, NOOR N M M, MOHEMAD R, et al. Semantic web-based knowledge extraction: Upper ontology guided crime knowledge discovery[C]. The 2nd International Conference on Advanced Computing Technologies and Applications, Mumbai, India, 2020: 311–323.
[26]	GÓMEZ-PÉREZ A. Evaluation of taxonomic knowledge in ontologies and knowledge bases[C]. The 12th Banff Knowledge Acquisition for Knowledge-Based Systems, Banff, Canada, 1999.
[27]	ADNAN K and AKBAR R. Limitations of information extraction methods and techniques for heterogeneous unstructured big data[J]. International Journal of Engineering Business Management, 2019, 11: 1–23. doi: 10.1177/1847979019890771
[28]	KHATUA A, KHATUA A, and CAMBRIA E. A tale of two epidemics: Contextual Word2Vec for classifying twitter streams during outbreaks[J]. Information Processing & Management, 2019, 56(1): 247–257. doi: 10.1016/j.ipm.2018.10.010
[29]	MORENJIUJIU. 中文命名实体识别[EB/OL]. https://github.com/morenjiujiu/chinese_ner_pytorch_bilstm_crf/blob/master/advanced_tutorial.ipynb. 2019.