Knowledge-based Rapid Preparation Method for Complex Product Assembly Process

doi:10.12382/bgxb.2022.1225

Abstract

Abstract:

Aiming at the problems of low preparation efficiency, high quality fluctuation and low automation and intelligence in the process of complex product assembly process design, a fast preparation method for assembly process with semantic-oriented knowledge instance retrieval and reuse is proposed. A two-layer assembly process knowledge model based on the knowledge retrieval layer and the knowledge instance layer is established by analyzing the assembly process of complex product, and the knowledge is classified in terms of content, type, function and application direction. On this basis, a process document semantic analysis method based on the Sentence-BERT sentence embeddings model is proposed for the existing knowledge instances. The semantic retrieval method of process knowledge is given combined with the cosine similarity algorithm, and the rapid reuse of knowledge in the design process of assembly process is realized. Taking aerospace products as an example, a rapid design management system of aerospace product assembly process is developed, and a knowledge base for the assembly process is constructed and put into operation in an aerospace enterprise to verify the feasibility of the proposed method, resulting in a significant increase in process preparation efficiency.

Key words: complex product, assembly, knowledge model, sentence embeddings, senmantic retrieval, knowledge base

CLC Number:

TP391

ZHAI Sikuan, LIU Jianhua, ZHUANG Cunbo. Knowledge-based Rapid Preparation Method for Complex Product Assembly Process[J]. Acta Armamentarii, 2024, 45(4): 1332-1343.

Figures/Tables 16

Fig.1 Business process for complex product assembly processes

Fig.2 Double layer assembly process knowledge model

Fig.3 Structure of Sentence-BERT model

Fig.4 Retrieval process for examples of assembly process knowledge

Fig.5 Process requirements illustrative document

Fig.6 Process card for the assembly process of a satellite payload bay structure

Table 1 Fields of Procedure table

PCD_ ID	PCD_ NAME	PCD_ WORKTYPE	PCD_ CONTENT	PCD_ ASMFLOW NODEID
123	下舱装配	总装	将下舱装入…	24

Table 2 Fields of Step table

STP_ ID	STP_ NAME	STP_ WORKTYPE	STP_ CONTENT	STP_ PARENTPRO CEDUREID
445	M6.1	钳工	将载荷舱底板安装在载荷舱转接环上,…	123

Fig.7 Sentence embeddings corresponding to text data

Table 3 Calculated results of sentence embeddings similarity

知识实例	相似度
Process-01	0.4454
Process-02	0.7964
Process-03	0.8296
Process-04	0.2633
Process-05	0.3256
Process-06	0.5859
Process-07	0.4655
Process-08	0.5212
Process-09	0.5063
Process-10	0.7524

Fig.8 Process design process based on process knowledge base

Fig.9 Interface of a typical process library

Fig.10 Upload process requirement

Fig.11 Assembly process search results

Fig.12 Assembly process content inheritance

Fig.13 Interface of automatic inspection of assembly process specification

References 24

[1]	尚育如, 富大欣, 李川生, 等. 航天工艺基础知识培训教材(下)[M]. 北京: 中国宇航出版社, 2005.
	SHANG Y R, FU D X, LI C S, et al. Training materials for basic knowledge of aerospace technology (below)[M]. Beijing: China Aerospace Press, 2005. (in Chinese)
[2]	叶剑辉, 刘少丽, 刘检华, 等. 基于流程的复杂产品装配车间现场监控技术[J]. 计算机集成制造系统, 2017, 23(7): 1469-1480.
	YE J H, LIU S L, LIU J H, et al. Process-based on-site monitoring technology for complex product assembly workshops[J]. Computer Integrated Manufacturing Systems, 2017, 23(7): 1469-1480. (in Chinese)
[3]	ZHOU W, LI S Q, HUANG Y Q, et al. Simulation-based planning of a kind of complex product general assembly line[J]. Procedia Cirp, 2018, 76: 25-30.
[4]	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. doi: 10.16183/j.cnki.jsjtu.2020.241
	SONG D Q, ZHOU B, SHEN X W, et al. A dynamic knowledge mapping modeling approach for ship segment manufacturing process[J]. Journal of Shanghai Jiaotong University, 2021, 55(5):544-556. (in Chinese)
[5]	代风, 翟翔, 施国强, 等. 面向航天产品研制的知识网络本体建模方法[J]. 浙江大学学报(工学版), 2018, 52(10):2023-2034.
	DAI F, ZHAI X, SHI G Q, et al. A knowledge network ontology modeling approach for aerospace product development[J]. Journal of Zhejiang University (Engineering Edition), 2018, 52(10):2023-2034. (in Chinese)
[6]	刘检华, 孙清超, 程晖, 等. 产品装配技术的研究现状、技术内涵及发展趋势[J]. 机械工程学报, 2018, 54(11): 2-28. doi: 10.3901/JME.2018.11.002
	LIU J H, SUN Q C, CHENG H, et al. Research status technical connotation and development trend of product assembly technology[J]. Journal of Mechanical Engineering, 2018, 54(11): 2-28. (in Chinese)
[7]	宋海薇, 左敦稳, 薛善良, 等. 基于工艺相似性的总装工艺快速设计技术研究[J]. 中国制造业信息化, 2009, 38(21): 29-31,35.
	SONG H W, ZUO D W, XUE S L, et al. Research on rapid design technology of assembly process based on process similarity[J]. China Manufacturing Informatization, 2009, 38(21): 29-31,35. (in Chinese)
[8]	王裴岩, 张桂平, 翟顺龙, 等. 基于多核学习的装配工艺过程重用[J]. 计算机集成制造系统, 2018, 24(7):1850-1857.
	WANG P Y, ZHANG G P, ZHAI S L, et al. Multi-core learning-based reuse of assembly processes[J]. Computer Integrated Manufacturing Systems, 2018, 24(7):1850-1857. (in Chinese)
[9]	孟倩, 刘检华, 唐承统, 等. 基于流程的复杂产品结构化装配工艺设计技术研究与应用[J]. 计算机集成制造系统, 2014, 20(2):301-312. doi: 10.13196/j.cims.2014.02.mengqian.0301.12.2014029
	MENG Q, LIU J H, TANG C T, et al. Research and application of process-based structured assembly process design technology for complex products[J]. Computer Integrated Manufacturing Systems, 2014, 20(2):301-312. (in Chinese)
[10]	丘宏俊, 陶华, 高晓兵, 等. 飞机装配工艺设计知识本体[J]. 西北工业大学学报, 2007, 25(1): 32-36.
	QIU H J, TAO H, GAO X B, et al. Ontology for Aircraft Assembly Process Planning Knowledge[J]. Journal of Northwestern Polytechnical University, 2007, 25(1): 32-36. (in Chinese)
[11]	刘艺涵, 茅健, 郑武. 面向智能装配的工艺知识管理方法[J]. 计算机制造集成系统, 2023, 29(8):2513-2523.
	LIU Y H MAO J, ZHENG W. A process knowledge management approach for intelligent assembly[J]. Computerized Manufacturing Integrated Systems, 2023, 29(8):2513-2523. (in Chinese)
[12]	ZHOU B, BAO J S, CHEN Z Y, et al. KGAssembly: knowledge graph-driven assembly process generation and evaluation for complex components[J]. International Journal of Computer Integrated Manufacturing, 2022, 35(10/11): 1151-1171.
[13]	顾星海, 鲍劲松, 吕超凡. 基于知识图谱的装配语义信息建模[J]. 航空制造技术, 2021, 64(4):74-81.
	GU X H, BAO J S, LÜ C F. Semantic information modeling of assembly based on knowledge graph[J]. Aerospace Manufacturing Technology, 2021, 64(4):74-81. (in Chinese)
[14]	WANG W M, PENG X, ZHU G N, et al. Dynamic representation of fuzzy knowledge based on fuzzy petri net and genetic-particle swarm optimization[J]. Expert Systems with Applications, 2014, 41(4): 1369-1376.
[15]	WANG R, NELLIPPALLIL A B, WANG G, et al. A process knowledge representation approach for decision support in design of complex engineered systems[J]. Advanced Engineering Informatics, 2021, 48: 101257.
[16]	ALOMRAN F N A, TREUDE C. Choosing an NLP library for analyzing software documentation: a systematic literature review and a series of experiments[C]// Proceedings of 2017 IEEE/ACM 14th international conference on mining software repositories (MSR). Buenos Aires, Argentina: IEEE, 2017: 187-197.
[17]	ZHANG Y J, XU Z T, ZHANG T. Fusion of multiple features for Chinese named entity recognition based on CRF model[J]. Lecture Notes in Computer Science, 2008, 4993: 95-106.
[18]	SUN S C, YUN J, LIN H F, et al. Granular transfer learning using type-2 fuzzy HMM for text sequence recognition[J]. Neurocomputing, 2016, 214: 126-133.
[19]	XING Y P, XIAO C B, WU Y F, et al. A convolutional neural network for aspect-level sentiment classification[J]. International Journal of Pattern Recognition and Artificial Intellgence, 2019, 33(14): 1959046.
[20]	WU Y Z, LIU Q, CHEN R R, et al. A group recommendation system of network document resource based on knowledge graph and LSTM in edge computing[J]. Security and Communication Networks, 2020, 2020: 8843803.
[21]	DEVLIN J, CHANG M W, LEE K, et al. BERT: pre-training of deep bidirectional transformers for language understanding[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies, Volume 1. Minneapolis, MN, US: Association for Computational Linguistics,2019: 4171-4186.
[22]	PAVAN KUMAR M R, JAYAGOPAL P. Context-sensitive lexicon for imbalanced text sentiment classification using bidirectional LSTM[J]. Journal of Intelligent Manufacturing, 2023, 34(5): 2123-2132.
[23]	ZHANG M S, YU N, FU G H. A simple and effective neural model for joint word segmentation and POS tagging[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2018, 26(9): 1528-1538.
[24]	REIMERS N, GUREVYCH I. Sentence-BERT: sentence embeddings using siamese BERT-networks[C]// Proceedings of the 2019 Congerence on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Hong Kong, China: Association for Computational Linguistics, 2019:3982-3992.