面向高端装备产品设计的多模式知识服务方法
|
摘要
在高端装备产品设计过程中,有效的知识服务方法能提高设计人员的工作效率,缩短产品的设计周期,提高产品设计质量。为保证将高端装备制造企业知识库中的历史设计方案和经验知识适时、准确地提供给合适的设计人员,针对高端装备制造企业设计人员的三层次知识服务需求,依托Lucene全文检索引擎,提出了基于设计任务知识需求情境的知识服务和基于用户兴趣的知识服务相结合的多模式知识服务方法,并开发了相应的知识服务系统。设计的知识服务案例验证了提出的多模式知识服务方法及开发的知识服务系统在高端装备产品设计过程中的有效性与实用性。
At the design stage of high-end equipment,effective knowledge service could provide designers with reference solutions and historical experiences in a timely and accurate manner,thus greatly improving their work performance,shortening the product design cycle and improving product design quality. To this end,we first analyzed the three-level knowledge service requirements of high-end equipment designers. Then,based on the Lucene fulltext search engine,we established multi-level knowledge service strategies and developed a knowledge service system for the design of high-end equipment. Here multi-level knowledge service strategies include the knowledge service method based on the context of design task,and the multi-mode knowledge service method that combines knowledge service based on user's interests. Corresponding knowledge service system was developed. The experimental results described in this paper demonstrate the practicability and effectiveness of the proposed multi-mode knowledge service method and the high-end equipment design process for developed knowledge service system.
At the design stage of high-end equipment,effective knowledge service could provide designers with reference solutions and historical experiences in a timely and accurate manner,thus greatly improving their work performance,shortening the product design cycle and improving product design quality. To this end,we first analyzed the three-level knowledge service requirements of high-end equipment designers. Then,based on the Lucene fulltext search engine,we established multi-level knowledge service strategies and developed a knowledge service system for the design of high-end equipment. Here multi-level knowledge service strategies include the knowledge service method based on the context of design task,and the multi-mode knowledge service method that combines knowledge service based on user's interests. Corresponding knowledge service system was developed. The experimental results described in this paper demonstrate the practicability and effectiveness of the proposed multi-mode knowledge service method and the high-end equipment design process for developed knowledge service system.
引文
[1]马绪凯,丁晟春.基于本体的产品设计知识检索研究[J].情报理论与实践,2014,37(6):112-116,106.
[2]郝佳.产品设计知识管理与重用关键技术研究[D].北京:北京理工大学,2014.
[3]李录,毛汉颖,吴振勇,等.机械零件设计的知识服务方法及系统实现[J].计算机应用与软件,2016,33(6):68-72.
[4]郭树行,兰雨晴,金茂忠,等.基于情境树相似性的知识检索技术[J].计算机集成制造系统,2008,14(12):2476-2483,2491.
[5]万立,侯添元,熊体凡.面向重用的产品设计过程知识建模与检索[J].计算机工程与设计,2012,33(8):3176-3183.
[6]OTEGI A,ARREGI X,ANSA O,et al.Using knowledgebased relatedness for information retrieval[J].Knowledge and information systems,2015,44(3):689-718.
[7]PARK M,LEE K W,LEE H S,et al.Ontology-based construction knowledge retrieval system[J].KSCE journal of civil engineering,2013,17(7):1654-1663.
[8]ZHANG Chao,ZHOU Guanghui,LU Qi,et al.Graphbased knowledge reuse for supporting knowledge-driven decision-making in new product development[J].International journal of production research,2017,55(23):7187-7203.
[9]CHRIST A,WENZEL V,FAATH A,et al.Integration of feature templates in product structures improves knowledge reuse[C]//Proceedings of the World Congress on Engineering and Computer Science 2013 Vol II.San Francisco,USA,2013:23-25.
[10]WANG Zhansong,TIAN Ling,WU Yuanhao,et al.Personalized knowledge push system based on design intent and user interest[J].Proceedings of the institution of mechanical engineers,part C:journal of mechanical engineering science,2016,230(11):1757-1772.
[11]XU Yuanhao,YIN Guofu,NIE Yong,et al.Research on an active knowledge push service based on collaborative intent capture[J].Journal of network and computer applications,2013,36(6):1418-1430.
[12]徐荣振,高琦,王昊,等.基于序列模式挖掘的变型设计知识推送[J].计算机集成制造系统,2016,22(5):1179-1186.
[13]余绅达,盛步云,付高财,等.基于用户兴趣特征的知识推送[J].计算机系统应用,2016,25(9):254-259.
[14]成龙.Lucene搜索引擎开发进阶实战[M].北京:机械工业出版社,2015.
[15]张超,白权栋,鲁麒,等.面向高端装备的知识分类与元知识建模技术[J].应用科技,2017,44(2):44-50.
[16]BLEI D M,NG A Y,JORDAN M I.Latent dirichlet allocation[J].The Journal of Machine Learning Research,2003,3:993-1022.
[17]Hankcs.LDA4j.[EB/OL].(2018-08-15).https://github.com/hankcs/LDA4j.
[2]郝佳.产品设计知识管理与重用关键技术研究[D].北京:北京理工大学,2014.
[3]李录,毛汉颖,吴振勇,等.机械零件设计的知识服务方法及系统实现[J].计算机应用与软件,2016,33(6):68-72.
[4]郭树行,兰雨晴,金茂忠,等.基于情境树相似性的知识检索技术[J].计算机集成制造系统,2008,14(12):2476-2483,2491.
[5]万立,侯添元,熊体凡.面向重用的产品设计过程知识建模与检索[J].计算机工程与设计,2012,33(8):3176-3183.
[6]OTEGI A,ARREGI X,ANSA O,et al.Using knowledgebased relatedness for information retrieval[J].Knowledge and information systems,2015,44(3):689-718.
[7]PARK M,LEE K W,LEE H S,et al.Ontology-based construction knowledge retrieval system[J].KSCE journal of civil engineering,2013,17(7):1654-1663.
[8]ZHANG Chao,ZHOU Guanghui,LU Qi,et al.Graphbased knowledge reuse for supporting knowledge-driven decision-making in new product development[J].International journal of production research,2017,55(23):7187-7203.
[9]CHRIST A,WENZEL V,FAATH A,et al.Integration of feature templates in product structures improves knowledge reuse[C]//Proceedings of the World Congress on Engineering and Computer Science 2013 Vol II.San Francisco,USA,2013:23-25.
[10]WANG Zhansong,TIAN Ling,WU Yuanhao,et al.Personalized knowledge push system based on design intent and user interest[J].Proceedings of the institution of mechanical engineers,part C:journal of mechanical engineering science,2016,230(11):1757-1772.
[11]XU Yuanhao,YIN Guofu,NIE Yong,et al.Research on an active knowledge push service based on collaborative intent capture[J].Journal of network and computer applications,2013,36(6):1418-1430.
[12]徐荣振,高琦,王昊,等.基于序列模式挖掘的变型设计知识推送[J].计算机集成制造系统,2016,22(5):1179-1186.
[13]余绅达,盛步云,付高财,等.基于用户兴趣特征的知识推送[J].计算机系统应用,2016,25(9):254-259.
[14]成龙.Lucene搜索引擎开发进阶实战[M].北京:机械工业出版社,2015.
[15]张超,白权栋,鲁麒,等.面向高端装备的知识分类与元知识建模技术[J].应用科技,2017,44(2):44-50.
[16]BLEI D M,NG A Y,JORDAN M I.Latent dirichlet allocation[J].The Journal of Machine Learning Research,2003,3:993-1022.
[17]Hankcs.LDA4j.[EB/OL].(2018-08-15).https://github.com/hankcs/LDA4j.