基于智能的冲压工艺设计专家系统推理机的研究
|
摘要
冲压件工艺设计是一项复杂的大系统任务,随着国民经济的发展,生产部门对冲压件工艺设计的效率提出了更高的要求。目前,想从根本上提高冲压件工艺设计的自动化程度,提高设计效率和设计质量,人工智能(AI)技术的应用将发挥举足轻重的作用。专家系统(ES)是一个智能计算机程序,它利用知识和经验,通过推理来解决某领域中只有人类专家才能解决的难题。它的研究和应用已经成为全世界人工智能研究的热点和焦点。专家系统运用专家的知识与经验进行推理、判断和决策,是解决冲压工艺设计效率问题的有效方法。推理机是专家系统的思维部件,是专家系统的重要组成部分之一。因此,冲压工艺设计专家系统推理机的研究,对构建冲压工艺设计系统具有十分重要的理论意义和应用价值。
冲压工艺设计专家系统利用人工智能技术为冲压专业设计人员提供智能化、建设性的设计帮助。区别于传统的程序,通过模拟专家的思维过程,利用知识来推理出结果,其结构可表达为“专家系统=知识+推理”,知识库是基础,推理机是它的核心。本文着重论述了推理机的设计和实现过程。
本文建立了冲压工艺设计专家系统推理机的结构模型;结合有关参数、机理公式等知识特点,基于产生式规则的知识表示形式,给出了匹配度的定义及计算方法,以及基于匹配度的冲突消解策略;利用可信度的概念,采用了用于系统推理的基于可信度的不确定性推理方法;微软.NET平台给专家系统开发提供了一个非常好的基础系统平台,充分利用面向对象技术,设计了正向推理的启发式专家系统的推理机。
系统很好地实现了知识处理与用户交互的分离和推理机与知识库的分离。基于匹配度的冲突消解策略,可以很好地解决冲压工艺设计规则的选择问题;基于可信度的不确定性推理方法能够提高推理结论的可信度。在此基础上设计的专家系统推理机能够快速准确地获取较优的推理结果。最后,利用该系统对一个具体零件冲压工艺进行了设计,得出了较为满意的结果。
Stamping process design is a complex systematic task. With the development of national economic, the manufacturers bring forward high requirement of the efficiency of stamping process design. Now, the radical improvement of the automation of stamping process design system, and the improvement of the efficiency and quality of the design, will depend much on the application of artificial intelligence(AI) techniques. An expert system(ES) is a computer program that is designed to emulate the logic and reasoning processes that an expert would use to solve a problem in his/her field of expertise, using artificial intelligence technology. The research and application of expert system have become the researching focus of the artificial intelligence of the world. Expert system, which using the experts’knowledge and experience to reason and make decision, is one effective way to solve the efficiency of stamping process planning. Reasoning machine is the thinking part of expert system and it is the one important part of expert system. Therefore, the research of expert system reasoning machine for stamping process planning has important theoretical significance and actual value to building the system for stamping process planning.
Expert system for stamping process planning applies artificial intelligence technology to aid professional pressing designers with intelligent and constructive help on the design. Distinct from the traditional process, it has simulated the expert thinking process and used such knowledge to get the results, therefore its structure can be concluded as“expert system = knowledge + consequence”with knowledge database as foundation and consequence machine as its core. This essay focuses on the design and realization of this reasoning machine.
In this paper, the structure model of expert system reasoning machine for stamping process planning was built. The definition of matching degree and its calculation was given based on the knowledge representation form of production rule, which combined with the knowledge characteristics, such as the related parameters and mechanism formulas, etc. Then, the conflict reduction strategy based on matching degree was presented. The uncertainty reasoning method based on the believable degree was proposed using the concept of believable degree. Microsoft .NET platform provides a very good basic system platform for expert system development. The direct heuristic reasoning machine of expert system was developed by using the .NET technology.
The system can separate business transaction from client interaction and reasoning machine form knowledge base well. The conflict reduction strategy based on matching degree can solve the problem of choosing stamping process planning rules well. The uncertainty reasoning method based on believable degree can improve believable degree of the conclusion. The designed reasoning machine of stamping process planning expert system can obtain better inference results more fast and accurate. At the end of this paper, an example of stamping process design for a material part is demonstrated the reliability and practicability of the methods.
冲压工艺设计专家系统利用人工智能技术为冲压专业设计人员提供智能化、建设性的设计帮助。区别于传统的程序,通过模拟专家的思维过程,利用知识来推理出结果,其结构可表达为“专家系统=知识+推理”,知识库是基础,推理机是它的核心。本文着重论述了推理机的设计和实现过程。
本文建立了冲压工艺设计专家系统推理机的结构模型;结合有关参数、机理公式等知识特点,基于产生式规则的知识表示形式,给出了匹配度的定义及计算方法,以及基于匹配度的冲突消解策略;利用可信度的概念,采用了用于系统推理的基于可信度的不确定性推理方法;微软.NET平台给专家系统开发提供了一个非常好的基础系统平台,充分利用面向对象技术,设计了正向推理的启发式专家系统的推理机。
系统很好地实现了知识处理与用户交互的分离和推理机与知识库的分离。基于匹配度的冲突消解策略,可以很好地解决冲压工艺设计规则的选择问题;基于可信度的不确定性推理方法能够提高推理结论的可信度。在此基础上设计的专家系统推理机能够快速准确地获取较优的推理结果。最后,利用该系统对一个具体零件冲压工艺进行了设计,得出了较为满意的结果。
Stamping process design is a complex systematic task. With the development of national economic, the manufacturers bring forward high requirement of the efficiency of stamping process design. Now, the radical improvement of the automation of stamping process design system, and the improvement of the efficiency and quality of the design, will depend much on the application of artificial intelligence(AI) techniques. An expert system(ES) is a computer program that is designed to emulate the logic and reasoning processes that an expert would use to solve a problem in his/her field of expertise, using artificial intelligence technology. The research and application of expert system have become the researching focus of the artificial intelligence of the world. Expert system, which using the experts’knowledge and experience to reason and make decision, is one effective way to solve the efficiency of stamping process planning. Reasoning machine is the thinking part of expert system and it is the one important part of expert system. Therefore, the research of expert system reasoning machine for stamping process planning has important theoretical significance and actual value to building the system for stamping process planning.
Expert system for stamping process planning applies artificial intelligence technology to aid professional pressing designers with intelligent and constructive help on the design. Distinct from the traditional process, it has simulated the expert thinking process and used such knowledge to get the results, therefore its structure can be concluded as“expert system = knowledge + consequence”with knowledge database as foundation and consequence machine as its core. This essay focuses on the design and realization of this reasoning machine.
In this paper, the structure model of expert system reasoning machine for stamping process planning was built. The definition of matching degree and its calculation was given based on the knowledge representation form of production rule, which combined with the knowledge characteristics, such as the related parameters and mechanism formulas, etc. Then, the conflict reduction strategy based on matching degree was presented. The uncertainty reasoning method based on the believable degree was proposed using the concept of believable degree. Microsoft .NET platform provides a very good basic system platform for expert system development. The direct heuristic reasoning machine of expert system was developed by using the .NET technology.
The system can separate business transaction from client interaction and reasoning machine form knowledge base well. The conflict reduction strategy based on matching degree can solve the problem of choosing stamping process planning rules well. The uncertainty reasoning method based on believable degree can improve believable degree of the conclusion. The designed reasoning machine of stamping process planning expert system can obtain better inference results more fast and accurate. At the end of this paper, an example of stamping process design for a material part is demonstrated the reliability and practicability of the methods.
引文
[1]包友霞,车身覆盖件冲压成形中拉深盘的优化设计方法研究[D],上海交通大学博士学位论文,2000.07
[2] Cheok B T,Foong K Y,Nee A Y C,et al,Some aspects of a knowledge-based approach for automating progressive metal stamping die design[J] ,Computer in Industry,1994,24(1):81-96
[3] Sitaraman Suresh K,Kinzel Gary L,Altan T,Knowledge-based system for process-sequence design in axisymmetric sheet-metal forming[J],Journal of Materials Processing Technology,1991,25(3):247-271
[4]肖祥芷,冲压工艺与模具计算机辅助设计[M],北京:国防工业出版社,1996
[5] Greska W,Franke V,Geiger M,Classification problems in manufacturing of sheet metal part[J],Computer in Industry,1997,33(1):17-30
[6] Lin Zone-Ching,Chang Da-Yuan,Application of a neuwork machine learning model in the slection system of sheet metal bending tooling[J],Artificial Intelligence in Engineering,1999(10):21-37
[7]郝泳涛,基于特征编码和人工神经网络的模式化智能工艺设计系统关键技术研究[D],上海交通大学博士学位论文,1999
[8]姚华,基于特征的拉深工艺智能设计系统研究,上海交通大学博士学位论文[D],1999
[9]杨兴,朱大奇,桑庆兵,专家系统研究现状与展望[J],计算机应用研究,2007,24(5):4~9
[10] Kolodner J L,An introduction to case-based reasoning[M],Morgan Kaufmann Publishers,San Francisco,California,1993
[11] Stuan Pugh Total Design Integrated Methods for successful Product Engieering[D],University of Strathclyde,1990
[12]石红,液压系统故障诊断专家系统的研究与设计[D],哈尔滨工程大学硕士论文,2000.12
[13]敖志刚,人工智能与专家系统导论[M],合肥:中国科学技术大学出版社,2002
[14]王万森,人工智能原理及其应用[M],北京:电子工业出版社,2000
[15]黄可鸣,专家系统导论[M],南京:东南大学出版社,1998
[16]丁洪,基于知识的复杂系统诊断推理与系统[D],华中理工大学博士学位论文,1990
[17]钟联炯,何博雄,范跃华等,故障诊断专家系统中测试的表示[J],光电与控制,1991,2:45~48
[18]王永庆,人工智能原理与方法[M],西安:西安交通大学出版社,2005
[19]吴慧中等,机械设计专家系统研究与实践[M],北京:中国铁道出版社,1994
[20]周济等著,机械设计专家系统概论[M],武汉:华中理工大学出版社,1989
[21]陈世福等,知识工程语言与应用[M],南京:南京大学出版社,1989
[22]何新贵编,知识处理与专家系统[M],北京:国防工业出版社,1990
[23]管纪文等,知识工程原理[M],吉林:吉林大学出版社,1988
[24]史忠植编,知识工程[M],北京:清华大学出版社,1988
[25]鲁东明,何志均,知识库组织和管理的概念模型研究[C],第三届中国人工智能联合学术会议论文集,清华大学出版社,1992
[26]徐宝祥,叶培华,知识表示方法的研究[J],情报科学,2007,25(5):690-694
[27] C.W.Chan,N.Cerconc,Knowledge Engineering for a Process Design[J],Inter. J. of Expert System,1996,9(4):43-56
[28]杨炳儒,知识工程与知识发现[M],北京:冶金出版社,2000.
[29]程慧霞等,用C++构造专家系统[M],北京:电子工业出版社,1996.
[30]蔡自兴,徐光佑,人工智能及其应用[M],北京:清华大学出版社,2003
[31]邵军力,人工智能基础[M],北京:电子工业出版社,2003
[32] Peddemors A J H,Hertzberger L O,High performance distributed database system for enhanced services[J],Future Generation Computer Systems, 1999,15(3):407-415
[33] Rafea A,Hassen H,Hazman M,Automatic knowledge acquisition tool for irrigation and fertilization expert systems[J],Expert Systems with Applications,2003,24(1):49-57
[34] Dasarathy B V,Proceedings of SPIE:Data Mining and Knowledge Discovery:Theory,Tools,and Technology[C],Proceedings of SPIE-The International Society for Optical Engineering,2003,5098
[35]徐毅,范会敏,基于产生式规则的煤性—炉型耦合专家系统的设计与研究[J],热力发电,2007(6):64-66
[36] Rob Callan,Aritificial intelligence[M],New York:Prentice Hall,2005
[37]李曙歌,基于面向对象知识表示的专家系统的实现[D],山东大学硕士学位论文,2006
[38]邓超,郭茂祖,王亚东,一种基于产生式规则的不确定推理模板模型的研究[J],计算机工程与应用,2003(30):57-61
[39]刘有才,刘增良编著,模糊专家系统原理与设计[M],北京航空航天大学出版社,1995
[40]曹承志,王楠,智能技术[M],北京:清华大学出版社出版,2004
[41]刘普寅,模糊理论及其应用[M],长沙:国防科技大学出版社,1998
[42]曹元大,徐漫江,面向对象知识表示在专家系统开发工具中的应用[J],北京理工大学学报,2000,20(12):687-692
[43]何新贵,模糊知识处理的理论与技术[M],长沙:国防工业出版社,1994
[44] Gruer P,Hilaire v,Koukam A,et al,A formal framework for multi-agent systems analysis and design[J],Expert Systems with Applications, 2002, 23(4):349-355
[45] King R L,Russ S H,Lambert A B,et al,Artificial immune system model for intelligent agents[J],Future Generation Computer Systems, 2001, 17(4): 335-343
[46] Walczak S,Knowledge acquisition and knowledge representation with class:The object-oriented paradigm[J],Expert Systems with Applications, 1998,15(3-4):235-244
[47] Wu X.D,Explicit schematic information in knowledge representation and acquisition[J],Expert Systems Applications,1998,15(3-4):215-221
[48] Park J H,Seong P H,An integrated knowledge base development tool for knowledge acquisition and verication for NPP dynamic alarm processing systems[J],Annals of Nuclear Energy,2002,29
[49] Kamrany A,Rong W,A genetic algorithm methodology for data mining and intelligent knowledge acquisition[J],Computers & Industrial Engineering, 2001,40(4):361-377
[50] Perrin P,Petry F E,Extraction and representation of contextual information for knowledge discovery in texts[J],Information Sciences,2003,151:125- 152
[51] Piessens F,Jacobs B,Joosen W,Software security:experiments on the .NET common language run-time and the Shared Source Common Language Infrastructure[J],Software IEE Proceedings,2003,150(5):303-307
[52] David M Peterson,Microsoft's .NET framework:New platform for software development[J],Business Communications Review,2002,32(11):57-61
[53]艾迪明,.NET框架体系结构[J],计算机上程与应用,2003,39(2):174-176
[54] Kevin Hoffman,Jeff Gabriel,.NET Framework高级编程[M],汪钟鸣,战晓苏,北京:清华大学出版社,2002
[55]秦鑫,朱绍文,.NET框架数据访问结构[J],计算机系统应用,2002, (12):25-27
[2] Cheok B T,Foong K Y,Nee A Y C,et al,Some aspects of a knowledge-based approach for automating progressive metal stamping die design[J] ,Computer in Industry,1994,24(1):81-96
[3] Sitaraman Suresh K,Kinzel Gary L,Altan T,Knowledge-based system for process-sequence design in axisymmetric sheet-metal forming[J],Journal of Materials Processing Technology,1991,25(3):247-271
[4]肖祥芷,冲压工艺与模具计算机辅助设计[M],北京:国防工业出版社,1996
[5] Greska W,Franke V,Geiger M,Classification problems in manufacturing of sheet metal part[J],Computer in Industry,1997,33(1):17-30
[6] Lin Zone-Ching,Chang Da-Yuan,Application of a neuwork machine learning model in the slection system of sheet metal bending tooling[J],Artificial Intelligence in Engineering,1999(10):21-37
[7]郝泳涛,基于特征编码和人工神经网络的模式化智能工艺设计系统关键技术研究[D],上海交通大学博士学位论文,1999
[8]姚华,基于特征的拉深工艺智能设计系统研究,上海交通大学博士学位论文[D],1999
[9]杨兴,朱大奇,桑庆兵,专家系统研究现状与展望[J],计算机应用研究,2007,24(5):4~9
[10] Kolodner J L,An introduction to case-based reasoning[M],Morgan Kaufmann Publishers,San Francisco,California,1993
[11] Stuan Pugh Total Design Integrated Methods for successful Product Engieering[D],University of Strathclyde,1990
[12]石红,液压系统故障诊断专家系统的研究与设计[D],哈尔滨工程大学硕士论文,2000.12
[13]敖志刚,人工智能与专家系统导论[M],合肥:中国科学技术大学出版社,2002
[14]王万森,人工智能原理及其应用[M],北京:电子工业出版社,2000
[15]黄可鸣,专家系统导论[M],南京:东南大学出版社,1998
[16]丁洪,基于知识的复杂系统诊断推理与系统[D],华中理工大学博士学位论文,1990
[17]钟联炯,何博雄,范跃华等,故障诊断专家系统中测试的表示[J],光电与控制,1991,2:45~48
[18]王永庆,人工智能原理与方法[M],西安:西安交通大学出版社,2005
[19]吴慧中等,机械设计专家系统研究与实践[M],北京:中国铁道出版社,1994
[20]周济等著,机械设计专家系统概论[M],武汉:华中理工大学出版社,1989
[21]陈世福等,知识工程语言与应用[M],南京:南京大学出版社,1989
[22]何新贵编,知识处理与专家系统[M],北京:国防工业出版社,1990
[23]管纪文等,知识工程原理[M],吉林:吉林大学出版社,1988
[24]史忠植编,知识工程[M],北京:清华大学出版社,1988
[25]鲁东明,何志均,知识库组织和管理的概念模型研究[C],第三届中国人工智能联合学术会议论文集,清华大学出版社,1992
[26]徐宝祥,叶培华,知识表示方法的研究[J],情报科学,2007,25(5):690-694
[27] C.W.Chan,N.Cerconc,Knowledge Engineering for a Process Design[J],Inter. J. of Expert System,1996,9(4):43-56
[28]杨炳儒,知识工程与知识发现[M],北京:冶金出版社,2000.
[29]程慧霞等,用C++构造专家系统[M],北京:电子工业出版社,1996.
[30]蔡自兴,徐光佑,人工智能及其应用[M],北京:清华大学出版社,2003
[31]邵军力,人工智能基础[M],北京:电子工业出版社,2003
[32] Peddemors A J H,Hertzberger L O,High performance distributed database system for enhanced services[J],Future Generation Computer Systems, 1999,15(3):407-415
[33] Rafea A,Hassen H,Hazman M,Automatic knowledge acquisition tool for irrigation and fertilization expert systems[J],Expert Systems with Applications,2003,24(1):49-57
[34] Dasarathy B V,Proceedings of SPIE:Data Mining and Knowledge Discovery:Theory,Tools,and Technology[C],Proceedings of SPIE-The International Society for Optical Engineering,2003,5098
[35]徐毅,范会敏,基于产生式规则的煤性—炉型耦合专家系统的设计与研究[J],热力发电,2007(6):64-66
[36] Rob Callan,Aritificial intelligence[M],New York:Prentice Hall,2005
[37]李曙歌,基于面向对象知识表示的专家系统的实现[D],山东大学硕士学位论文,2006
[38]邓超,郭茂祖,王亚东,一种基于产生式规则的不确定推理模板模型的研究[J],计算机工程与应用,2003(30):57-61
[39]刘有才,刘增良编著,模糊专家系统原理与设计[M],北京航空航天大学出版社,1995
[40]曹承志,王楠,智能技术[M],北京:清华大学出版社出版,2004
[41]刘普寅,模糊理论及其应用[M],长沙:国防科技大学出版社,1998
[42]曹元大,徐漫江,面向对象知识表示在专家系统开发工具中的应用[J],北京理工大学学报,2000,20(12):687-692
[43]何新贵,模糊知识处理的理论与技术[M],长沙:国防工业出版社,1994
[44] Gruer P,Hilaire v,Koukam A,et al,A formal framework for multi-agent systems analysis and design[J],Expert Systems with Applications, 2002, 23(4):349-355
[45] King R L,Russ S H,Lambert A B,et al,Artificial immune system model for intelligent agents[J],Future Generation Computer Systems, 2001, 17(4): 335-343
[46] Walczak S,Knowledge acquisition and knowledge representation with class:The object-oriented paradigm[J],Expert Systems with Applications, 1998,15(3-4):235-244
[47] Wu X.D,Explicit schematic information in knowledge representation and acquisition[J],Expert Systems Applications,1998,15(3-4):215-221
[48] Park J H,Seong P H,An integrated knowledge base development tool for knowledge acquisition and verication for NPP dynamic alarm processing systems[J],Annals of Nuclear Energy,2002,29
[49] Kamrany A,Rong W,A genetic algorithm methodology for data mining and intelligent knowledge acquisition[J],Computers & Industrial Engineering, 2001,40(4):361-377
[50] Perrin P,Petry F E,Extraction and representation of contextual information for knowledge discovery in texts[J],Information Sciences,2003,151:125- 152
[51] Piessens F,Jacobs B,Joosen W,Software security:experiments on the .NET common language run-time and the Shared Source Common Language Infrastructure[J],Software IEE Proceedings,2003,150(5):303-307
[52] David M Peterson,Microsoft's .NET framework:New platform for software development[J],Business Communications Review,2002,32(11):57-61
[53]艾迪明,.NET框架体系结构[J],计算机上程与应用,2003,39(2):174-176
[54] Kevin Hoffman,Jeff Gabriel,.NET Framework高级编程[M],汪钟鸣,战晓苏,北京:清华大学出版社,2002
[55]秦鑫,朱绍文,.NET框架数据访问结构[J],计算机系统应用,2002, (12):25-27