摘要
随着经济全球化趋势的不断加强，产业结构调整步伐的不断加快，制造企业面临的市场环境发生了巨大变化，尤其表现在客户对产品的个性化需求、对产品交货期的及时性和生命周期的短暂性等要求越来越苛刻。由于生产单元可将生产过程组织为协调高效的物流，因此可显著缩短制造周期、节约生产面积、避免库存积压、提高设备利用率，在离散制造业、冶金、造船等多个行业有着广泛应用。
在实际生产中，由于经常性的临时插单、零部件种类繁多、产品结构复杂、工艺路线和设备配置非常灵活，导致生产单元换线频繁。同时，换线决策具有复杂性、动态随机性和多目标性等特点，采用以经验丰富的工程师人工决策为主的传统换线决策方式已无法满足日渐复杂的生产环境的要求，而换线决策的优劣直接影响产品质量、生产周期和生产单元柔性等重要因素。基于此，如何客观和准确地反映生产换线决策的上述特点，合理进行生产单元换线决策，成为学术界和企业界面临的重大课题。
目前，由于生产单元自身的自治性、演化性、复杂性及人在生产单元中工作方式、任务流程和行为表现的不确定性和动态性，单纯基于数学优化模型的换线决策分析尚存在如下问题：第一、生产单元日益显现出动态化、多目标化等特征，单纯的数学建模很难满足全局最优和高可行性的生产要求；第二、受产品需求的多样化、临时插单、紧急跟单和产品交货期等因素的影响，对制造系统柔性的要求越来越高，生产单元出现复杂巨系统趋势，数学建模很难全面和准确地反映客观的实际生产情况；第三、部分影响人的决策的因素很难进行量化，单纯的数学建模方法无法体现这些因素的作用。针对传统换线决策研究的局限性，以及目前基于神经网络专家系统的不足，如：知识收集手段的欠缺、生产换线专家系统规则抽取手段的缺失以及应用模式的狭窄，本论文提出了基于交互仿真及混合神经网络的生产单元换线决策专家系统研究，全文的研究内容主要包括：
首先，对一般专家系统和基于神经网络的专家系统结构及其原理进行了深入探讨，提出了基于交互仿真及混合神经网络的生产单元换线决策专家系统实现原理和系统实现的关键技术及技术路线，考虑到后期换线领域专家知识的扩充，提出了基于Web Service的系统工作过程和应用模式。
其次，对目前专家系统知识获取的不足，为利用交互仿真对知识获取，提出了制造系统仿真模型和交互仿真模型的构建过程，提出了交互仿真稳定判定算法、专家决策遴选的算法，并通过实例介绍了的交互仿真的实现过程。
再次，具体研究了生产单元换线决策专家系统的实现技术，包括：对生产换线决策影响因素的复杂性和多样性应用主成分分析对生产状态矢量进行降维；运用融合Fisher分类器和回归神经网络的计算技术处理生产控制策略中变量的多模式性；提出了一种基于IER-Trepan算法和预置文本技术构成的推理机规则提取技术解决了传统生产换线专家系统规则抽取手段的不足；针对传统生产换线决策专家系统应用模式的狭窄性，提出了基于Web Serviece应用模式的生产单元换线决策专家系统，用一种以双层COM对象结构封装以及专家系统的程序实现。
最后，以某摩托车发动机生产单元生产换线决策为研究背景，对提出的实现原理和技术进行了可行性验证。结果表明，基于交互仿真技术及混合神经网络的生产单元换线决策专家系统的实现具有较好的可行性和可操作性，为生产单元智能换线决策提供了一种可行的方法。
With the continuous strengthening of the trend of economic globalization, and theaccelerating of the pace of industrial restructuring, the market environment ofmanufacturing enterprise has been facing to changing dramatically, especially in theseaspects: individual needs of customers for products, timeliness of product delivery andtransient lifecycle. The production cell can shorten significantly the manufacturingcycle, save the production area, avoid the backlog of inventory, improve utilization ofequipment because it could coordinate the production process to efficient logistics, so ithas been widely using in discrete manufacturing, metallurgy, ship building industry andso on.
In practice, the production cell changeover frequently, which is caused by regularorder inserting, numerous items of parts, complex produce structure, and flexibleprocess route and device configuration. At the same time, the decision-making ofchangeover is characterized by complex, dynamic randomness and multi-objective, sothe traditional method of changeover which mainly depends on the experiencedengineer could not meet the requirements of increasingly complex productionenvironment. But the merits and defects of a decision of changeover directly impact onproduct quality, production cycle and production cells flexibility. Therefore, how toobjectively and accurately reflect the above-mentioned characteristics of the productionchangeover decision-making and rationally make the decision of the production cellchangeover, has became a major issue for academia and the business community.
At present, due to the production cell autonomy, evolution and complexity, and theuncertain and dynamic work method, task process and behavior of people in theproduction cell, the changeover decision-making method that is simply based onmathematical optimization model exists the following questions. First, the simplemathematical model is difficult to meet the global optimum and high feasibility of theproduction requirement because the production cell has increasingly shown a dynamicand multi-objective characteristics. Second, the production cell has been tending to be acomplex giant system because of the improve of requirement to flexible manufacturingsystem, which is effected by diversification of product demand, the temporary insertingorder, emergency order and product delivery deadline, so mathematical modeling isdifficult to reflect fully and accurately the practical producing situation. Third, it is difficult to quantify the factors effecting person making a decision, and simplemathematical modeling methods can not reflect the role of these factors. In the view ofthe limitations of traditional changeover decision-making method, and the shortage ofcurrent expert system based on neural networks such as the lack of mean of knowledgecollection, the absence of the rule extracting of productionchangeover expert systemand narrow application mode, this paper puts forward the production cell changeoverdecision-making expert system based on interactive simulation and the hybrid neuralnetwork. The content includes the following:
Firstly, on the basis of the research in general expert systems and the expert systemstructure and principle based on neural network, this paper comes up with theimplement principle and the key route and technology of the production cell changeoverdecision-making expert system based on interactive simulation and the hybrid neuralnetwork. In addition, taking into account the knowledge expansion of the changeoverexpert, the paper proposes the working process and application model based on WebService.
Secondly, to solve the problem of the lack of the current expert system knowledgeacquisition, the paper uses interactive simulation to access knowledge acquisition,elaborates the building process of simulation models of manufacturing systems andinteractive simulation model, puts forward the decision algorithm and the expertdecision-making selection algorithm, and introduces the process of interactivesimulation by an actual examples.
Thirdly, the paper provides specifically the implementation technology of theproduction changeover decision-making expert system. For the complexity anddiversity of the influence factor of production changeover decision-making, usesprincipal component analysis to reduce the dimensionality of the production state vector;deals with multi-mode of variable in the production control strategy by using integrationFisher classifier and regression neural network computing technology; puts forward theextractive technique of the rules of inference engine based on the IER-Trepan algorithmand preset text technology, which solves the shortage of the extraction mean oftraditional expert system rule. For the narrow nature of the application mode oftraditional production changeover decision-making expert system, proposes theapplication model of productioncell changeover decision-making expert system basedon Web Service, which is achieved by using the package of two-tier COM objectstructure and expert system program.
Finally, taking the production changeover decision-making of a motorcycle engineproduction cell as a research example, the paper verifies the feasibility of theimplementation principles and techniques. The results show that the production cellchangeover decision-making expert system based on interactive simulation and thehybrid neural network is feasible and operable, and it provides a feasible method for theproduction cell changeover decision-making intelligently.
引文
[1] Schlick C., Reuth R., Luczak H. Comparative Simulation Study of Work Processes inAutonomous Production Cells. Human Factors in Manufacturing,2002,12（1）,31-54.
[2]陈雪芳,张洁.敏捷化智能制造单元及其关键技术[J].组合机床与自动化加工技术,2005,6,13-16.
[3]孟飚,范玉青,林楠.模块化精益生产组织改造评估与决策[J].计算机集成制造系统,2006,12（7）,1141-1145.
[4]汤向东.大规模定制模式下的组织柔性取向[J].企业改革与管理,2004,12,24-25.
[5]董伯麟,王治森,王向阳.人机协同车间数字化制造模式的研究[J].合肥工业大学学报,2008,31（9）,1403-1407.
[6]宋豫川，苏传邴，李丹，陈德敏，刘飞.机械加工车间现场工具配送方法及实现[J].重庆大学学报，2010，33（5）：48-54.
[7] Shahrukh A. Irani. Handbook of Cellular Manufacturing Systems[M]. New York, Wiley,2007.
[8] Salvendy G. Handbook of Industrial Engineering （3rd Edition）[M]. New York, Wiley,2001.
[9]刘飞,但斌,张晓冬等.先进制造与管理[M].北京：中国高等教育出版社,2008.
[10] Shingo S. A revolution in manufacturing, the SMEDsystem[M]. Productivity Press,1985.
[11] Agustin Roberto O, Santiago Fely. Single mi-nute exchange of die[C]. Proceedings of the19967th Annual IEEE/SEMI Advanced Sem-iconductor Manufacturing Conference, ASMC96, Cambridge, MA, USA, Nov12-141996. United States: Institute of Electrical andElec-tronics Engineers,1996,214-217.
[12] http://en.wikipedia.org/wiki/Single_Minute_Exchange_of_Die, This page was last modifiedon4April2012at17:35.
[13] Mclntosh Richard, Owen Geraint, Culley Ste-ve Mileham Tony. Changeover improvement:Reinterpreting Shingo’s “SMED” methodology[J]. IEEE Transactions on EngineeringMang-ement,2007,54（1）:98-111.
[14] James D. Blocher, Suresh Chand. A forward branch-and-search algorithm and forecasthorizon results for the changeover scheduling problem[J]. European Journal of OperationalResearch91,1996,456-470.
[15] C. Gicquel,L. Hege,M. Minoux,W. van Canneyt. A discrete time exact solution approach for acomplex hybrid flow-shop scheduling problem with limited-wait constraints[J]. Computers&Operations Research,2012,39（3）:629-636.
[16] Mehmet Cakmakci.Process improvement: performance analysis of the setup timereduction-SMED in the automobile industry[J]. Int J Adv Manuf Technol,2009,41:168–179.
[17] http://www.wlline.cn/wenda/327.html
[18]夏欣跃.快速换线[J].工业工程与管理,2001,5:14-17
[19]施纪红.SMT快速换线流程的分析与改善[J].应用技术,2011,10:157-161
[20]贾庆东,王剑,祝陶美,上官伟.高速铁路列控系统CTC子系统仿真换线技术研究[J].铁道通信信号,2011,47（9）:10-14
[21]杨燚,李慧.SMED技术在SMT车间的应用[J].科技广场,2011,5:110-112.
[22]王炳刚,饶运清,邵新宇,徐迟.基于多目标遗传算法的混流加工/装配系统排序问题研究[J].中国机械工程,2009,20（12）:1434-1438.
[23]孙延丽.基于精益思想对苏州大众电脑公司的运行机制研究[D].哈尔滨理工大学，2008.
[24]贾瑞玉,程慧霞,曹先彬.混合型神经网络专家系统[J].安徽大学学报（自然科学版），1998，22（2）:60一61
[25] J. Józefowska, A. Zimniak. Optimization tool for short-term production planning andscheduling[J].2006（3）:100-103.
[26] Soyuer, H, Kocamaz, M. Scheduling jobs through multiple parallel channels using an expertsystem[J]. Production Planning and Control,2007,18（1）:35-43.
[27] Ozbayrak, Mustafa, Bell, Robert. A knowledge-based decision support system for themanagement of parts and tools in FMS[J]. Decision Support Systems,2003,35（4）:487-515.
[28] Looney C G.Neural Networks as Expert systems[J]. Expert System Application,1993,6:129一136.
[29] YehY C，KuoY H，HsuD S. Building an Expert for Debugging FEM InPut Data withArtificial Neural Networks[J]. Expert System Application,1992，5:59一70
[30] Davut Hanbay,Ibrahim Turkoglu,Yakup Demir. An expert system based on waveletdecomposition and neural network for modeling Chua’s circuit[J]. Expert SystemApplication,2008,34（4）:2278–2283.
[31] Kozo Osakada,Guobin Yang.Application of Neural Networks to an Expert for ColdForging[J]. International Journal of Machine Tools and Manufacture,1991,31（4）:577-587.
[32] Youngohc Yoon,Tor Guimaraes,George Swales. Integrating artificial neural networks withrule-based expert systems[J]. Decision Support Systems,1994,11（5）:497-507.
[33]陈红伟,汪滨琦.基于神经网络的专家系统可视化研究[J].电脑信息与技术,2001,6,1-11.
[34]郭震.基于神经网络的专家系统实现研究[J].红水河,2003,22（3）:62-65.
[35]徐志强,潘紫微.一种基于神经网络的专家系统构造方法[J].安徽工业大学学报,2001,18（2）:132-134.
[36]李军,阮晓钢.一种基于神经网络的专家系统设计[J].北京工业大学学报,2003,29（2）:171-174.
[37]许占文,窦曦光,葛岳.一种基于神经网络的专家系统的推理机研究[J].沈阳工业大学学报,1999,21（5）:432-434.
[38]丁宁,王龙山,李国发,孟繁禹.磨削质量智能优化控制策略研究[J].中国机械工程,2003,14（2）:1899-1903.
[39]王雪青.国际工程投标报价决策系统研究[D].天津大学,2003.
[40]齐永欣.基于神经网络的专家系统工具[D].河北农业大学,2002.
[41]王兵,莫建军,王玉莹.实时监控与发射决策专家系统推理机设计[J].系统仿真学报,2003,15（6）:820-822.
[42]魏传锋,李运泽,王浚,于涛.航天器热故障诊断专家系统推理机的设计[J].北京航空航天大学学报,2005,31（1）:60-62.
[43]张绍兵,季厌浮,高志军.基于神经网络专家系统的研究与实现[J].计算机工程与科学,2008,30（4）:156-158.
[44]冯玉强,黄梯云,侯变兰.专家系统与神经网络集成系统的设计[J].管理科学学报,1999,2（1）:79-85.
[45]胡月明,薛月菊,李波,谢健文,陈飞香,包世泰.从神经网络中抽取土地评价模糊规则[J].农业工程学报,2005,21（12）:93-97.
[46]齐新战,刘丙杰.神经网络规则抽取评估方法[J].计算机应用,2008,28,91-93.
[47]陈秀琼.一种融合粗集理论和神经网络的分类数据挖掘算法[J].三明学院学报,2005,22（2）:185-189.
[48]张仲明,于明光,东伟.基于聚类的神经网络规则抽取算法[J].吉林大学学报（信息科学版）,2010,28（5）:506-512.
[49]荣莉莉,王众托.基于知识的阶层型神经网络结构及参数的一种确定方法[J].计算机研究与发展,2003,40（2）:169-176.
[50]王文剑.从预测模型中提取规则[J].计算机工程,2000,26（11）:56-57.
[51]王晓晔,张继东,孙济洲.一种高效的分类规则挖掘算法[J].计算机工程与应用,2006,33,174-176.
[52]李仁璞,王正欧.基于粗集理论和神经网络结合的数据挖掘新方法[J].情报学报,2002,21（6）:674-679.
[53]王涛,孟庆春,殷波,李祯,李占斌.神经网络规则提取及其在特征带识别中的应用[J].数据采集与处理,2003,18,12-16.
[54]任永昌,邢涛,于忠党,王晓轩.基于真值维持结构和关系数据库的解释机制研究[J].微电子学与计算机,2009,26（6）:242-245.
[55]李锋刚,基于优化型案例推理的智能决策技术研究[D].合肥工业大学.2007.
[56]曾志高,易胜秋.基于神经网络的数据库安全专家系统的实现[J].通信技术,2009,2（42）:247-249.
[57] Laughery K, Lebiere C. Modeling Human Performance in COMplex Systems[J]. Handbookof Human Factors and Ergonomics, New York, Wiley,2006:967-996.
[58] Baines T, Ladbrook J. Using Empirical Evidence of Variations in Worker Performance toExtend the Capabilities of Discrete Event Simulations[J]. Proceedings of the2003WinterSimulation Conference,2003:1210-216.
[59] D.J. van der Zee. Modeling decision making and control in manufacturing simulation.International Journal of Production Economics [J].2004（2）:104-110.
[60] Noemi M. Paz. The Development of Knowledge for Maintenance Management UsingSimulation[J]. IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS,1994,24（4）:574-593.
[61] ROBINSON S, EDWARDS J. Modelling and Improving Human Decision Making withSimulation[C] WSC Arlingdon,2001: Association for COMputing Machinery,2001:913-920.
[62] ROBINSON S, LEE E, EDWARDS, J. Improving the Use of Visual Interactive Simulationas a Knowledge Elicitation Tool[J]. World Review of Entrepreneurship, Management andSustainable Development,2007,3（3/4）:260-272.
[63] ROBINSON, S., Alifantis, A., Hurrion, R.D., Edwards, J.S., Ladbrook, J. and Waller, T.（2003）. Modelling and Improving Maintenance Decisions: Having Foresight withSimulation and Artificial Intelligence. In SAE2002Transactions Journal of Materials&Manufacturing. SAE International, Warrendale, PA, pp.256-264.
[64] Edwards, J.S., Alifantis, A., Hurrion, R.D., Ladbrook, J., ROBINSON, S. and Waller, T.（2004）. Using a Simulation Model for Knowledge Elicitation and Knowledge Management.Simulation Modelling Practice and Theory,12（7-8）, pp.527-540.
[65] ROBINSON, S., Alifantis, T., Edwards, J.S., Ladbrook, J. and Waller, T.（2005）. KnowledgeBased Improvement: Simulation and Artificial Intelligence for Identifying and ImprovingHuman Decision-Making in an Operations System. Journal of the Operational ResearchSociety,56（8）, pp.912-921.
[66] Stewart Robinson, Ernie P K Lee,John S Edwards. Simulation based knowledge elicitation:Effect of visual representation and model parameters[J]. Expert Systems withApplications,2012,39,8479-8489
[67] Paul Kirkpatrick,Peter C Bell. Simulation modelling: A comparison of visual interactive andtraditional approaches[J]. European Journal of operational Research,1989,39（2）:138-149.
[68]任光,孙巧梅,齐小伟.交互学习神经网络模型及其仿真研究[J].系统仿真学报,2009,21（17）:5314-5317.
[69]周洪玉,周岩,张世雄.临境环境下专家系统推理可视化与人机交互技术[J].哈尔滨理工大学学报,2000,5（2）:1-3.
[70]王君,樊治平.一种基于组件技术的专家系统构建框架[J].东北大学学报（自然科学版）,2003,24（5）:503-506.
[71]李建涛，徐晓刚,郑胜国,刘广.基于灰色关联分析的专家系统知识获取方法[J].四川兵工学报,2010,31（3）:112-114.
[72]杨志凌,董兴辉,李成榕.复杂电力设备多学科协同/虚拟仿真的关键技术[J].现代电力,2009,26（1）:63-67.
[73]黄杰,薛禹胜,文福拴,许剑冰等.电力市场仿真平台的评述[J].电力系统自动化,2011,35（9）:6-13.
[74]张美玉,侯向辉.一种融合专家和数据的综合知识建模框架[J].浙江工业大学学报,2007,35（4）:441-443.
[75]邹光明,孔建益,王兴东,汤勃.基于粗糙集的产品概念设计知识发现[J].机械设计,2011,28（6）:1-4.
[76]陶贵明,张锡恩,曾兴志.电路仿真与故障知识获取研究[J].系统工程与电子技术,2006,28（12）:1945-1947.
[77]陶贵明,张锡恩.基于运动仿真的故障知识获取研究[J].微计算机信息,2006,22（3）:215-217.
[78]陶贵明,马立元.基于运动仿真的导弹发射车故障知识获取研究[J].战术导弹技术,2007,5,89-92.
[79]黄考利,连光耀,杨叶舟,魏忠林.装备故障诊断专家系统知识获取方法[J].计算机工程,2004,30（23）:163-183.
[80]付燕,杨阳.基于粗糙集的瓦斯预测专家系统知识获取[J].煤矿安全,2009,2,22-24.
[81]宣建强,李清东,江加和,任章,陈璐璐.基于测试事件图的故障诊断系统知识获取技术[J].上海交通大学学报,2011,45（2）:179-183.
[82]周宽久,仇鹏,王磊.基于实践论的隐性知识获取模型研究[J].管理学报,2009,6（3）:309-314.
[83]王丽伟,展巍,张伟.基于半自动化知识获取的操作票专家系统的研究与实现[J].信息化纵横,2009,6,15-17.
[84]郭庆琳,祖向荣.基于神经网络与遗传算法的汽轮机组数据挖掘方法[J].电力自动化设备,2008,28（3）:41-45.
[85]张伟,马靓,傅焕章,郭阳.基于运动跟踪和交互仿真的工作设计[J].系统仿真学报,2010,22（4）:1047-1050.
[86]何祖威,唐胜利,杨晨,苟小龙.基于模型和知识库的交互式自学习仿真培训系统[J].系统仿真学报,2001,13（1）:47-77.
[87]黄建新,李群,余文广,王维平.基于线程的进程交互仿真框架研究[J].系统仿真学报,2011,23（4）:652-658.
[88]马富银,吴伟蔚.交互仿真技术[J].机械设计与研究,2010,26（6）:75-77.
[89]张仁忠,韩雷,倪长顺,党爱民.分布交互仿真研究[J].哈尔滨工程大学学报,1999,20（2）:34-40.
[90]赵晨光,张多林,李为民.分布式交互仿真与高层体系结构[J].空军工程大学学报（自然科学版）,2003,4（4）:56-59.
[91]张晓冬,杨育,易树平. Schlick C., Schmidt L.制造系统人因仿真参考模型及若干关键技术研究[J].机械工程学报,2006,42（3）,56-64.
[92]张晓冬,杨育,郭波.以人为中心的生产单元人因失误对比仿真实例研究[J].计算机集成制造系统,2006,12（5）,672-681.
[93]路甬祥.坚持科学发展,推进制造业的历史性跨越[J].机械工程学报,2007,43（11）,1-6.
[94]武波,马玉祥.专家系统[M].北京：北京理工大学出版社，2001.
[95]冯定.神经网络专家系统[M].北京：科学出版社，2006.
[96]姜世平.基于人工神经网络的机械设计过程专家系统知识库的设计与实现[J].中国机械工程,2002,13（12）1034-1037.
[97]蹇崇军，洪欣.基于Web服务的FMS远程故障诊断系统研究[J].机械设计与制造，2011,（12）：258-260.
[98]申利民，吕福军,李峰.面向企业信息系统集成的Web服务推荐模型[J].计算机集成制造系统，2011,17（1）：186-190.
[99] MW Craven, JW Shavlik. Using sampling and queries to extract rules from trained neuralnetworks. Proceedings of the11th International Conference on Machine[C].1994.
[100] MW Craven, JW Shavlik Using neural networks for data mining Future GenerationCOMputer Systems[C].1997.
[101]宇传华. ROC分析方法及其在医学研究中的应用[D].西安：第四军医大学预防医学系,2000.
[102]宋花玲. ROC曲线的评价研究和应用[D].上海：第二军医大学,2006.
[103]刘飞，张晓冬，杨丹.制造系统工程[M].北京：国防工业出版社，2006.
[104]韦卫星.一种基于神经网络的知识获取方法研究与应用[J].计算机工程与应用,2004,5,95-98.
[105]田雨波.混合神经网络技术[M].北京：科学出版社,2009.
[106]肖胜中.小波神经网络理论与应用[M].沈阳：东北大学出版社,2006.
[107]闻新,宋屹,周露.模糊系统和神经网络的融合技术[J].系统工程与电子技术,1999,21（5）55-58.
[108]李敏强,徐博艺,寇纪松.遗传算法与神经网络的结合[J].系统工程理论与实践,1999,2,65-69.
[109]杨虎,刘琼荪,钟波.数理统计[M].北京：高等教育出版社,2004.
[110]胡月.基于主成分分析和独立成分分析的人脸识别研究[D].吉林大学，2010.
[111]邓登.区间型符号数据主成分分析和聚类分析的有效性评价[D].天津大学，2010.
[112]何志国. PAC学习模型研究[J].微机发展.2004,8,45-48.
[113]庄进发,罗键,彭彦卿.基于改进随机森林的故障诊断方法研究[J].计算机集成制造系统.2009,4,67-72.
[114]王丽婷,丁晓青,方驰.基于随机森林的人脸关键点精确定位方法[J].清华大学学报（自然科学版）.2009（4）:89-92.
[115]朱昌平，邓靖璇，顾慧，王智，单鸣雷.基于RFID技术的电池追踪与回收系统设计与实践[J].实验技术与管理，2010，27（12）：61-65.
[116]曲仁秀，王志国.基于RFID技术的离散制造过程其量指标监控研究[J].广西大学学报，2011，36（2）：263-268.
[117]景熠，王旭，李文川.基于RFID的变速器装配线质量追溯系统研究[J].现代科学仪器，2011，（5）：63-67.
[118]郑林江，刘卫宁，孙棣华.制造系统RFID应用可靠性评价及数据处理模型[J].中国机械工程，2010，21（11）：1325-1330.