摘要
电火花线切割加工作为电火花加工的一种类型，在模具、成形电极、难加工材料和精密复杂零件的加工中具有重要的地位。随着技术的发展，对电火花线切割加工的表面质量和加工精度提出了更高的要求。在用线切割加工变厚度工件时，断丝和效率低下是两个普遍存在的问题。当加工工件的厚度由厚变薄时，由于放电能量集中，易于断丝；反之，则效率低下。本文针对线切割加工变厚度工件时的断丝和效率低下问题，开展了离线与在线厚度识别、3D工件模型高度信息提取、加工过程模型建立、以及模型预测控制等方面的研究，以期提高加工的稳定性和加工效率。
本文首先建立了基于Linux的线切割加工机床全软数控系统，采用RTAI实时内核满足了系统对实时性的要求。该数控系统包括人机界面、代码解释器、任务管理器、运动控制、机床I/O控制五个模块。运动控制模块产生的控制信号通过多功能I/O卡来驱动机床工作运动。在分析线切割放电电压和电流波形的基础上，根据法拉第电磁感应定律开发了放电频率检测电路。以上即为研究变厚度线切割加工的软硬件平台。
为了避免加工变厚度工件时易于断丝和加工效率低下的问题，首先需要获得工件在加工路径上的厚度，然后才能根据厚度选取合适的加工参数。本文针对电火花线切割加工时有无工件的3D模型提出了采用“黑盒法”和“白盒法”分别处理。当缺少工件三维模型时，利用“黑盒法”建立工件厚度的辨识模型。当已知工件三维模型数据时，则利用“白盒法”从工件三维模型中直接提取加工路径上的工件厚度信息，经过数控系统处理，用于在线控制加工过程。
鉴于支持向量机在非线性系统建模方面的优异特性，本文利用支持向量机，根据线切割加工过程中采集的放电频率和进给速度以及控制输入量伺服电压和脉冲间隔，建立工件厚度辨识模型，即所谓的“黑盒法”。输出量是待辨识的工件厚度，而模型输入量为放电加工参数(伺服电压和脉冲间隔)以及放电频率和机床的进给速度。在建立了工件厚度辨识模型之后，在加工中应用该模型在线实时地辨识工件厚度。以工件厚度为依据选取合适的加工参数控制加工过程。
当加工具有三维模型数据的工件时，从工件三维模型中直接提取加工路径上的工件厚度，并应用到数控系统中在线控制加工过程，即所谓的“白盒法”。随着工件厚度范围的不断扩大，加工过程中所采集的加工信息也不断增加。这些数据不但可以在线指导加工过程，而且还可以用于在线修正工件厚度辨识模型，目的是使模型包含的加工状况更丰富、模型更准确。本文利用最小二乘支持向量机的在线算法实时修正工件厚度辨识模型。当新的数据产生后，在线算法根据投影法稀疏性处理判断新的数据是否需要参与模型计算。如果新的数据需要参与模型计算，则删除支持向量中对模型影响最小的向量。该算法确保参与建模的数据量不会超过预先设定的数量，这不仅减少了计算量和存储量，而且解决了最小二乘支持向量机固有的稀疏性问题。
无论是通过“黑盒法”还是“白盒法”获得的工件厚度，最终目的是根据工件厚度，选取合适的加工参数，控制加工过程，达到避免断丝和提高加工效率的目的。为了控制加工过程，基于标准支持向量机建立了加工过程模型，设计了适合变厚度线切割加工的模型预测控制器，当工件厚度变化时，由检测到的工件厚度实时计算出放电频率和加工速度参考值，模型预测控制器根据参考值实时调整输入量伺服电压和脉冲间隔，控制加工过程在不断丝的前提下保持高的加工效率。
As one of the non-traditional machining approaches, wire electrical dischargemachining(WEDM) plays an important role in the manufacture of molds, shaped elec-trodes, hard-to-cut materials and precise parts with intricate shapes. With the devel-opment of technologies, the requirements for quality and precision of WEDM arebecoming more demanding. When machining workpieces with a variable height, wirebreakage and low machining efficiency are the two major issues. When the workpieceheight along a machining path changes from high to low, the discharge energy willbe concentrated on a short range of the wire. As a result, wire breakage is likely tooccur. On the contrary, when the workpiece height varies from low to high, the densi-ty of discharge along the wire becomes low, thus resulting in a low material removalrate(MRR).
In order to avoid wire breakage and improve machining efficiency when machin-ing workpieces with variable heights by WEDM, this dissertation investigates severaltopics which are crucial for variable height machining by WEDM, those include of-fline and online workpiece height estimation, extraction of workpiece heights from3D models, modelling of WEDM processes, as well as model predictive control forWEDM processes.
In this dissertation, a CNC (computer numerical control) system for a WEDMwas developed based on Linux operating system. The RTAI kernel is attached to theLinux to meet the real time requirement for CNC systems. The CNC system consists offive modules, which include GUI module, code interpreter module, task managementmodule, motion control module and I/O control module. The control signals generatedby the motion control module drive the machine through a multi-function I/O card.After analyzing the discharge current and voltage wave forms collected during the machining，on the basis of Farad’s induction theory, a discharge frequency monitorsystem was developed to detect the discharge frequency.
For variable height WEDM, the workpiece height must be provided to CNC sys-tem, so that appropriate machining parameters can then be determined according toit. In this dissertation, depending on the availability of a3D model, two cases areprocessed separately. If there is no3D model of a workpiece, a black box methodis adopted to build up a workpiece height estimation model. When the3D model isavailable, a white box method is applied to extract the workpiece height informationalone the machining path from the3D model. The workpiece height data is finally fedinto the CNC system.
Due to its good performance in modelling nonlinear systems, support vector ma-chine (SVM) is used to build up a workpiece height estimation model with the ma-chining data collected. This is the so-called black box method. The input and outputof the model are chosen from those machining parameters which have no noticeableimpacts on the surface quality. The output variable is the workpiece height that is tobe estimated, and the input variables are a set of machining parameters, discharge fre-quency and feed rate. The estimated workpiece height will be then used as a referencefor appropriately determining a set of machining parameters.
When the3D model of a workpiece is available, the workpiece height extractedfrom the3D model can be directly applied to the CNC system. This is the so-calledwhite box method. As the range of workpiece heights becomes larger, the machiningdata collected is increasing. Not only can this data be used to control the machiningprocess in progress, but also can be used to update the workpiece height estimationmodel online. By learning the new dynamics which have not been excited before, theheight estimation model can be refined, thus improving its prediction accuracy. Theupdate of the workpiece height estimation model was achieved by using the on lineleast square support vector machine (LS-SVM). When a new data pair is available, ajudgment must be made whether the new data pair should be selected as a new basicvector (BV) based on the projecting method. If the new data pair is selected as a newBV, the old BV which has the least significant impact on the model should be removedfrom the BV set. By keeping the number of BVs within a predefined value, this online algorithm can not only reduce the computational load and the requirement for memoryspace, but also overcome the non-sparsity of LS-SVM.
No matter how the workpiece height is obtained either by the black box methodor by the white box method, the workpiece height will be used to determine an appro-priate set of machining parameters so as to avoid wire breakage and improve MRR.A model predictive controller is designed in such a way that the reference dischargefrequency will be followed to maintain a stable machining. The optimal control inputsare then generated by solving an online optimization problem.
引文
[1]刘晋春,白基成,郭永丰.特种加工(第五版)[M].北京:机械工业出版社,2008.
[2]韩福柱.电火花线切割加工技术的发展动态[C]//2005年中国机械工程学会年会第11届全国特种加工学术会议专辑.北京:机械工业出版社,2005.
[3] Ho K H, Newman S T, Rahimifard S, et al. State of the art in wire electricaldischarge machining(WEDM)[J]. International Journal of Machine Tools andManufacture,2004,44(12):1247-1259.
[4]刘晓,康小明,赵万生.带叶冠整体式涡轮盘的多轴联动数控电火花加工[J].航空制造技术,2009,2:100-102.
[5]刘晓,康小明,赵万生.闭式整体涡轮叶盘多轴联动电火花加工电极运动路径规划[J].电加工与模具,2012(1):11-14.
[6]刘晓,梁为,康小明,等.闭式整体泵叶轮电火花加工电极运动路径规划[J].电加工与模具,2012,5:008.
[7]叶军,陈德忠.第十二届中国国际机床展览会特种加工机床评述(下)[J].世界制造技术与装备市场.2012(1):69-73.
[8] CIMT2007特种加工机床评述专家组.第十届中国国际机床展览会特种加工机床评述[J].电加工与模具.2007(3):1-10.
[9]李明辉.电火花线切割技术的研究现状及发展趋势[J].模具技术,2002,6(4).
[10]朱宁,叶军,韩福柱,等.电火花线切割加工技术及其发展动向[J].电加工与模具,2010,1.
[11] Obara H. Wire-cut electric discharge machine: U.S. Patent4,510,367[P].1985-4-9.
[12] Ishibashi Y, Komori A. Wire electric discharge machine having alterable dis-charge period: U.S. Patent5,362,936[P].1994-11-8.
[13] Rajurkar K P, Wang W M, Lindsay R P. On-line monitor and control for wirebreakage in WEDM[J]. CIRP Annals-Manufacturing Technology,1991,40(1):219-222.
[14] Rajurkar K P, Wang W M, McGeough J A. WEDM identification and adaptivecontrol for variable-height components[J]. CIRP Annals-Manufacturing Tech-nology,1994,43(1):199-202.
[15] Rajurkar K P, Wang W M, Zhao W S. WEDM-Adaptive Control with a Mul-tiple Input Model for Indentification of Workpiece Height[J]. CIRP Annals-Manufacturing Technology,1997,46(1):147-150.
[16] Y.S. Liao, T.J. Chuang, Y.P. Yu. On-line Estimation of Workpiece Height inWEDM[C]//Proceedings of the16th International Symposium on Electroma-chining. Shanghai, China: SJTU Press,2010,255-260.
[17] Liao Y S, Yan M T, Chang C C. A neural network approach for the on-lineestimation of workpiece height in WEDM[J]. Journal of materials processingtechnology,2002,121(2):252-258.
[18] Yan M T, Liao Y S, Chang C C. On-line estimation of workpiece height by usingneural networks and hierarchical adaptive control of WEDM[J]. The Interna-tional Journal of Advanced Manufacturing Technology,2001,18(12):884-891.
[19]宗福来.电火花线切割变厚度加工自适应控制技术的研究[D].哈尔滨工业大学,2006.
[20]黄河,白基成,宗福来,等.电火花线切割变厚度加工自适应控制技术的研究[C]//第13届全国特种加工学术会议论文集.2009.
[21]李其政.类神经网络应用于线切割放电加工厚度变化工件之研究[D].国立台湾大学,2004.
[22]林奕圻.模糊控制应用于线切割放电加工厚度变化工件之研究[D].国立台湾大学,2004.
[23]霍孟友,张建华,艾兴.电火花放电加工间隙状态检测方法综述[J].电加工与模具,2003,3:17-20.
[24]迟关心,狄士春,况火根.电火花加工间隙平均电压检测及其电路仿真研究[J].现代制造工程,2006,7(3).
[25]伍俊,李明辉.电火花线切割加工中放电间隙状态的检测[J].上海交通大学学报,2001,35(7):986-988.
[26]伍俊,李明辉.电火花线切割加工中放电间隙大小在线识别[J].中国机械工程,2002,13(7):574-576.
[27] Watanabe H, Sato T, Suzuki I, et al. WEDM monitoring with a statisticalpulse-classification method[J]. CIRP Annals-Manufacturing Technology,1990,39(1):175-178.
[28] Rajurkar K P, Wang W M. Thermal modeling and on-line monitoring of wire-EDM[J]. Journal of Materials Processing Technology,1993,38(1):417-430.
[29] Rajurkar K P, Wang W M. Improvement of EDM performance with advancedmonitoring and control systems[J]. Journal of manufacturing science and engi-neering,1997,119(4):770-775.
[30] Yan M T, Chien H T. Monitoring and control of the micro wire-EDM process[J].International Journal of Machine Tools and Manufacture,2007,47(1):148-157.
[31] Liao Y S, Chu Y Y, Yan M T. Study of wire breaking process and monitoringof WEDM[J]. International Journal of Machine Tools and Manufacture,1997,37(4):555-567.
[32] Liao Y S, Chang T Y, Chuang T J. An on-line monitoring system for a microelectrical discharge machining(micro-EDM) process[J]. Journal of Microme-chanics and Microengineering,2008,18(3):035009.
[33] Cabanes I, Portillo E, Marcos M, et al. On-line prevention of wire breakage inwire electro-discharge machining[J]. Robotics and Computer-Integrated Manu-facturing,2008,24(2):287-298.
[34] Cabanes I, Portillo E, Marcos M, et al. An industrial application for on-linedetection of instability and wire breakage in wire EDM[J]. Journal of MaterialsProcessing Technology,2008,195(1):101-109.
[35] Portillo Perez E, Marcos M, Cabanes I, et al. Real-Time Monitoring and Di-agnosis Platform for a Machining Process[C]//World Congress.2008,17(1):10674-10679.
[36] Portillo Perez E, Marcos M, Cabanes I, et al. ANN for Interpolating InstabilityTrends in WEDM[C]//World Congress.2008,17(1):2230-2235.
[37] Yeo S H, Aligiri E, Tan P C, et al. A new pulse discriminating system for micro-EDM[J]. Materials and Manufacturing Processes,2009,24(12):1297-1305.
[38] Spedding T A, Wang Z Q. Study on modeling of wire EDM process[J]. Journalof Materials Processing Technology,1997,69(1):18-28.
[39] Hong-bin Z, Zhi-xin J. Research in Reliability Modeling of WEDM Basedon Neural Network[C]//Measuring Technology and Mechatronics Automation,2009. ICMTMA’09. International Conference on. IEEE,2009,3:277-280.
[40] Tsai K M, Wang P J. Predictions on surface finish in electrical discharge ma-chining based upon neural network models[J]. International Journal of MachineTools and Manufacture,2001,41(10):1385-1403.
[41] Wang K, Gelgele H L, Wang Y, et al. A hybrid intelligent method for modellingthe EDM process[J]. International Journal of Machine Tools and Manufacture,2003,43(10):995-999.
[42] Guiqin L, Fanhui K, Wenle L, et al. The Neural-fuzzy Modeling and GeneticOptimization in WEDM[C]//Control and Automation,2007. ICCA2007. IEEEInternational Conference on. IEEE,2007:1440-1443.
[43] Mandal D, Pal S K, Saha P. Modeling of electrical discharge machining processusing back propagation neural network and multi-objective optimization usingnon-dominating sorting genetic algorithm-II[J]. Journal of Materials ProcessingTechnology,2007,186(1):154-162.
[44]张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,26(1):32-42.
[45]吴巧敏.基于支持向量机的文本分类算法研究[D].长沙:湖南大学,2007.
[46]杨大鹏,赵京东,崔平远,等.基于支持向量机的人手姿态肌电模式识别与力检测[J].高技术通讯,2010(006):618-622.
[47]杜树新,吴铁军.模式识别中的支持向量机方法[J].浙江大学学报(工学版),2003.
[48]张敏贵.基于小波和支持向量机的人脸识别方法研究[D].西安:西北工业大学,2003.
[49]钟伟民,皮道映,孙优贤.基于支持向量机的直接逆模型辨识[J].控制理论与应用,2005,22(2):307-310.
[50]尉询楷,李应红,王剑影,等.基于支持向量机的航空发动机辨识模型[J].航空动力学报,2004,19(5):684-688.
[51]钟伟民.支持向量机在先进控制中的应用研究[D].浙江大学,2006.
[52]何熠.基于支持向量机的非线性系统辨识建模与控制[D].天津大学,2007.
[53]李凌均,张周锁,何正嘉.支持向量机在机械故障诊断中的应用研究[J].计算机工程与应用,2002,38(19):19-21.
[54]包哲静.支持向量机在智能建模和模型预测控制中的应用[D].杭州:浙江大学,2007.
[55]阎威武,朱宏栋,邵惠鹤.基于最小二乘支持向量机的软测量建模[J].系统仿真学报,2003,15(10):1494-1496.
[56]王华忠,张雪申,俞金寿.基于支持向量机的故障诊断方法[J].华东理工大学学报,2004,30(2):179-182.
[57]王定成,方廷健,高理富,等.支持向量机回归在线建模及应用[J].控制与决策,2003,18(1):89-91.
[58]王定成,方廷健,唐毅,等.支持向量机回归理论与控制的综述[J].模式识别与人工智能,2003,16(2):192-197.
[59] Yan M T, Liao Y S. A self-learning fuzzy controller for wire rupture preventionin WEDM[J]. The International Journal of Advanced Manufacturing Technolo-gy,1996,11(4):267-275.
[60] Lee W M, Liao Y S. Self-tuning fuzzy control with a grey prediction for wirerupture prevention in WEDM[J]. The International Journal of Advanced Man-ufacturing Technology,2003,22(7-8):481-490.
[61]夏田,文怀兴,魏康民.基于PC的开放式数控系统体系结构的分析[J].航空制造技术,2002,12:62-63.
[62]王彬,杨建芳,郭妍,等.基于RT―Linux的开放式五轴联动电火花加工数控系统及其在带冠涡轮盘加工中的应用[J].电加工与模具,2012(5):16-20.
[63]郑君民,赵万生,李志勇,等.基于RTLinux平台的开放式电火花数控系统[J].计算机集成制造系统,2005,8.
[64]赵万生,李论,李志勇.六轴联动电火花加工数控系统的研究[J].计算机集成制造系统-CIMS,2004.
[65]郭锐,赵万生,李论,等.基于Linux的微细电火花加工数控系统的研究[J].计算机集成制造系统-CIMS,2007,13(2).
[66]吴鹏,夏田.基于RT-Linux的AD喷涂机开放式数控系统的研究[J].组合机床与自动化加工技术,2007,2:010.
[67]郭锐.基于Linux的微细电火花加工数控系统及其相关关键技术的研究[D].哈尔滨工业大学,2007.
[68]范剑,白建华,潘建峰.基于Windows的全软件数控系统实时控制的研究[J].机械制造,2004,42(10):48-50.
[69]王芳,王琨琦,梅雪松.基于Windows全软件数控系统实时性的研究[J].西安工业大学学报,2009,29(3).
[70]王普,张蕾,郝立伟.基于RTX的全软件数控系统的研究[J].燕山大学学报,2007,31(6):513-516.
[71]陈光胜,陶涛,梅雪松. Windows平台下的软件化数控系统研究[J].制造技术与机床,2010(001):74-78.
[72]李论,赵万生.基于实时Linux平台的数控系统研究[J].航空精密制造技术,2004,40(1):27-3O.
[73]王彬,杨建芳,郭妍,等.基于RT―Linux的开放式五轴联动电火花加工数控系统及其在带冠涡轮盘加工中的应用[J].电加工与模具,2012(5):16-20.
[74]李志勇,赵万生,吕善进,等.基于Linux平台的电火花数控系统[J].机械工程学报,2003,39(11).
[75]李志勇,赵万生.基于Linux内核的数控系统关键技术研究[J].计算机集成制造系统,2004,10(5):569-573.
[76]李志勇.基于Linux多轴联动电火花加工数控系统及相关技术研究[D].哈尔滨工业大学,2004.
[77]郑君民,赵万生,李志勇,等.基于RTLinux平台的开放式电火花数控系统[J].计算机集成制造系统,2005,8.
[78]郑君民,王振龙,赵万生.基于实时Linux的模块化EDM数控系统设计[J].航空精密制造技术,2007,43(2).
[79]周坚,余承业,张祖尧.低速走丝线切割机上下异型面加工[J].航空制造技术,1990,6:002.
[80]周坚,余承业,张祖尧,等.线切割上下异型面加工工件描述新方法[J].南京航空学院学报,1991,3(3).
[81]周坚,余承业,张祖尧,等.线切割锥度切割中轨迹投影规律及其应用[J].电加工与模具,1992,4:003.
[82]孔振宇,马骏,迟关心,等.线切割数控系统ISO代码解释器的研究[J].电加工,1997(1):21-23.
[83]曾国,郭烈恩,胡云堂.利用LEX与YACC实现数控线切割的加工程序编译器[J].机电工程,2004,21(1):58-61.
[84]徐笠云,顾琳,曹琨,等.基于Lex和Yacc的多数控代码解释器研究与应用[J].电加工与模具,2009,3:012.
[85]郑君民,王振龙,赵万生.基于Lex&Yacc的电火花加工译码系统[J].电加工与模具,2005,6:007.
[86]陈成细,奚学程,徐辉,等.基于RS274的电火花线切割加工数控系统解释器的设计与实现[J].电加工与模具,2011,2:002.
[87]罗凌,曹琨,陈成细,等.基于RS274/NGC的电火花线切割加工数控代码解释器的开发[J].电加工与模具,2010(003):6-10.
[88] Liu Y, Guo X, Li W, et al. An intelligent NC program processor for CNC systemof machine tool[J]. Robotics and Computer-Integrated Manufacturing,2007,23(2):160-169.
[89]甘星明.基于RS274/NGC的数控系统刀具补偿的设计与实现[D].沈阳:中国科学院研究生院,2006.
[90]牛现云.五坐标并联机床数控加工程序解释器的设计与实现[D].中国科学院研究生院(沈阳计算技术研究所),2006.
[91] Kramer T R, Proctor F M, Messina E. The NIST RS274/NGC Interpreter-Version3[J]. ISD of NIST, Gaithersburg, MD,2000.
[92] Xu Y, Guo X H, Liu C. Study on Wire Breakage in WEDM by3D Technolo-gy[J]. Applied Mechanics and Materials,2011,44:1442-1448.
[93] Platt J C.12Fast Training of Support Vector Machines using Sequential Mini-mal Optimization[J].1999.
[94] Suykens J A K, Vandewalle J. Least squares support vector machine classifier-s[J]. Neural processing letters,1999,9(3):293-300.
[95] Johan A.K. Suykens, Tony Van Gestel, Jos De Brabanter, Bart De Moor, et al.Least Squares Support Vector Machines[M].2002.
[96] Suykens J A K. Nonlinear modelling and support vector ma-chines[C]//Instrumentation and Measurement Technology Conference,2001. IMTC2001. Proceedings of the18th IEEE. IEEE,2001,1:287-294.
[97] Suykens J A K, Vandewalle J. Recurrent least squares support vector ma-chines[J]. Circuits and Systems I: Fundamental Theory and Applications, IEEETransactions on,2000,47(7):1109-1114.
[98] Suykens J A K, Vandewalle J, De Moor B. Optimal control by least squaressupport vector machines[J]. Neural Networks,2001,14(1):23-35.
[99] Suykens J A K, Lukas L, Vandewalle J. Sparse approximation using leastsquares support vector machines[C]//Circuits and Systems,2000. Proceedings.ISCAS2000Geneva. The2000IEEE International Symposium on. IEEE,2000,2:757-760.
[100] Jiao L, Bo L, Wang L. Fast sparse approximation for least squares support vec-tor machine[J]. Neural Networks, IEEE Transactions on,2007,18(3):685-697.
[101]张浩然,汪晓东.回归最小二乘支持向量机的增量和在线式学习算法[J].计算机学报,2006,29(3):400-406.
[102]赵永平,孙健国.基于滚动窗法最小二乘支持向量机的稳健预测模型[J].模式识别与人工智能,2008,21(1):1-5.
[103]薄翠梅,张湜,李俊.工业共沸精馏塔软测量建模方法的研究与应用[J].南京工业大学学报(自然科学版),2006,3:009.
[104]赵永平,孙健国.基于线性无关度的稀疏最小二乘支持向量回归机[J].中国图象图形学报,2009,14(6):1136-1140.
[105]赵永平,孙健国.一种快速稀疏最小二乘支持向量回归机[J].控制与决策,2008,23(12):1347-1352.
[106]邢永忠,吴晓蓓,徐志良.基于矢量基学习的自适应迭代最小二乘支持向量机回归算法[J].南京理工大学学报(自然科学版),2011,35(3).
[107] Csato′, L., Opper M. Sparse representation for Gaussian process models[J]. Ad-vances in neural information processing systems,2001:444-450.
[108] Csato′, L., Opper M. Sparse on-line Gaussian processes[J]. Neural Computation,2002,14(3):641-668.
[109] Csato′, L. Gaussian processes: iterative sparse approximations[D]. Aston Uni-versity,2002.
[110] LI L J, SU H Y, Chu J. Generalized predictive control with online least squaressupport vector machines[J]. Acta Automatica Sinica,2007,33(11):1182-1188.
[111] http://www.opencascade.org/.
[112] Liu X, Zhao W, Li C, et al. Research on the information extraction technology ofcutting tool based on open CASCADE[C]//Systems and Informatics (ICSAI),2012International Conference on. IEEE,2012:996-999.
[113] Liu J, Han L. The3D Model Conversion Tool for OGRE System[M]//AsiaSim2012. Springer Berlin Heidelberg,2012:288-295.
[114] Zhuo Y, Peng J, Wu Y J. Design and Simulation of3D Layout for MID Basedon Open CASCADE[J]. Advanced Materials Research,2012,479:1978-1981.
[115] Wu Y J, Zhuo Y, Peng J, et al. Kinematic Analysis and Simulation of MIDLaser Direct Structuring Equipment[J]. Advanced Materials Research,2012,590:236-241.
[116] Li L, Su H, Chu J. Sparse representation based on projection method in on-line least squares support vector machines[J]. Journal of Control Theory andApplications,2009,7(2):163-168.
[117]李丽娟,苏宏业,褚建.在线最小二乘支持向量机及其在C8芳烃异构化建模中的应用(英文)[J]. Chinese Journal of Chemical Engineering,2009,3:014.
[118] Xi X C, Poo A N, Chou S K. Support vector regression model predictive controlon a HVAC plant[J]. Control engineering practice,2007,15(8):897-908.
[119]卢居亮.基于LS-SVM在线模型的非线性预测控制研究[D].南京理工大学,2009.
[120] Mjalli F S. Neural network model-based predictive control of liquid–liquidextraction contactors[J]. Chemical engineering science,2005,60(1):239-253.
[121] Yu D L, Gomm J B. Implementation of neural network predictive control to amultivariable chemical reactor[J]. Control Engineering Practice,2003,11(11):1315-1323.
[122] Ou J, Rhinehart R R. Grouped neural network model-predictive control[J]. Con-trol engineering practice,2003,11(7):723-732.
[123] Wang L X, Wan F. Structured neural networks for constrained model predictivecontrol[J]. Automatica,2001,37(8):1235-1243.
[124] Liu G P, Daley S. Output-model-based predictive control of unstable com-bustion systems using neural networks[J]. Control Engineering Practice,1999,7(5):591-600.
[125] Karer G, MusˇicˇG,Sˇkrjanc I, et al. Hybrid fuzzy model-based predictive controlof temperature in a batch reactor[J]. Computers&Chemical Engineering,2007,31(12):1552-1564.
[126] Su B, Chen Z, Yuan Z. Constrained predictive control based on TS fuzzy modelfor nonlinear systems[J]. Journal of systems engineering and electronics,2007,18(1):95-100.
[127] Mahfouf M, Kandiah S, Linkens D A. Fuzzy model-based predictive controlusing an ARX structure with feedforward[J]. Fuzzy sets and systems,2002,125(1):39-59.
[128] Li N, Li S Y, Xi Y G. Multi-model predictive control based on the Takag-i–Sugeno fuzzy models: a case study[J]. Information Sciences,2004,165(3):247-263.
[129] Bao Z, Pi D, Sun Y. Nonlinear model predictive control based on support vectormachine with multi-kernel[J]. Chinese Journal of Chemical Engineering,2007,15(5):691-697.
[130] Ong C J, Sui D, Gilbert E G. Enlarging the terminal region of nonlinear mod-el predictive control using the support vector machine method[J]. Automatica,2006,42(6):1011-1016.
[131] Kocijan J, Murray-Smith R, Rasmussen C E, et al. Gaussian process modelbased predictive control[C]//American Control Conference,2004. Proceedingsof the2004. IEEE,2004,3:2214-2219.
[132] Likar B, Kocijan J. Predictive control of a gas–liquid separation plant based ona Gaussian process model[J]. Computers&chemical engineering,2007,31(3):142-152.
[133] Xi X C, Poo A N, Chou S K. Support vector regression model predictive controlon a HVAC plant[J]. Control engineering practice,2007,15(8):897-908.
[134] Kawathekar R, Riggs J B. Nonlinear model predictive control of a reactive dis-tillation column[J]. Control Engineering Practice,2007,15(2):231-239.
[135] Nagy Z K, Mahn B, Franke R, et al. Evaluation study of an efficient outputfeedback nonlinear model predictive control for temperature tracking in an in-dustrial batch reactor[J]. Control Engineering Practice,2007,15(7):839-850.
[136] Duarte M, Suarez A, Bassi D. Control of grinding plants using predictive mul-tivariable neural control[J]. Powder technology,2001,115(2):193-206.
[137] Potocˇnik P, Grabec I. Nonlinear model predictive control of a cutting process[J].Neurocomputing,2002,43(1):107-126.
[138] Scho¨lkopf B, Smola A J. Learning with kernels: support vector machines, reg-ularization, optimization and beyond[M]. the MIT Press,2002.
[139] Camacho E F, Bordons C, Camacho E F, et al. Model predictive control[M].London: Springer,2004.
[140]周永华.预测控制及其与智能控制结合的发展前景[J].昆明工学院学报,1995,20(6):58-63.
[141]丁宝苍.预测控制的理论与方法[M].机械工业出版社,2008.
[142]徐保国,胡立萍.基于支持向量机的非线性系统模型预测控制[J].计算机测量与控制,2005,13(8).
[143]张浩然,韩正之,李昌刚.基于支持向量机的非线性模型预测控制[J].系统工程与电子技术,2003,25(3):330-334.
[144] Luus R. Iterative dynamic programming[M]. Chapman and Hall/CRC,2010.
[145] Luus R. Optimization of fed batch fermentors by iterative dynamic program-ming[J]. Biotechnology and Bioengineering,1993,41(5):599-602.