复合材料液—固挤压模糊神经网络建模及优化研究
|
摘要
复合材料管、棒材液-固挤压成形工艺是近几年发展起来的一种金属成形新工艺，具有工序少、成本低、制件性能好等特点，应用前景广阔，但该工艺是一多变量非线性时变系统，很难建立精确的数学模型，过程参数难于控制，限制了该工艺的实际应用。
本文通过大量的试验，对液-固挤压成形工艺中的影响因素进行了研究，初步掌握了该成形工艺的一般规律；在分析实验数据的基础上确定了实验样本集，并初步确定了该工艺系统的模糊推理规则；利用模糊神经网络技术对液-固挤压工艺系统进行建模，实现了对样本数据的良好拟合；补偿模糊神经网络在训练过程中能够根据样本动态调整网络参数，提取较为准确的模糊推理规则；通过利用该工艺系统模型进行参数预测，得到了与实验数据吻合较好的预测结果。
遗传算法在优化过程中不需要求导或其它辅助知识，只需要影响搜索方向的目标函数和相应的适应度函数，对难于建立数学模型的非线形系统有较强的优化能力。本文根据液-固挤压成形工艺的特点，利用遗传算法建立了工艺参数优化模型、进行了工艺参数优化，结果比较理想。
通过对复合材料液-固挤压成形工艺系统建模的研究，探讨了模糊神经网络参数的物理意义及其对网络学习速度的影响，确定了可加快网络学习速度的参数赋值方法；结合液-固挤压工艺特点探讨了利用遗传算法进行参数优化过程中一些问题的处理方法及遗传操作算子对优化过程的影响，确定了参数选取的合理范围。
本文利用Microsoft VC 6.0、Matlab以及Microsoft Access等软件，自行编制了一套基于模糊神经网络与遗传算法的集工艺建模、参数预测、参数优化、图形输出及数据库访问为一体的液-固挤压成形工艺应用软件，实现了该软件的可视化及良好的交互性。通过该软件可实现工艺参数的预测及优化，为液-固挤压工艺过程参数的正确选取及实际应用奠定了基础。
Liquid-solid extrusion of composite material is a new kind of metal forming process, which has been developed in recent years with a promising practical application prospect for its simple working procedure, low cost and good workpiece performance. But it is difficult to set up an accurate mathematical model because the process is a multivariable nonlinear time varying system. So this process can't be put into practical uses for the difficulties in process parameters control.
In this paper, some key factors in the process of composite liquid-solid extrusion had been researched through a large amount of experiments and the common rules of composite liquid-solid extrusion had been obtained. The sample data was built and the common fuzzy rule was set up through analyzing the experimental data collected during the experiments. The fuzzy neural network model of composite liquid-solid extrusion had been set up, the sample data had been fitted and the accurate fuzzy rule had been concluded through training the fuzzy neural model with the sample data. The process parameters had been predicted by use of the fuzzy neural network model constructed, and the predicted results coincide well with the experimental data.
Optimization can be conducted by use of genetic algorithms. This optimization method needn't the differential coefficient and other assistant knowledge, but of the object function and the adaptive evaluation function. It's powerful to optimize the nonlinear system difficult to set up the mathematical model. In this paper, the composite liquid-solid extrusion optimization model is built by means of genetic algorithm. The process parameters had been optimized and the ideal optimization results are obtained.
The physical meaning of the fuzzy neural network parameters and their influence on the model performance are discussed through the research of composite liquid-solid extrusion model, and the reasonable method of evaluating the network parameters is confirmed which can quicken the training speed. Some problems and the influence of the evolution operator on the optimization course are discussed, arid the reasonable range of the evolution parameter is concluded.
In this paper, a set of composites liquid-solid extrusion application software is complied by using of the Visual C++, Matlab and Access software. The visualization and interaction are realized through this software, what's more, the functions of fuzzy neural model setting up, parameter prediction, parameter optimization, figure
exporting and database accessing are included. The composite liquid-solid extrusion process parameters can be predicted and optimized by use of the software. The author's work lay a foundation for the reasonable choose of the process parameters and practical application of the composite liquid-solid extrusion.
本文通过大量的试验，对液-固挤压成形工艺中的影响因素进行了研究，初步掌握了该成形工艺的一般规律；在分析实验数据的基础上确定了实验样本集，并初步确定了该工艺系统的模糊推理规则；利用模糊神经网络技术对液-固挤压工艺系统进行建模，实现了对样本数据的良好拟合；补偿模糊神经网络在训练过程中能够根据样本动态调整网络参数，提取较为准确的模糊推理规则；通过利用该工艺系统模型进行参数预测，得到了与实验数据吻合较好的预测结果。
遗传算法在优化过程中不需要求导或其它辅助知识，只需要影响搜索方向的目标函数和相应的适应度函数，对难于建立数学模型的非线形系统有较强的优化能力。本文根据液-固挤压成形工艺的特点，利用遗传算法建立了工艺参数优化模型、进行了工艺参数优化，结果比较理想。
通过对复合材料液-固挤压成形工艺系统建模的研究，探讨了模糊神经网络参数的物理意义及其对网络学习速度的影响，确定了可加快网络学习速度的参数赋值方法；结合液-固挤压工艺特点探讨了利用遗传算法进行参数优化过程中一些问题的处理方法及遗传操作算子对优化过程的影响，确定了参数选取的合理范围。
本文利用Microsoft VC 6.0、Matlab以及Microsoft Access等软件，自行编制了一套基于模糊神经网络与遗传算法的集工艺建模、参数预测、参数优化、图形输出及数据库访问为一体的液-固挤压成形工艺应用软件，实现了该软件的可视化及良好的交互性。通过该软件可实现工艺参数的预测及优化，为液-固挤压工艺过程参数的正确选取及实际应用奠定了基础。
Liquid-solid extrusion of composite material is a new kind of metal forming process, which has been developed in recent years with a promising practical application prospect for its simple working procedure, low cost and good workpiece performance. But it is difficult to set up an accurate mathematical model because the process is a multivariable nonlinear time varying system. So this process can't be put into practical uses for the difficulties in process parameters control.
In this paper, some key factors in the process of composite liquid-solid extrusion had been researched through a large amount of experiments and the common rules of composite liquid-solid extrusion had been obtained. The sample data was built and the common fuzzy rule was set up through analyzing the experimental data collected during the experiments. The fuzzy neural network model of composite liquid-solid extrusion had been set up, the sample data had been fitted and the accurate fuzzy rule had been concluded through training the fuzzy neural model with the sample data. The process parameters had been predicted by use of the fuzzy neural network model constructed, and the predicted results coincide well with the experimental data.
Optimization can be conducted by use of genetic algorithms. This optimization method needn't the differential coefficient and other assistant knowledge, but of the object function and the adaptive evaluation function. It's powerful to optimize the nonlinear system difficult to set up the mathematical model. In this paper, the composite liquid-solid extrusion optimization model is built by means of genetic algorithm. The process parameters had been optimized and the ideal optimization results are obtained.
The physical meaning of the fuzzy neural network parameters and their influence on the model performance are discussed through the research of composite liquid-solid extrusion model, and the reasonable method of evaluating the network parameters is confirmed which can quicken the training speed. Some problems and the influence of the evolution operator on the optimization course are discussed, arid the reasonable range of the evolution parameter is concluded.
In this paper, a set of composites liquid-solid extrusion application software is complied by using of the Visual C++, Matlab and Access software. The visualization and interaction are realized through this software, what's more, the functions of fuzzy neural model setting up, parameter prediction, parameter optimization, figure
exporting and database accessing are included. The composite liquid-solid extrusion process parameters can be predicted and optimized by use of the software. The author's work lay a foundation for the reasonable choose of the process parameters and practical application of the composite liquid-solid extrusion.
引文
[1] 齐乐华，侯俊杰，孙乐民等．高效成形复合材料管、棒材新工艺研究．西北工业大学学报．1999，17(4)：629
[2] Hu Lianxi, Luo Shoujing. Development of the technology of extrusion directly following infiltration for the manufacturing of metal-matrix composite. J. of materials processing technology. 1995(49): 287
[3] 齐乐华，崔培玲，史忠科，李贺军．液-固挤压，Al_2O_(3sf)LY12复合材料管材成形过程的数值模拟．机械工程学报．2002，38(2)：53-56
[4] Qi Lehua, Li Hejun, Shi Hou Junjie, etc al. Research on the Neural Networks Used for Shaping Tubes by the Liquid Extrusion Process. Journal of Material Engineering and Performance. 2000, 9: 28-32
[5] Qi Lehua. The Influence of liquid Extrusion on the Microstructure and Properties of an A1-Si Alloy. Materials and Manufacturing Process. 1998, 13(3) 405-413
[6] 罗守靖，田文彤，李金平．21世纪最具发展前景的近静成形技术．第一届半固态金属加工技术研讨会．2000．4：1-5
[7] 齐乐华，李贺军，罗守靖，霍文灿．液态挤压下ZA27合金的性能与组织特征．有色金属学报．1997，49(1)：90-94
[8] 齐乐华，李贺军，罗守靖．锌合金的液态模锻强化．材料研究学报．1997，11(2)：178-180．
[9] 齐乐华，崔培玲，史忠科，李贺军．液-固挤压复合材料管材成形过程中温度场的有限元分析．金属学报．2002，38(5)：549-554
[10] 李贺军，齐乐华，胡连喜等。液态挤压的金属流动特征研究．锻压技术．1993(增刊)11-13
[11] 罗守靖，李贺军，胡连喜．液态挤压下金属成形的力学研究．锻压技术．1993 NO．2，16-19
[12] 罗守靖，李贺军，杨琦雯．液态挤压下Al Zn合金的强韧化．材料科学进展．1993，7(2)110
[14] 齐乐华，李贺军，罗守靖．液态模锻和液态挤压强韧化的机理研究．兵器材料科学与工程．1996，19(4)：56-60
[15] Hejun Li, Lehua Qi, Shoujing Luo. Research into the properties and microstructure of ZA13 Alloy tubes formed by liquid extrusion. Journal of materials processing Tecnology. 55(1995): 19-23
[16] Qi Lehua, Li Hejun, Shi Zhongke and Cui Peiling. Research on the forming of tubes and Bars of Alumina/LY12 Alloy Composites by Liquid extrusion Process. Proceeding of the third China International diecasting Congress. Northeastern University Press. 2002: 161-168
[17] Luo Shoujing, Zu Lijun. Semi-solid extrusion of TiC_p/2024 Al composites prepared by contact reaction method. Trans. Nonferrous Met. Soc. China. 2000 10(3):305-308
[18] 胡连喜．液态浸渗侯直接挤压铝基复合材料的组织特征．特种铸造及有色金属．1996(1)：1-3
[19] 胡连喜，罗守靖，霍文灿．液态浸渗后直接挤压过程的载荷位移特征．轻合金加工技术．1998，26(10)：43-47
[20] 袁增任等 人工神经网络原理及其应用 清华大学出版社 1999，10
[21] 罗莉，胡守仁．有限精度的BP神经网络高速算法．国防科技大学学报．1998，20(1)
[22] 高大启．有教师的线性基本函数前向三层网络结构研究．电路与系统学报．1997 2(3)：31-37．
[23] 王铁，陈进．BP算法中学习速率及形状因子对科学进度的综合影响．上海交通大学学报．1997，31(3)：109-112
[24] Vittoris Maniezzo. Genetic evolution of the topology and weight distribution of neural netwoks. IEEE Trans on neural networks. 1994, 5(1)
[25] 周尚明，魏华梁．复杂过程建模的模糊集和神经网络方法．系统仿真学报．1998，2：20-26
[26] 吴晓峰，李恩伟．神经网络在加热炉自控系统中的应用．人工智能及应用 1998，4：32-34
[27] 杨自厚，许宝栋．神经网络在高炉模式识别中的应用．冶金自动化．1992，16(5)：3-6．
[28] 马建苍，罗磊，吴启彬．小波—人工神经网络信息融合故障诊断方法．中国机械工程．1997，8(2)：38-40
[29] 董选明，裘丽华．液压泵的人工神经网络在线故障诊断系统．中国机械工程．1997，8(2)：44-46
[30] A. Xiaoguang, H. Ning etc. al. Application of synergetic intelligence to the scheduling in the finishing train of the hot strip mills. Journal of material process technology. 1996(60): 405-408
[31] 高行山，叶天麒，吕胜利．神经网络计算机及其在薄板弯曲分析中的应用．机械科学与技术．May 1995，18(3)：417-419
[32] 侯俊杰．西北工业大学硕士论文．1999
[33] J. Wang, X Wu, P. F. Thmson, A. Flitman. A neural network approach to investigating the geometrical influence on wrinkling in sheet metal forming. Journal of materials processing technology. 105(2000) 215-220.
[34] Geigerl. L, Cser. J, G. Lenond. Neural networks in metal forming. Neural networks in metal forming.
[35] K. Osakada, G. B. Yang. Neural networks for process planning of cold
forming. Annuals of the CIRP. 1991 Vol, 40 No.1 243-246.
[36] Y. S. Liaoa, M. T. Yanb, C. C. Chang. Journal of Materials Processing Technology 121(2002) 252-258
[37] 章卫国，杨向忠．模糊控制理论与应用．西北工业大学出版社．1999
[38] 罗蓬等．基于模糊控制论的压铸浇注系统工艺参数设计新方法．铸造技术．1998，5：24-25
[39] 王守琰，孔德英．基于模式识别的金属材料海水腐蚀形貌诊断系统．金属学报．May 2001，37(5)：517-521
[40] 刘文剑，柏合民，蔡鹤皋．基于模糊推理的工件定位面选择．哈尔滨工业大学学报 2000．12，2(6)：87-90
[41] 姜道连，张亮等 自学习模糊控制系统在微波治疗设备中的应用．自动化与仪表．2000，16(5)：37-38
[42] 周志坚，毛守源等．模糊神经网络交叉技术．电路与系统学报．1998，9．3(3)：81-85
[43] 谭群华，李伟等．基于行为建模的机器人混合模糊—神经控制方法．清华大学学报(自然科学版)．1997，37(2)：38-41
[44] 李君，张建武等．自学习模糊神经网络AMT车辆巡航控制．机械工程学报．2001，37(1)：63-68
[45] 李映，白本督，焦李成．一种基于非线性复杂系统辨识的自适应模糊控制神经网络．电子信息学报．2001，23(4)．
[46] 汪锐，罗亚军等．基于模糊神经网络的压边力优化控制专家系统 上海交通大学学报 Mar．2001，35(3)：411-415
[47] Hisao Ishibuchi, Kitaek Kwon, Hideo Tandka. A learning algorithn of fuzzy neural networks with triangular fuzzy weight. Fuzzy sets and system. 71(1995) 277-293
[48] Wei Li, Chenyu Ma, F. M. Wahl. A neuro-fuzzy system architecture for behavior-based control of a mobile robot in unknown environments Fuzzy Sets and system 87(1997) 133-140
[49] R. -J, Kuo. A robotic die polishing system through fuzzy neural networks Computer in industry 32(1997)273-280
[50] Jelena Godjevac, Nigel Steele. Neurocomputing 28(1999) 127} 143
[51] J. Kim, N. Kasabov. Neural Networks 12(1999) 1301-1319
[52] 孙增析．智能控制理论与技术 清华大学出版社．1997年4月
[53] 王小平，曹立明．遗传算法理论、应用与软件实现 西安交通大学出版社．2002年1月第一版
[54] Miller John A, Potter Watter D An evalution of a improment for genetic algorithms. IEEE Trans on syst Man and Cybernetics 1993 23
(5) 1340-1350
[55] Fogel David B. Evolutionary computation -Toward a new philosophy of machine intelligence. IEEE press 1995
[56] 章珂，刘贵忠．交叉位置非等概率选取的遗传操作．信息与控制．1997，26(1)：53-56．
[57] 汪朝军，刘艳明等．变搜索域遗传算法及其在铣削加工参数优化中的应用．中国机械工程．1998，9(4)：33-34
[58] 冯春，黄洪钟，谢泗维．机械工程全局优化算法．机械科学与技术．1997，16(1)：21-24
[59] 吴立成，陆震，于守谦，郑红．柔性杆子杆模型的遗传算法优化求解．北京航空航天大学学报．2001，2．27(1)：97-100
[60] Rafik A. Alive, Bijan Fazlollahi, Rustam M, Vahidov. Genetic algorithm-based learning of fuzzy neural networks Part 1: feed-forward fuzzy neural networks
[61] 郭礼辉，孔繁森，宗长富．遗传算法在汽车操纵稳定性评价及结构参数优化中的应用．机械工程学报．2000，10．36(10)：34-36
[62] Yunqing Zhang, Member, IEEE, and Abraham Kandel, Fellow, IEEE. Compensatory Neurofuzzy System with Fast Learning Algorithms IEEE TRANSACTION ON NEURAL NETWORKS. JAN. 1998, 9(1)
[63] 张立明．人工神经网络及其应用．复旦大学出版社 1994
[64] 张智星，孙春在，[日]水谷英二等．神经—模糊和软计算．
[65] 周志坚等．模糊神经网络的交叉应用 电路与系统学报．Sep．1998，3(3)
[66] 谢维信，钱法涛．模糊神经网络研究．深圳大学学报(理工版)．1999年9月第16卷2-3期
[67] 方开泰，马长兴著．正交与均匀试验设计 科学出版社 2001．9
[68] 王永红．VC++设计应用程序界面 计算机技术与应用安徽建筑 2001，3
[69] 李博轩等．Visual C++6．O数据库开发指南 清华大学出版社 2000年5月第1版
[70] Simpson, Elizabeth等著，邱仲潘等译。Access97从入门到精通电子工业出版社．1997，10
[71] David. J. Kruginski, Scot Wingo George Shepherd. Visual C++6.0技术内幕第五版．北京希望电子出版社．1999年5月第1版
[72] 程卫国 冯封等．Matlab 5．3应用指南．人民邮电出版社．1999年9月第1版
[73] 苏金明 阮沈勇编著．Matlab 6．1实用指南．电子工业出版社．2002年1月第1版
[74] 刘志俭等编著．Matlab应用程序接口用户指南．科学出版社
2000年8月第1版
[75] 汤丽萍 施小成等．利用Matlab计算引擎实现VC和Matlab的混合编程电脑学习．2000，6
[76] 杨成，申丽然等．Matlab引擎的VC++接口接口调用及其面向对象编程应用科技．Nov．2001，28(11)
[77] 萨师煊 王珊，数据库概论(第二版 1990．5)
[78] 王能斌，董逸生．数据库设计与实现．北京航空航天大学出版社 1994
[79] 钱能主编．C++程序设计教程．清华大学出版社．1999年4月第一版
[2] Hu Lianxi, Luo Shoujing. Development of the technology of extrusion directly following infiltration for the manufacturing of metal-matrix composite. J. of materials processing technology. 1995(49): 287
[3] 齐乐华，崔培玲，史忠科，李贺军．液-固挤压，Al_2O_(3sf)LY12复合材料管材成形过程的数值模拟．机械工程学报．2002，38(2)：53-56
[4] Qi Lehua, Li Hejun, Shi Hou Junjie, etc al. Research on the Neural Networks Used for Shaping Tubes by the Liquid Extrusion Process. Journal of Material Engineering and Performance. 2000, 9: 28-32
[5] Qi Lehua. The Influence of liquid Extrusion on the Microstructure and Properties of an A1-Si Alloy. Materials and Manufacturing Process. 1998, 13(3) 405-413
[6] 罗守靖，田文彤，李金平．21世纪最具发展前景的近静成形技术．第一届半固态金属加工技术研讨会．2000．4：1-5
[7] 齐乐华，李贺军，罗守靖，霍文灿．液态挤压下ZA27合金的性能与组织特征．有色金属学报．1997，49(1)：90-94
[8] 齐乐华，李贺军，罗守靖．锌合金的液态模锻强化．材料研究学报．1997，11(2)：178-180．
[9] 齐乐华，崔培玲，史忠科，李贺军．液-固挤压复合材料管材成形过程中温度场的有限元分析．金属学报．2002，38(5)：549-554
[10] 李贺军，齐乐华，胡连喜等。液态挤压的金属流动特征研究．锻压技术．1993(增刊)11-13
[11] 罗守靖，李贺军，胡连喜．液态挤压下金属成形的力学研究．锻压技术．1993 NO．2，16-19
[12] 罗守靖，李贺军，杨琦雯．液态挤压下Al Zn合金的强韧化．材料科学进展．1993，7(2)110
[14] 齐乐华，李贺军，罗守靖．液态模锻和液态挤压强韧化的机理研究．兵器材料科学与工程．1996，19(4)：56-60
[15] Hejun Li, Lehua Qi, Shoujing Luo. Research into the properties and microstructure of ZA13 Alloy tubes formed by liquid extrusion. Journal of materials processing Tecnology. 55(1995): 19-23
[16] Qi Lehua, Li Hejun, Shi Zhongke and Cui Peiling. Research on the forming of tubes and Bars of Alumina/LY12 Alloy Composites by Liquid extrusion Process. Proceeding of the third China International diecasting Congress. Northeastern University Press. 2002: 161-168
[17] Luo Shoujing, Zu Lijun. Semi-solid extrusion of TiC_p/2024 Al composites prepared by contact reaction method. Trans. Nonferrous Met. Soc. China. 2000 10(3):305-308
[18] 胡连喜．液态浸渗侯直接挤压铝基复合材料的组织特征．特种铸造及有色金属．1996(1)：1-3
[19] 胡连喜，罗守靖，霍文灿．液态浸渗后直接挤压过程的载荷位移特征．轻合金加工技术．1998，26(10)：43-47
[20] 袁增任等 人工神经网络原理及其应用 清华大学出版社 1999，10
[21] 罗莉，胡守仁．有限精度的BP神经网络高速算法．国防科技大学学报．1998，20(1)
[22] 高大启．有教师的线性基本函数前向三层网络结构研究．电路与系统学报．1997 2(3)：31-37．
[23] 王铁，陈进．BP算法中学习速率及形状因子对科学进度的综合影响．上海交通大学学报．1997，31(3)：109-112
[24] Vittoris Maniezzo. Genetic evolution of the topology and weight distribution of neural netwoks. IEEE Trans on neural networks. 1994, 5(1)
[25] 周尚明，魏华梁．复杂过程建模的模糊集和神经网络方法．系统仿真学报．1998，2：20-26
[26] 吴晓峰，李恩伟．神经网络在加热炉自控系统中的应用．人工智能及应用 1998，4：32-34
[27] 杨自厚，许宝栋．神经网络在高炉模式识别中的应用．冶金自动化．1992，16(5)：3-6．
[28] 马建苍，罗磊，吴启彬．小波—人工神经网络信息融合故障诊断方法．中国机械工程．1997，8(2)：38-40
[29] 董选明，裘丽华．液压泵的人工神经网络在线故障诊断系统．中国机械工程．1997，8(2)：44-46
[30] A. Xiaoguang, H. Ning etc. al. Application of synergetic intelligence to the scheduling in the finishing train of the hot strip mills. Journal of material process technology. 1996(60): 405-408
[31] 高行山，叶天麒，吕胜利．神经网络计算机及其在薄板弯曲分析中的应用．机械科学与技术．May 1995，18(3)：417-419
[32] 侯俊杰．西北工业大学硕士论文．1999
[33] J. Wang, X Wu, P. F. Thmson, A. Flitman. A neural network approach to investigating the geometrical influence on wrinkling in sheet metal forming. Journal of materials processing technology. 105(2000) 215-220.
[34] Geigerl. L, Cser. J, G. Lenond. Neural networks in metal forming. Neural networks in metal forming.
[35] K. Osakada, G. B. Yang. Neural networks for process planning of cold
forming. Annuals of the CIRP. 1991 Vol, 40 No.1 243-246.
[36] Y. S. Liaoa, M. T. Yanb, C. C. Chang. Journal of Materials Processing Technology 121(2002) 252-258
[37] 章卫国，杨向忠．模糊控制理论与应用．西北工业大学出版社．1999
[38] 罗蓬等．基于模糊控制论的压铸浇注系统工艺参数设计新方法．铸造技术．1998，5：24-25
[39] 王守琰，孔德英．基于模式识别的金属材料海水腐蚀形貌诊断系统．金属学报．May 2001，37(5)：517-521
[40] 刘文剑，柏合民，蔡鹤皋．基于模糊推理的工件定位面选择．哈尔滨工业大学学报 2000．12，2(6)：87-90
[41] 姜道连，张亮等 自学习模糊控制系统在微波治疗设备中的应用．自动化与仪表．2000，16(5)：37-38
[42] 周志坚，毛守源等．模糊神经网络交叉技术．电路与系统学报．1998，9．3(3)：81-85
[43] 谭群华，李伟等．基于行为建模的机器人混合模糊—神经控制方法．清华大学学报(自然科学版)．1997，37(2)：38-41
[44] 李君，张建武等．自学习模糊神经网络AMT车辆巡航控制．机械工程学报．2001，37(1)：63-68
[45] 李映，白本督，焦李成．一种基于非线性复杂系统辨识的自适应模糊控制神经网络．电子信息学报．2001，23(4)．
[46] 汪锐，罗亚军等．基于模糊神经网络的压边力优化控制专家系统 上海交通大学学报 Mar．2001，35(3)：411-415
[47] Hisao Ishibuchi, Kitaek Kwon, Hideo Tandka. A learning algorithn of fuzzy neural networks with triangular fuzzy weight. Fuzzy sets and system. 71(1995) 277-293
[48] Wei Li, Chenyu Ma, F. M. Wahl. A neuro-fuzzy system architecture for behavior-based control of a mobile robot in unknown environments Fuzzy Sets and system 87(1997) 133-140
[49] R. -J, Kuo. A robotic die polishing system through fuzzy neural networks Computer in industry 32(1997)273-280
[50] Jelena Godjevac, Nigel Steele. Neurocomputing 28(1999) 127} 143
[51] J. Kim, N. Kasabov. Neural Networks 12(1999) 1301-1319
[52] 孙增析．智能控制理论与技术 清华大学出版社．1997年4月
[53] 王小平，曹立明．遗传算法理论、应用与软件实现 西安交通大学出版社．2002年1月第一版
[54] Miller John A, Potter Watter D An evalution of a improment for genetic algorithms. IEEE Trans on syst Man and Cybernetics 1993 23
(5) 1340-1350
[55] Fogel David B. Evolutionary computation -Toward a new philosophy of machine intelligence. IEEE press 1995
[56] 章珂，刘贵忠．交叉位置非等概率选取的遗传操作．信息与控制．1997，26(1)：53-56．
[57] 汪朝军，刘艳明等．变搜索域遗传算法及其在铣削加工参数优化中的应用．中国机械工程．1998，9(4)：33-34
[58] 冯春，黄洪钟，谢泗维．机械工程全局优化算法．机械科学与技术．1997，16(1)：21-24
[59] 吴立成，陆震，于守谦，郑红．柔性杆子杆模型的遗传算法优化求解．北京航空航天大学学报．2001，2．27(1)：97-100
[60] Rafik A. Alive, Bijan Fazlollahi, Rustam M, Vahidov. Genetic algorithm-based learning of fuzzy neural networks Part 1: feed-forward fuzzy neural networks
[61] 郭礼辉，孔繁森，宗长富．遗传算法在汽车操纵稳定性评价及结构参数优化中的应用．机械工程学报．2000，10．36(10)：34-36
[62] Yunqing Zhang, Member, IEEE, and Abraham Kandel, Fellow, IEEE. Compensatory Neurofuzzy System with Fast Learning Algorithms IEEE TRANSACTION ON NEURAL NETWORKS. JAN. 1998, 9(1)
[63] 张立明．人工神经网络及其应用．复旦大学出版社 1994
[64] 张智星，孙春在，[日]水谷英二等．神经—模糊和软计算．
[65] 周志坚等．模糊神经网络的交叉应用 电路与系统学报．Sep．1998，3(3)
[66] 谢维信，钱法涛．模糊神经网络研究．深圳大学学报(理工版)．1999年9月第16卷2-3期
[67] 方开泰，马长兴著．正交与均匀试验设计 科学出版社 2001．9
[68] 王永红．VC++设计应用程序界面 计算机技术与应用安徽建筑 2001，3
[69] 李博轩等．Visual C++6．O数据库开发指南 清华大学出版社 2000年5月第1版
[70] Simpson, Elizabeth等著，邱仲潘等译。Access97从入门到精通电子工业出版社．1997，10
[71] David. J. Kruginski, Scot Wingo George Shepherd. Visual C++6.0技术内幕第五版．北京希望电子出版社．1999年5月第1版
[72] 程卫国 冯封等．Matlab 5．3应用指南．人民邮电出版社．1999年9月第1版
[73] 苏金明 阮沈勇编著．Matlab 6．1实用指南．电子工业出版社．2002年1月第1版
[74] 刘志俭等编著．Matlab应用程序接口用户指南．科学出版社
2000年8月第1版
[75] 汤丽萍 施小成等．利用Matlab计算引擎实现VC和Matlab的混合编程电脑学习．2000，6
[76] 杨成，申丽然等．Matlab引擎的VC++接口接口调用及其面向对象编程应用科技．Nov．2001，28(11)
[77] 萨师煊 王珊，数据库概论(第二版 1990．5)
[78] 王能斌，董逸生．数据库设计与实现．北京航空航天大学出版社 1994
[79] 钱能主编．C++程序设计教程．清华大学出版社．1999年4月第一版