用粒子群模糊神经网络预测绝缘工程陶瓷线电极放电磨削加工效果
|
摘要
在绝缘工程陶瓷线电极放电磨削加工过程中,加工技术指标与各工艺参数间联系密切。在实际加工中,操作者通常根据以往的加工经验设置工艺参数,并对加工结果进行一定的预判。若工艺参数设置不合理,将极大影响机床的加工效率、加工精度和加工能力。为此,以BP模糊神经网络为基础,提出了一种适用于绝缘工程陶瓷线电极放电磨削加工的技术指标效果预测模型,用粗糙集理论对训练样本集进行属性和规则约简,并用改进的粒子群算法优化模糊神经网络。根据优化前后的模型对碳化硼(B_4C)陶瓷加工进行仿真实验对比,发现优化后的模型对技术指标的预测速度快、误差小、精度高。
In the process of wire electrode discharge grinding(WEDG) of insulating engineering ceramic, there is a close relationship between the technical indexes and process parameters. The operators can only set the process parameters according to their past experience during the practice, and predict the processing results to a certain extent. If the setting of process parameters is unreasonable, it will greatly affect the processing efficiency, accuracy and capacity of machine tools. Therefore, based on BP fuzzy neural network(BPFNN), a prediction model is presented for the effect of technical indicators for WEDG of insulating engineering ceramic. Rough set theory is used to reduce the attributes and rules of training samples and improved particle swarm optimization(PSO) is used to optimize the network. The models before and after optimization are used to simulate the processing of boron carbide(B_4C) ceramics and the results are compared. It is found that the optimized model has the advantages of fast prediction speed, small error and high precision.
In the process of wire electrode discharge grinding(WEDG) of insulating engineering ceramic, there is a close relationship between the technical indexes and process parameters. The operators can only set the process parameters according to their past experience during the practice, and predict the processing results to a certain extent. If the setting of process parameters is unreasonable, it will greatly affect the processing efficiency, accuracy and capacity of machine tools. Therefore, based on BP fuzzy neural network(BPFNN), a prediction model is presented for the effect of technical indicators for WEDG of insulating engineering ceramic. Rough set theory is used to reduce the attributes and rules of training samples and improved particle swarm optimization(PSO) is used to optimize the network. The models before and after optimization are used to simulate the processing of boron carbide(B_4C) ceramics and the results are compared. It is found that the optimized model has the advantages of fast prediction speed, small error and high precision.
引文
[1] 杨浩泉,周平.基于人工神经网络的电火花加工工艺建模方法研究 [J].机械设计与制造,2010,48(1):128-129.YANG Haoquan,ZHOU Ping.Artificial neural network model of EDM process [J].Machinery Design & Manufacture,2010,48(1):128-129.
[2] 骆志高.陶瓷材料电加工表面质量的研究 [J].机械工程学报,2000,36(11):75-79.LUO Zhigao.Research on surface quality of ceramic material by electric machining [J].Chinese Journal of Mechanical Engineering,2000,36(11):75-79.
[3] 谢桂芝,黄含,盛晓敏,等.工程陶瓷高效深磨磨削力和损伤的研究 [J].湖南大学学报(自然科学版),2008,35(5):26-30.XIE Guizhi,HUANG Han,SHENG Xiaoming,et al.Investigation on the grinding force and the ground damages in the high efficiency deep grinding of advanced ceramics [J].Journal of Hunan University (Natural Science),2008,35(5):26-30.
[4] 纪仁杰,刘永红,于丽丽,等.电火花磨削非导电工程陶瓷实验研究 [J].电加工于模具,2007,42(6):11-14.JI Renjie,LIU Yonghong,YU Lili,et al.Experimental investigations of machining nonconductive engineering ceramics with electrical discharge grinding(EDG) [J].Electromachaning & Mould,2007,42(6):11-14.
[5] 李小朋,刘永红,纪仁杰,等.非导电工程陶瓷电火花单脉冲放电加工实验研究 [J].制造技术与机床,2007,57(12):78-81.LI Xiaopeng,LIU Yonghong,JI Renjie,et al.Experiments of single pulse discharges on non-conductive engineering ceramics [J].Manufacturing Technology & Machine Tool,2007,57(12):78-81.
[6] 李小朋,刘永红,纪仁杰,等.非导电工程陶瓷电火花磨削工艺规律研究 [J].机床与液压,2007,35(10):1-4.LI Xiaopeng,LIU Yonghong,JI Renjie,et al.Research on electrical discharge grinding of non-conductive engineering ceramics [J].Machine Tool & Hydraulics,2007,35(10):1-4.
[7] 赵万生.特种加工技术 [M].北京:高等教育出版社,2001.ZHAO Wansheng.Special machining technology [M].Beijing:Higher Education Press,2001.
[8] 徐小兵,莫易敏,陈蔚鸿,等.基于神经网络和遗传算法的绝缘陶瓷电火花加工电参数优化 [J].机械设计与制造,2008,46(4):125-127.XU Xiaobing,MO Yimin,CHEN Weihong,et al.Optimization of electrical parameters of insulating ceramics EDM based on ANN and GA [J].Machinery Design & Manufacture,2008,46(4):125-127.
[9] 徐小兵.绝缘陶瓷材料电火花加工技术及仿真研究 [D].武汉:武汉理工大学,2009.XU Xiaobing.Research on EDM technology and simulation of insulating ceramics [D].Wuhan:Wuhan University of Technology,2009.
[10] 范久臣,孙雪梅,王帅,等.工程陶瓷回转表面线电极磨削加工粗糙度预测模型 [J].长春工业大学学报,2016,37(6):535-539.FAN Jiuchen,SUN Xuemei,WANG Shuai,et al.Roughness prediction model for engineering ceramics rotating surface wire electrical discharge grinding [J].Journal of Changchun University of Technology,2016,37(6):535-539.
[11] 王岚.工程陶瓷磨削加工仿真系统平台设计与开发 [D].天津:天津大学,2007.WANG Lan.Design and development of engineering ceramics grinding simulation system platform [D].Tianjin:Tianjin University,2007.
[12] 李雪,王鹤,范久臣,等.神经网络在工程陶瓷电火花加工中的应用研究 [J].制造技术与机床,2010,60(10):25-27.LI Xue,WANG He,FAN Jiuchen.Application study of neural network in electrical discharge machining engineering ceramics [J].Manufacturing Technology & Machine Tool,2010,60(10):25-27.
[13] 袁曾任.人工神经网络及其应用 [M].北京:清华大学出版社,1999.YUAN Zengren.Artificial neural network and its application [M].Beijing:Tsinghua University Press,1999.
[14] 蒋宗礼.人工神经网络导论 [M].北京:高等教育出版社,2001.JIANG Zongli.Introduction to artificial neural networks [M].Beijing:Higher Education Press,2001.
[15] 朱大奇,史慧.人工神经网络原理及应用 [M].北京:科学出版社,2006.ZHU Daqi,SHI Hui.Principle and application of artificial neural network [M].Beijing:Science Press,2006.
[16] 张文修,吴伟志,梁吉业,等.粗糙集理论与方法 [M].北京:科学出版社,2001.ZHANG Wenxiu,WU Weizhi,LIANG Jiye,et al.Rough set theory and method [M].Beijing:Science Press,2001.
[17] 曾黄麟.粗集理论及其应用 [M].重庆:重庆大学出版社,1996.ZENG Huanglin.Rough set theory and its application [M].Chongqing:Chongqing University Press,1996.
[18] 王鹤,邵凤翔,李辉,等.基于模糊神经网络的工程陶瓷电火花加工工艺模型研究 [J].现代制造工程,2016,38(8):130-133.WANG He,SHAO Fengxiang,LI Hui,et al.Optimization of electrical parameter in electrical discharge machining of engineering ceramics based on fuzzy neural network [J].Modern Manufacturing Engineering,2016,38(8):130-133.
[19] 张宏,马岩,李勇,等.基于遗传BP 神经网络的核桃破裂功预测模型 [J].农业工程学报,2014,30(18):78-84.ZHANG Hong,MA Yan,LI Yong,et al.Rupture energy prediction model for walnut shell breaking based on genetic BP neural network [J].Transactions of the Chinese Society of Agricultural Engineering,2014,30(18):78-84.
[20] KENNEDY J.Particle swarm optimization [M].Berlin:Springer,2010.
[21] POLI R,KENNEDY J,BLACKWELL T.Particle swarm optimization [J].Swarm Intelligence,2007,1(1):33-57.
[22] 王新,孙河南.基于粒子群神经网络的级联式变频器故障诊断 [J].计算机仿真,2015,32(7):421-425.WANG Xin,SUN Henan.Fault diagnosis of casaded inverter based on PSO and neural network [J].Computer Simulation,2015,32(7):421-425.
[23] URSEM R K .Diversity-guided evolutionary algorithm [M].Berlin:Springer,2002.
[24] 薛文涛,吴晓蓓,徐志良.一种基于双变异算子的免疫网络算法 [J].控制与决策,2008,23(12):1417-1422.XUE Wentao,WU Xiaobei,XU Zhiliang.Immune network algorithm based on double mutation operators [J].Control and Decision,2008,23(12):1417-1422.
[2] 骆志高.陶瓷材料电加工表面质量的研究 [J].机械工程学报,2000,36(11):75-79.LUO Zhigao.Research on surface quality of ceramic material by electric machining [J].Chinese Journal of Mechanical Engineering,2000,36(11):75-79.
[3] 谢桂芝,黄含,盛晓敏,等.工程陶瓷高效深磨磨削力和损伤的研究 [J].湖南大学学报(自然科学版),2008,35(5):26-30.XIE Guizhi,HUANG Han,SHENG Xiaoming,et al.Investigation on the grinding force and the ground damages in the high efficiency deep grinding of advanced ceramics [J].Journal of Hunan University (Natural Science),2008,35(5):26-30.
[4] 纪仁杰,刘永红,于丽丽,等.电火花磨削非导电工程陶瓷实验研究 [J].电加工于模具,2007,42(6):11-14.JI Renjie,LIU Yonghong,YU Lili,et al.Experimental investigations of machining nonconductive engineering ceramics with electrical discharge grinding(EDG) [J].Electromachaning & Mould,2007,42(6):11-14.
[5] 李小朋,刘永红,纪仁杰,等.非导电工程陶瓷电火花单脉冲放电加工实验研究 [J].制造技术与机床,2007,57(12):78-81.LI Xiaopeng,LIU Yonghong,JI Renjie,et al.Experiments of single pulse discharges on non-conductive engineering ceramics [J].Manufacturing Technology & Machine Tool,2007,57(12):78-81.
[6] 李小朋,刘永红,纪仁杰,等.非导电工程陶瓷电火花磨削工艺规律研究 [J].机床与液压,2007,35(10):1-4.LI Xiaopeng,LIU Yonghong,JI Renjie,et al.Research on electrical discharge grinding of non-conductive engineering ceramics [J].Machine Tool & Hydraulics,2007,35(10):1-4.
[7] 赵万生.特种加工技术 [M].北京:高等教育出版社,2001.ZHAO Wansheng.Special machining technology [M].Beijing:Higher Education Press,2001.
[8] 徐小兵,莫易敏,陈蔚鸿,等.基于神经网络和遗传算法的绝缘陶瓷电火花加工电参数优化 [J].机械设计与制造,2008,46(4):125-127.XU Xiaobing,MO Yimin,CHEN Weihong,et al.Optimization of electrical parameters of insulating ceramics EDM based on ANN and GA [J].Machinery Design & Manufacture,2008,46(4):125-127.
[9] 徐小兵.绝缘陶瓷材料电火花加工技术及仿真研究 [D].武汉:武汉理工大学,2009.XU Xiaobing.Research on EDM technology and simulation of insulating ceramics [D].Wuhan:Wuhan University of Technology,2009.
[10] 范久臣,孙雪梅,王帅,等.工程陶瓷回转表面线电极磨削加工粗糙度预测模型 [J].长春工业大学学报,2016,37(6):535-539.FAN Jiuchen,SUN Xuemei,WANG Shuai,et al.Roughness prediction model for engineering ceramics rotating surface wire electrical discharge grinding [J].Journal of Changchun University of Technology,2016,37(6):535-539.
[11] 王岚.工程陶瓷磨削加工仿真系统平台设计与开发 [D].天津:天津大学,2007.WANG Lan.Design and development of engineering ceramics grinding simulation system platform [D].Tianjin:Tianjin University,2007.
[12] 李雪,王鹤,范久臣,等.神经网络在工程陶瓷电火花加工中的应用研究 [J].制造技术与机床,2010,60(10):25-27.LI Xue,WANG He,FAN Jiuchen.Application study of neural network in electrical discharge machining engineering ceramics [J].Manufacturing Technology & Machine Tool,2010,60(10):25-27.
[13] 袁曾任.人工神经网络及其应用 [M].北京:清华大学出版社,1999.YUAN Zengren.Artificial neural network and its application [M].Beijing:Tsinghua University Press,1999.
[14] 蒋宗礼.人工神经网络导论 [M].北京:高等教育出版社,2001.JIANG Zongli.Introduction to artificial neural networks [M].Beijing:Higher Education Press,2001.
[15] 朱大奇,史慧.人工神经网络原理及应用 [M].北京:科学出版社,2006.ZHU Daqi,SHI Hui.Principle and application of artificial neural network [M].Beijing:Science Press,2006.
[16] 张文修,吴伟志,梁吉业,等.粗糙集理论与方法 [M].北京:科学出版社,2001.ZHANG Wenxiu,WU Weizhi,LIANG Jiye,et al.Rough set theory and method [M].Beijing:Science Press,2001.
[17] 曾黄麟.粗集理论及其应用 [M].重庆:重庆大学出版社,1996.ZENG Huanglin.Rough set theory and its application [M].Chongqing:Chongqing University Press,1996.
[18] 王鹤,邵凤翔,李辉,等.基于模糊神经网络的工程陶瓷电火花加工工艺模型研究 [J].现代制造工程,2016,38(8):130-133.WANG He,SHAO Fengxiang,LI Hui,et al.Optimization of electrical parameter in electrical discharge machining of engineering ceramics based on fuzzy neural network [J].Modern Manufacturing Engineering,2016,38(8):130-133.
[19] 张宏,马岩,李勇,等.基于遗传BP 神经网络的核桃破裂功预测模型 [J].农业工程学报,2014,30(18):78-84.ZHANG Hong,MA Yan,LI Yong,et al.Rupture energy prediction model for walnut shell breaking based on genetic BP neural network [J].Transactions of the Chinese Society of Agricultural Engineering,2014,30(18):78-84.
[20] KENNEDY J.Particle swarm optimization [M].Berlin:Springer,2010.
[21] POLI R,KENNEDY J,BLACKWELL T.Particle swarm optimization [J].Swarm Intelligence,2007,1(1):33-57.
[22] 王新,孙河南.基于粒子群神经网络的级联式变频器故障诊断 [J].计算机仿真,2015,32(7):421-425.WANG Xin,SUN Henan.Fault diagnosis of casaded inverter based on PSO and neural network [J].Computer Simulation,2015,32(7):421-425.
[23] URSEM R K .Diversity-guided evolutionary algorithm [M].Berlin:Springer,2002.
[24] 薛文涛,吴晓蓓,徐志良.一种基于双变异算子的免疫网络算法 [J].控制与决策,2008,23(12):1417-1422.XUE Wentao,WU Xiaobei,XU Zhiliang.Immune network algorithm based on double mutation operators [J].Control and Decision,2008,23(12):1417-1422.