基于神经网络的动态误差建模及实验研究
|
摘要
科技的发展,对测量技术提出了新的更高的要求,促使其不断地向更高的水平发展。目前,动态测量已逐渐成为现代测量的主流。如何提高其测量精度,一直是工程测量与仪器设计人员关注的重点。动态精度已引起人们的高度重视,成为精度理论研究中迫切需要解决的课题。
本文根据神经网络原理,研究动态误差的建模方法。利用BP网络以及RBF网络两种方法分别进行动态误差的建模和预测。
在自行设计的动态误差实验系统中,同步采集标准信号(电机脉冲数)和测量信号(光栅脉冲数),实时比对分离出动态误差。通过设计实验装置的电路部分,实现对信号的采集、计数和比对。主要包括电机信号处理电路和计数电路。利用Am261s32对电机输出信号进行差分处理;利用74LS161、74HC573等芯片进行计数;利用AC6651采集卡进行数据采集,选用计数位数更多的HCTL-2020芯片,改善了计数效果;通过LABVIEW软件设计了界面,实现数据的实时保存。
通过对实验装置的安装与调试,成功分离出角位移测量的动态误差。基于BP、RBF神经网络模型对实验系统的动态误差进行建模和预测。
With the development of technology, it is required higher on measurement technology to develop to a higher level. Dynamic measurement has gradually become the mainstream of modern measurement now. It, how to improve measurement accuracy, is always peoples' research focus in engineering measurement and instrument design. Great attention has been aroused in dynamic accuracy, which becomes an urgent need to address issues in theoretical research on accuracy.
According neural network theory, we studied the method of modeling for Dynamic Error. Two kinds of methods, BP network and RBF network, were used to model and predict for the Dynamic Error.
In a self-designed dynamic error experimental system, the standard signal (motor pulses) and the measured signal (grating pulses) were collected synchronously, and isolated the dynamic error. Through the design of the circuit of the experimental system, the signal was collected, counted and contrasted. Differential treatment was used in motor output signal with Am261s32;and counting was carried on with 74LS161 and 74HC573; and data was acquired with AC6651;Counting result was improved due to improved experimental device and HCTL-2020 with more counting median; and interface was designed with LABVIEW, with which data can be preserved real-time.
Through the installing and commissioning for experimental device, we successfully separated the dynamic angular displacement measurement error. Based on BP and RBF neural network model, the dynamic error of experiment was modeled and forecasted.
本文根据神经网络原理,研究动态误差的建模方法。利用BP网络以及RBF网络两种方法分别进行动态误差的建模和预测。
在自行设计的动态误差实验系统中,同步采集标准信号(电机脉冲数)和测量信号(光栅脉冲数),实时比对分离出动态误差。通过设计实验装置的电路部分,实现对信号的采集、计数和比对。主要包括电机信号处理电路和计数电路。利用Am261s32对电机输出信号进行差分处理;利用74LS161、74HC573等芯片进行计数;利用AC6651采集卡进行数据采集,选用计数位数更多的HCTL-2020芯片,改善了计数效果;通过LABVIEW软件设计了界面,实现数据的实时保存。
通过对实验装置的安装与调试,成功分离出角位移测量的动态误差。基于BP、RBF神经网络模型对实验系统的动态误差进行建模和预测。
With the development of technology, it is required higher on measurement technology to develop to a higher level. Dynamic measurement has gradually become the mainstream of modern measurement now. It, how to improve measurement accuracy, is always peoples' research focus in engineering measurement and instrument design. Great attention has been aroused in dynamic accuracy, which becomes an urgent need to address issues in theoretical research on accuracy.
According neural network theory, we studied the method of modeling for Dynamic Error. Two kinds of methods, BP network and RBF network, were used to model and predict for the Dynamic Error.
In a self-designed dynamic error experimental system, the standard signal (motor pulses) and the measured signal (grating pulses) were collected synchronously, and isolated the dynamic error. Through the design of the circuit of the experimental system, the signal was collected, counted and contrasted. Differential treatment was used in motor output signal with Am261s32;and counting was carried on with 74LS161 and 74HC573; and data was acquired with AC6651;Counting result was improved due to improved experimental device and HCTL-2020 with more counting median; and interface was designed with LABVIEW, with which data can be preserved real-time.
Through the installing and commissioning for experimental device, we successfully separated the dynamic angular displacement measurement error. Based on BP and RBF neural network model, the dynamic error of experiment was modeled and forecasted.
引文
[1]费业泰.误差理论与数据处理(第四版)[M].北京:机械工业出版社,2000.p1-12
[2]费业泰,卢荣胜.动态测量误差修正原理与技术.中国计量出版社[M],2001年7月,p1-3
[3]陈晓怀,费业泰,黄强先.全系统动态测量精度理论的基本问题[J].制造业自动化,Vol.21,No.6,1999,12
[4]费业泰.误差理论的研究与进展[J].计量技术,1998,(8):40-41
[5]许桢英,费业泰,陈晓怀.动态精度理论研究与发展[J],仪器仪表学报,Vol.22,No.4,2001,P70-71,74
[6]陈晓怀.动态测量精度理论及应用关键问题研究[D].合肥工业大学博士学位论文,2006
[7]亓四华等.机械加工精度动态损失模型的研究[J].组合机床与自动化加工技术,2002第4期
[8]从爽.神经网络、模糊系统及其在运动控制中的应用[M].合肥:中国科学技术大学出版社,2001.p30-60
[9]张璐璐,陈晓怀,程真英.加工装置的精度动态损失贝叶斯建模预报[J].黑龙江科技学院学报,2006,3,VOL 16,NO.2
[9]飞思科技产品研究中心.神经网络理论与MATLAB7实现[M].北京:电子工业出版社,2005.3
[10]许祯英.动态测量误差溯源与精度损失诊断的理论与方法研究[D].合肥工业大学博士学位论文,2004年1月
[11]张伟,王力,赵晶.电路设计与制版-ProtelDXP入门与提高(第一版)[M].人民邮电出版社,2003,2,p220-300
[12]松下A4系列伺服电机说明书
[13]叶兵.基于遗传神经网络模型实时误差修正任意角测量系统[D].合肥工业大学博士学位论文,2004年2月
[14]AC6651使用手册,2004,11
[15]李鹏.控制电机及应用[M].高等教育出版社.1998
[16]候国屏,王坤,叶齐鑫.Labview7.1编程与虚拟仪器设计[M].清华大学出版社,2004,8.p200-235
[17]宋宜斌,王培进.一种基于RBF神经网络的预测器模型及其研究[M].计算机工程与应用,2004,6,VOL 105,NO.2.
[18]汪思敏,姚鹏翼,胡烨.Prote2004电路原理图及PCB设计[M].机械工业出版社.2006,9 p22-39
[19]沈兰荪.智能仪器与信号处理技术[M].1990.6.p3-28
[20]张国雄,金篆芷.测控电路[M].机械工业出版社,2000,9.p89-92
[21]强锡福.传感器[M],机械工业出版社.2000.p20-50
[22]魏巍.应用数学工具箱技术手册[M].北京:国防工业出版社,2004.1pp40-42,339.p60-220
[23]沈兰荪.智能仪器与信号处理技术[M].1990.6.p40-50
[24]霍俊.实用预测学[M],北京,科学普及出版社.1987.3,pp1-2.p190-203
[25]韩力群.人工神经网络理论、设计及应用[M].北京:化学工业出版社,2001.9.p1-20
[26]王科俊,王克成.神经网络建模、预报与控制[M].哈尔滨:哈尔滨工程大学出版社,1996,12.p2-6
[27]李力争,何清华.用光电编码器测量转角的一种误差来源[J].传感器世界.2006,5.
[28]李洪,冯长有,丁林辉.光电轴角编码器细分误差动态评估方法[J].传感技术学报.2005,12.VOL 18,NO.4.
[29]蔡锁章.数学建模原理与方法[M].北京:海洋出版社,2000.p1-42
[30]陈桂明.应用MATLAB建模与仿真[J].北京:科学出版社2001.3
[31]张凯,周陬,郭栋.LabVIEW虚拟仪器工程设计与开发[J].北京:国防工业出版社,2004
[32]金泰义.精度理论与应用[M].中国科技大学出版社.2005.p1-15
[33]康华光,陈大钦.电子技术基础(第四版)[M].高等教育出版社,1999,6.p220-232
[34]蒋敏兰.测量系统精度损失溯源与预测模型研究[D].合肥工业大学博士学位论文.2007年6月
[35]莫云峰.精度损失实验系统装置的研究[J].黑龙江科技学院学报.2007.4
[2]费业泰,卢荣胜.动态测量误差修正原理与技术.中国计量出版社[M],2001年7月,p1-3
[3]陈晓怀,费业泰,黄强先.全系统动态测量精度理论的基本问题[J].制造业自动化,Vol.21,No.6,1999,12
[4]费业泰.误差理论的研究与进展[J].计量技术,1998,(8):40-41
[5]许桢英,费业泰,陈晓怀.动态精度理论研究与发展[J],仪器仪表学报,Vol.22,No.4,2001,P70-71,74
[6]陈晓怀.动态测量精度理论及应用关键问题研究[D].合肥工业大学博士学位论文,2006
[7]亓四华等.机械加工精度动态损失模型的研究[J].组合机床与自动化加工技术,2002第4期
[8]从爽.神经网络、模糊系统及其在运动控制中的应用[M].合肥:中国科学技术大学出版社,2001.p30-60
[9]张璐璐,陈晓怀,程真英.加工装置的精度动态损失贝叶斯建模预报[J].黑龙江科技学院学报,2006,3,VOL 16,NO.2
[9]飞思科技产品研究中心.神经网络理论与MATLAB7实现[M].北京:电子工业出版社,2005.3
[10]许祯英.动态测量误差溯源与精度损失诊断的理论与方法研究[D].合肥工业大学博士学位论文,2004年1月
[11]张伟,王力,赵晶.电路设计与制版-ProtelDXP入门与提高(第一版)[M].人民邮电出版社,2003,2,p220-300
[12]松下A4系列伺服电机说明书
[13]叶兵.基于遗传神经网络模型实时误差修正任意角测量系统[D].合肥工业大学博士学位论文,2004年2月
[14]AC6651使用手册,2004,11
[15]李鹏.控制电机及应用[M].高等教育出版社.1998
[16]候国屏,王坤,叶齐鑫.Labview7.1编程与虚拟仪器设计[M].清华大学出版社,2004,8.p200-235
[17]宋宜斌,王培进.一种基于RBF神经网络的预测器模型及其研究[M].计算机工程与应用,2004,6,VOL 105,NO.2.
[18]汪思敏,姚鹏翼,胡烨.Prote2004电路原理图及PCB设计[M].机械工业出版社.2006,9 p22-39
[19]沈兰荪.智能仪器与信号处理技术[M].1990.6.p3-28
[20]张国雄,金篆芷.测控电路[M].机械工业出版社,2000,9.p89-92
[21]强锡福.传感器[M],机械工业出版社.2000.p20-50
[22]魏巍.应用数学工具箱技术手册[M].北京:国防工业出版社,2004.1pp40-42,339.p60-220
[23]沈兰荪.智能仪器与信号处理技术[M].1990.6.p40-50
[24]霍俊.实用预测学[M],北京,科学普及出版社.1987.3,pp1-2.p190-203
[25]韩力群.人工神经网络理论、设计及应用[M].北京:化学工业出版社,2001.9.p1-20
[26]王科俊,王克成.神经网络建模、预报与控制[M].哈尔滨:哈尔滨工程大学出版社,1996,12.p2-6
[27]李力争,何清华.用光电编码器测量转角的一种误差来源[J].传感器世界.2006,5.
[28]李洪,冯长有,丁林辉.光电轴角编码器细分误差动态评估方法[J].传感技术学报.2005,12.VOL 18,NO.4.
[29]蔡锁章.数学建模原理与方法[M].北京:海洋出版社,2000.p1-42
[30]陈桂明.应用MATLAB建模与仿真[J].北京:科学出版社2001.3
[31]张凯,周陬,郭栋.LabVIEW虚拟仪器工程设计与开发[J].北京:国防工业出版社,2004
[32]金泰义.精度理论与应用[M].中国科技大学出版社.2005.p1-15
[33]康华光,陈大钦.电子技术基础(第四版)[M].高等教育出版社,1999,6.p220-232
[34]蒋敏兰.测量系统精度损失溯源与预测模型研究[D].合肥工业大学博士学位论文.2007年6月
[35]莫云峰.精度损失实验系统装置的研究[J].黑龙江科技学院学报.2007.4