基于反馈型神经网络的公路车辆动态称重系统设计
|
摘要
公路车辆动态称重系统作为ITS(公路智能运输系统)的重要组成部分,是抑制公路车辆超载超限有效手段。目前,国内动态称重技术正处在快速发展阶段。
本文从动态车辆称重系统中的几个关键部分着手,提出采用ATM-AVR单片机进行车辆称重信号的A/D转换和数据通信,拟定了数据通信协议并实现数据通信。设计了整体系统方案。针对现有传感器的使用情况,选择使用石英压电传感器作为系统的称重单元,并对数据采集调理电路做了相应的改进。
利用Microsoft Visual C++ 6.0软件完成对车辆数据的录入和显示,包括对上位机串口设置,数据的存储和实时曲线显示。
针对现有数据处理方法的优缺点,在分析车辆称重信号特点的基础上,利用小波多分辨率技术进行信号预处理,提出了使用Elman反馈型神经网络来确定传感器输出电压值与车辆静态重量的对应关系,从而更加准确的得到车辆的真实重量。最后,根据神经网络理论,比较了Elman网络内部各要素对数据分析性能的影响,以及反馈型神经网络和其他神经网络在车辆称重数据处理性能上的优劣。仿真结果表明,相对于BP和RBF网络,Elman网络在车辆动态称重系统中具有更优越的数据处理性能。
As being the effective tool to forbid overloading, vehicles'weigh-in-motion (WIM) system is the important part of intelligent transport system(ITS). Nowadays, the WIM technology is being in the rapid developing period.
In this article, something important as keys of the system were found such as ATM-AVR singlechip, A/D conversion and data communication. At the same time, the communications protocols were designed. Furthermore, we made some describing about the way using Studio software and designed the whole project. Based on the situation of sensor's development and performance, we chose quartz piezoelectric sensors to be as the weight part of the WIM system, and made some improvements to the data acquisition circuit.
We gained the vehicles'data by using the Microsoft Visual C++ 6.0 software and implemented the communication between upper computer and lower computer. And, at the same time, we stored the data in the document and drew relevant real time curve.
Focusing on the merits and drawbacks of the being used methods of data processing and basing on the feature of the WIM signal, we completed data pretreatment by using wavelet multi-resolution techniques. Behind pretreatment, the corresponding relationship between the output of sensors and the static weight of vehicle was found by recurrent networks, which was first touched in this article. At the end of the article, aiming to show the advantages of recurrent networks in the data processing of WIM system, we made matlab stimulation and comparisons not only among different performance acting by different impact factors inside networks, but also between recurrent networks and other neural networks, such as BP network and RBF network.
本文从动态车辆称重系统中的几个关键部分着手,提出采用ATM-AVR单片机进行车辆称重信号的A/D转换和数据通信,拟定了数据通信协议并实现数据通信。设计了整体系统方案。针对现有传感器的使用情况,选择使用石英压电传感器作为系统的称重单元,并对数据采集调理电路做了相应的改进。
利用Microsoft Visual C++ 6.0软件完成对车辆数据的录入和显示,包括对上位机串口设置,数据的存储和实时曲线显示。
针对现有数据处理方法的优缺点,在分析车辆称重信号特点的基础上,利用小波多分辨率技术进行信号预处理,提出了使用Elman反馈型神经网络来确定传感器输出电压值与车辆静态重量的对应关系,从而更加准确的得到车辆的真实重量。最后,根据神经网络理论,比较了Elman网络内部各要素对数据分析性能的影响,以及反馈型神经网络和其他神经网络在车辆称重数据处理性能上的优劣。仿真结果表明,相对于BP和RBF网络,Elman网络在车辆动态称重系统中具有更优越的数据处理性能。
As being the effective tool to forbid overloading, vehicles'weigh-in-motion (WIM) system is the important part of intelligent transport system(ITS). Nowadays, the WIM technology is being in the rapid developing period.
In this article, something important as keys of the system were found such as ATM-AVR singlechip, A/D conversion and data communication. At the same time, the communications protocols were designed. Furthermore, we made some describing about the way using Studio software and designed the whole project. Based on the situation of sensor's development and performance, we chose quartz piezoelectric sensors to be as the weight part of the WIM system, and made some improvements to the data acquisition circuit.
We gained the vehicles'data by using the Microsoft Visual C++ 6.0 software and implemented the communication between upper computer and lower computer. And, at the same time, we stored the data in the document and drew relevant real time curve.
Focusing on the merits and drawbacks of the being used methods of data processing and basing on the feature of the WIM signal, we completed data pretreatment by using wavelet multi-resolution techniques. Behind pretreatment, the corresponding relationship between the output of sensors and the static weight of vehicle was found by recurrent networks, which was first touched in this article. At the end of the article, aiming to show the advantages of recurrent networks in the data processing of WIM system, we made matlab stimulation and comparisons not only among different performance acting by different impact factors inside networks, but also between recurrent networks and other neural networks, such as BP network and RBF network.
引文
[1]王长君,马兆有,张亚军.高速公路交通安全形势及管理对策[J].道路交通与安全,2009,(13)：107～109.
[2]易玮.浅谈货车超限超载运输的危害及其治理对策[J].山西建筑,2008,34(9)：296～297.
[3]陈琦.车辆动态称重系统研究现状[J].设备管理&维修技术,2009,(3).77～80.
[4]王丹.基于ETC的车辆动态称重系统应用研究[D].长安大学硕士学位论文,2009.
[5]张鑫,郭清南,李学磊.压力传感器研究现状及发展趋势[J].电机电器技术,2004,(4)：28～29.
[6]王金斗,宋颖.压电传感技术的研究及应用[J].测控技术与仪器仪表,2008,34(8)：89～92.
[7]宋颖,王志臣,杜彦良.压电传感测试技术的应用研究进展[J].传感器与微系统,2008,27(5)：8-11.
[8]徐东宇.水泥基压电传感器的制备、性能及其在土木工程领域的应用研究[D].山东大学博士学位论文,2010.
[9]凌杰.公路动态称重系统的设计理论研究[D].长安大学博士学位论文,2001.
[10]Stephane T R. Fiber optic weigh-in-motion:looking back and ahead[J]. Optical Engineering, 1998,3326:129～137.
[11]Ansari F, Wang J. Rate sensitivity of high birefringent fiber optic sensors under largedynamic loads[J]. Lightwave Technology,1995,13(10):1992～1997.
[12]唐宇,刘传菊.光纤传感器及其研究现状[J].2009,7：17-18.
[13]黎志刚,蔡萍,周志峰.基于BP网络的汽车动态称重数据处理方法[J].微计算机信息,2006,22(82)：251～253.
[14]许嘉,蔡萍,周志峰,陈日兴.参数估计算法在汽车动态称重中的应用[J].仪器仪表与检测技术,2005,24(8)：69～71.
[15]于哲峰,杨智春.EMD技术在动态称重数据处理中的应用[J].机械科学与技术,2004,23(4)：444～446.
[16]姚恩涛,季娟,张明.两轴车辆动态称重信号分析方法研究[J].传感技术,2005,24(12)：22～24.
[17]于海燕.动态称重技术的研究[D].西安理工大学硕士学位论文,2006.
[18]程路.车辆动态称重技术研究[D].浙江大学博士学位论文,2008.
[19]ASTM, E1318-02. Committee. Standard Specification for Highway Weigh-in-motion(WIM) System with user Requirements and Test Method[S]. West Conshohocken：Ameriean Soeietyfor Testingand Materials,2002.
[20]杨卫东,刘亚蒙.动态称重系统的标准与规范[J].中国公路,2005,1：112～113.
[21]全国衡器计量技术委员会[S].JJG 907-2006动态公路车辆自动衡器鉴定规程.北京：中国计量出版社,2006.
[22]Mamlouk M S. Effect of Vehicle-pavement Interaction on Weigh-in-Motion Equipment Design[J]. International Journal of Heavy Vehicle Systems,1997,3(1):306-322.
[23]王吉忠,刘晓斌,张泰等.花纹磨光轮胎接地特性试验研究[J].农业机械学报.2001,32(2)：18～20.
[24]包学海,楚永萍,唐永明,周睿.弹性构架对车辆系统振动响应的影响[J].铁道车辆,2010,48(3)：4-7.
[25]邓学钧,孙璐.车辆-地面结构系统动力学[M].北京：人民交通出版社,1998.
[26]Grundmann H, Lieb M, Trommer E. The response of a layered half-space to traffic loads moving along its surface[J]. Archives of Applied Mechanics,1999,69(1):55-67.
[27]刘九卿.压电石英称重传感器及其在动态公路车辆称重系统中的应用[C].称重科技暨第六届称重技术研讨会.北京.2007.53～60.
[28]苏艳阳,李锐,陈宇,黄哲,何诗文,蔡天净.传感技术综述[J].数字通信,2009,36(4).20～26.
[29]谷有臣,孔英,陈若.传感器技术的发展和趋势综述[J].物理实验,2002,22(12)：40～42.
[30]李俄收,张少靖,吴文民.汽车传感器应用综述[J].汽车电器,2008,5：1～5.
[31]陈绚,杨安.综述生物传感器及发展研究前景[J].南昌高专学报,2005,1：94～96.
[32]杨兆建,王勤贤.测力传感器研究发展综述[J].山西机械,2003,1：1～3.
[33]王兴举,李进墨.压电式传感器测量电路的性能分析[J].技术与应用,2007,13(5).22～24.
[34]李金田.压电传感器与前置放大器的配接[J].传感器技术,2004,23(1)：54～59
[35]张国华.高保真运算放大器OPA604[J].器件与原件,1995,12：23～24.
[36]金春林,邱慧芳,张皆喜.AVR系列单片机C语言编程与应用实例[M].北京：清华大学出版社,2003.
[37]郭华伟,胡军科.单片机在智能检测中的应用综述[J].发展与综述,2002,1：8～15
[38]包秀荣,王楠.AVR单片机的特点及其应用[J].内蒙古科技与经济,2004,6：51～52.
[39]隋越.基于AVR单片机的应用设计实践[D].吉林大学硕士学位论文,2004.
[40]ATmegal6(L) data sheet[z].2466G-AVR-10/03.
[41]于志赣,刘国平,张旭斌.液显LCD1602模块的应用[J].计算机应用,2009,3：21～23.
[42]赵艳妮.基于VC++的电动汽车试验数据分析系统设计[D].武汉理工大学硕士学位论文,2010.
[43]龚建伟,熊光明.Visual C++/Turbo C串口通信编程实践[M].北京：电子工业出版社,2008.
[44]孙鑫,余安萍.VC++深入详解[M].北京：电子工业出版社,2006.
[45]Weeks M. Digital Signal Processing Using MATLAB and Wavelets[M]. Hingham Massachusetts American：Infinity Science Press LLC,2007.
[46]Mallat S. A Theory for Multiresolution Signal Decomposition：The Wavelet Transform[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,11(7)：674～692.
[47]胡广书.现代数字信号处理[M].北京：清华大学出版社,2004.
[48]蒋正言,周一届.基于小波变换的车辆动态轴重信号消噪[J].2005,13(7)：680～683.
[49]Mallat S G. A theory for multiresolution signal decomposition:the wavelet representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(7):674～693.
[50]Hecht-Nielsen R. Theory of the backpropagation neural network[C]. IEEE International Joint Conference on Neural Networks,1989,1:593～605.
[51]Wang J. Analysis and design of a recurrent neural network for linear programming[J]. IEEE Transactions on Circuits Systems I:Fundamental Theory and Application,1993,40(9): 613-618.
[52]Adeli H, Jiang X. Intelligent Infrastructure. Neural Networks, Wavelets, and Chaos Theory for Intelligent Transportation Systems and Smart Structures[M]. Boca Raton, London：CRC Press,2009.
[53]Bishop C M. Neural networks and their application[J]. Review of Scientific Instruments, 2009,65(6):1803～1832.
[54]Jackel L D, Howard R E, Graf H P, Straughn B, Denker J S. Artificial neural networks for computing[J]. Journal of Vacuum Science & Technology B:Microelectronics and Nanometer Structures,2009,4(1):61～63.
[55]周开刑,康耀红.神经网络模型及其Matlab仿真程序设计[J].北京：清华大学出版社,2005.
[56]Haykin S.神经网络原理[M].叶世伟,史忠植译.北京：机械工业出版社,2004.
[57]戚德虎,康继昌.BP神经网络设计[J].机械工程与设计,1998,19(2)：48～50.
[58]Basheer I A, Hajmeer M. Artificial neural networks:fundamentals, computing, design, and application[J]. Journal of Microbiological Methods,2000,43(1):3～31.
[59]刘军.人工神经网络研究与发展综述[D].江西师范大学硕士学位论文,2009.
[60]王辉.人工神经网络研究与发展综述[J].人工智能及识别技术,2008,4(3)：710～711.
[61]何丽红,张元,吕运鹏.神经网络在汽车动态称重数据处理中的应用[J].自动化仪表,2007,28(5)：17～19.
[2]易玮.浅谈货车超限超载运输的危害及其治理对策[J].山西建筑,2008,34(9)：296～297.
[3]陈琦.车辆动态称重系统研究现状[J].设备管理&维修技术,2009,(3).77～80.
[4]王丹.基于ETC的车辆动态称重系统应用研究[D].长安大学硕士学位论文,2009.
[5]张鑫,郭清南,李学磊.压力传感器研究现状及发展趋势[J].电机电器技术,2004,(4)：28～29.
[6]王金斗,宋颖.压电传感技术的研究及应用[J].测控技术与仪器仪表,2008,34(8)：89～92.
[7]宋颖,王志臣,杜彦良.压电传感测试技术的应用研究进展[J].传感器与微系统,2008,27(5)：8-11.
[8]徐东宇.水泥基压电传感器的制备、性能及其在土木工程领域的应用研究[D].山东大学博士学位论文,2010.
[9]凌杰.公路动态称重系统的设计理论研究[D].长安大学博士学位论文,2001.
[10]Stephane T R. Fiber optic weigh-in-motion:looking back and ahead[J]. Optical Engineering, 1998,3326:129～137.
[11]Ansari F, Wang J. Rate sensitivity of high birefringent fiber optic sensors under largedynamic loads[J]. Lightwave Technology,1995,13(10):1992～1997.
[12]唐宇,刘传菊.光纤传感器及其研究现状[J].2009,7：17-18.
[13]黎志刚,蔡萍,周志峰.基于BP网络的汽车动态称重数据处理方法[J].微计算机信息,2006,22(82)：251～253.
[14]许嘉,蔡萍,周志峰,陈日兴.参数估计算法在汽车动态称重中的应用[J].仪器仪表与检测技术,2005,24(8)：69～71.
[15]于哲峰,杨智春.EMD技术在动态称重数据处理中的应用[J].机械科学与技术,2004,23(4)：444～446.
[16]姚恩涛,季娟,张明.两轴车辆动态称重信号分析方法研究[J].传感技术,2005,24(12)：22～24.
[17]于海燕.动态称重技术的研究[D].西安理工大学硕士学位论文,2006.
[18]程路.车辆动态称重技术研究[D].浙江大学博士学位论文,2008.
[19]ASTM, E1318-02. Committee. Standard Specification for Highway Weigh-in-motion(WIM) System with user Requirements and Test Method[S]. West Conshohocken：Ameriean Soeietyfor Testingand Materials,2002.
[20]杨卫东,刘亚蒙.动态称重系统的标准与规范[J].中国公路,2005,1：112～113.
[21]全国衡器计量技术委员会[S].JJG 907-2006动态公路车辆自动衡器鉴定规程.北京：中国计量出版社,2006.
[22]Mamlouk M S. Effect of Vehicle-pavement Interaction on Weigh-in-Motion Equipment Design[J]. International Journal of Heavy Vehicle Systems,1997,3(1):306-322.
[23]王吉忠,刘晓斌,张泰等.花纹磨光轮胎接地特性试验研究[J].农业机械学报.2001,32(2)：18～20.
[24]包学海,楚永萍,唐永明,周睿.弹性构架对车辆系统振动响应的影响[J].铁道车辆,2010,48(3)：4-7.
[25]邓学钧,孙璐.车辆-地面结构系统动力学[M].北京：人民交通出版社,1998.
[26]Grundmann H, Lieb M, Trommer E. The response of a layered half-space to traffic loads moving along its surface[J]. Archives of Applied Mechanics,1999,69(1):55-67.
[27]刘九卿.压电石英称重传感器及其在动态公路车辆称重系统中的应用[C].称重科技暨第六届称重技术研讨会.北京.2007.53～60.
[28]苏艳阳,李锐,陈宇,黄哲,何诗文,蔡天净.传感技术综述[J].数字通信,2009,36(4).20～26.
[29]谷有臣,孔英,陈若.传感器技术的发展和趋势综述[J].物理实验,2002,22(12)：40～42.
[30]李俄收,张少靖,吴文民.汽车传感器应用综述[J].汽车电器,2008,5：1～5.
[31]陈绚,杨安.综述生物传感器及发展研究前景[J].南昌高专学报,2005,1：94～96.
[32]杨兆建,王勤贤.测力传感器研究发展综述[J].山西机械,2003,1：1～3.
[33]王兴举,李进墨.压电式传感器测量电路的性能分析[J].技术与应用,2007,13(5).22～24.
[34]李金田.压电传感器与前置放大器的配接[J].传感器技术,2004,23(1)：54～59
[35]张国华.高保真运算放大器OPA604[J].器件与原件,1995,12：23～24.
[36]金春林,邱慧芳,张皆喜.AVR系列单片机C语言编程与应用实例[M].北京：清华大学出版社,2003.
[37]郭华伟,胡军科.单片机在智能检测中的应用综述[J].发展与综述,2002,1：8～15
[38]包秀荣,王楠.AVR单片机的特点及其应用[J].内蒙古科技与经济,2004,6：51～52.
[39]隋越.基于AVR单片机的应用设计实践[D].吉林大学硕士学位论文,2004.
[40]ATmegal6(L) data sheet[z].2466G-AVR-10/03.
[41]于志赣,刘国平,张旭斌.液显LCD1602模块的应用[J].计算机应用,2009,3：21～23.
[42]赵艳妮.基于VC++的电动汽车试验数据分析系统设计[D].武汉理工大学硕士学位论文,2010.
[43]龚建伟,熊光明.Visual C++/Turbo C串口通信编程实践[M].北京：电子工业出版社,2008.
[44]孙鑫,余安萍.VC++深入详解[M].北京：电子工业出版社,2006.
[45]Weeks M. Digital Signal Processing Using MATLAB and Wavelets[M]. Hingham Massachusetts American：Infinity Science Press LLC,2007.
[46]Mallat S. A Theory for Multiresolution Signal Decomposition：The Wavelet Transform[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1998,11(7)：674～692.
[47]胡广书.现代数字信号处理[M].北京：清华大学出版社,2004.
[48]蒋正言,周一届.基于小波变换的车辆动态轴重信号消噪[J].2005,13(7)：680～683.
[49]Mallat S G. A theory for multiresolution signal decomposition:the wavelet representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1989,11(7):674～693.
[50]Hecht-Nielsen R. Theory of the backpropagation neural network[C]. IEEE International Joint Conference on Neural Networks,1989,1:593～605.
[51]Wang J. Analysis and design of a recurrent neural network for linear programming[J]. IEEE Transactions on Circuits Systems I:Fundamental Theory and Application,1993,40(9): 613-618.
[52]Adeli H, Jiang X. Intelligent Infrastructure. Neural Networks, Wavelets, and Chaos Theory for Intelligent Transportation Systems and Smart Structures[M]. Boca Raton, London：CRC Press,2009.
[53]Bishop C M. Neural networks and their application[J]. Review of Scientific Instruments, 2009,65(6):1803～1832.
[54]Jackel L D, Howard R E, Graf H P, Straughn B, Denker J S. Artificial neural networks for computing[J]. Journal of Vacuum Science & Technology B:Microelectronics and Nanometer Structures,2009,4(1):61～63.
[55]周开刑,康耀红.神经网络模型及其Matlab仿真程序设计[J].北京：清华大学出版社,2005.
[56]Haykin S.神经网络原理[M].叶世伟,史忠植译.北京：机械工业出版社,2004.
[57]戚德虎,康继昌.BP神经网络设计[J].机械工程与设计,1998,19(2)：48～50.
[58]Basheer I A, Hajmeer M. Artificial neural networks:fundamentals, computing, design, and application[J]. Journal of Microbiological Methods,2000,43(1):3～31.
[59]刘军.人工神经网络研究与发展综述[D].江西师范大学硕士学位论文,2009.
[60]王辉.人工神经网络研究与发展综述[J].人工智能及识别技术,2008,4(3)：710～711.
[61]何丽红,张元,吕运鹏.神经网络在汽车动态称重数据处理中的应用[J].自动化仪表,2007,28(5)：17～19.