模糊神经网络在列车制动控制中的建模及应用
|
摘要
安全和效率是铁路运输生产永恒的主题,尤其是近年来随着我国铁路事业的快速发展,铁路运输呈现重载、高速、高密度的特点,而这一切需要可靠性高的列车运行控制系统作保障。制动控制作为列车运行控制的一部分,对列车的安全性起着关键作用。现行的基于牵引计算理论的制动模式曲线和列车实际运行存在偏差,导致控制效果并不理想,因此如何构造更准确的制动控制模型成为研究的热点。
复杂系统的建模仿真,是系统建模领域的关键问题。模糊神经网络理论融合了模糊系统和神经网络二者的优势,能较好地实现复杂系统建模。本文以复杂系统建模为背景,对模糊神经网络建模方法、适合于列车制动控制建模的模糊神经网络结构及其应用进行了研究。
论文在借鉴国内外已有研究成果的基础上,围绕列车制动控制建模这一问题,主要研究了以下内容:
1.本文从复杂系统建模的观点分析了列车制动控制中所存在的模糊性问题及其产生的原因,得出将模糊神经网络引入列车制动建模是可行的。
2.本文重点研究了在制动控制系统特性不够清楚的前提下构造适合于列车制动控制的模糊神经网络结构模型。通过对标准的模糊神经网络结构进行改进,得到一个四层的改进型模糊神经网络,从理论上证明模型具有全局逼近的特性,并推导了参数对应的学习算法。然后运用改进的模型对列车制动过程进行了建模,从实际操纵的角度上分析并确定了模型的输入输出变量,使该模型更符合列车实际运行环境,这和以往的模型所采用的结构及所选用的变量不同。
3.为避免传统意义上语言变量划分太细导致模糊规则数目过多,影响网络的学习速度和精度,本文将聚类算法引入模糊神经网络结构辨识中对数据进行分类,同时结合实际操纵,确定所需规则数,兼顾了数据建模和实际操纵两方面的特点。
4.为了验证改进的网络结构用于列车制动控制建模的有效性,本文以一列货物列车为例进行建模和计算,数值计算结果表明改进的模糊神经网络模型具有运算速度快、精度较高的特点;通过运用Matlab中Simulink模块对列车制动过程进行仿真,证明改进的模型运用于列车制动控制的建模是可行的。
Safety and efficiency are eternal themes for railway transportation, especially as the rapid development of China's railway. In recent years, the railway transportation has shown heavy, high-speed, high-density characteristics, all which need a high reliable train control system as a guarantee. Braking control, as a part of the train control, plays a key role in train safety. But there are some errors between the braking mode curve based on train-traction-calculation theory and the actual operation of the train, which results in that the effect of the control is not good. Therefore, how to construct a more accurate train braking control model becomes a hot research in recent years.
Complex systems modeling and simulation is a key issue in systems modeling field. Fuzzy Neural Network(FNN) integrated both advantages of fuzzy systems and neural networks, can better realize complex systems modeling. In this paper, the method of FNN modeling, FNN structure which is suitable for modeling of the train braking control and its applications have been studied, which is based on the background of complex systems modeling.
This paper, based on the research at home and abroad, is on the issue of train braking control modeling, and the main research contents are as follows:
1. The fuzzy problems existed in the train braking control and its causes have been analyzed from the perspective of complex systems modeling, and it is drawn that the FNN used in the train braking modeling is feasible.
2. In this paper, it is focused on how to construct a suitable FNN model for train braking control under the premise that the characteristics of the braking control system is not clear enough. Then the standard FNN has been improved and an improved four layers fuzzy neural network was acquired with its learning algorithm deduced, which is proved that this model has the characteristics of the overall approach in theory .Afterwards, we used the improved model to the train braking process and determine the input and output variables from practical point of view on the manipulation, which made the model is more adapted to the actual operating environment. This is different from the previous model structure and the variables selected are also different.
3. Traditionally, too many language variables often lead too many fuzzy rules, and they have impact on network learning speed and accuracy. To avoid it, K-means clustering algorithm has been introduced to the FNN structure identification and been used for the data classification. At the same time, the actual manipulation is also considered combined with the classification to determine the necessary rules. It both takes into account the actual data modeling and the characteristics of the manipulation.
4. In order to verify the validity of the improved network structure used in the train braking control modeling, in this paper, a fright train was used as an example for modeling and calculation. The numerical results show that improved fuzzy neural network model has the characteristics of high speed and precision. Then we used the Matlab module- Simulink to simulate the train braking process, and it proved that the improved model used in the train braking control is feasible.
复杂系统的建模仿真,是系统建模领域的关键问题。模糊神经网络理论融合了模糊系统和神经网络二者的优势,能较好地实现复杂系统建模。本文以复杂系统建模为背景,对模糊神经网络建模方法、适合于列车制动控制建模的模糊神经网络结构及其应用进行了研究。
论文在借鉴国内外已有研究成果的基础上,围绕列车制动控制建模这一问题,主要研究了以下内容:
1.本文从复杂系统建模的观点分析了列车制动控制中所存在的模糊性问题及其产生的原因,得出将模糊神经网络引入列车制动建模是可行的。
2.本文重点研究了在制动控制系统特性不够清楚的前提下构造适合于列车制动控制的模糊神经网络结构模型。通过对标准的模糊神经网络结构进行改进,得到一个四层的改进型模糊神经网络,从理论上证明模型具有全局逼近的特性,并推导了参数对应的学习算法。然后运用改进的模型对列车制动过程进行了建模,从实际操纵的角度上分析并确定了模型的输入输出变量,使该模型更符合列车实际运行环境,这和以往的模型所采用的结构及所选用的变量不同。
3.为避免传统意义上语言变量划分太细导致模糊规则数目过多,影响网络的学习速度和精度,本文将聚类算法引入模糊神经网络结构辨识中对数据进行分类,同时结合实际操纵,确定所需规则数,兼顾了数据建模和实际操纵两方面的特点。
4.为了验证改进的网络结构用于列车制动控制建模的有效性,本文以一列货物列车为例进行建模和计算,数值计算结果表明改进的模糊神经网络模型具有运算速度快、精度较高的特点;通过运用Matlab中Simulink模块对列车制动过程进行仿真,证明改进的模型运用于列车制动控制的建模是可行的。
Safety and efficiency are eternal themes for railway transportation, especially as the rapid development of China's railway. In recent years, the railway transportation has shown heavy, high-speed, high-density characteristics, all which need a high reliable train control system as a guarantee. Braking control, as a part of the train control, plays a key role in train safety. But there are some errors between the braking mode curve based on train-traction-calculation theory and the actual operation of the train, which results in that the effect of the control is not good. Therefore, how to construct a more accurate train braking control model becomes a hot research in recent years.
Complex systems modeling and simulation is a key issue in systems modeling field. Fuzzy Neural Network(FNN) integrated both advantages of fuzzy systems and neural networks, can better realize complex systems modeling. In this paper, the method of FNN modeling, FNN structure which is suitable for modeling of the train braking control and its applications have been studied, which is based on the background of complex systems modeling.
This paper, based on the research at home and abroad, is on the issue of train braking control modeling, and the main research contents are as follows:
1. The fuzzy problems existed in the train braking control and its causes have been analyzed from the perspective of complex systems modeling, and it is drawn that the FNN used in the train braking modeling is feasible.
2. In this paper, it is focused on how to construct a suitable FNN model for train braking control under the premise that the characteristics of the braking control system is not clear enough. Then the standard FNN has been improved and an improved four layers fuzzy neural network was acquired with its learning algorithm deduced, which is proved that this model has the characteristics of the overall approach in theory .Afterwards, we used the improved model to the train braking process and determine the input and output variables from practical point of view on the manipulation, which made the model is more adapted to the actual operating environment. This is different from the previous model structure and the variables selected are also different.
3. Traditionally, too many language variables often lead too many fuzzy rules, and they have impact on network learning speed and accuracy. To avoid it, K-means clustering algorithm has been introduced to the FNN structure identification and been used for the data classification. At the same time, the actual manipulation is also considered combined with the classification to determine the necessary rules. It both takes into account the actual data modeling and the characteristics of the manipulation.
4. In order to verify the validity of the improved network structure used in the train braking control modeling, in this paper, a fright train was used as an example for modeling and calculation. The numerical results show that improved fuzzy neural network model has the characteristics of high speed and precision. Then we used the Matlab module- Simulink to simulate the train braking process, and it proved that the improved model used in the train braking control is feasible.
引文
[1]毛保华.城市轨道交通系统运营管理[M].北京.人民交通出版社.2006.
[2]毛保华.列车运行计算与没计[M].北京.人民交通出版社.2008.
[3]郭齐胜,杨秀月,王杏林,徐享忠,段莉.系统建模[M].北京:国防工业出版社,2006.
[4]李人厚.智能控制理论和方法[M].西安:西安电子科技大学出版社.1999.
[5]张乃尧,阎平凡.神经网络与模糊控制[M].清华大学出版社,1998.
[6]刘贺文,赵海东,贾利民.列车运行自动控制算法的研究[J].中国铁道学报.2000.21(4).38-43.
[7]唐涛,黄良骥.列车自动驾驶系统控制算法综述[J].铁道学报.2003.25(2).98-102.
[8]Li Keping,Gao Ziyou,Ning Bin.Cellular automaton model for railway traffic[J].Journal of Computational Physics.2005(209).179-192.
[9]刘海东,毛保华,丁勇,何天健.列车自动驾驶仿真系统算法及其实施研究[J].系统仿真学报.2005.3(17).577-580.
[10]王立新.模糊系统与模糊控制教程[M].北京:清华大学出版社.2003.
[11]Zadeh,L.A.Outline of a new approach to the analysis of complex systems and decision processes[J].IEEE Trans.on Systems,Man,and Cybern.1973.3(1).28-44.
[12]Mamdani,E.H.,S.Assilian.An experiment in linguistic synthesis with a fuzzy logic controller [J].Int.J.Man Mach.Studies.1975.7(1).1-13.
[13]Yasunobu,S.Fuzzy.Control for automatic train operation system[A].Proc.4th IFAC/IFIP/IFORS Int.Congress on Congress on Control in Transportation Systems.Baden-Baden.1983.
[14]Yasunobu S,et al.Application of Predictive Fuzzy Control to Automatic Train Operation Controller[A].In:Proc.of IECON'84[C]1984.657-662.
[15]Yasunobu,S.,S.Sekino.Automatic train operation and automatic crane operation systems based on predictive fuzzy control[A].Proc.2nd IFSA Congress,Tokyo.Japan.1987:835-838.
[16]Oshima H,et al.Automatic train operation system based on predictive fuzzy control[A].In:Artificial Intelligence for Industrial Applications.1988.IEEEAI'88.Proceedings of the International Workshop[C].1988.485-489.
[17]贾利民.列车运行过程的智能控制[J].中国铁道科学,1992,(1):65-78.
[18]张建华.新型模糊预测控制及其在列车自动运行过程中的应用[J].中国铁道科学报.1996.17(4).101-109.
[19]Feng Xiaoyun,et al.The Research of Fuzzy Prediction and Its Application in Train's Automatic Control[A].In:Autonomous Decentralized Systems.2000.Proceedings.2000 International Work-shoo[C1.2000.82-86.
[20]冯晓云.模糊预测控制及其在列下白动驾驶中的应用研究[D].西南交通大学博士学位论文.2001.
[21]张琦,王建英.基于神经网络的高速列车运行模拟系统的研究[J].中国铁道科学报,1998,19(3):18-25.
[22]Sekine S,et al.Application of Fuzzy Neural Network control to Automatic Train Operation and Tuning of Its Control Rules[A].In:Volume:4.Fuzzy Systems.1995.Proceedings of 1995 IEEE International Conference[c].1995.1741-1746.
[23]Wang Jing,et al.Direct Fuzzy Neural Control with Application to Automatic Train Opera-tion[J].Control Theory and Applications.1998.15(3).391-399.
[24]武妍,施鸿宝.基丁神经网络的地铁列车运行过程的集成型智能控制[J].铁道学报,2000.22(3).10-15.
[25]武妍,施鸿宝.神经网络与模糊逻辑的集成及其在列车控制系统中的应用[J].计算机应用研究.2000.(6).87-90.
[26]腾振宇,武妍.基于再励学习的地铁列车运行过程的模糊自适应控制[J].计算机工程.2003.29(20).63-65.
[27]吴桂云,武妍.一种基于模糊神经网络的正则化学习算法的地铁列车运行控制[J].计算机工程与应用.2004.(2).201-204.
[28]王卓,王艳辉,贾利民,李平.基于ANFIS的高速列车制动控制仿真研究[J].铁道学报.2005.27(3).113-117.
[29]Chang C S,Sim S S.Optimizing Train Movements through Coast Control Using Genetic Algorithms[J].IEE Proc.-Electr.Power Appl.1997.144(1).65-73.
[30]Chang C S,et al.Pareto-Optimal Set Based Multiobjective Tuning of Fuzzy Automatic Train Operation for Mass Transit System[J].IEE Proc.-Electr.PowerAppl.1999.146(5).577-583.
[31]黄良骥,程琳香,唐涛.遗传算法模糊神经网络在列车驾驶中的应用[J].辽宁工程技术大学学报(自然科学版).2001.20(5).640-643.
[32]汪希时.智能铁路运输系统[M].北京.中国铁道出版社.2004年.
[33]王士同.模糊系统.模糊神经网络及应用程序设计[M].上海.上海科学技术文献出版社.1997.
[34]李国勇等.智能控制及其MATLAB实现[M].北京.电子工业出版社.2005.
[35]蔡自兴,徐光佑.人工智能及其应用[M].北京.清华大学出版社.2004.
[36]赵振宇,徐用懋.模糊理论和神经网络基础与应用[M].北京.清华大学出版社.1995.
[37]张智星,孙春在,水谷英二等.神经模糊和软计算[M].两安.两安交通大学出版社.2000.
[38]铁道部.列车牵引计算规程[S].北京.中国铁道出版社.1998.
[39]铁道部.机车操作规程[S].北京.中国铁道出版社.2000.
[40]铁道部.铁路技术管理规程[S].北京:中国铁道出版社,2000.
[41]李群.铁路列车运行安全模糊神经网络控制方法分析[D].北方交通大学博士论文.1996.
[42]刘俊强.基于模糊神经网络的仿真系统建模方法及其应用研究[D].哈尔滨工业大学博士学位论文.2000.
[43]王熙照,王亚东,湛燕,袁方.学习特征权值对K-均值聚类算法的优化[J].计算机研究与发展.2003.40(6).869-873.
[44]吴海俊,丁勇,毛保华,姚宪辉.基于模糊神经网络的列车制动控制智能算法研究[J].交通与计算机.2008.(1).55-57.
[45]郑阿奇,曹戈.MATLAB实用教程(第2版)[M].北京:电子工业出版社.2007.
[2]毛保华.列车运行计算与没计[M].北京.人民交通出版社.2008.
[3]郭齐胜,杨秀月,王杏林,徐享忠,段莉.系统建模[M].北京:国防工业出版社,2006.
[4]李人厚.智能控制理论和方法[M].西安:西安电子科技大学出版社.1999.
[5]张乃尧,阎平凡.神经网络与模糊控制[M].清华大学出版社,1998.
[6]刘贺文,赵海东,贾利民.列车运行自动控制算法的研究[J].中国铁道学报.2000.21(4).38-43.
[7]唐涛,黄良骥.列车自动驾驶系统控制算法综述[J].铁道学报.2003.25(2).98-102.
[8]Li Keping,Gao Ziyou,Ning Bin.Cellular automaton model for railway traffic[J].Journal of Computational Physics.2005(209).179-192.
[9]刘海东,毛保华,丁勇,何天健.列车自动驾驶仿真系统算法及其实施研究[J].系统仿真学报.2005.3(17).577-580.
[10]王立新.模糊系统与模糊控制教程[M].北京:清华大学出版社.2003.
[11]Zadeh,L.A.Outline of a new approach to the analysis of complex systems and decision processes[J].IEEE Trans.on Systems,Man,and Cybern.1973.3(1).28-44.
[12]Mamdani,E.H.,S.Assilian.An experiment in linguistic synthesis with a fuzzy logic controller [J].Int.J.Man Mach.Studies.1975.7(1).1-13.
[13]Yasunobu,S.Fuzzy.Control for automatic train operation system[A].Proc.4th IFAC/IFIP/IFORS Int.Congress on Congress on Control in Transportation Systems.Baden-Baden.1983.
[14]Yasunobu S,et al.Application of Predictive Fuzzy Control to Automatic Train Operation Controller[A].In:Proc.of IECON'84[C]1984.657-662.
[15]Yasunobu,S.,S.Sekino.Automatic train operation and automatic crane operation systems based on predictive fuzzy control[A].Proc.2nd IFSA Congress,Tokyo.Japan.1987:835-838.
[16]Oshima H,et al.Automatic train operation system based on predictive fuzzy control[A].In:Artificial Intelligence for Industrial Applications.1988.IEEEAI'88.Proceedings of the International Workshop[C].1988.485-489.
[17]贾利民.列车运行过程的智能控制[J].中国铁道科学,1992,(1):65-78.
[18]张建华.新型模糊预测控制及其在列车自动运行过程中的应用[J].中国铁道科学报.1996.17(4).101-109.
[19]Feng Xiaoyun,et al.The Research of Fuzzy Prediction and Its Application in Train's Automatic Control[A].In:Autonomous Decentralized Systems.2000.Proceedings.2000 International Work-shoo[C1.2000.82-86.
[20]冯晓云.模糊预测控制及其在列下白动驾驶中的应用研究[D].西南交通大学博士学位论文.2001.
[21]张琦,王建英.基于神经网络的高速列车运行模拟系统的研究[J].中国铁道科学报,1998,19(3):18-25.
[22]Sekine S,et al.Application of Fuzzy Neural Network control to Automatic Train Operation and Tuning of Its Control Rules[A].In:Volume:4.Fuzzy Systems.1995.Proceedings of 1995 IEEE International Conference[c].1995.1741-1746.
[23]Wang Jing,et al.Direct Fuzzy Neural Control with Application to Automatic Train Opera-tion[J].Control Theory and Applications.1998.15(3).391-399.
[24]武妍,施鸿宝.基丁神经网络的地铁列车运行过程的集成型智能控制[J].铁道学报,2000.22(3).10-15.
[25]武妍,施鸿宝.神经网络与模糊逻辑的集成及其在列车控制系统中的应用[J].计算机应用研究.2000.(6).87-90.
[26]腾振宇,武妍.基于再励学习的地铁列车运行过程的模糊自适应控制[J].计算机工程.2003.29(20).63-65.
[27]吴桂云,武妍.一种基于模糊神经网络的正则化学习算法的地铁列车运行控制[J].计算机工程与应用.2004.(2).201-204.
[28]王卓,王艳辉,贾利民,李平.基于ANFIS的高速列车制动控制仿真研究[J].铁道学报.2005.27(3).113-117.
[29]Chang C S,Sim S S.Optimizing Train Movements through Coast Control Using Genetic Algorithms[J].IEE Proc.-Electr.Power Appl.1997.144(1).65-73.
[30]Chang C S,et al.Pareto-Optimal Set Based Multiobjective Tuning of Fuzzy Automatic Train Operation for Mass Transit System[J].IEE Proc.-Electr.PowerAppl.1999.146(5).577-583.
[31]黄良骥,程琳香,唐涛.遗传算法模糊神经网络在列车驾驶中的应用[J].辽宁工程技术大学学报(自然科学版).2001.20(5).640-643.
[32]汪希时.智能铁路运输系统[M].北京.中国铁道出版社.2004年.
[33]王士同.模糊系统.模糊神经网络及应用程序设计[M].上海.上海科学技术文献出版社.1997.
[34]李国勇等.智能控制及其MATLAB实现[M].北京.电子工业出版社.2005.
[35]蔡自兴,徐光佑.人工智能及其应用[M].北京.清华大学出版社.2004.
[36]赵振宇,徐用懋.模糊理论和神经网络基础与应用[M].北京.清华大学出版社.1995.
[37]张智星,孙春在,水谷英二等.神经模糊和软计算[M].两安.两安交通大学出版社.2000.
[38]铁道部.列车牵引计算规程[S].北京.中国铁道出版社.1998.
[39]铁道部.机车操作规程[S].北京.中国铁道出版社.2000.
[40]铁道部.铁路技术管理规程[S].北京:中国铁道出版社,2000.
[41]李群.铁路列车运行安全模糊神经网络控制方法分析[D].北方交通大学博士论文.1996.
[42]刘俊强.基于模糊神经网络的仿真系统建模方法及其应用研究[D].哈尔滨工业大学博士学位论文.2000.
[43]王熙照,王亚东,湛燕,袁方.学习特征权值对K-均值聚类算法的优化[J].计算机研究与发展.2003.40(6).869-873.
[44]吴海俊,丁勇,毛保华,姚宪辉.基于模糊神经网络的列车制动控制智能算法研究[J].交通与计算机.2008.(1).55-57.
[45]郑阿奇,曹戈.MATLAB实用教程(第2版)[M].北京:电子工业出版社.2007.