YANG Yang1,2, CHEN Guang-wu1,2, WANG Jing-wen3, LI Cheng-dong4
（1. Automatic Control Research Institute, Lanzhou Jiaotong University, Lanzhou 730070, China；2. Gansu Provincial Key Laboratory of Traffic Information Engineering and Control, Lanzhou 730070, China；3. Gansu Provincial Education Examinations Authority, Lanzhou 730070, China；4. CASCO Signal Ltd., Beijing 100160, China）
Abstract： Train positioning is the key to ensure the transportation and efficient operation of the railway. Due to the low accuracy and the poor real-time of the train positioning, a train positioning system based on global navigation satellite system/inertial measurement unit/odometer (GNSS/IMU/ODO) combination framework and a train integrated positioning method based on grey neural network are put forward. A data updating method based on the established grey prediction model of train positioning is put forward, which uses the accumulation and summary of the grey theory for the rough prediction of the data. The purpose of the method is to reduce the noise of the original data. Moreover, the radial basis function (RBF) neural network is introduced to correct residual sequence of the grey prediction model. Compared with the single model calibration, this method can make full use of the advantages of each model, thus getting a high positioning accuracy in the case of small samples and poor information. Experiments show that the method has good real-time performance and high accuracy, and has certain application value.
Key words： rail transport; GNSS/IMU/ODO; grey neural network; train positioning
CLD number： U284.48 Document code： A
Article ID： 1674-8042（2019）02-0143-07 doi： 10.3969/j.issn.1674-8042.2019.02.006
References
［1］Fan Y M, Cai B G, Wang J, et al. Research on Beidou-GYRO integrated positioning based track occupancy discrimination method. Journal of the China Railway Society, 2013, 35(9)： 45-46.
［2］Liu J, Cai B G, Wang J. Status and development of satellite navigation system based train positioning technology. Journal of Central South University (Science and Technology), 2014, 45(11)： 4033-4042.
［3］Khaleghi B, Khamis A, Karray F O, et al. Multisensor data fusion： a review of the state-of-the-art. Information Fusion, 2013, 14(1)： 28-44.
［4］Wei M, Chen M, Zhou D. Multi-sensor information based remaining useful life prediction with anticipated performance. IEEE Transactions on Reliability, 2013, 62(1)： 183-198.
［5］Liu J, Cai B G, Wang J, et al. Study on wheel diameter calibration method in integrated train positioning based on gray theory. Journal of the China Railway Society, 2011, 33(5)： 54-59.
［6］Yang X H, Guo S X, Zhang Y H, et al. A sort of new energy consumption forecast method. In： Proceedings of World Congress on Intelligent Control & Automation, Chongqing, 2008.
［7］Zhang Y, Yang J, Jiang H. Machine tool thermal error modeling and prediction by grey neural network. International Journal of Advanced Manufacturing Technology, 2012, 59(9-12)： 1065-1072.
［8］Wen H, Xie W, Pei J, et al. An incremental learning algorithm for the hybrid RBF-BP network classifier. EURASIP Journal on Advances in Signal Processing, 2016, (1)： 57.
［9］Ye G Q, Li W G, Wan H. Study of RBF neural network based on PSO algorithm in nonlinear system identification. In： Proceedings of International Conference on Intelligent Computation Technology & Automation, IEEE, 2016.
［10］Chen H, Gong Y, Hong X. Online modeling with tunable RBF network. IEEE Transactions on Cybernetics, 2013, 43(3)： 935-947.
［11］Ma J J, You J X, Chen Z. Grey neural network model based on modified particle swarm optimization algorithm an its application. Journal of Tongji University (Natural Science), 2012, 40(5)： 740-743.
［12］Chen X, Wang T, Liang W. General aircraft material demand forecast based on PSO-BP neural network. International Journal of Control and Automation, 2016, 9(5)： 407-418.
［13］Azimifar Z, Yazdian-Dehkordi M. Novel N-scan GM-PHD-based approach for multi-target tracking. IET Signal Processing, 2016, 10(5)： 493-503.
基于灰色神经网络的列车组合定位方法研究
杨扬1,2， 陈光武1,2， 王婧雯3， 李成东4
（1. 兰州交通大学 自动控制研究所， 甘肃 兰州 730070； 2. 甘肃省高原交通信息工程及控制重点实验室， 甘肃 兰州 730070； 3. 甘肃省教育厅教育考试院， 甘肃 兰州 730070； 4.卡斯柯信号有限公司, 北京 100160）
摘要： 列车定位是保障铁路运输和高效运营的关键。 针对我国铁路列车定位精度低、 实时性差的问题， 提出了一种基于GNSS/IMU/ODO组合的列车定位系统框架。 同时提出一种基于灰色神经网络的列车组合定位方法。 该方法建立了列车定位灰色预测模型， 利用灰色理论累加求和特性对数据进行粗预测处理， 以减小原始数据的噪声， 在此基础上引入RBF神经网络对灰色预测模型的残差序列进行修正。 与单一模型校正相比， 该方法能充分利用各个模型的优点， 在小样本、 贫信息的情况下依然可以获得很高的定位精度。 实验证明该方法实时性好、 精度高， 具有一定的应用价值。
关键词： 铁路运输； GNSS/IMU/ODO； 灰色神经网络； 列车定位
引用格式：YANG Yang, CHEN Guang-wu, WANG Jing-wen, et al. Research on train integrated positioning based on grey neural network. Journal of Measurement Science and Instrumentation, 2019, 10（2）： 143-149. ［doi： 10.3969／j.issn.1674-8042.2019.02.006］
[full text view]
