计算机工程与科学2013，Vol.35Issue(2)：159-163,5.DOI:10.3969/j.issn.1007-130X.2013.02.028
BP神经网络在轨道电路分路不良预警中的应用
Application of the BP neural network in the pre-warning of the poor shunting of the track circuit
摘要
Abstract
In recent years, the poor shunting of the track circuit has been one of the serious problems in Railway Signaling & Telecommunication Department. Aiming at this problem in 25 Hz phase detecting track circuit, we established the pre-warning index system, designed the pre-warning model by u-sing the BP neural network in the poor shunting of the track circuit, assessed the faults' risks and realized the pre-warning. The pre-warning result shows that, by inputting the normalized pre-warning index data into the trained network, a credible pre-warning result can be obtained in a short time. Compared with the traditional pre-warning method that set several voltage lines to realize the alarm function in order to judge if the poor shunting of track circuit has happened, the proposed method has higher efficiency. It offers a certain reference value and guide significance for the maintenance of the track circuit.关键词
轨道电路/分路不良/预警/BP神经网络/Levenberg-Marquardt算法Key words
track circuit/poor shunting/pre-warning/BP neural network/Levenberg-Marquardt algorithm分类
信息技术与安全科学引用本文复制引用
米根锁,王彦快,马学霞..BP神经网络在轨道电路分路不良预警中的应用[J].计算机工程与科学,2013,35(2):159-163,5.基金项目
国家自然科学基金资助项目(61164010) （61164010）
甘肃省自然科学基金资助项目(1010RJZA064) （1010RJZA064）
