摘要
近年来,轨道电路分路不良已成为电务部门安全整治的严重问题之一。针对站内25Hz相敏轨道电路分路不良,建立预警指标体系,设计轨道电路分路不良BP神经网络预警模型,并进行故障危险性评价及预测预警。预警结果表明,采用BP神经网络进行轨道电路分路不良故障预警时,将预警指标进行数据的归一化处理后输入到已训练好的网络中,可以在较短的时间内得出可靠的预警结果。该预警方法较现场所采用的传统预警方法,即设置数条轨道电压警线判断分路不良发生与否而实现报警的方法效率高,对现场轨道电路故障维修具有一定的参考价值和指导意义。
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 25Hz phase detecting track circuit, we established the prewarning index system, designed the prewarning model by using the BP neural network in the poor shunting of the track circuit, assessed the faults’ risks and realized the prewarning. The prewarning result shows that, by inputting the normalized prewarning index data into the trained network, a credible prewarning result can be obtained in a short time. Compared with the traditional prewarning 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.
出处
《计算机工程与科学》
CSCD
北大核心
2013年第2期159-163,共5页
Computer Engineering & Science
基金
国家自然科学基金资助项目(61164010)
甘肃省自然科学基金资助项目(1010RJZA064)