ABSTRACT

The platform screen door system related to the safety of passengers, vehicle and station operation in rail transit is the research object. Relay, the key component of the PSD system, is selected as the breakthrough point, and the number of pull-in is used as the evaluation index of the service life of the relay. The precise and complex mapping between the influencing factors of the relay (coil resistance, pull-in voltage, release voltage, pull-in time, release time and contact resistance) and the remaining service life of the PSD system are established based on genetic algorithm to optimise BP neural network, and a new model for predicting the remaining life of the PSD is constructed. The PSD system of Guangzhou Metro Line 8 – KeCun Station is taken as the experimental test object. By comparing the BP algorithm, the PSO-BP algorithm and the GA-BP algorithm, it is demonstrated in detail how the prediction model can effectively predict the remaining service life of the PSD system with high precision, so that the equipment early warning before failure occurs to ensure the normal operation of subway lines. Experimental examples effectively prove the stability and accuracy of the GA-BP algorithm proposed.

摘要

以轨道交通中涉及乘客、车辆和车站运行安全的站台屏蔽门系统为研究对象。选取PSD系统的关键部件继电器作为切入点，以吸合次数作为继电器使用寿命的评价指标。基于遗传算法建立继电器影响因素（线圈电阻、吸合电压、释放电压、吸合时间、释放时间和接触电阻）与PSD系统剩余使用寿命之间的精确复杂映射优化BP神经网络，构建了预测PSD剩余寿命的新模型。以广州地铁8号线-客村站PSD系统为实验测试对象。通过比较BP算法，PSO-BP算法和GA-BP算法，详细演示了预测模型如何有效、高精度地预测PSD系统的剩余使用寿命，使设备在故障发生前预警，保证正常运行的地铁线路。实验实例有效地证明了所提出的GA-BP算法的稳定性和准确性。