中文摘要：

在闭塞区间主流设备越来越多的采用ZPW-2000A型无绝缘轨道电路的背景下，针对单一故障诊断方法的诊断精度偏低问题，提出基于信息融合的故障诊断模型和故障诊断方法。该方法分别用BP神经网络和模糊综合评判对轨道电路进行故障诊断，然后将这2种方法的诊断结果作为D—S证据理论的证据体，利用神经网络输出和模糊综合评判输出来构造D—S证据理论中的概率分配，最后利用D—S证据理论将BP神经网络和模糊综合评判对轨道电路的故障诊断结果在决策级进行融合，诊断轨道电路是否有故障并判断故障的模式。仿真结果表明：该诊断方法具有较高的故障诊断精度，诊断结论的可信度有明显提高。

英文摘要：

Based on the fact that there are more and more mainstream equipment using ZPW -2000A track cir- cuit, and the single fault diagnosis method shows low precision, the fault diagnosis method based on the module of information fusion was proposed. This method works as follows ： Firstly, the fault is diagnosed by using the BP neural network and fuzzy comprehensive evaluation, then the diagnostic results of these two methods are seen as the evidence body in D - S evidence theory, and the probability assignment of D - S evidence theory is structured by the output of the neural network and the fuzzy comprehensive evaluation. At last by the D - S evidence theo- ry, the diagnosis result through using BP -neural network and fuzzy comprehensive evaluation is then fused on the decision - level so as to judge whether the track suit indicates that this diagnostic method has a high result has been obviously improved. circuit has fault and the type of the fault. The simulation re- accuracy of fault diagnosis, and the credibility of diagnostic result has been obviously improved.