基于神经网络与证据理论的煤矿通风机故障诊断

为了能够从多方面反映煤矿通风机系统状态,实现对故障模式的自动识别与准确诊断,将数据融合技术与神经网络相结合,建立通风机故障诊断系统。采用并行神经网络进行局部诊断,获得彼此独立的证据,再运用D-S证据理论融合算法对各证据进行融合,实现对通风电机故障的准确诊断。

Coal Mine Ventilation Motor Fault Diagnosis Based on Neural Network and Evidence Theory

The motor fusion diagnosis system was built for reflecting coal mine ventilation motor system state in multi-aspects,realize automatically identifying ventilation motor fault patterns and accurately diagnosing the faults by using and evidence theory.The parallel multi-neural networks were firstly used to carry on local motor fault diagnosis,then D-S evidence theory fusion algorithm was used to fuse every evidence.Thus accurate ventilation motor fault diagnosis was fulfilled in the end.