旋转机械故障诊断的量子神经网络算法

A Quantum Neural Networks Fault Diagnosis Algorithm for Rotating Machinery

针对故障模式之间存在交叉数据的诊断不确定问题,将多层激励函数的量子神经网络引入多传感器信息融合之中,提出一种基于量子神经网络的多传感器信息融合故障诊断算法。并将其应用到旋转机械故障诊断中,通过测试被诊断设备的振动速度和加速度信号,求出两传感器对各故障模式的故障隶属度,利用多层激励函数的量子神经网络进行信息融合,得到融合的各故障模式隶属度值,确定真正的故障模式,提高了故障诊断的准确率。

An information fusion fault diagnosis algorithm based on the quantum neural networks is presented for the pattern recognition with overlapping classes, and it is used in the fault diagnosis of rotating machinery. By measuring the speed and acceleration of the vibration, the membership function assignment of two sensors to all fault patterns is calculated, and the fusion membership function assignment is gained by using the 5-level transfer function quantum neural networks（QNN）, then according to the fusion data, the fault pattern is found. Comparing the diagnosis results based on separate original data with the ones based on QNN fused data, it is shown that the quantum fusion fault diagnosis method is more accurate.