关键词: 量子计算, 通用量子门, 量子神经网络, 齿轮, 故障诊断

Abstract:

In order to improve the ability of gear fault diagnosis,considering the current  research of  neural network mechanism, a  quantum neuron model  was proposed based on universal quantum gate and an universal quantum gate neural network(UQGN) was established. Firstly, the input was quantum training samples after transformed. Then, quantum rotation gate and  an  universal quantum gate were used for rotation selection overturn and aggregation, and the network parameters  were  updated. Finally, the trained results were as output. The generalization performance of UQGN was proved in mathematics. The proposed  method was applied to pattern recognition of gear fault conditions. The experimental results indicate that, compared with common neural network and common quantum neural network, UQGN has better effects on generalization performance, robustness accuracy and execution time.

Key words: quantum computation, universal quantum gate, quantum neural network, gear, fault diagnosis