通用量子门神经网络在齿轮故障诊断中的应用

为进一步提高齿轮故障诊断能力,结合目前神经网络机理的研究进展,建立了一种基于通用量子门的量子神经元模型,提出了通用量子门神经网络(universal  quantum  gate neural network,UQGN)算法。首先,该算法将转换后的量子态训练样本作为输入。然后,利用量子旋转门和通用量子门完成旋转、选择、翻转和聚合等一系列操作，并完成网络参数的更新。最后，将训练后的结果输出。在数学上，证明了UQGN算法的泛化能力。利用该算法对齿轮的正常、齿面磨损、齿根裂纹和断齿4种情况进行了模式识别。实验结果表明，与普通神经网络和普通量子神经网络相比，UQGN算法在泛化性能、鲁棒性、准确率和执行时间等方面具有较好的效果。

Application of Universal Quantum Gate Neural Network in Gear Fault Diagnosis

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.