An Improved Quantum-Inspired Differential Evolution Algorithm for Deep Belief Network
An Improved Quantum-Inspired Differential Evolution Algorithm for Deep Belief Network
复制标题
一种改进的深度信念网络量子启发差分进化算法
DOI：
10.1109/tim.2020.2983233
复制
发表时间：
2020-10-01
影响因子：
5.6
通讯作者：
Song, Yingjie
中科院分区：
文献类型：
--
作者：
Deng, Wu;Liu, Hailong;Song, Yingjie
深度信念网络（DBN）是最具代表性的深度学习模型之一。然而，它的缺点是网络结构和参数基本上由经验确定。为了避免早熟收敛和提高全局搜索能力，本文提出了一种改进的量子差分进化算法，即基于Mexh小波函数、标准正态分布、自适应量子态更新和量子非门变异的量子差分进化算法。然后，利用具有全局优化能力的MSIQDE对DBN的参数进行优化，构建最优DBN模型，并进一步应用该模型提出了一种新的故障分类方法，即MSIQDE-DBN方法。最后，滚动轴承的振动数据从凯斯西储大学和一个实际的工程应用进行了验证的MSIQDE-DBN方法的性能。实验结果表明，MSIQDE具有更好的优化性能，MSIQDE-DBN可以获得更高的分类精度比其他比较方法。
Deep belief network (DBN) is one of the most representative deep learning models. However, it has a disadvantage that the network structure and parameters are basically determined by experiences. In this article, an improved quantum-inspired differential evolution (MSIQDE), namely MSIQDE algorithm based on making use of the merits of the Mexh wavelet function, standard normal distribution, adaptive quantum state update, and quantum nongate mutation, is proposed to avoid premature convergence and improve the global search ability. Then, the MSIQDE with global optimization ability is used to optimize the parameters of the DBN to construct an optimal DBN model, which is further applied to propose a new fault classification, namely MSIQDE-DBN method. Finally, the vibration data of rolling bearings from the Case Western Reserve University and a real-world engineering application are carried out to verify the performance of the MSIQDE-DBN method. The experimental results show that the MSIQDE takes on better optimization performance, and the MSIQDE-DBN can obtain higher classification accuracy than the other comparison methods.