Accurate judgment of gear working state is essential to the normal operation of mechanical equipment. To effectively extract the dynamic features representing the gear state from the vibration signals, this paper proposes refined composite hierarchical fluctuation dispersion entropy (RCHFDE), where the composite hierarchical decomposition is employed to replace the traditional hierarchical decomposition to improve the performance of HFDE. Combining RCHFDE and manifold learning, a new gear fault diagnosis method is proposed. Firstly, RCHFDE is used to extract the original fault features. After that, optimized discriminant diffusion maps analysis is adopted to map high-dimensional features to low-dimensional subsets. Finally, the low-dimensional features are input into optimized kernel extreme learning machine to identify different fault states of gear. The experimental results show that, compared with other contrastive methods, the proposed method enjoys better performance, which can effectively complete the determination of different gear fault states.

准确判断齿轮工作状态对机械设备的正常运行至关重要。为了有效地从振动信号中提取代表齿轮状态的动态特征，本文提出了精细复合层次波动色散熵（RCHFDE），其中复合层次分解被用来代替传统的层次分解，以提高HFDE的性能。结合RCHFDE和流形学习，提出了一种新的齿轮故障诊断方法。首先利用RCHFDE提取原始故障特征。之后，采用优化判别扩散图分析将高维特征映射到低维子集。最后，将低维特征输入到优化的内核极限学习机中，识别齿轮的不同故障状态。实验结果表明，与其他对比方法相比，该方法具有更好的性能，可以有效地完成对不同齿轮故障状态的判断。