School of Mechatronic Engineering, China University of Mining and Technology
Tiandi Shanghai Mining Equipment Technology Co., Ltd.

采煤机摇臂截割部行星齿轮的健康状态直接影响截割效率。针对采煤机截割煤岩过程中受多重冲击引起的强噪声干扰、齿轮结构复杂且传递路径多变导致故障特征难以提取等特点，提出了一种基于频谱平均降噪和相关谱的采煤机行星齿轮故障诊断方法。根据信号频谱分布特征及噪声随机特性，采用频谱平均降噪方法抑制噪声对信号频谱的干扰，获得信号降噪频谱。构建相关谱以建立少样本降噪频谱和多样本降噪频谱的内在联系，减少频谱平均降噪对样本数量的需求。采用一维卷积神经网络（1D CNN）建立相关谱与故障类别之间的精确映射关系，以相关谱为输入、故障类别为输出，实现行星齿轮故障分类识别。在DDS传动系统故障诊断实验台对基于频谱平均降噪和相关谱的采煤机行星齿轮故障诊断方法进行实验验证，结果表明该方法能够增强表征故障特征的关键频率，对正常、断齿、磨损、缺齿和裂纹5种行星齿轮健康状态信号的整体识别率达96%，在信噪比不低于15 dB时可有效、准确地实现齿轮故障诊断。

The health status of the planetary gears in the cutting section of shearer's rocker arm directly affects the cutting efficiency. The strong noise interference caused by multiple impacts during the cutting of coal and rock by the shearer, the complex gear structure, and the variable transmission path make it difficult to extract fault features. In order to solve the above problems, a fault diagnosis method for planetary gears in shearer based on spectral average denoising and correlation spectrum is proposed. Based on the distribution features of signal spectrum and the random features of noise, the spectrum average denoising method is adopted to suppress the interference of noise on the signal spectrum and obtain the signal denoising spectrum. The method constructs relevant spectra to establish the intrinsic relationship between few sample denoising spectra and multi sample denoising spectra, and reduce the demand for sample size for average spectrum denoising. The method uses a one-dimensional convolutional neural network (1D CNN) to establish an accurate mapping relationship between correlation spectra and fault categories, with correlation spectra as input and fault categories as output, to achieve planetary gear fault classification and recognition. The experimental verification of the fault diagnosis method for planetary gears in shearer based on spectral average denoising and correlation spectrum is carried out on the drivetrain diagnostics simulator transmission system fault diagnosis experimental platform. The results show that the method can enhance the key frequency that characterizes the fault features. The overall recognition rate for five types of health status signals of planetary gears, including normal, broken teeth, wear, missing teeth, and cracks, reaches 96%. Gear fault diagnosis can be effectively and accurately achieved when the signal-to-noise ratio is not less than 15 dB.

国家自然科学基金青年基金项目（52204178）。

李勇，张启志，庄德玉，等. 强噪声干扰下采煤机行星齿轮故障诊断方法[J]. 工矿自动化，2024，50（6）：142-149.

LI Yong, ZHANG Qizhi, ZHUANG Deyu, et al. Diagnosis method for planetary gear faults in shearer under strong noise interference[J]. Journal of Mine Automation，2024，50（6）：142-149.