文献类型：期刊文献

中文题名：基于SSA-SVD降噪和卷积神经网络的行星齿轮箱故障诊断研究

英文题名：Research on Fault Diagnosis of Planetary Gearbox Based on SSA-SVD Noise Reduction and Convolution Neural Network

作者：张亦伟[1];周邵萍[1];王伟[2];杨鑫锐[3];戚知宽[1]

机构：[1]华东理工大学机械与动力工程学院,上海200237;[2]中船重工(重庆)西南装备研究院有限公司,重庆401123;[3]重庆清平机械有限责任公司,重庆401123

年份：2023

卷号：60

期号：1

起止页码：55

中文期刊名：化工设备与管道

外文期刊名：Process Equipment & Piping

收录：CSTPCD;;北大核心:【北大核心2020】；

语种：中文

中文关键词：行星齿轮箱;奇异值分解;麻雀搜索;卷积神经网络;故障诊断

外文关键词：planetary gearbox;singular value decomposition;sparrow search algorithm;convolution neural network,;fault diagnosis

摘要：行星齿轮箱作为重要的机械传动部件,其健康运行关系着整个工程机组的安全运作。卷积神经网络常用于解决行星齿轮箱故障分类问题,但由于实际监测中有各种噪声源的存在,振动信号成分复杂,信噪比下降,仅仅使用卷积神经网络进行故障诊断效果不佳。因此提出一种麻雀搜索算法优化的奇异值分解降噪方案,采用该方案对监测的振动信号进行降噪处理,突出低频的故障特征,结合卷积神经网络实现对含噪声振动信号的故障诊断。实验结果表明,两种方法结合可使卷积神经网络模型收敛速度更快,并将诊断准确率提升至97.43%。
As an important mechanical transmission component,the healthy operation of planetary gear box is related to the safe operation of the entire engineering unit.Convolution neural network(CNN)is often used to solve the problem of planetary gearbox fault classification.However,due to the existence of various noise sources in the actual monitoring,the vibration signal components are complex,and the signal-to-noise ratio is reduced.Only using convolution neural network for fault diagnosis is not effective.Therefore,in this paper,a Singular Value Decomposition(SVD)noise reduction scheme optimized by the Sparrow Search Algorithm(SSA)was proposed.which is used to denoise the monitored vibration signal,highlight the low-frequency fault characteristics,and combine with convolution neural network to realize fault diagnosis of noisy vibration signal.The experimental results showed that the combination of the two methods could make the convolution neural network model converge faster and improve the diagnostic accuracy to 97.43%.