基于DWT的旋转机械振动故障检测方法研究  

Research on Vibration Fault Detection Method for Rotating Machinery Based on DWT

作　　者：张艳南 王达 程燕 ZHANG Yannan;WANG Da;CHENG Yan(Hangzhou Institute of Quality Metrology,Hangzhou,Zhejiang Province,310020 China;Zhejiang Provincial Highway Society,Hangzhou,Zhejiang Province,310014 China)

机构地区：[1]杭州市质量计量科学研究院,浙江杭州310020 [2]浙江省公路学会,浙江杭州310014

出　　处：《科技资讯》2025年第2期129-131,共3页Science & Technology Information

摘　　要：旋转机械振动信号包含多种频率成分,难以捕捉突变点,为此,提出基于离散小波变换(Discrete Wavelet Transform,DWT)的旋转机械振动故障检测方法。首先,对被测装置的振动信号进行检测,并对其进行必要的预处理,从而达到去除噪声的目的。其次,采用小波变换方法,实现对振动信号的多尺度分解,以提取不同频率和尺度上的特征信息,这些特征信息包含了旋转机械在不同工作状态下的振动特性。最后,基于提取的故障特征,引入注意力机制来实现对振动故障的快速、准确检测。实验结果表明,研究提出的旋转机械振动故障检测方法在突变信号检测方面表现出了显著的优势,应用效果更好。The vibration signals generated by rotating machinery contain various frequency components,making it difficult to capture sudden changes in the vibration signal and limiting the detection range.Therefore,a research was conducted on the vibration fault detection method of rotating machinery based on Discrete Wavelet Transform(DWT).Firstly,the vibration signal of the measured device is detected and necessary pretreatment is carried out to remove noise.Secondly,the wavelet transform method is used to realize the multiscale decomposition of the vibration signal to extract the feature information at different frequencies and scales.These characteristic information contains the vibrational properties of the rotating machinery in different working states.Finally,based on the extracted fault features,the attention mechanism is introduced to realize the rapid and accurate detection of vibration faults.The experimental results show that the proposed method for detecting vibration faults in rotating machinery exhibits significant advantages in detecting sudden changes in signals and has better application effects.

关 键 词：旋转机械 机械振动故障 故障检测 振动故障信号 

分 类 号：TP277[自动化与计算机技术—检测技术与自动化装置]