小波分析球磨机轴承振动信号特征提取方法

Feature Extraction Method for Ball-mill Bearing's Vibration Signals Using Wavelet Analysis

为了对球磨机磨矿过程中筒体内部负荷(填充率、料球比)进行研究,提出采用小波分析方法对球磨机轴承振动信号进行特征提取。以实验球磨机为对象,采集轴承座振动信号,经降噪处理和Welch法功率谱分析后得到频谱图,选用合适的小波函数,进行小波包分解后得到信号各频段的能量值和总能量值,再以各节点能量值作为对应内部负荷的特征向量,引入欧氏距离对不同内部负荷进行区别。通过实验证明该方法有效。

To study the fill-up rate and material-to-ball ratio of the ball-mill in grinding process, a wavelet analysis method for feature extraction of the bearing’s vibration signals of the mill was proposed. With a testing mill as the object, the ball-mill bearing vibration signals were collected. After the noise reduction processing and the power spectrum analysis based on Welch method, a spectrum map was obtained. Selecting reasonable wavelet function, the energy values of different frequency bands of the signals and their total energy values were gained after the wavelet packet decomposition. Then, with the energy value of each node as a feature vector corresponding to the internal mill load, the Euclidean distance was introduced to distinguish different mill load. The test results proved the effectiveness of this method.