基于近似熵和LCD-KELM的滚动轴承故障诊断

摘要

由于提取滚动轴承的非平稳非线性信号特征较为困难,强噪声背景下难以诊断早期故障,故而提出一种基于局部特征尺度分解(Local Characteristic-scale Decomposition,LCD)和核极限学习机(Kernel Extreme Learning Machine,KELM)的智能诊断方法(LCD_KELM).该方法首先对信号进行LCD分解,将其分解成多个內禀尺度函数(Intrinsic Scale Component,ISC),选取包含有效频率成分的ISC并计算其近似熵值(Approximate Entropy,ApEn),使用KELM对随机选取的近似熵值进行训练,保存训练参数后,利用剩余的近似熵值进行测试,实验结果表明LCD_KELM具有较高的诊断准确率,能够对滚动轴承运行状态进行高精度诊断,从而判断滚动轴承的运转状况.%In the strong noise background,it is difficult to extract the non-stationary nonlinear signal features of rolling bearings.Therefore,an LCD-KELM intelligent diagnostic method based on local characteristic-scale decomposition(LCD) and kernel extreme learning machine(KELM)is proposed.Firstly,the measured vibration signals are processed with LCD and decomposed into a series of intrinsic scale components (ISC). Then, a number of ISCs containing valid information components are selected and their approximate entropies (ApEns) are computed. And the KELM is used to train the randomly selected ApEns.After saving the training parameters, the remaining ApEns are used to diagnose the faults.The experimental results show that the LCD-KELM has a high diagnostic accuracy,can effectively diagnose the rolling bearings and judge the operation state of the rolling bearings.