信息熵与优化LS-SVM的轴承性能退化模糊粒化预测

为了提高滚动轴承性能退化指标的预测精度,得到性能退化指标的一个预测范围,本文提出信息熵与优化最小二乘支持向量机(LS-SVM)的轴承性能退化趋势模糊粒化预测。首先利用信息熵理论提取轴承信号的性能退化指标序列,再利用模糊信息粒化理论对该性能退化指标序列进行模糊信息粒化;然后将粒化后的数据输入给LS-SVM进行回归预测,并采用粒子群算法(PSO)优化LS-SVM的惩罚参数和核函数参数;最后根据实测值和预测值的对比分析评估预测模型的优良性。实验结果表明,对于每个时间段内的轴承性能退化指标,该方法均能获得准确的预测结果,具备较强的实用性和工程应用价值。

Fuzzy granulation prediction for bearing performance degradation based on information entropy and optimized LS SVM

In order to improve the prediction accuracy of the rolling bearing performance degradation and get a prediction range, a novel prediction method based on information entropy and optimized least squares support vector machine (LS SVM) is proposed. The performance degradation index sequences are extracted from the bearing vibration signal, and fuzzy information granulation is executed for those degradation index sequences. Then, those granulation data are input into the LS SVM to perform regression prediction. In this process, particle swarm optimization (PSO) is used to optimize LS SVM penalty parameters and kernel parameters. Finally, the prediction model is evaluated according to the comparison between the measured values and the predicted values. Experimental results show that the proposed method can obtain accurate prediction results for the bearing performance degradation index in each time period, and strong practicability and engineering application value are expected.