KNN-朴素贝叶斯算法的滚动轴承故障诊断

Fault Diagnosis of Rolling Bearing Based on KNN-Naive Bayesian Algorithm

滚动轴承的故障诊断对于提高工业生产效率,保障工业生产的稳定安全地运行具有重要意义;为了提高滚动轴承故障识别的正确率,提出一种使用KNN-朴素贝叶斯决策组合算法对滚动轴承故障诊断;组合算法利用朴素贝叶斯算法对使用不同K值的KNN算法初步分类结果进行再分类以达到提高滚动轴承故障识别的目的;首先,使用小波包能量法对滚动轴承振动信号进行能量特征提取,然后使用多个参数K值不同的KNN算法对能量特征数据预分类,得到多个KNN算法分类结果集,将分类结果集进行处理得到预分类结果集,将预分类结果集作为朴素贝叶斯算法的输入,使用朴素贝叶斯算法对数据再分类;实验结果表明,组合算法相较于传统KNN算法及贝叶斯算法在滚动轴承的故障诊断率得到了有效提高,实现了对滚动轴承故障的有效诊断。

Fault diagnosis of rolling bearings is of great importance to improve the efficiency of industrial production and ensure the stable and safe operation of industrial production.In order to improve the accuracy of rolling bearing fault recognition,a fault diagnosis method based on KNN-naive Bayesian decision combination algorithm is proposed.The combined algorithm uses the naive Bayesian algorithm to reclassify the KNN algorithm using different K values to achieve the purpose of improving the fault identification of rolling bearings.Firstly,the energy feature extraction of the rolling bearing vibration signal is carried out by using the wavelet packet energy method.Then,the KNN algorithm is used to pre-classify the energy characteristic data,and the KNN algorithm is used to classify the result group.The classification result set is used as the input of the naive Bayesian algorithm,and the data is reclassified using the naive Bayesian algorithm.The experimental results show that the combined algorithm is effective compared with the traditional KNN algorithm and the Bayesian algorithm in the fault diagnosis of rolling bearings,The combination algorithm realizes the effective diagnosis of rolling bearing faults.