The Method Of Imbalanced Data Processing And Its Application Research In Fault Diagnosis Of Axial Piston Pump

With the deepening of science and technology and data mining research,the era of big data has come.In line with the trend of The Times,machine learning has become a popular research direction.However,the traditional machine learning algorithm can only play a good role when the data distribution is balanced,but most of the data in the actual operation is not balanced,so the traditional machine learning algorithm is not suitable.Taking the fault diagnosis of axial piston pump as an example,in the actual fault diagnosis,the number of fault samples is far less than the number of normal samples,so it is difficult for the commonly used classification algorithm to achieve good results.Therefore,it is very important to introduce unbalanced data processing method into fault diagnosis of axial piston pump.This paper mainly studies the unbalanced data processing method and its application in fault diagnosis of axial piston pump.The main contents are as follows:Aiming at the second-class imbalance problem,this paper proposes an improved SMOTE algorithm based on feature selection and spatial clustering.This method has been improved for the problems of the SMOTE algorithm,such as noise and blurred boundaries.In order to verify the effect of the algorithm,the algorithm is compared with the traditional algorithm on the UCI data set.The results show that the improved algorithm has better results.Aiming at the situation that fault data collected in actual fault diagnosis of axial piston pump is far less than normal data,an axial piston pump fault diagnosis method based on Balanced Random Forest(BRF)algorithm is proposed to improve the classification precision of faulty classes.BRF algorithm is an improved algorithm of Random Forest(RF)which combines under-sampling method with RF and strengthens the ability of RF to process imbalanced data.The algorithm performance is tested on the UCI open source datasets.Compared with RF and SMOTE-RF,BRF algorithm improves the precision of minority classes.Finally,BRF algorithm is applied to the axial piston pump fault diagnosis.The results show that BRF has higher classification precision of faulty classes than RF and SMOTE-RF under imbalanced datasets.