Intelligent Fault Diagnosis Technique Based on Multifractal and Singularity Value Decomposition for Reciprocating Compressor

This paper presents an intelligent fault diagnosis fault technique based on multifractal and singularity value decomposition for reciprocating compressor,according to the complex structure and scattered fault location of reciprocating compressor and difficulty to diagnose multiple faults by single measurement point.The generalized fractal dimension can characterize local scale behavior of signal more appropriately,so an initial feature matrix was built by calculating the generalized fractal dimension of vibration signal for multiple measurement points.The matrix was compressed by singular value decomposition method,and the eigenvalue of matrix was taken as feature vector.Taken reciprocating compressor transmission mechanism as research object,feature vectors of common faults were extracted.Support vector machine was established as pattern classifier to identify faults.Compared with results of single measure ment point multifractal method and multiple measurement points fractal method,the validity of this method is proved.