A Novel Feature Extraction Approach for Mechanical Fault Diagnosis Based on ESAX and BoW Model
Dongfang Zhao, Shulin Liu, Zhonghua Miao, Hongli Zhang, Yuan Wei, Shungen Xiao
Abstract
Condition monitoring and fault diagnosis are of great significance to the development of modern industry, for they enable enterprises to avoid unexpected interruptions or severe accidents, and extracting the fault-related features from vibration signals is a critical step to achieve accurate diagnosis. Among diverse of feature extraction approaches, symbolic aggregate approximation is a promising one that has been introduced into fault diagnosis recently. Nevertheless, when dealing with the sampled vibration signals, the symbolic aggregate approximation ignores the change of signal frequency characteristics, which eventually leads to information aliasing and cannot ensure the information validity. In this work, the information aliasing is analyzed from the perspective of signal processing, and the extremum symbolic aggregate approximation is developed as a substitution on the premise of maintaining the validity of the information. Subsequently, to convert the symbol strings generated by the extremum symbolic aggregate approximation into usable digital feature vectors, the bag-of-words model in natural language processing is employed to perform the counting statistics of the fault-related words, and the laplacian score algorithm is then utilized to re-rank the statistical results, thereby realizing the extraction of mechanical fault feature. The superiority of the developed method is verified by experiments.