Subsequence Time Series Clustering-Based Unsupervised Approach for Anomaly Detection of Axial Piston Pumps

Abstract

Axial piston pump is the key component of a hydraulic system. The reliability of the axial piston pump influences the reliability of the fluid power system directly. Discharge pressure signals are easy to obtain and can reflect the dynamic performance of the axial piston pump. Although many studies have been developed for fault diagnosis of the axial piston pump, most of these methods are based on supervised artificial intelligence-based methods that rely on massive labeled data. However, in practice application, the external load of the hydraulic system often varies and it is quite impractical or expensive to obtain massive labeled data. This article proposes a novel Subsequence Time Series(STS) clustering based unsupervised approach for anomaly detection of the axial piston pump using discharge pressure signal. The proposed approach comprises two stages, norm cluster search, and anomaly subsequence clustering. The proposed approach performs multiple STS clustering to search the norm cluster whose center can encode the time series better. The proposed approach comprises of four modules: motif discovery, parameter-free minimum description length(MDL) clustering, subsequence search, and scoring the norm cluster. Subsequence search via dynamic time warping(DTW) enables the approach to discover the subsequences of variable length. In particular, weak fault signal detection is achieved by evaluating the local distribution of subsequence. The effectiveness of the proposed approach is validated through experiments under different external loads.