Visible to the public A Multivariate Time Series Classification based Multiple Fault Diagnosis Method for Hydraulic Systems

TitleA Multivariate Time Series Classification based Multiple Fault Diagnosis Method for Hydraulic Systems
Publication TypeConference Paper
Year of Publication2019
AuthorsZhao, Xiaohang, Zhang, Ke, Chai, Yi
Conference Name2019 Chinese Control Conference (CCC)
Keywords1-NN method, classification, cyber physical systems, fault diagnosis, human factors, hydraulic systems, mechanical engineering computing, Metrics, multi-class OVO-SVM, multiple fault diagnosis, multiple fault diagnosis method, multiple faults conditions, multiple-faults classification, multivariable timing characteristics, multivariate time series analysis, multivariate time series classification, neural nets, nonlinear complex systems, pubcrawl, Resiliency, signal classification, signal detection, Support vector machines, time series, Transforms
AbstractHydraulic systems is a class of nonlinear complex systems. There are many typical characteristics with the systems: multiple functional components, multiple operation modes, space-time coupling work, and monitoring signals for faults are multivariate time series data, etc. Because of the characteristics, fault diagnosis for Hydraulic systems is not easy. Traditional fault diagnosis methods mostly ignore the multivariable timing characteristics of monitoring signals, it has made many detection and diagnosis (especially for multiple fault) can not keep high accuracy, and some of the methods are not even be able to multiple fault diagnosis. Aim at the problem, a multivariate time series classification based diagnosis method is proposed. Firstly, extracting timing characteristics (transformed features) from the time series data collected via sensors by 1-NN method. Secondly, training the transformed features by multi-class OVO-SVM to classify multivariate time series. Simulation of the method contains single fault and multiple faults conditions, the results show that the method has high accuracy, it can complete multiple-faults classification.
Citation Keyzhao_multivariate_2019