Canonical variable analysis and long short-term memory for fault diagnosis and performance estimation of a centrifugal compressor. (March 2018)

• Record Type: Journal Article
• Authors: Li, Xiaochuan; Duan, Fang; Loukopoulos, Panagiotis; Bennett, Ian; Mba, David
• Is Part Of: Control engineering practice. Volume 72(2018)
• Page Start: 177
• Page End: 191
• Publication Date: 2018-03
• Subjects: Condition monitoring -- Long short-term memory -- Canonical variable analysis -- Fault identification -- Performance estimation; Automatic control -- Periodicals; 629.89
• DOI: 10.1016/j.conengprac.2017.12.006
• Languages: English
• ISSNs: 0967-0661

Abstract

Abstract: Centrifugal compressors are widely used for gas lift, re-injection and transport in the oil and gas industry. Critical compressors that compress flammable gases and operate at high speeds are prioritized on maintenance lists to minimize safety risks and operational downtime hazards. Identifying incipient faults and predicting fault evolution for centrifugal compressors could improve plant safety and efficiency and reduce maintenance and operation costs. This study proposes a dynamic process monitoring method based on canonical variable analysis (CVA) and long short-term memory (LSTM). CVA was used to perform fault detection and identification based on the abnormalities in the canonical state and the residual space. In addition, CVA combined with LSTM was used to estimate the behavior of a system after the occurrence of a fault using data captured from the early stages of deterioration. The approach was evaluated using process data obtained from an operational industrial centrifugal compressor. The results show that the proposed method can effectively detect process abnormalities and perform multi-step-ahead prediction of the system's behavior after the appearance of a fault. Highlights: The use of CVA for fault detection using data captured from an operational industrial centrifugal compressor. The combination of the canonical state space and the residual space information for fault root-cause analysis. The application of LSTM to predict the inlet gas temperature of the compressor under study. The combination of CVA and LSTM for multi-step-ahead prediction of the system's behavior after the occurrence of a fault.