Experimental investigation of the fault diagnosis of typical faults in reciprocating compressor valves

Abstract

The failure of suction/discharge valves is the most common cause of unscheduled compressor shutdowns; therefore, the in-time fault diagnosis of valves is crucial to the reliable operation of reciprocating compressors. Major valve faults include leakage, valve flutter, delayed closing, and improper lift. To determine the features for diagnosing these typical valve faults, this paper presents an experimental study of the fault diagnosis of reciprocating compressor valves with acoustic emission technology and simulated valve motion. The measured AE signals and simulated valve motions of normal and failed valves are studied. The results of the fault diagnosis indicate that an earlier occurrence of the suction process can diagnose suction valve leakage and that an earlier occurrence of the discharge process can be used for detecting discharge valve leakage. The leakage also causes an increase in the amplitude of the continuous acoustic emission signal. Valve faults resulting from improper valve lift can be diagnosed by the amplitude of the burst acoustic emission signal. The number of burst acoustic emission signals and the shape of the simulated valve motion can be used to monitor the valve flutter conditions. The location where the valve closes can diagnose a valve-delayed closing fault.

Assessment of characteristics of acoustic emission parameters for valve damage detection under varying compressor speeds

“…35,53,54 This is further supported by the results from Wang et al. 55,56 that the burst AE signals coincide exactly with the valve opening and closing timing measured by the displacement sensor. However, although the authors stated that increasing discharge pressure can cause a delay in suction valve opening (SVO) and discharge valve closing (DVC), detailed relationship between discharge pressure and AE amplitude is not examined.…”

A review on deep learning based condition monitoring and fault diagnosis of rotating machinery

“…Sensors that are often employed for this function include eddy current displacement (ECD), inductive (magnetic), and optical transducers. 32,33…”

Diagnosis of air compressor condition using minimum redundancy maximum relevance (MRMR) algorithm and distance metric based classification

“…4 (2021) divided equally into a training and testing samples. In reference [11], the simulated motion of the suction and discharge valves as well as the measured AE signals are studied for the purpose of the fault diagnosis of valves in air compressors. It was found in the study that the valve fault can be identified as an increase in the AE amplitude.…”