A Data Driven Approach for Condition Monitoring of Reciprocating Compressor Valves

Abstract

This paper focuses on conditionmonitoring of three different valve failure modes common in reciprocating compressors. They are missing valve poppets, valve spring fatigue, and valve seat wear. First, a targeted instrumentation study is performed on a Dresser–Rand ESH1 industrial reciprocating compressor to investigate detection methods for these failures. This is followed by the development of a novel health classification methodology based on frequency analysis and Bayes theorem. The method is shown to successfully classify the condition of the valves to a high degree of accuracy when applied to actual seeded valve faults in the compressor.