Monitoring system for reciprocating compressor valves - a data-driven approach

Leaking valves are the most common reason for unexpected shutdowns of reciprocating compressors. Therefore a leaking valve has to be detected early and reliable, even for arbitrary operating conditions. In this book, a data-driven approach for compressor valve monitoring is proposed. As compressors are equipped with different sensing systems and usually retrofitting new sensors is not desired or even impossible, two independent approaches are developed. In the first approach, accelerometers are mounted at the valve covers to perform vibration analysis. In the case of a leaking valve, certain time-frequency patterns occur, different from the patterns in the case of varying operating condition. It is thus possible to extract features from the time-frequency representation that are specific for leaks. In the second approach, pV diagrams of compression cycles are analysed. Gas flowing through a leak affects the pressure in the compression cylinder and thus the pV diagram, which is also affected by varying operating conditions. Appropriate features to distinguish these cases are extracted both from the logarithmic pV diagram and the pressure conditions.