Detecting cracks in reciprocating compressor valves using pattern recognition in the pV diagram

We present a novel approach to detecting leaking reciprocating compressor valves based on the idea that a leaking valve affects the shape of the pressure-volume diagram (pV diagram). This effect can be observed when the valves are closed. To avoid disturbances due to the load control, we concentrate on the expansion phase, and linearize it using the logarithmic pV diagram. The gradient of the expansion phase serves as an indicator for the fault state of the valve. Since the gradient is also affected by the pressure conditions, both are used as features in our approach. After feature extraction, classification is performed using several established approaches and a one-class classification method based on linearizing the classification boundary and thresholding. The method was validated using real-world data, and the results show high classification accuracy for varying compressor loads and pressure conditions as well as different valve types.