Research on drilling mud pump fault diagnosis based on fusion of acoustic emission and vibration technology

A mud pump is one of the three key components of a drilling site and its lifetime and reliability are related to safety and cost. The fluid end, which mainly comprises the pump valve and piston, is the most easily damaged part of the mud pump. To ensure normal operation, the fault modes of the fluid end need to be effectively identified. In this paper, the fault mode is identified using multi-sensor information fusion, which fuses the acoustic emission (AE) signal and the vibration acceleration signal. The features of these signals are extracted using wavelet packet signal processing; then, the faults are diagnosed using neural network algorithms. This method is verified by conducting experiments on a BW-250 triplex mud pump and the results show that the wavelet packet signal processing method can effectively extract the frequency band energy eigenvalues of the signals and that the fault diagnosis accuracy is improved by using multi-sensor information fusion. This research presents a practical diagnosis method that can effectively improve the fault diagnosis level for the fluid end of high-pressure reciprocating mud pumps.