A Hybrid Approach to Hydraulic Vane Pump Condition Monitoring and Fault Detection

Health monitoring of hydraulic vane pumps is currently achieved through oil analysis. Monitoring pump operatingparameters to detect faults on-line could improve condition-based maintenance techniques. This research developed anon-line hydraulic vane pump fault detection system. This fault detection system decomposed vertical pump vibration signalsusing wavelet packet analysis. Packets containing signal features distinguishing normal and failed pump operation wereentered into an adaptive neuro-fuzzy inference system (ANFIS) for pump health classification. Two particular verticalvibration signal packets (7,11 and 7,60 from the Daubechies 3 packet analysis) were found most effective in classifying pumpcondition when entered into the ANFIS structure. Pump health classification using these inputs was 90% accurate with amissed alarm rate of 3% and a false alarm rate of 6%.