| Popis: |
In this paper, we propose a novel feature extraction approach for detecting wear in internal gear pumps. In a data-driven approach, the pressure reduction time (PRT) was identified as a useful feature for wear detection. It measures the time for reducing the internal pump pressure from one certain level to another when the pump engine is stopped and the valves are closed. The PRT can thus be interpreted as an internal leakage factor of the pump. When the internal leakage increases due to wear, the pressure in the pump decreases faster (implying a decreased PRT). The proposed approach has been developed and tested with data of real internal gear pumps with different operating times. The PRT shows a close relation to the operating time of the pump. Moreover, we compared PRT with the two well known approaches pressure holding speed (PHS) and head flow diagram (HFD). Especially for medium operating times of a pump, PRT shows better sensitivity than PHS and HFD. |
