论文部分内容阅读
对用人工神经网络识别往复泵活塞磨损故障进行了研究。以在往复泵缸套压盖上采集的振动信号的振动功率谱为主要征兆，建立了基于人工神经网络的往复泵活塞磨损故障诊断系统。计算机模拟识别表明，运用该系统可较为准确地判别出活塞的磨损（破损）故障。
The artificial neural network was used to identify the reciprocating pump piston wear failure. Taking the vibration power spectrum of the vibration signal collected on the reciprocating pump cylinder cover as the main indication, a reciprocating pump piston wear fault diagnosis system based on artificial neural network was established. Computer simulation shows that the use of the system can be more accurately identify the piston wear (damage) failure.