Fault Diagnosis System Of Rotating Machinery Based On Virtual Instrument

PC-DAQ virtual instrument system is developed in the article. Typical faults on large-scale rotating machinery are simulated using rotor vibration, and the signal is adopted into computer through eddy current sensor. Signal sample is analyzed through wavelet packet theory, best base is chose, and the average energy of every sub frequency band is calculated, at last 14 links of characteristic vectors are get. After choosing the characteristic vector, BP network of three layers is structured and trained, discern the faults to the sample, and made a good result. It proved that extracting symptom with method of wavelet packet theory is efficiency, and application of BP network in pattern recognition is useful. The whole course used figure programming language LabVIEW and MATLAB programming to realize.