Skip to Main Content
A detection system of oil tube defect based on wavelet neural network is presented, it got the original information by multigroup vortex sensors and leakage magnetic sensors. We made multiscale wavelet transform and frequency analysis to multichannels original data and extracted multi-attribute parameters from time domain and frequency domain, then we selected the key attribute parameters that have bigger correlativity with the defect pattern of oil tube among of multi-attribute parameters. The oil tube defect pattern had four class that is crack, etch pits, eccentric wear and unbroken. The wavelet neural network was adopt to make the multisensor data fusion to detect the defect pattern of oil tube and those key attribute parameters were used to as input of network. The experimental results show that this method is feasible and effective.