Error compensation of magnetic flux leakage inspecting based on multi-sensor fusion

The equipment inspecting the transportation pipelines of oil and gas works with high temperature and high pressure. The sensors in the equipment used to test the leakage of magnetic flux are sensitive to temperature. An approach based on multi-sensor fusion is put forward in order to compensate the temperature error of these sensors. The temperature character of the chosen magnet sensitive sensors is analyzed. Then, the multi-sensor fusion model is constructed. The test data of multiple magnet sensors and a temperature sensor are processed by a Radial basis function (RBF) neural network. Genetic arithmetic. is chosen to train the network. The data waveform which is tested under several different temperature points in lab and the simulated shapes of defects before and after fusion show that compensate temperature error using multi-sensor fusion is a simple and convenient way. The mean of the temperature sensitive coefficient reduces sharply to less than 1/100 to the one before fusion.