Nonlinear calibration for petroleum water content measurement using PSO

摘要

To improve the measurement precision of the capacitance method for petroleum water content, this paper presents a nonlinear calibration technique based on neural networks. Consider that the traditional BP algorithm has shortcomings of converging slowly and easily trapping a local minimum value, a combination algorithm using particle swarm optimization (PSO) and back propagation (BP) is adopted to train the neural network. It will enable the calibration process with an overall accuracy and a higher converging speed. Simulation results show that this method can effectively eliminate the impact of non-target parameters to the sensor output and has certain project value.