Research of PSO-BP Optimal Algorithm in Material Moisture Measurement

Based on PSO-BP optimal algorithm an evolutionary neural network model is presented to improve the measurement accuracy with microwave resonant. Firstly, the global search ability and rate-displacement model of the PSO algorithm are used to follow the current instance dynamically and modulate its search strategy. And then BP local searching ability which avoids oscillating near the optimal solution or suboptimal solution and converges on the optimal solution speedy is considered. Experiments show that the PSO-BP optimal algorithm has the merits of high prediction precision, rapid convergence, global superiority and accuracy for optimization. It improves the measurement precision with the mean squared error 0.0118, the mean absolute error 0.0619, the mean relative error 0.1176 and the certain coefficient 0.9956 between the predicted moisture content and the real value.