基于改进混沌自适应粒子群神经网络的磨矿粒度软测量

Soft Sensor of Particle Size of Grinding Process Based on Improved CSAPSO Neural Networks

针对磨矿粒度难以实现直接在线测量且化验过程滞后的难题,结合一段磨矿回路的特性,提出基于改进的混沌自适应粒子群优化算法和BP神经网络结合的磨矿粒度软测量模型,本算法利用混沌理论的遍历性和粒子群较强的全局最优搜索能力的优点,自适应的调整BP网络的权值,避免网络陷入局部最优。通过MATLAB仿真表明,改进的混沌自适应PSO-BP神经网络与PSO-BP神经网络和CPSO-BP神经网络相比较,其测量精度明显提高,且网络具有较强的收敛性能和优化能力,结果表明所提出方法的有效性。

Aiming at the problems that the particle size can＇t be measured online and the offline analysis by lab sample existing in large-time delay, by combining the characteristics of the one stage grinding circuit, the soft sensor model of particle size was proposed by the combination of improved chaotic self-adaptive particle swarm optimization and BP neural network algorithm. Taking advantages of chaotic theory ergodicity and PSO global optimal searching ability, the algorithm above couldadjust the weights of BP network adaptively and avoid falling into the local optimum. As a result of MATLAB simulation, the measurement accuracy of the improved CSAPSO-BP NN is higher than the PSO-BP NN and CPSO-BP N-N, and it also has better ability of convergence and optimization performance. To sum up, the proposed soft sensor approach is efficient.