Settlement NARMAX model based on changed step CMAC
一种变步长CMAC的沉降NARMAX模型*

To improve quality and reduce energy consumption of alumina production, the paper analyzes the various factors of alumina settlement process. The system identification method is used to establish the Auto-Regressive Moving Average Exogenous (ARMAX) model of settlement systems based on cerebella model articulation controller (CMAC). Consider the convergence performance problem of CMAC neural networks, the changed step method is presented to solve the problems of standard algorithm, such as convergence speed and accuracy, which adopts hyperbolic secant function to optimize learning step of CMAC. The ARMAX model of settlement density is optimized based on the changed step CMAC. Simulation results show that the density of the settlement process is accurately identified by ARMAX model based on the presented algorithm and the settlement of alumina production operations can be guided.