【摘要】 基于RLS算法的连续CMAC是在对CMAC的结构进行相应改变的基础上提出的,收敛速度快,收敛性得到了证明,可以有效的提高CMAC的性能,但连续CMAC-RLS算法的仿真和应用研究还比较少,有待于更多的发展。将RLS算法引入CMAC网络从而构成的基于RLS算法的连续CMAC网络,并给出了完整的连续CMAC-RLS算法的数学描述。随后讨论了CSTR系统,并采用基于RLS算法的连续CMAC对具有代表性的强非线性系统CSTR进行建模。仿真结果表明,关于连续CMAC网络对强非线性系统具有良好的建模效果,可应用于较复杂的工业系统建模。更多还原

【Abstract】 Consecutive CMAC based on RLS algorithm was put forward according to the changes of the CMAC structures. It has fast convergence and the convergence ability has been scientifically proved. Consecutive CMAC-RLS can effectively improve the performance of CMAC, but the study of simulation and application of consecutive CMAC-RLS are still limited and need to be well developed. This paper firstly introduced the RLS algorithm to the consecutive CMAC to construct consecutive CMAC based on RLS algorithm and a complete consecutive CMAC-RLS algorithm was described mathematically. Then the CSTR system was discussed and a model was set up with consecutive CMAC based on RLS algorithm for the strong nonlinear CSTR system. Simulation results indicate that such a consecutive CMAC network has a good modeling effect on nonlinear system, which means it can be modeled in the relatively complex industrial system.更多还原