论文部分内容阅读
Wiener模型是一种典型的模块化非线性模型,广泛应用于工业过程控制领域.由于其结构的非线性,参数辨识无法直接得到解析解.为此,将Wiener模型的参数估计转化为带约束的非线性优化问题,以头脑风暴优化(BSO)算法并行搜索该问题的最优解,并以搜索过程中的反馈信息调整BSO算法的变异过程,以改进算法的收敛速度和辨识精度.数值仿真和工业数据验证了所提算法的有效性.
The Wiener model is a typical modular nonlinear model and is widely used in the field of industrial process control. Because of the non-linearity of the structure, the parameter identification can not be analytically solved directly. Therefore, the Wiener model’s parameter estimation is transformed into a constrained Nonlinear optimization problem, the optimal solution of the problem is searched in parallel with the brainstorm optimization (BSO) algorithm, and the mutation process of the BSO algorithm is adjusted by the feedback information in the search process to improve the convergence speed and identification accuracy of the algorithm.Numerical simulation and Industrial data verify the validity of the proposed algorithm.