GLBest-PSO算法在热工过程模型参数辨识中的应用

过程对象的数学模型,对热工控制系统的设计和分析有着重要的意义.为了达到精确建模的目的,提出了一种基于全局-局部参数最优的粒子群优化算法的辨识方法.将过程模型的每个参数作为群体的一个粒子,利用粒子在空间进行高效并行的搜索来获得最佳参数值,提高了辨识精度和效率.对典型热工过程进行辨识表明:该方法对过程模型的阶次不敏感,对不同输入信号均能得到满意的辨识精度和效率,模型输出与实际输出基本一致,辨识效果较好.

Application of GLBest-PSO algorithm for parameters identification of thermal process model

The mathematical model of process object is of significance to the design and analysis of the thermal control system.For the purpose of achieving accurate model,an identification method based on particle swarm optimization algorithm combining the global-local best parameter is proposed.By taking every parameter of process model as a particle of the swarm and applying particles to search optimal parameters of process model concurrently and efficiently in the parameter space,the precision and efficiency of parameter identification are improved.The identification results for the typical thermal process show that the method is not sensitive to the order of the model,and can obtain satisfactory identification precision and efficiency for different input signal.The model outputs coincide with actual outputs.The identification method achieves good result.