论文部分内容阅读
针对主蒸汽温度系统现场数据的模型辨识问题,提出了结合粒子群优化算法的改进和声搜索算法.采用经验模态分解法对带噪声污染的现场数据进行滤波处理,采用离散相似法进行模型辨识的计算机仿真实现和数值计算.应用该改进算法对循环流化床主蒸汽温度系统模型进行了现场数据辨识.结果表明:所辨识的模型具有较高的精度,能够反映实际主蒸汽温度系统的动静态特性;改进和声搜索算法比粒子群优化算法具有更好的稳定性和全局寻优能力,以及更快的收敛速度.
In order to solve the model identification problem of on-site data of main steam temperature system, an improved harmony search algorithm based on Particle Swarm Optimization (PSO) algorithm is proposed. Empirical mode decomposition method is used to filter the scene data with noise pollution and the discrete similarity method is used to identify the model Computer simulation and numerical calculation.The field data of the main steam temperature system of the circulating fluidized bed was identified by using the improved algorithm.The results show that the identified model has high accuracy and can reflect the actual movement of the main steam temperature system Static characteristics; improved harmony search algorithm has better stability and global optimization ability than particle swarm optimization algorithm, and faster convergence speed.