论文部分内容阅读
提出一种基于改进型极限学习机的内模控制策略,以改进型极限学习机建立控制系统的内模,利用泰勒级数对内模进行一次项展开,来间接获得控制系统的控制量,避免了直接求解模型的逆.同时,对所提出的内模控制系统在建模误差和干扰条件下分析系统稳定性条件和误差.将所提出的控制策略应用于连续搅拌釜反应器系统中实现内模控制仿真.仿真结果表明该控制策略能很好地实现反应器的浓度控制,且具备很强的抗干扰性.同时基于改进极限学习机的系统比极限学习机具有更好的控制性能.
In this paper, an internal model control strategy based on the improved extreme learning machine is proposed. The internal model of the control system is established by the improved extreme learning machine. The Taylor series is used to expand the internal model one term to obtain the indirect control of the control system. The inverse of the model is solved directly.At the same time, the system stability conditions and errors of the proposed internal model control system are analyzed under the modeling error and interference conditions.The proposed control strategy is applied to the implementation of the continuous stirred tank reactor system The simulation results show that the proposed control strategy can well control the concentration of reactor and has strong anti-interference ability.At the same time, the system based on improved extreme learning machine has better control performance than the limit learning machine.