基于支持向量机的航空发动机PID解耦控制

针对航空发动机多变量控制系统中各回路之间存在的耦合现象,提出了一种基于支持向量机(support vector machines,SVM)的航空发动机PID(proportion integration differentiation)解耦控制方法.利用SVM辨识发动机非线性模型,并获得SVM瞬时线性化模型,在线性化模型的基础上完成了PID参数的在线自整定.利用Lyapunov稳定性定理对控制器的收敛性进行了分析.通过对某型航空发动机的仿真,验证了该方法的有效性和可行性.

PID decoupling controller for aero-engine based on support vector machines

To solve the coupling problem in aero-engine multivariable control system,a new PID(proportion integration differentiation) decoupling controller based on support vector machines(SVM) was proposed.The SVM was applied to identify the aero-engine model,and then linearized to extract the instantaneous linear model.The PID parameter was obtained based on the linear model.The convergence of PID decoupling controller was proved with the help of Lyapunov stability theorem.Simulation results of certain aero-engine system demonstrate the effectiveness and feasibility of the PID decoupling controller based on SVM.