论文部分内容阅读
在多变量发动机寻优控制中,用支持向量回归算法(SVR)对粒子群优化算法(PSO)进行改进可以有效避免局部最优解的出现.将改进算法应用于航空发动机实时稳定性控制,根据发动机仿真计算程序计算出发动机在各工作点处的稳定裕度,根据控制参数的变化域进行全局寻优,寻找满足压缩系统稳定裕度最小的工作点.仿真和分析表明:该算法实时性高,收敛速度快,具有较强的全局寻优能力,能在保证发动机稳定裕度最小的同时有效降低涡轮前温度和耗油率.
In multivariable engine optimization control, Particle Swarm Optimization (PSO) is improved by Support Vector Regression (SVR) to avoid the local optimal solution effectively.The improved algorithm is applied to the real-time stability control of aero-engine based on The simulation calculation program of the engine calculates the stability margin of the engine at each working point and finds the working point which satisfies the minimum margin of stability of the compression system according to the changing domain of the control parameters.The simulation and analysis show that the algorithm has high real- , Fast convergence, has a strong global optimization ability, can ensure the minimum engine stability margin while reducing the temperature before the turbine and fuel consumption.