离线优化在线查表的双层结构预测控制

Off-line optimization and online table lookup for double-layer structure predictive control

双层结构预测控制包括稳态优化和动态控制,计算复杂度较大,难以在实时性要求较高或者是主控制器计算能力较弱的场合应用.本文阐述了一种离线计算在线查表的稳态优化方法和详细的技术实施方案.首先采用枚举方式离线计算稳态优化值,然后通过在线查表得到实时优化值.当在线查表不可行时,通过查找距离该查表点最近的多个可查表点,以距离作为加权系数,近似计算最优稳态目标值.最后,通过性能分析和仿真实验证明了本文提出的该方法有效的降低了计算复杂度,减少了计算时间.

Double-layer structure model prediction control, composed of steady-state target calculation and dynamic optimization, is restricted in the field of high real-time control and poor computational controller. A new method of steadystate target calculation, called off-line optimization and online table lookup, is proposed. Also the calculation method is given in detail. First, the steady-state optimization database is estimated through enumeration and off-line optimization.Then the steady-state optimization is addressed based on online lookup table. For the case that online table lookup is not feasible, the steady-state optimization is calculated approximately by seeking the multiple points which are nearest to the lookup table point in the lookup table, and selecting the distances as the weighting coefficient. Finally, The capabilities of the method in this paper are investigated through computational complexity analysis and computer simulation.