针对存在初始设置偏差的离散多变量生产制造过程,研究了调整误差服从自回归模型的情况下,考虑调整花费成本为二次型函数时的设置调整问题,在建立过程状态空间方程的基础上,利用卡尔曼滤波方法在线估计过程的状态变量,根据随机二次型最优控制理论得到了使过程质量损失最小的最优调整策略。通过算例解释了最优调整策略的实现方法,并进行了仿真验证,结果表明,得到的调整策略与调整误差为白噪声时的调整策略相比,能更好地减少过程总体质量损失。
For the finite horizon multivariate process with setup error,the optimal adjustment scheme was developed to minimize the total process quality loss with quadratic cost and autoregressive adjustment error.Based on the state-space process control model,the optimal adjustment scheme was derived by Kalman filter on line estimation and Linear Quadratic Gaussian(LQG) theory.The implementation method of the optimal adjustment policy was illustrated by a case,and the simulation experiment was presented.The result showed that the proposed adjustment solution could reduce the total quality loss of the process by comparing with the quality adjustment policy when adjustment error was the white noise.