This paper introduces an approach for determining parameters of learning function in iterative learning control without using the mathematical model of the controlled plant, which guarantees definitely the convergence requirement of the learning process. The learning parameter is intelligently computed based on system’s tracking errors from the two previous consecutive trials by minimizing a suitable cost function. Then, analysis of stability and convergence using injective property and Jacobian matrix of the input-output mapping is also given in this paper. Finally, some numerical simulations with actual system model of robot manipulators are performed to illustrate and support the proposed method.

本文介绍了一种在迭代学习控制中确定学习函数参数的方法，该方法不使用被控对象的数学模型，明确保证了学习过程的收敛性要求。通过最小化合适的成本函数，根据来自前两次连续试验的系统跟踪误差智能计算学习参数。然后，本文还利用输入输出映射的单射性质和雅可比矩阵分析了稳定性和收敛性。最后，对机器人机械手的实际系统模型进行了一些数值模拟，以说明和支持所提出的方法。