We propose a Deep Operator Network~(DeepONet) framework to learn the dynamic response of continuous-time nonlinear control systems from data. To this end, we first construct and train a DeepONet that approximates the control system's local solution operator. Then, we design a numerical scheme that recursively uses the trained DeepONet to simulate the control system's long/medium-term dynamic response for given control inputs and initial conditions. We accompany the proposed scheme with an estimate for the error bound of the associated cumulative error. Furthermore, we design a data-driven Runge-Kutta~(RK) explicit scheme that uses the DeepONet forward pass and automatic differentiation to better approximate the system's response when the numerical scheme's step size is sufficiently small. Numerical experiments on the predator-prey, pendulum, and cart pole systems confirm that our DeepONet framework learns to approximate the dynamic response of nonlinear control systems effectively.
翻译:我们提议了一个深操作员网络~( DeepONet) 框架, 以从数据中学习连续时间非线性控制系统的动态反应。 为此, 我们首先建造并培训一个能接近控制系统本地溶液操作员的 DeepONet 。 然后, 我们设计一个数字方案, 反复使用经过训练的 DeepONet 模拟控制系统对特定控制输入和初始条件的长期/ 中期动态反应。 我们伴随提议的方案, 估计相关累积错误的误差。 此外, 我们设计了一个数据驱动的 Runge- Kutta~( RK) 明确方案, 使用 DeepONet 远端通道和自动区分, 以在数字方案步数大小足够小时更接近系统的反应 。 对掠食者- 预测器、 笔和 车杆系统的数值实验证实, 我们的深ONet 框架学会了如何有效地比较非线性控制系统的动态反应 。