DiffLoop: Tuning PID controllers by differentiating through the feedback loop
This addresses PID tuning for industrial control applications, presenting an incremental improvement over existing methods.
The paper tackles the problem of tuning PID controllers and anti-windup measures in industrial control by using back-calculation and automatic differentiation to optimize feedback gains through gradient descent, showing efficacy in numerical experiments on linear systems with actuator saturation.
Since most industrial control applications use PID controllers, PID tuning and anti-windup measures are significant problems. This paper investigates tuning the feedback gains of a PID controller via back-calculation and automatic differentiation tools. In particular, we episodically use a cost function to generate gradients and perform gradient descent to improve controller performance. We provide a theoretical framework for analyzing this non-convex optimization and establish a relationship between back-calculation and disturbance feedback policies. We include numerical experiments on linear systems with actuator saturation to show the efficacy of this approach.