English

DiffLoop: Tuning PID controllers by differentiating through the feedback loop

Systems and Control 2022-07-05 v3 Machine Learning Systems and Control Optimization and Control

Abstract

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.

Keywords

Cite

@article{arxiv.2106.10516,
  title  = {DiffLoop: Tuning PID controllers by differentiating through the feedback loop},
  author = {Athindran Ramesh Kumar and Peter J. Ramadge},
  journal= {arXiv preprint arXiv:2106.10516},
  year   = {2022}
}

Comments

Extension of paper in 2021 55th Annual Conference on Information Sciences and Systems (CISS). IEEE, 2021

R2 v1 2026-06-24T03:23:18.520Z