# Data-efficient Auto-tuning with Bayesian Optimization: An Industrial Control Study

## TL;DR

This paper presents a Bayesian optimization approach for automatic controller tuning in industrial systems, demonstrating efficient, data-driven parameter optimization that outperforms manual methods with fewer experiments.

## Contribution

It introduces a flexible Bayesian auto-tuning framework that efficiently finds optimal controller parameters using Gaussian processes and information gain, applicable to various control structures.

## Key findings

- Outperforms manual calibration in throttle valve control
- Achieves better performance with fewer experiments
- Flexible framework adaptable to different control objectives

## Abstract

Bayesian optimization is proposed for automatic learning of optimal controller parameters from experimental data. A probabilistic description (a Gaussian process) is used to model the unknown function from controller parameters to a user-defined cost. The probabilistic model is updated with data, which is obtained by testing a set of parameters on the physical system and evaluating the cost. In order to learn fast, the Bayesian optimization algorithm selects the next parameters to evaluate in a systematic way, for example, by maximizing information gain about the optimum. The algorithm thus iteratively finds the globally optimal parameters with only few experiments. Taking throttle valve control as a representative industrial control example, the proposed auto-tuning method is shown to outperform manual calibration: it consistently achieves better performance with a low number of experiments. The proposed auto-tuning framework is flexible and can handle different control structures and objectives.