GenControl: Generative AI-Driven Autonomous Design of Control Algorithms

Abstract: Designing controllers for complex industrial electronic systems is challenging due to nonlinearities and parameter uncertainties, and traditional methods are often slow and costly. To address this, we propose a novel autonomous design framework driven by LLMs. Our approach employs a bi-level optimization strategy: an LLM intelligently explores and iteratively improves the control algorithm's structure, while a Particle Swarm Optimization (PSO) algorithm efficiently refines the parameters for any given structure. This method achieves end-to-end automated design. Validated through a simulation of a DC-DC Boost converter, our framework successfully evolved a basic controller into a high-performance adaptive version that met all stringent design specifications for fast response, low error, and robustness. This work presents a new paradigm for control design that significantly enhances automation and efficiency.