Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2506.12554 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908460123160576 |
|---|---|
| author | Cui, Chenggang Liu, Jiaming Hui, Peifeng Lin, Pengfeng Zhang, Chuanlin |
| author_facet | Cui, Chenggang Liu, Jiaming Hui, Peifeng Lin, Pengfeng Zhang, Chuanlin |
| contents | 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 Large Language Models (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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_12554 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GenControl: Generative AI-Driven Autonomous Design of Control Algorithms Cui, Chenggang Liu, Jiaming Hui, Peifeng Lin, Pengfeng Zhang, Chuanlin Systems and Control 93C40, 49K15 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 Large Language Models (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. |
| title | GenControl: Generative AI-Driven Autonomous Design of Control Algorithms |
| topic | Systems and Control 93C40, 49K15 |
| url | https://arxiv.org/abs/2506.12554 |