A Multi-Agent System for IPMSM Design Optimization via an FEA-AI Hybrid Approach

2026-06-08

AI Summary

This study addresses the challenges in multi-objective optimization of interior permanent magnet synchronous motors (IPMSMs), which include complex physical constraints, high computational cost of finite element analysis (FEA), and unreliable surrogate model predictions in sparse or out-of-distribution regions. To overcome these issues, this work proposes the first hybrid FEA–AI optimization framework that integrates retrieval-augmented generation (RAG) with uncertainty-aware mechanisms, enabling an end-to-end closed-loop process through multi-agent collaboration for problem formulation, sample generation, model training, and optimization. The approach innovatively employs RAG to structurally extract motor design knowledge and introduces a dynamic FEA–AI switching strategy based on predictive uncertainty. Experimental results demonstrate that, under identical high-fidelity FEA budgets, the proposed method outperforms purely FEA- or AI-based approaches by achieving superior design performance with lower prediction uncertainty while significantly reducing computational overhead.

Abstract

Interior permanent magnet synchronous motor (IPMSM) design requires balancing conflicting objectives and multi-physics constraints, while modern optimization workflows face three bottlenecks: manual problem setup, high finite element analysis (FEA) cost, and unreliable surrogate-based search in sparse or out-of-distribution regions. To address these limitations, we propose an end-to-end automated IPMSM design optimization framework that integrates retrieval-augmented generation (RAG) for structured problem definition with an uncertainty-aware FEA-AI hybrid optimization pipeline. A Design agent, connected to a motor textbook through RAG, provides domain-knowledge-based options and engineering tips, and compiles an optimization card and a design-of-experiments plan for AI-model training. A Training agent automates electromagnetic FEA, records geometry-validation and solver-failure logs, analyzes failed geometries using ANOVA-based data analysis and LLM reasoning, and invokes a Design Sampling agent to redefine the design space and generate additional samples. An Optimization agent performs GA-based search with uncertainty-driven switching: low-uncertainty candidates are evaluated by AI-surrogate inference, whereas high-uncertainty and reliability-critical Pareto-front or top-K candidates are corrected by high-fidelity FEA and reused for iterative retraining. The framework converts manual, experience-dependent configuration into a reproducible workflow that balances computational cost and prediction reliability. Experimental results under a matched high-fidelity FEA budget show that the proposed hybrid approach achieves better objective performance while maintaining low and further reducible predictive uncertainty, outperforming FEA-only search, which is limited by early budget exhaustion, and AI-only search, which converges to a low-confidence optimum.

Problem

• IPMSM design optimization
• finite element analysis
• surrogate-based optimization
• multi-objective optimization
• design automation

Innovation

• multi-agent system
• FEA-AI hybrid optimization
• retrieval-augmented generation (RAG)
• uncertainty-aware surrogate modeling
• automated motor design