Generative AI Applications in Engineering Design Optimization

Abstract

Generative Artificial Intelligence (Generative AI) is transforming engineering design optimization by enabling intelligent, data-driven design generation beyond traditional methods such as finite element analysis (FEA), computational fluid dynamics (CFD), and evolutionary optimization. By leveraging deep learning, transformer models, generative adversarial networks (GANs), diffusion models, and large language models (LLMs), Generative AI can automatically generate, evaluate, and optimize multiple engineering design alternatives. This research proposes an integrated engineering design optimization framework that combines generative foundation models, engineering simulations, machine learning, reinforcement learning, and optimization algorithms within a closed-loop architecture. The framework interprets engineering requirements, generates candidate designs, validates performance through simulation, and continuously refines designs to optimize multiple objectives, including weight, strength, cost, manufacturability, energy efficiency, reliability, and sustainability. The framework is applicable to aerospace, automotive, renewable energy, biomedical engineering, and smart manufacturing while addressing challenges such as model interpretability, data quality, computational scalability, cyber security, intellectual property protection, and human–AI collaboration. Mathematical models for multi-objective optimization support industrial implementation. The proposed approach is expected to reduce design time, improve solution quality and computational efficiency, accelerate product innovation, and promote sustainable engineering development. Overall, the research provides a practical framework that integrates artificial intelligence, computational engineering, optimization, and digital manufacturing to support next-generation intelligent engineering design.