Title: AI, Innovation and Global Transformation: Interdisciplinary Perspectives on Technology, Business and Society
Editors: Dr. J. Preetha, and Dr. Siddhartha Mehrotra
ISBN: 978-81-69857-64-2
Chapter: 15
DOI: https://doi.org/10.59646/809/15
Author: Dr. L. Jayakumar
Abstract
Generative design (GD) coupled with artificial intelligence (AI) is transforming traditional engineering product development into an automated, performance-driven paradigm. By leveraging deep generative models, physics-informed neural networks (PINNs), and high-fidelity surrogate modeling, engineering teams can explore vast, non-intuitive multi-physics design spaces beyond human cognitive limits. This chapter systematically investigates an end-to-end framework integrating deep learning surrogates, conditional variational autoencoders (CVAEs), and topology optimization (TO) to accelerate the product synthesis lifecycle while enforcing strict manufacturability and structural constraints. We evaluate the proposed pipeline across 1,500 parametric design configurations of safety-critical aerospace and automotive structural components. Results demonstrate that deep-learning surrogate models reduce structural evaluation latency by over 98% relative to finite element analysis (FEA), while the generative framework achieves a 26.4% mean mass reduction and preserves structural compliance within 3.8% of numerical baselines. The methodology establishes an actionable pathway for AI-assisted engineering workflows in advanced manufacturing.
Keywords: Generative Design; Artificial Intelligence; Topology Optimization; Physics-Informed Neural Networks; Surrogate Modeling; Additive Manufacturing.