Accelerated Gradient-based Design Optimization Via Differentiable Physics-Informed Neural Operator: A Composites Autoclave Processing Case Study

2025-02-17

AI Summary

In composite autoclave curing processes, finite-element simulations incur prohibitive computational costs, while conventional surrogate models exhibit poor generalization in high-dimensional, nonlinear design spaces. To address these challenges, this paper proposes a differentiable Physics-Informed Deep Operator Network (PIDON). PIDON is the first to integrate gradient backpropagation into the DeepONet architecture, synergistically embedding physical constraints with operator learning to accurately model high-dimensional, strongly nonlinear, and multi-condition dynamic processes. The framework enables end-to-end differentiable optimization and supports zero-shot super-resolution prediction and cross-condition transfer without retraining. Evaluated on aerospace composite curing optimization, PIDON achieves a 3× speedup over traditional finite-element simulation, significantly enhancing design efficiency, prediction accuracy, and scalability.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Machine Learning: Deep Neural Architectures and Foundation Models
• Computer Vision: Learning & Optimization for CV

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Simulation and optimization are crucial for advancing the engineering design of complex systems and processes. Traditional optimization methods require substantial computational time and effort due to their reliance on resource-intensive simulations, such as finite element analysis, and the complexity of rigorous optimization algorithms. Data-agnostic AI-based surrogate models, such as Physics-Informed Neural Operators (PINOs), offer a promising alternative to these conventional simulations, providing drastically reduced inference time, unparalleled data efficiency, and zero-shot super-resolution capability. However, the predictive accuracy of these models is often constrained to small, low-dimensional design spaces or systems with relatively simple dynamics. To address this, we introduce a novel Physics-Informed DeepONet (PIDON) architecture, which extends the capabilities of conventional neural operators to effectively model the nonlinear behavior of complex engineering systems across high-dimensional design spaces and a wide range of dynamic design configurations. This new architecture outperforms existing SOTA models, enabling better predictions across broader design spaces. Leveraging PIDON's differentiability, we integrate a gradient-based optimization approach using the Adam optimizer to efficiently determine optimal design variables. This forms an end-to-end gradient-based optimization framework that accelerates the design process while enhancing scalability and efficiency. We demonstrate the effectiveness of this framework in the optimization of aerospace-grade composites curing processes achieving a 3x speedup in obtaining optimal design variables compared to gradient-free methods. Beyond composites processing, the proposed model has the potential to be used as a scalable and efficient optimization tool for broader applications in advanced engineering and digital twin systems.

Problem

• Accelerates design optimization via differentiable neural operators
• Enhances predictive accuracy in high-dimensional design spaces
• Improves efficiency in aerospace composites curing processes

Innovation

• Physics-Informed DeepONet architecture
• Gradient-based optimization framework
• Accelerates composite curing processes