3028. AI-Enhanced Decision Framework for Innovative Conceptual Design in Sustainable Food Engineering
Invited abstract in session TB-16: Optimization of complex systems in Agriculture, stream Sustainable Food & Agroforestry.
Tuesday, 10:30-12:00Room: Esther Simpson 2.07
Authors (first author is the speaker)
| 1. | Mohamed Saâd El Harrab
|
| Industrial Engineering Department, Co-Innovation Lab, École nationale des ponts et chaussées | |
| 2. | Michel Nakhla
|
| CGS (Centre de Gestion Scientifique), Mines Paris - PSL |
Abstract
Conceptual design in sustainable food engineering demands structured approaches to explore and optimize innovative, viable solutions systematically. Traditional heuristic methods often lack the necessary rigor and structure, limiting their effectiveness in generating feasible outcomes. While large language models (LLMs) effectively enhance knowledge retrieval, they typically do not incorporate structured optimization processes essential for systematic decision-making.
This study introduces a structured decision-making framework integrating Markov Decision Processes (MDPs), Reinforcement Learning (RL), and knowledge integration via LLMs, explicitly targeting conceptual design in sustainable food engineering. Our approach systematically models design decision processes, effectively balancing exploratory creativity with the targeted optimization of sustainability metrics, including nutritional quality, environmental footprint, economic viability, and innovative product differentiation. A practical case study in sustainable food product innovation demonstrates the framework's ability to improve the feasibility, diversity, and sustainability performance of proposed solutions, highlighting its potential as a robust, structured approach to conceptual design.
Keywords
- Industrial Optimization
- Sustainable Development
- Artificial Intelligence
Status: accepted
Back to the list of papers