Towards Resilient and Sustainable Global Industrial Systems: An Evolutionary-Based Approach

TL;DR

The paper tackles the design of resilient and sustainable global industrial systems for complex, distributed manufacturing (notably aerospace) by formulating a two-phase optimization framework. Phase I uses an Evolutionary Algorithm to generate valid production assignments under a rich set of constraints, while Phase II builds a time-aware transportation network with batching decisions and applies the DRAGO optimizer to refine flows and logistics. A Web Ontology Language (OWL) knowledge base ensures data consistency and feasibility between parts and transport resources, enabling scalable, data-driven decision-making. The approach is validated on Airbus-like data with single and double sourcing, demonstrating multi-objective improvements in CO$_2$ emissions, transportation duration, distance, and costs, and highlighting trade-offs across transport modes. The work provides a practical, generalizable framework for designing resilient and sustainable global industrial networks beyond aerospace, with clear pathways for integrating additional optimization techniques and simulation in future work.

Abstract

This paper presents a new complex optimization problem in the field of automatic design of advanced industrial systems and proposes a hybrid optimization approach to solve the problem. The problem is multi-objective as it aims at finding solutions that minimize CO2 emissions, transportation time, and costs. The optimization approach combines an evolutionary algorithm and classical mathematical programming to design resilient and sustainable global manufacturing networks. Further, it makes use of the OWL ontology for data consistency and constraint management. The experimental validation demonstrates the effectiveness of the approach in both single and double sourcing scenarios. The proposed methodology, in general, can be applied to any industry case with complex manufacturing and supply chain challenges.

Figures (3)

• Figure 1: An illustrative example of a part of the production assignment realizing the production of Section 6 from two source parts, S6 Lower Shell and S6 Upper Shell, where the double sourcing is required.
• Figure 2: Part of the transport network with transport links, distances according to transportation means, and two warehouses. In the depicted oriented graph, vertices represent production units and edges between vertices represent transport links between production units. There is typically more than one edge between two vertices, where every edge stands for a different transportation resource. There are two warehouses named "City_2 Harbor" and "City_4 Harbor".
• Figure 3: The production graph (top) and an example of a part of the optimized industrial system with details of the corresponding transportation graph (bottom). Arrows in the production graph represent the specialisation relation.