Laboratoire des Sciences pour la Conception, l'Optimisation et la Production

International audience

This study proposes an integrated heuristic framework for the strategic optimization of distributed maintenance operations in geo-distributed production systems (GDPS). It introduces a dual-entity maintenance structure comprising a Centralized Maintenance Workshop (CMW) and a Mobile Maintenance Workshop (MMW), aimed at minimizing total long-term maintenance costs. The cost function incorporates transport, operations, and downtime penalties, optimized via a two-stage algorithmic approach: a Maintenance Planning Algorithm (MPA) based on predictive maintenance scheduling, and a Long-term Heuristic Scheduling Algorithm (LHSA) addressing a capacitated vehicle routing problem with time windows (CVRPTW). A novel contribution includes a heuristic for CMW location determination using the weighted barycentre of site failure probabilities and a discrete selection of MMW capacities. Mixed Integer Linear Programming (MILP) and a divide-and-conquer heuristic are utilized to handle the NP-hard nature of the problem. Experimental validation using Weibull-distributed failure data and various cost scenarios demonstrates that the proposed Optimised Maintenance and Capacitated Routing (OMCR) framework can reduce lifecycle maintenance costs by up to 50%, with increased scalability for systems exceeding 30 GDPS. The framework is applicable to sectors requiring high availability and centralized servicing, including aerospace, railway, and energy industries.

This work deals with the generation of theoretical correlation matrices with specific sparsity patterns, associated to graph structures. We present a novel approach based on convex optimization, offering greater flexibility compared to existing techniques, notably by controlling the mean of the entry distribution in the generated correlation matrices. This allows for the generation of correlation matrices that better represent realistic data and can be used to benchmark statistical methods for graph inference.

Data-driven organizations aim to control business decisions based on data. However, despite significant investments in digitalization, studies show that many organizations continue to face challenges in fully realizing the benefits of data. Existing maturity models for digital transformation, data management, and data-driven organizations lack a comprehensive, industry-agnostic, and practically validated approach to addressing industry challenges. This work introduces a refined data management maturity model developed using De Bruin’s maturity model assessment methodology. The model aims to incorporate all key elements of a data-driven organization, emphasizing the interdependencies required to evaluate maturity levels and provide targeted recommendations for addressing data-related challenges during the transition to a data-driven organization. An initial validation with 31 industry experts confirmed the model’s feasibility and practical applicability. As the next step, we plan to validate the model further by deploying the full questionnaire and deriving the maturity of each process dimension, along with its weighting, through assessments with industry partners from various sectors, including automotive, aviation, consumer goods/manufacturing, pharma, and media. Preliminary findings also underscored the importance of a deeper focus on the organization dimension, particularly in the context of Industry 5.0. Future research will refine the model through iterative development phases to address this critical area.

This work deals with the generation of theoretical correlation matrices with specific sparsity patterns, associated to graph structures. We present a novel approach based on convex optimization, offering greater flexibility compared to existing techniques, notably by controlling the mean of the entry distribution in the generated correlation matrices. This allows for the generation of correlation matrices that better represent realistic data and can be used to benchmark statistical methods for graph inference.

This paper provides a comprehensive literature review on the integration of Artificial Intelligence (AI) into Digital Twin (DT) systems for predictive maintenance across various industries. As industries adopt digital transformation, Digital Twins have emerged as powerful tools, linking physical assets with their digital counterparts for real-time monitoring, analysis, and diagnostics. By leveraging AI methods like machine learning and deep learning, predictive maintenance within DTs can identify and mitigate potential failures before they disrupt operations. This review synthesizes recent advancements in AI applications within DTs, examining sector-specific methods, applications, and the impact on operational efficiency. We explore challenges such as real-time data processing, model complexity, and system integration, presenting a comparative analysis across industries including manufacturing, healthcare, energy, and transportation.

In this article, we present the development and analysis of a global model for an automotive production system, focusing on the integration of corrective and preventive maintenance strategies. Using Arena software, we simulate normal system operation, focusing on maintenance operations and strategic decisions. This model provides a valuable reference for understanding standard system behavior, making it easier to optimize maintenance strategies. The results obtained demonstrate the effectiveness of integrating preventive and corrective maintenance approaches, helping to improve the reliability and efficiency of production systems.