Yan-Fu Li, Tsinghua University

Hoang Pham, Rutgers University

Xu-Feng Zhao, Nanjing University of Aeronautics and Astronautics

Industrial systems produce vast sensor-generated datasets that strain computational resources. Advanced machine learning techniques including transfer learning, federated learning, quantum machine learning, and reinforcement learning provide scalable solutions for handling large data volumes and enabling informed decision-making. Recent applications of these techniques to system reliability management encompass fault diagnosis, health assessment, remaining useful life prediction, degradation analysis, and maintenance optimization. This special issue seeks original research papers, reviews, and case studies exploring these emerging applications.

Appel publié par Annals of Operations Research. Voir l'appel sur le site de l'éditeur. Fiche de l'appel sur kerostig.

Potential topics

• Deep learning for anomaly detection and/or fault detection
• Machine learning-enhanced maintenance optimization
• Federated learning for system monitoring and predictive maintenance
• Reinforcement learning for maintenance decision making
• Transfer learning for cross-domain maintenance
• Generative models for synthetic data generation for predictive maintenance
• Self-supervised learning for unlabeled data for fault detection
• Large models for fault detection and/or diagnosis
• Generative models for reliability testing
• Meta-heuristics for large-scale reliability design optimization

Timeline

• September 30, 2026: Submission deadline

Yi-Kuei Lin, National Yang Ming Chiao Tung University

This special issue seeks contributions on reliability modeling and decision support for industrial engineering systems, including manufacturing, supply chains, logistics, energy systems, transportation, and service operations. While traditional probabilistic and stochastic approaches remain important, advances in sensor technologies and data collection have enabled new data-driven approaches that combine machine learning and statistical methods with classical reliability theory.

The special issue welcomes both theoretical developments and practical applications that demonstrate how data-driven reliability analysis can enhance decision-making in maintenance planning, resource allocation, system design, and operational optimization. Papers should show methodological rigor and clear relevance to real-world industrial challenges, illustrating how reliability-informed approaches improve system performance.

Appel publié par Annals of Operations Research. Voir l'appel sur le site de l'éditeur. Fiche de l'appel sur kerostig.

Potential topics

• Data-driven reliability modeling and parameter estimation using operational data
• Reliability analysis using statistical learning and machine learning methods
• Reliability models combining analytical formulations with data-driven learning approaches
• Decision support systems incorporating reliability analysis and risk information
• Optimization and decision-making problems informed by reliability performance
• Predictive maintenance and condition monitoring using data and learning models
• Multistate system and network reliability analysis
• Reliability evaluation of manufacturing, logistics, and supply chain systems
• Reliability modeling in energy, power, and infrastructure systems
• Stochastic modeling and uncertainty analysis in data-driven reliability studies
• Simulation, enumeration, and approximation methods for reliability evaluation
• System design and resource allocation considering reliability and operational data
• Reliability analysis supported by digital twins, data analytics, and intelligent systems
• Reliability, robustness, and resilience of industrial engineering systems

Timeline

• July 31, 2027: Submission deadline