Industrial engineering is one of the earliest fields to utilize computers in research, education, and practice. Over the years, computers and electronic communication have become an integral part of industrial engineering. Computers & Industrial Engineering (CAIE) is aimed at an audience of researchers, educators and practitioners of industrial engineering and associated fields.

It publishes original contributions on the development of new computerized methodologies for solving industrial engineering problems, as well as the applications of those methodologies to problems of interest in the broad industrial engineering and associated communities. The journal encourages submissions that expand the frontiers of the fundamental theories and concepts underlying industrial engineering techniques.

CAIE also serves as a venue for articles evaluating the state-of-the-art of computer applications in various industrial engineering and related topics, and research in the utilization of computers in industrial engineering education. Papers reporting on applications of industrial engineering techniques to real life problems are welcome, as long as they satisfy the criteria of originality in the choice of the problem and the tools utilized to solve it, generality of the approach for applicability to other problems, and significance of the results produced.

A major aim of the journal is to foster international exchange of ideas and experiences among scholars and practitioners with shared interests all over the world.

Special Issue on Machine Learning and Optimization Methodologies in Railway Transportation
Submission Date: 2025-12-31

Railway optimization problems are inherently complex due to various factors, such as safety requirements, capacity limitations, and large-scale problem sizes. This complexity makes precise modeling and obtaining accurate solutions highly challenging, often necessitating a trade-off between computational performance and solution quality. In recent years, the rapid development of Machine Learning (ML) has driven innovative research in railway transportation, bringing many advantages and solutions. The application of ML enables in-depth analysis and exploration of the massive data generated within railway systems, uncovering hidden patterns and trends. Moreover, ML can also overcome the limitations of traditional methods. For example, when combined with optimization methodologies, ML may optimize the decision-making process, provide an innovative and effective means to significantly enhance the accuracy, timeliness, and scientific nature of railway management decisions. Therefore, the comprehensive application of ML and optimization methodologies holds enormous potential for addressing challenges in railway transportation.

Guest editors:

Prof. Maged Dessouky
University of Southern California, Los Angeles, CA
maged@usc.edu

Prof. Lixing Yang
Beijing Jiaotong University, Beijing, China
lxyang@bjtu.edu.cn

Dr. Xiaoming Xu
Hefei University of Technology, Hefei, China
xmxu@hfut.edu.cn

Special issue information:

This Special Issue on “Machine Learning and Optimization Methodologies in Railway Transportation” aims to provide a unique platform for researchers and practitioners from academia and industry in railway transportation to share their latest developments, methods, and practices in using ML and optimization technologies to address challenges in railways. With a focus on the integration of ML and OR techniques into Railway Transportation, this SI will encompass a wide range of topics, including but not limited to:

    Train scheduling, rescheduling
    Train marshalling, shunting
    Rolling stock scheduling
    Line planning
    Railway maintenance planning
    Railway infrastructure management
    Railway construction project scheduling
    Railway traffic simulation
    Crew scheduling, rostering
    Intelligent railway transportation systems
    Green and low-carbon railway transportation
    Passenger demand prediction in railways
    Big data analytics in transportation
    Traffic safety and risk management

Special Issue on Industrial AI Empowered Smart Manufacturing
Submission Date: 2026-03-15

Guest editors:

Dr Yiwei Wang,
Manager Guest Editor, Associate Professor, Beihang University, Beijing, China
Email: wangyiwei@buaa.edu.cn 

Dr Christian Gogu,
Professor, Institut supérieur de l'aéronautique et de l'espace, ISAE-SUPAERO Toulouse, Toulouse, France
Email: christian.gogu@isae-supaero.fr

Dr Pai Zheng,
Associate Professor, The Hong Kong Polytechnic University, Hong Kong, Hongkong
Email: pai.zheng@polyu.edu.hk

Dr Yang Zhang,
Professor, Dalian University of Technology, Dalian, China
Email: zy2018@dlut.edu.cn

Dr Jiewu Leng,
Professor, Guangdong University of Technology, Guangzhou, China
Email: jwleng@gdut.edu.cn

Special issue information:

The merging and penetrating of AI into various industries is accelerating the new need for new smart manufacturing methodologies and approaches. Industrial AI is an interdisciplinary research field and is redefining manufacturing and service paradigms. Industrial AI deeply integrates industrial scenarios with advanced AI models/methods such that industrial systems have enhanced perception, cognition, learning, organization, self-decision-making, execution, and mutual adaptation capabilities, which empower the entire product life cycle including design, processing (both machining and additive manufacturing), assembly, operation management, maintenance and services to improve manufacturing quality, efficiency, flexibility, and effectiveness, fostering a human-centric, adaptive, and sustainable industrial ecosystem. The integration of Industrial AI in key domains such as human-robot collaboration (HRC), intelligent assembly, smart operation and maintenance has accelerated the evolution of manufacturing. For instance, the collaborative intelligent assembly of large-scale aerospace products with wearable mixed reality devices has transformed traditional manual operations into intelligent, interactive, and guided paradigms. Similarly, predictive maintenance systems based on advanced prognostics and health management architectures are optimizing the operation and maintenance of critical industrial equipment. To advance the adoption and innovation of industrial AI in manufacturing and services, this Special Issue aims to explore the latest developments in theories, methodologies, tools, systems, and case studies that exemplify intelligent empowerment across various industrial applications.

Topic Areas

Relevant topics for the special issue would include, but would not be limited to, the following:

    Generative AI based scheduling and optimization for dynamic and agile production
    Generative AI in learning policy, decision-making, and advanced control for manufacturing systems
    Generative AI based self-sensing/cognizing/planning/execution in Human-Robot interactions and collaboration in assembly and maintenance.
    Generative AI based solutions for resource allocation and workflow management in assembly and maintenance
    Generative AI based prognostics and health management
    Intelligent systems for ergonomic and empathic collaboration
    Reconfigurable manufacturing systems for adaptive production

Manuscript submission information:

Submission Open Date: 15 September 2025
Submission Due Date: 15 March 2026

Authors are advised to select the article type of 'VSI: Industrial AI Empowered Smart Manufacturing' in the editorial system of the journal, to make sure the submissions are grouped under this special issue for the review process. 

Keywords:

Generative AI, Industrial AI, Assembly, Maintenance and Operation, Reconfigurable Manufacturing Systems