The International Journal of Intelligent Real-Time Automation

A journal of IFAC, the International Federation of Automatic Control Artificial Intelligence (AI) is playing a major role in the fourth industrial revolution and we are seeing a lot of evolution in various machine learning methodologies. AI techniques are widely used by the practicing engineer to solve a whole range of hitherto intractable problems. This journal provides an international forum for rapid publication of work describing the practical application of AI methods in all branches of engineering. Submitted papers should report some novel aspects of AI used for a real world engineering application and also validated using some public data sets for easy replicability of the research results.

Papers which do not respect the 4 following conditions will be desk-rejected without being sent to reviewers:

    Papers on new metaphor-based metaheuristics are very rarely accepted by EAAI (see details on this in the guide online).
    The abstract should clearly specify which is the contribution in AI and which is the application in engineering.
    The use of undefined acronyms in the title and in the abstract is forbidden.
    The papers must be formatted in single-column format.

Focal points of the journal include, but are not limited to innovative applications of:

    Internet–of–things and cyber-physical systems
    Intelligent transportation systems & smart vehicles
    Big data analytics, understanding complex networks
    Neural networks, fuzzy systems, neuro-fuzzy systems
    Deep learning and real world applications
    Self-organizing, emerging or bio-inspired system
    Global optimization, Meta-heuristics and their applications: Evolutionary Algorithms, swarm intelligence, nature and biologically inspired meta-heuristics, etc.
    Architectures, algorithms and techniques for distributed AI systems, including multi-agent based control and holonic control
    Decision-support systems
    Aspects of reasoning: abductive, case-based, model-based, non-monotonic, incomplete, progressive and approximate reasoning
    Applications of chaos theory and fractals
    Real-time intelligent automation, and their associated supporting methodologies and techniques, including control theory and industrial informatics
    Knowledge processing, knowledge elicitation and acquisition, knowledge representation, knowledge compaction, knowledge bases, expert systems
    Perception, e.g. image processing, pattern recognition, vision systems, tactile systems, speech recognition and synthesis
    Aspects of software engineering, e.g. intelligent programming environments, verification and validation of AI-based software, software and hardware architectures for the real-time use of AI techniques, safety and reliability
    Intelligent fault detection, fault analysis, diagnostics and monitoring
    Industrial experiences in the application of the above techniques, e.g. case studies or benchmarking exercises
    Robotics

Engineering Applications of Artificial Intelligence publishes:

    Survey papers/tutorials
    Contributed papers — detailed expositions of new research or applications
    Case studies or software reviews — evaluative and descriptive reviews of existing available AI software systems, discussing the experience gained and lessons learnt from using or developing AI systems for engineering applications

    IFAC EAAI Forum — problems arising from engineering practice, needing to be solved by somebody; solutions to problems discussed in this forum or elsewhere; critiques of a position or claim found in the literature

The Editors of Engineering Applications of Artificial Intelligence wish to inform authors that this journal will not publish papers that propose "novel" metaphor-based metaheuristics, unless the authors:

    present their method using the normal, standard optimization terminology;
    show that the new method brings useful and novel concepts to the field;
    motivate the use of the metaphor on a sound, scientific basis;
    present a fair comparison with other state-of-the-art methods using state-of-the-art practices for benchmarking algorithms.

For more details on the International Federation of Automatic Control (IFAC), visit their home page at http://www.ifac-control.org

Software publication

We invite you to convert your open source software into an additional journal publication in Software Impacts, a multi-disciplinary open access journal. Software Impacts provides a scholarly reference to software that has been used to address a research challenge. The journal disseminates impactful and re-usable scientific software through Original Software Publications which describe the application of the software to research and the published outputs.

For more information contact us at: software.impacts@elsevier.com

Special Issue on Physics-Informed Machine Learning (PIML) in Engineering Applications
提出日: 2025-08-11

This Special Issue explores Physics-Informed Machine Learning (PIML) as a transformative approach to solving complex engineering problems. By integrating physics-based priors with ML, PIML enhances predictive accuracy, computational efficiency, and physical consistency. Topics include Physics-Informed Modelling, Hybrid AI Methods, Surrogate Modelling, and Emerging Architectures such as PINNs and PIKANs. The special issue highlights real-world applications in civil engineering, mechanical engineering, electrical engineering, medical and healthcare, mechanics in engineering, and beyond, demonstrating how PIML outperforms traditional AI/ML in data-sparse environments. Contributions will showcase novel methodologies, computational strategies, and engineering breakthroughs enabled by PIML driven solutions.

Guest editors:

Prof. YuanTong Gu
School of Mechanical, Medical and Process Engineering, Queensland University of Technology, Brisbane, Australia
Email: yuantong.gu@qut.edu.au

Prof. Clinton Fookes
Faculty of Engineering, School of Electrical Engineering & Robotics, Queensland University of Technology,  Brisbane, Australia
Email: c.fookes@qut.edu.au

Dr. Kien Nguyen
Faculty of Engineering, School of Electrical Engineering & Robotics, Queensland University of Technology,  Brisbane, Australia
Email: k.nguyenthanh@qut.edu.au

Dr. Chayan Banerjee (Executive Guest Editor)
Faculty of Engineering, School of Electrical Engineering & Robotics, Queensland University of Technology,  Brisbane, Australia
Email: c.banerjee@qut.edu.au

Assoc. Prof. Carlos Murguia
Singapore University of Technology and Design, Singapore
Eindhoven University of Technology, The Netherlands
Email: murguia_rendon@sutd.edu.au; c.g.murguia@tue.nl

Assist. Prof. Maziar Raissi
University of Colorado Boulder, Boulder, USA
Email: Maziar.Raissi@colorado.edu

Prof. Truyen Tran
Deakin University, Geelong, Australia
Email: truyen.tran@deakin.edu.au

Special issue information:

Physics-Informed Machine Learning (PIML) is transforming engineering by enabling data-efficient, physics-consistent, and computationally scalable solutions. Traditional machine learning models rely on statistical correlations, making them less effective with sparse or constrained data. PIML integrates physics-based priors, governing equations, and domain knowledge, enhancing interpretability, generalization, and efficiency.

Beyond Physics-Informed Neural Networks (PINNs), emerging approaches like Physics-Informed Kolmogorov-Arnold Networks (PIKANs), Deep Neural Operators, and Hybrid Modelling are unlocking new capabilities, particularly in structural mechanics, robotics & industrial automation, computer-vision, reinforcement-learning, biomechanics and medicine where conventional methods struggle.

Key Topics of Interest

Physics-Informed Modelling & Hybrid Approaches
Physics-based priors for interpretability and accuracy.
Hybrid modelling, integrating ML with numerical methods (e.g., FEM, CFD, FEA).
Domain decomposition, selectively applying
PINNs/PIKANs with traditional solvers.
Optimization, Theoretical Insights & Uncertainty
Quantification
Optimizing PINNs/hybrid models for performance.
Uncertainty quantification (UQ), including Bayesian PINNs and deep ensembles.
Emerging PIML Architectures
PIKANs for compact, efficient physics-informed learning.
Deep Neural Operators (e.g., DeepONet) for parametric PDE solutions.
Spiking Neural Networks (SNNs) for real-time, low-power PIML on neuromorphic chips.
Surrogate Modelling, Model Fusion & Regularization
PIML-driven surrogate models for high-fidelity physics simulations.
Model fusion for robustness, integrating physics-based and ML models.
Physics-based regularization, enforcing consistency in PIML models.
Real-World PIML Applications -
Civil engineering: Structural health monitoring and damage detection in bridges and buildings, predictive maintenance of infrastructure using sensor data and models, and urban flood modelling and management.
Mechanical engineering: Predicting material fatigue life under cyclic loading, CFD simulations for aerodynamic design, and vibration analysis and control in mechanical systems.
Electrical engineering: Focus on fault detection and diagnosis in power grids, optimization of power electronic devices for efficiency and reliability, and modelling and control of electromagnetic fields in electrical machines.
Intelligent Transportation, Robotics, Industrial Automation: Autonomous vehicle navigation and control using sensor data and physical constraints, robotic manipulation in manufacturing, and multiscale modelling of materials and processes in industrial applications.
Mechanics: Fluid Mechanics, Biomechanics, and Computational Mechanics.
Other engineering applications: the special issue is open to other engineering applications that PIML can be applied to.

Manuscript submission information:

Important Dates:

    Submission Open Date: April 7, 2025
    Submission Deadline: August 11, 2025
    Notification of Acceptance: December 15, 2025

Contributed papers must be submitted via the Engineering Applications of Artificial Intelligence online submission system (Editorial Manager®): Please select the article type “VSI: PIML in Engineering Applications” when submitting the manuscript online.

All submissions deemed suitable to be sent for peer review will be reviewed by at least two independent reviewers. Once your manuscript is accepted, it will go into production and will be simultaneously published in the current regular issue and pulled into the online Special Issue. Articles from this Special Issue will appear in different regular issues of the journal, though they will be clearly marked and branded as Special Issue articles.

Please refer to the Guide for Authors to prepare your manuscript.

For any further information, the authors may contact the Guest Editors.

Keywords:

(PIML) OR (PINNs) OR (PIRL) OR (Hybrid Modelling) OR (Deep Neural Operators) OR (PIKANs) OR (Physics Informed Surrogate Modelling) OR (Uncertainty Quantification) OR (Engineering Applications) OR (Spiking Neural Networks)

Special Issue on Investigating the Use of Quantum Technologies in Industrial and Practical Applications
提出日: 2025-12-31

Quantum computing is seen as the next major advancement in computing, capturing significant interest from the scientific community. These technologies utilize quantum mechanics to develop innovative approaches for efficiently solving a diverse range of problems, including those in machine learning, optimization, and simulation. Leveraging quantum phenomena like superposition and entanglement, quantum information processing and hybrid algorithms (which integrate classical and quantum methods) are anticipated to deliver enhanced speed and accuracy in system modeling and solving complex optimization problems. With the increasing interest in this field, quantum computing has already been successfully applied to various use cases, particularly in addressing industrial challenges.

Moreover, quantum technologies are revolutionizing design, control, and monitoring through new quantum sensors that significantly enhance measurement accuracy. By collecting data at the atomic level, advanced versions of everyday technologies will feature more reliable geolocation and less vulnerable guidance systems, which will be fundamental for many industrial applications.

This special issue aims to promote discussions on the latest discoveries and research achievements, as well as the exchange of innovative ideas in the application of quantum technologies to industry.

Guest editors:

Dr. Eneko Osaba
Tecnalia Research & Innovation Foundation
San Sebastian
20009
Spain
E-mail: eneko.osaba@tecnalia.com

Dr. Esther Villar-Rodriguez
Tecnalia Research & Innovation Foundation
San Sebastian
20009
Spain
E-mail: esther.villar@tecnalia.com

Dr. Izaskun Oregi
Tecnalia Research & Innovation Foundation
San Sebastian
20009
Spain
E-mail: izaskun.oregui@tecnalia.com

Special issue information:

Scope of the Special Issue:

This special issue aims to promote discussions on the latest discoveries and research achievements, as well as the exchange of innovative ideas in the application of quantum technologies to industry.

Topics of interest include, but are not limited to:

    Hybrid classical-quantum methods for addressing optimization problems.
    Application of Quantum Annealers for solving real-world oriented problems.
    Development of quantum-gates based methods (QAOA, VQE…).
    Quantum Algorithms and Complexity.
    Quantum Machine Learning Approaches.
    Latest advances of quantum-inspired computation, especially for optimization, machine learning and deep learning.
    Quantum sensing applied to industrial settings.
    Quantum simulation for complex industrial problems

Applied to the following fields (not limited):

    Transportation and logistics: routing problems, efficient management of vehicle fleets, last-mile logistics, traffic flow optimization...
    Efficient management of warehouses: bin packing problems, collision-free robot path planning, optimization of empty container movements…
    Optimization of industrial processes: job-shop scheduling problem, multi-car paint shop problem…
    Environmentally friendly industrial planning.
    Design of industrial facilities: quadratic assignment problem...

Manuscript submission information:

Tentative Schedule:

    Submission Open Date: March 02, 2025
    Submission Deadline: December 31, 2025
    Notification of Acceptance: March 02, 2026

Contributed papers must be submitted via the Engineering Applications of Artificial Intelligence online submission system (Editorial Manager®): Please select the article type “VSI: Quantum Technologies for Practical Applications” when submitting the manuscript online.

Please refer to the Guide for Authors to prepare your manuscript.

For any further information, the authors may contact the Guest Editors.

Learn more about the benefits of publishing in a special issue.

Interested in becoming a guest editor? Discover the benefits of guest editing a special issue and the valuable contribution that you can make to your field.

Keywords:

(Quantum Optimization) OR (Quantum Annealing) OR (Quantum Gates) OR (Quantum Optimization) OR (Quantum Machine Learning) OR (Quantum Sensing)

Special Issue on Data-Driven and AI-Assisted Evaluation and Design of Cement-Based Materials and Structures for Environmental Sustainability
提出日: 2026-01-31

In recent years, the integration of data analytics and Artificial Intelligence (AI) into the construction sector has begun to transform how materials are developed and used, particularly within the realm of cement-based materials. Driven by the need to minimize environmental impacts and enhance the sustainability and resilience of building practices, these technologies are playing a crucial role in evolving industry standards and practices. However, the challenges of ensuring that these new materials and methods can be introduced in the industry reveal significant gaps in current research, particularly in terms of environmental sustainability.

This special issue focuses on cutting-edge research and innovations in data-driven strategies and AI applications for the sustainable and resilient design of cement-based materials and structures. It features contributions on AI-enhanced predictive modeling, optimization of material compositions, and advanced analytics for design, retrofit, lifecycle assessment, and resource efficiency. These contributions showcase significant progress in reducing environmental impacts and enhancing structural resilience, while also highlighting the need for further research to address challenges like data scarcity, model predictive performances, and the integration of AI with traditional construction methods. This issue aims to drive advancements towards smarter, more resilient, and environmentally friendly building solutions.

Guest editors:

Dr. Jinjun Xu (Executive Guest Editor)
Nanjing Tech University, Nanjing, P.R. China
E-mail: jjxu_concrete@njtech.edu.cn
Areas of Expertise: Recycled Aggregate Concrete and Structures; Low-Carbon Concrete; Steel-Concrete Composite Structures; Data-Driven and AI-Assisted Modeling in Materials and Structures

Dr. Cristoforo Demartino
Roma Tre University, Roma, Italy
E-mail: cristoforo.demartino@me.com
Areas of Expertise: Sustainable Construction Materials; AI-Driven Structural Analysis; Environmental Impact Minimization; Machine Learning in Civil Engineering; Green Building Technologies

Dr. Marco Martino Rosso
Politecnico di Torino, Torino, Italy
E-mail: marco.rosso@polito.it
Areas of Expertise: Artificial Intelligence and Machine Learning in Structural Engineering; Structural Health Monitoring and Modal Analysis; Deep Learning and Data Processing in Structural Assessments; DynamicResponse and Performance of Structures; Structural Optimization and Computational Design

Dr. Kai Wu
Tongji University, Shanghai, P.R. China
E-mail: 03wukai@tongji.edu.cn
Areas of Expertise: Sustainable Construction Materials; AI-Driven construction materials design and performance prediction; Degradation and protection solution for construction material under extreme environment

Dr. Yohchia Frank Chen
Pennsylvania State University, Pennsylvania, USA
E-mail: yxc2@psu.edu
Areas of Expertise: Steel-Concrete Composite Structures; AI-Driven Structural Analysis; Computational Methods in Civil Engineering; Limit State Design

Special issue information:

The issue can accommodate the original contributions from within the below domains (not limited to):

    AI-enhanced material design and evaluation techniques.
    Data-driven approaches to reducing the carbon footprint of cement production.
    Predictive analytics for lifecycle sustainability and performance of cement-based structures.
    Multi-objective optimization of materials for resilience and environmental impact.
    Integration of AI models with experimental and field data.
    Case studies on AI-assisted sustainable construction practices.

This special issue aims to advance knowledge and foster innovation in achieving smarter, more sustainable construction solutions while addressing critical research and practical challenges.

Manuscript submission information:

Important Dates:

    Submission Open Date: May 1, 2025
    Submission Deadline: January 31, 2026
    Notification of Acceptance: July 1, 2026

Contributed papers must be submitted via the Engineering Applications of Artificial Intelligence online submission system (Editorial Manager®): Please select the article type “VSI: Data & AI-CBMS” when submitting the manuscript online.

All submissions deemed suitable to be sent for peer review will be reviewed by at least two independent reviewers. Once your manuscript is accepted, it will go into production and will be simultaneously published in the current regular issue and pulled into the online Special Issue. Articles from this Special Issue will appear in different regular issues of the journal, though they will be
clearly marked and branded as Special Issue articles.

Please refer to the Guide for Authors to prepare your manuscript.

For any further information, the authors may contact the Guest Editors.

Keywords:

AI-assisted material design; Data-driven structural optimization; Sustainable cement-based construction; Lifecycle assessment and resilience; Machine learning in civil engineering; Predictive analytics for structural performance