The science of supporting knowledge-intensive activities

Advanced computing methods and related technologies are changing the way engineers interact with the information infrastructure. Explicit knowledge representation formalisms and new reasoning techniques are no longer the sole territory of computer science. For knowledge-intensive tasks in engineering, a new philosophy and body of knowledge called Engineering Informatics is emerging.

Advanced Engineering Informatics solicits research papers with particular emphases both on 'knowledge' and 'engineering applications'. As an international Journal, original papers typically:

• Report progress in the engineering discipline of applying methods of engineering informatics.
• Have engineering relevance and help provide the scientific base to make engineering decision-making more reliable, spontaneous and creative.
• Contain novel research that demonstrates the science of supporting knowledge-intensive engineering tasks.
• Validate the generality, power and scalability of new methods through vigorous evaluation, preferably both qualitatively and quantitatively.

In addition, the Journal welcomes high quality review articles that summarise, compare, and evaluate methodologies and representations that are proposed for the field of engineering informatics. Similarly, summaries and comparisons of full-scale applications are welcomed, particularly those where scientific shortcomings have hindered success. Typically, such papers have expanded literature reviews and discussion of findings that reflect mastery of the current body of knowledge and propose novel additions to contemporary research.

Papers missing explicit representation and use of knowledge, such as those describing soft computing techniques, mathematical optimization methods, pattern recognition techniques, and numerical computation methods, do not normally qualify for publication in the Journal. Papers must illustrate contributions using examples of automating and supporting knowledge intensive tasks in artifacts-centered engineering fields such as mechanical, manufacturing, architecture, civil, electrical, transportation, environmental, and chemical engineering. Papers that report application of an established method to a new engineering subdomain will qualify only if they convincingly demonstrate noteworthy new power, generality or scalability in comparison with previously reported validation results. Finally, papers that discuss software engineering issues only are not in the scope of this journal.

Special Issue on Towards a Cognitive Product Design and Manufacturing System: Enhancing Industrial Information Integration with KG and/or LLM
提出日: 2025-02-28

Current product design and manufacturing systems (PDMS) have embraced perception technology with excellent performance, such as recognizing objects from sketches and recognizing objects in assembly process. The next step is enhancing the cognitive capability of PDMS, i.e. the capability of understanding, reasoning and learning design and manufacturing information/knowledge. Given a task or object, a cognitive PDMS should know “what-it-is”, “what-I-can-do” and “how-to-do”.

To achieve this, the PDMS should integrate related information/knowledge as much as possible and transform the related information/knowledge into machine-readable and machine-understandable format. But a critical issue in PDMS is that the information/knowledge in this area is usually multi-sourced and multi-modal. Two research topics still need to be further investigated: 1) how to integrate and understand the multi-sourced and multi-modal knowledge in PDMS in the semantic level, 2) how to apply the integrated information/knowledge with semantic meanings for the product design and manufacturing tasks.

The convergence of large language models (LLMs) and knowledge graphs (KGs) presents a promising opportunity for advanced PDMS. KG enhances cognitive capabilities, such as semantic understanding and complex reasoning, while LLMs could exploit pre-training techniques for comprehensive understanding and reasoning. The collaboration of LLMs and KGs would advance product design and manufacturing systems on many scenarios, such as requirement extraction based on multimodal data, multimodal design case retrieval, assembly process recommendation in natural interactions, real-time production process monitoring and optimization, etc. Despite successes, studies on LLMs and KGs in PDMS remain limited. This special issue (SI) welcomes researchers, scholars, and practitioners to contribute original research papers, reviews, and case studies that explore the applications of LLMs and/or KGs in PDMS area. The topics of interest include, but are not limited to:

    Theory and framework of LLM/KG-augmented PDMS
    Knowledge integration/reasoning/management/application approaches in PDMS
    Data integration/analysis/management/application approaches in PDMS
    Advanced product design approaches using KG or LLM, e.g., complex product design approach, collaborative design approach, bio-inspired design approach, conceptual product design approach, embodiment design approach, etc.
    Advanced manufacturing approaches using KG or LLM, e.g., assembly approach, human-robot collaboration approach, quality control approach, etc.
    The mechanism of LLM-KG integration in PDMS
    Review articles of LLM/KG-driven PDMS
    Case studies of LLM/KG-driven PDMS

Guest editors:

Prof. Ying Liu
Cardiff University, Cardiff, United Kingdom

Dr. Zuoxu Wang
Beihang University, Beijing, China

Dr. Xinyu Li
Donghua University, Shanghai, China

Dr. Ru Wang
Beijing Institute of Technology, Beijing, China

Dr. Xingyu Li
Purdue University, West Lafayette, IN, United States

Prof. Ang Liu
University of New South Wales, Sydney, Australia

Special Issue on Human-AI Collaboration for Engineering Designs and Services in the Evolution of Industry 5.0 and Beyond
提出日: 2025-03-31

In the field of engineering, the arrival of the digital transformation era has brought about a fundamental paradigm change that presents both previously unthinkable possibilities and difficult challenges (Lee et al., 2021). One notable challenge is the increasing complexity of cybersecurity threats, as interconnected systems become more prevalent, posing risks to integrity and security of critical engineering infrastructure. Additionally, the rapid pace of technological evolution has led to challenges in workforce adaptation, requiring continuous skill development to keep pace with emerging technologies and methodologies. Moreover, ethical implications surrounding the use of artificial intelligence (AI) in engineering, such as bias in algorithms and responsible technology integration, represent another significant challenge that necessitates careful consideration and resolution within the evolving digital landscape (Lee et al., d2021; Lepri et al., 2021; Rožanec, et al., 2023). The fast adoption of modern technologies by various industries has made the integration of AI and human intelligence (HI) a crucial focus in the field of engineering designs and services (Lee et al., 2022; Lepri et al., 2021; Rožanec, et al., 2023, Agrawal et al., 2023). The transition from Industry 4.0 to Industry 5.0 represents a critical turning point in the dynamic environment of the digital transformation age, stressing a deep reorientation towards human-centric, linked systems (Zhang et al., 2023; Zizic et al., 2022). The essential requirement for research on human-AI collaboration, which is emphasized by a number of aspects, is at the center of this shift. Industry 5.0 sees a future where human creativity and intuition are crucial, encouraging collaborative innovation in engineering designs and services, whereas Industry 4.0 was primarily focused on technology efficiency (Trappey et al., 2017; Marcon et al, 2022; Zizic et al., 2022). The shift to Industry 5.0 demands efficient decision-making that combines human contextual awareness with AI-driven insights. Furthermore, social and ethical issues take center stage, necessitating a responsible integration of AI that is consistent with human values (Rožanec et al., 2023; Grabowska et al., 2022, Colabianchi et al., 2023). Research on human-AI collaboration is crucial for developing educational initiatives that highlight the symbiotic relationship between people and AI as we equip the labor force for Industry 5.0 (Grabowska et al., 2022; Lepri et al., 2021; Zhang et al., 2023). Digital Twin as a highly automated, AI-enabled artifact heavily impacts the Human-Machine collaboration: “Where humans fit in?” (Agrawal et al., 2023, Colabianchi et al., 2023). Human-AI collaboration refers to the synergistic and interactive partnership between HI and AI systems to achieve shared goals or tasks. It involves the seamless integration of human expertise, creativity, and contextual understanding with the computational capabilities of AI, fostering a mutually beneficial relationship (Grabowska et al., 2022; Lepri et al., 2021; Zhang et al., 2023, Agrawal et al., 2023). This collaboration often encompasses joint decision-making, problem-solving, and information processing, where the strengths of both human and AI entities are leveraged to enhance overall performance and outcomes. In the context of Industry 5.0 and digital transformation, human-AI collaboration emphasizes a cooperative and symbiotic approach, recognizing the unique strengths of each component and optimizing their collective potential for innovation, efficiency, and responsible technological integration.
We extend an invitation to researchers, academics, and industry professionals to participate in a thorough examination of the field of human-AI collaboration as it develops in relation to engineering designs and services as Guest Editors of this special issue. The combination of AI and HI is changing the engineering design and service landscape in the age of digital transformation. In the context of engineering, this special issue seeks to investigate and present cutting-edge research, approaches, and case studies that demonstrate the dynamic interplay between human expertise and AI technologies. A wide range of subjects pertaining to human-AI collaboration in engineering designs and services will be covered. Among the possible topics of interest include, but not
1. Theoretical foundations and concepts of human-AI collaboration on engineering designs and services

Exploring cognitive models for Human-AI interaction in engineering designs
Developing conceptual frameworks for ethical Human-AI Collaboration in engineering services
Exploring innovation theories in Human-AI Co-Creation for engineering solutions

2. Human-AI collaborative design processes

Examining how humans and AI systems collaborate in the design process, exploring the challenges and opportunities for enhancing creativity, efficiency, and innovation.
Exploration of collaborative frameworks that seamlessly integrate human and AI contributions in the design and innovation processes within engineering disciplines.
Analyze the evolving skillsets required in the era of human-AI collaboration and propose strategies for upskilling the workforce.

3. Human-AI interaction and human-AI systems design

Development of interfaces and interaction models that facilitate effective communication and collaboration between human (designer, engineer, etc.) and AI algorithms, ensuring seamless integration and mutual understanding.
Investigating User Experience (UX) principles that optimize the integration of AI tools into daily workflows, ensuring a positive and efficient user experience.
Exploring how AI technologies can augment human cognitive abilities, leading to enhanced problem-solving, decision-making, and creativity in the workplace.

4. Human-centric and AI-augmented designs and services in the evolution of Industry 5.0

Integrating user-centric approaches in the design and implementation of digital transformations under Industry 5.0.
Exploring generative AI-driven digital transformations from a human factor perspective under Industry 5.0.
Examining human-AI collaboration in enhancing engineering services, such as manufacturing monitoring, and optimization, quality assurance and maintenance, and also exploring new service models enabled by human-AI collaboration.

5. Neuro-informed AI systems for enhancing human design decision-making in engineering

Leveraging neuroscientific principles for effective decision making and management strategies.
Understanding the impact of neuro management on organizational performance and effectiveness of product and service design.
Exploring scenarios of neuro management, emotional intelligence in engineering management and decision making.

6. Adaptive learning environments for user acceptance and adoption of human-AI collaboration in engineering

Exploring approaches to integrating human-AI collaboration into engineering education and training programs, preparing the next generation of engineers for a collaborative digital future.
Studies on factors influencing the acceptance and adoption of human-AI collaboration by engineering professionals and the broader community.
Examining human-AI collaboration in educational settings, tailoring learning experiences to the individual needs and learning styles of students.

7. Ethical considerations in human-AI cooperative Industry 5.0
Understanding ethical and responsible AI for human-centered technological innovation.
Investigations into ethical implications, challenges, and responsible practices concerning the collaboration between humans and AI in engineering contexts.
Addressing societal concerns and ensuring responsible technological innovation in Human-AI Cooperative Industry 5.0.
Handling issues of trust and risks in human-AI collaborative Industry 5.0 and beyond.
Handling of legislative and regulatory rules and practices in human-AI collaborative Industry 5.0.

8. Case studies and best practices in human-AI collaborations

Evolution of human roles and responsibilities in human-AI collaborative Industry 5.0 and beyond.
Presenting real-world engineering applications and success stories in human-centered digital transformations.
Exploring best practices and changing dynamics with advanced digital transformation enablers, emphasizing human-AI collaborative Industry 5.0.

Guest editors:
Prof. Amy TrappeyNational Tsing Hua University, Hsinchu, Taiwan
Dr. Josip StjepandicPROSTEP AG, Darmstadt, Germany
Prof. John MoRMIT University, Melbourne, Australia
Dr. Ching-Hung LeeXi'an Jiaotong University, Xi'an, China
Dr. Yi ZhangUniversity of Technology Sydney, Sydney, Australia 

Special Issue on Human-Robot Interactions in Construction
提出日: 2025-03-31

The construction sector is the foundational sector of the worldwide economy. However, the construction industry faces challenges of insufficient safety and labor. Thus, construction robots are invented and applied to improve safety and (partially) substitute construction workers and/or machines. Human-robot interactions (HRIs) appear as a new construction environment. With the development of artificial intelligence technology, sensor technology and BIM technology, construction robotics for on-site construction is maturing, and single-task construction robots (handling robots, installation robots, etc.) and integrated robots are emerging in large numbers on construction sites.

The increased use of robots in construction is changing the skill requirements of construction workers, construction safety management, and the plan of labor and machines. Thus, HRIs may bring new challenges and benefits for construction workers, such as distraction by robots and active dodging of workers[2]. Considering the various types of robots and workers, HRIs are complex to study and manage. Compared with manmade robots, workers are harder to understand and control. Thus, comprehensive understanding and effective management of construction workers in HRIs are vital for smart construction.

The academia is also actively discussing issues related to HRIs, including risk identification, skill training, etc. Recently, the research has been more in-depth, including five main contents: first, how robots influence construction workers in HRIs; second, how to train construction workers to adapt to HRIs; third, AI-based robots who could recognize construction workers and react to workers’ behaviors; fourth, safety issues and management of HRIs; fifth, how to improve the effectiveness of HRIs.

As an emerging cross-discipline, human-computer interaction technology has been actively applied in various fields. However, with the emergence of new production modes, not all the consequent new problems have been properly resolved. The most basic issues of how workers and robots interact with each other, such as the degree of workers' trust in robots in HRI, have not yet been discussed and solved in depth. Most of the HRIs in construction are human-led, and the autonomy of the robots needs to be further developed. Considering the complexity and uniqueness of the HRI process, it is unclear how the HRI process will impact construction productivity. Furthermore, it is difficult to achieve HRI stability with a single human-computer interface. This requires further refinement of the integration of multiple interfaces and multi-sensory channels to improve the reliability and stability of perceiving and communicating human intentions.

This special issue addresses this void by specifically encouraging state-of-the-art research that provides theoretical breakthroughs into understanding and optimizing HRIs. The SI accepts scientific contributions based on different cognitive, behavioral, and managerial methodologies.

Guest editors:

Assoc Prof. Jing Lin
Dalian University of Technology, Dalian, China

Prof. Eric Jing Du​​
University of Florida, Gainesville, Florida, United States of America

Dr. Brian Guo
University of Canterbury, Christchurch, New Zealand