Journal of Engineering Design

AI-Driven Human–System Interaction Models for Intelligent and Resilient Manufacturing

The increasing adoption of artificial intelligence in modern manufacturing has created a new paradigm for engineering design that enhances human–system interaction, improves safety, and supports resilient factory operations. AI-driven interaction models allow human operators to communicate more intuitively with machines through real-time analytics, digital twins, adaptive interfaces, and predictive decision-support tools. These advances transform the design of industrial systems by elevating usability, reducing operator errors, and improving workflow reliability in dynamic production environments. Design-focused AI interaction helps manufacturing systems optimize cycle time, enhance quality control, and reduce maintenance interruptions. Human workers benefit from intelligent assistance that improves situational awareness, ergonomics, and task efficiency. From a design perspective, AI enables new approaches in layout planning, collaborative robotics, industrial sensing, and adaptive work instructions. These developments promote a safer and more responsive industrial ecosystem that aligns with the goals of sustainable manufacturing, energy-efficient operations, and intelligent system performance.

Challenges remain in designing AI-driven interaction systems that maintain reliable communication between human workers, automated machinery, and complex factory environments. Integrating AI tools with existing legacy systems involves difficulties in interoperability, system validation, and long-term maintainability. Trust and transparency must be achieved to ensure that operators understand system recommendations, assess automated suggestions, and maintain oversight during abnormal conditions. Human–system interaction must preserve safety and ergonomic priorities while adapting to fluctuating workloads and varying skill levels. Engineering design must also respond to cybersecurity risks, data privacy concerns, and the ethical use of AI-driven decision tools. Rapid industrial deployment requires user-friendly design principles that support worker training, minimize cognitive load, and ensure consistent performance in real-world scenarios. Developing scalable design standards that unify AI models, safety controls, usability engineering, and industrial reliability remains an important research direction for future manufacturing systems. Potential topics included, but not limited,

·       Design principles for AI-driven human–machine interaction in resilient manufacturing systems

·       Digital twin–enhanced engineering design for adaptive production environments

·       AI-assisted safety, ergonomics, and usability engineering in industrial workstations

·       Intelligent interface design for collaborative robots and smart factory systems

·       Real-time control and adaptive design supported by AI decision tools

·       Engineering design for human-in-the-loop operation and multi-agent robotic cells

·       Predictive maintenance design integrating AI analytics and operator supervision

·       Cybersecure interaction design for industrial safety and operational resilience

·       Design and evaluation of cognitive load, situational awareness, and user adaptation in AI-integrated systems

·       Industrial sensing architectures for human–system collaboration and real-time operational feedback