Manuscript Topics

Artificial Intelligence (AI) has become a paradigm shift in engineering systems with data-driven responses to difficult control and decision-making issues. Among these, Hybrid Electric Vehicles (HEVs) are a key application domain due to their complex energy management requirements and time-varying operating conditions. To solve such problems AI is increasingly being coupled with mathematical modeling methods for intelligent control that emulates human thinking. Methods such as singular perturbation are used in chemical engineering to separate rapid and slow dynamics of systems to make control more efficient. One of the most effective control systems in the process is Model Predictive Control (MPC), widely used to control nonlinear systems with constraints. With AI algorithm improvement, MPC is more adaptive and able to optimize performance under real-time uncertainty. Besides, the integration of AI into internet-based computing platforms has enhanced the simulation, prediction and stability analysis of engineering systems. The developments facilitate the creation of intelligent, dependable and energy-efficient solutions in different industrial applications.

Though tremendous advancements have been made, the application of AI-augmented MPC in engineering systems is hampered by a number of practical issues. These are real-time processing difficulties with data, poor generalizability of learned models under different conditions and integration problems across different system architectures. In HEVs the efficacy of energy management relies significantly on the precision of dynamic models and the adaptability of AI algorithms to evolving inputs. Artificial neural networks employed in predictive modeling can be afflicted with too little training data or poorly tuned hyperparameters resulting in lackluster control. Moreover, system stability alongside real-time performance is an ever-lasting concern. Over these drawbacks, rseaecrhers are looking to adaptive AI models, sensor fusion methodologies of high robustness and RL approaches for continuous learning of systems. Improvements in explainable AI and blockchain-based integrity of data are also being explored to enhance transparency and trust. Combined these advancements are bringing the next generation of MPC systems powered by AI closer to increased autonomy, sustainability and human-focussed collaboration.

This special issue examines cutting-edge research and sophisticated methodologies in AI-based mathematical modeling for MPC in sophisticated engineering systems. It presents the incorporation of AI within HEVs and chemical processes to improve control, decision-making and energy management. Solving real-time processing, model generalizability and system stability issues the work underscores solutions including adaptive AI models, RL and explainable AI. The researchers are urged to come up with smart, clear and green MPC mechanisms for future autonomous and energy-saving engineering systems.

The topics of interest include:

• Adaptive Neural Network Models for Real-Time Control in Hybrid Electric Vehicles.
• Reinforcement Learning Strategies for Energy Optimization in Dynamic Driving Systems.
• Explainable AI Frameworks for Trustworthy Model Predictive Control.
• Singular Perturbation Techniques in AI-Enhanced Chemical Process Control.
• Blockchain-Based Data Security in Predictive Maintenance Systems.
• Sensor Fusion Approaches for Robust MPC in Vehicle Energy Management.
• Autonomous Maintenance Systems Using AI for Next-Gen Industrial Control.
• Model Predictive Control Using IoT-Driven Real-Time Data Streams.
• Digital Twin Applications for Predictive Fault Diagnosis in Hybrid Systems.
• Trustworthy AI Interfaces for Human-Machine Collaboration in System Control.
• Natural Language Interfaces for Collaborative Predictive Maintenance Planning.
• Generative AI Techniques for Maintenance Instruction and System Simulation.
• Cyber–Physical System Integration with MPC for Real-Time Industrial Automation

Instructions for authors
https://www.aimspress.com/nhm/news/solo-detail/instructionsforauthors
Please submit your manuscript to online submission system
https://aimspress.jams.pub/