Manuscript Topics

Artificial intelligence (AI) has become a cornerstone technology in predictive maintenance, revolutionizing how industries monitor, diagnose and anticipate equipment failures to optimize operational efficiency and safety. By processing vast amounts of data generated from sensors, machine logs and IoT devices, AI-driven predictive maintenance systems leverage advanced machine learning and deep learning models to identify subtle patterns and anomalies that traditional maintenance strategies often overlook. These systems enable precise forecasting of equipment health, allowing timely interventions that reduce unplanned downtime, extend asset lifespans, and lower maintenance costs. In industrial environments such as automotive manufacturing, aerospace, energy production, and smart factories, AI-enhanced predictive maintenance plays a critical role in managing complex machinery and processes. The fusion of AI with real-time data streams and optimization algorithms facilitates adaptive maintenance schedules that dynamically respond to evolving operating conditions. Furthermore, explainable AI techniques improve transparency and user trust by providing interpretable insights into prediction outcomes, supporting informed decision-making by maintenance personnel and management.

Despite these significant advancements, several challenges remain. Data quality and availability vary widely across industries and facilities, limiting model accuracy and generalizability. Many AI models require large, labeled datasets which are costly and time-consuming to obtain, especially for rare failure events. Integration of AI systems with legacy infrastructure can be complex and resource-intensive. Moreover, models must address heterogeneity in equipment types, operational environments and user requirements while maintaining low latency and computational efficiency particularly when deployed on edge devices with limited processing power. Looking ahead, future research must focus on developing more robust and scalable AI frameworks that can operate effectively under uncertain and dynamic industrial conditions. Advances in transfer learning, few-shot learning, and unsupervised methods offer promising avenues to reduce data dependency and improve model adaptability. The convergence of AI with emerging technologies such as digital twins, robotics, and advanced materials promises to further enhance predictive maintenance capabilities. Additionally, interdisciplinary approaches that combine AI, optimization and human factors engineering are essential to design maintenance systems that are not only intelligent but also user-centric and economically viable. This special issue welcomes contributions that advance the theory and practice of AI-driven predictive maintenance and optimization across industries. We seek innovative research, case studies and reviews addressing technical methodologies, system design, deployment challenges and impacts on operational performance and sustainability.

Topics of interest include but are not limited to:

1. AI-driven predictive maintenance frameworks and architectures
2. Machine learning models for fault detection and prognosis
3. Explainable AI in predictive maintenance applications
4. Optimization techniques for maintenance scheduling and resource allocation
5. Integration of AI and IoT for real-time condition monitoring
6. Edge and cloud computing in industrial predictive maintenance
7. Predictive maintenance in automotive, aerospace, and manufacturing sectors
8. Data fusion and multisensor analytics for equipment health assessment
9. Robotics and automation supporting predictive maintenance
10. AI for battery management and electric vehicle maintenance
11. Case studies on AI-based maintenance in smart factories
12. Challenges in deploying AI predictive maintenance systems at scale
13. Economic and environmental impact of AI-driven maintenance optimization

Instruction for Authors
http://aimspress.com/jgm/news/solo-detail/instructionsforauthors
Please submit your manuscript to online submission system
https://aimspress.jams.pub/