stdClass Object
(
    [id] => 18118
    [paper_index] => 202511-02-024874
    [title] => AI-POWERED PREDICTIVE MAINTENANCE IN MANUFACTURING
    [description] => 
    [author] => Varuchi Maurya , Dr. Archana Kumar
    [googlescholar] => 
    [doi] => 
    [year] => 2025
    [month] => November
    [volume] => 10
    [issue] => 11
    [file] => fm/jpanel/upload/2025/November/202511-02-024874.pdf
    [abstract] => The emergence of Industry 4.0 has transformed modern manufacturing into a network of intelligent, data-driven systems. Among the technologies driving this change, Artificial Intelligence (AI)-based Predictive Maintenance (PdM) has proven to be one of the most effective tools for enhancing equipment reliability and reducing production downtime. This research paper explores the real-world application of AI-driven PdM in three major manufacturing organizations—General Motors, Siemens, and Bosch—each of which represents a distinct yet successful approach to implementing smart maintenance.
General Motors deployed an AI and IoT-based anomaly detection system, reducing unplanned downtime by 60% and saving approximately $40 million annually. Siemens implemented Digital Twin technology integrated with AI, achieving a 30% reduction in maintenance costs and a 25% increase in operational efficiency. Bosch adopted a cloud-based AI maintenance platform, extending machine lifespan by 25% and cutting costs by 20%.
By comparing these implementations, the study highlights how the integration of AI, IoT, and data analytics transforms tradi- tional maintenance into a proactive, efficient, and sustainable process. The findings reinforce Predictive Maintenance as a key enabler of smart manufacturing and industrial innovation in the era of Industry 4.0.

    [keywords] => Predictive Maintenance, Artificial Intelligence, Ma- chine Learning, Internet of Things, Digital Twin, Industry 4.0, Manufacturing Efficiency, Anomaly Detection, Remaining Useful Life Prediction, Siemens MindSphere, Edge Computing, Indus- trial Automation
    [doj] => 2025-11-14
    [hit] => 
    [status] => 
    [award_status] => P
    [orderr] => 33
    [journal_id] => 2
    [googlesearch_link] => 
    [edit_on] => 
    [is_status] => 1
    [journalname] => EPRA International Journal of Research & Development (IJRD)
    [short_code] => IJSR
    [eissn] =>  2455-7838 (Online)
    [pissn] => - -
    [home_page_wrapper] => images/products_image/2-n.png
)
Error fetching PDF file.