Journal of Frontiers in Multidisciplinary Research · 2021 · 21 citations · 0 references
ComputingIndustrial EngineeringManufacturing EngineeringBig Data AnalyticsMachine LearningPredictive AnalyticsIndustrial AutomationIndustrial Internet Of ThingsMaintenance AnalyticsPredictive MaintenanceReal-time AnalyticsStream ProcessingIntelligent Manufacturing SystemsMachine Learning For Production SystemsManufacturing Data AnalyticsOperational EfficiencyPredictive Maintenance AnalyticsPredictive Maintenance SchedulingReal-time Data AnalyticsSystematic Literature Review
This paper explores the integration of streaming analytics and predictive maintenance (PdM) in industrial manufacturing systems, focusing on real-time applications to enhance operational efficiency and minimize downtime. By leveraging technologies such as big data analytics, machine learning (ML), and the Internet of Things (IoT), the proposed framework enables manufacturers to process high-velocity data streams, predict equipment failures, and optimize maintenance schedules. A systematic literature review synthesizes insights on streaming analytics, PdM algorithms, and their implementation in manufacturing. Case studies across automotive, aerospace, and chemical industries validate the framework, demonstrating up to 40% reduction in downtime and 30% cost savings. The study contributes to the literature on Industry 4.0 and offers practical guidelines for deploying real-time analytics in manufacturing.