Aug 2026· Journal of Intelligent Decision Making and Information Science· 0 citations· 61 references
TL;DR
An integrated AI-IoT framework for smart manufacturing that continuously acquires machine data, performs real-time analytics, predicts equipment failures, optimizes production scheduling, and supports data-driven decision-making is proposed.
Abstract
Smart manufacturing is transforming industrial production through the integration of the Internet of Things (IoT) and Artificial Intelligence (AI), enabling intelligent decision-making, predictive maintenance, real-time monitoring, and autonomous process optimization. Conventional lean manufacturing techniques primarily rely on human expertise and periodic inspections, limiting their ability to respond dynamically to changing production environments. The convergence of IoT-enabled sensing technologies with AI-driven analytics introduces a new generation of intelligent lean operations capable of minimizing waste, improving productivity, reducing operational costs, and enhancing overall equipment effectiveness (OEE). This paper proposes an integrated AI-IoT framework for smart manufacturing that continuously acquires machine data, performs real-time analytics, predicts equipment failures, optimizes production scheduling, and supports data-driven decision-making. The proposed architecture employs interconnected sensors, edge computing, cloud analytics, machine learning models, and digital dashboards to improve operational efficiency while maintaining product quality and resource sustainability. Performance evaluation demonstrates improvements in production throughput, energy efficiency, machine utilization, defect reduction, predictive maintenance accuracy, and manufacturing flexibility compared with conventional manufacturing systems. The proposed framework provides an intelligent, scalable, and sustainable solution aligned with Industry 4.0 principles and offers practical guidance for implementing AI-enabled lean manufacturing across modern industrial enterprises.
Smart manufacturing analytics (sma) is a key component of industry 4.0 that combines the industrial internet of things (iiot), artificial intelligence (ai), machine learning (ml), cloud and edge computing, and big data analytics to improve manufacturing processes. It continuously collects and analyzes real-time data from sensors, machines, robots, and production systems to support intelligent decision-making.sma enables predictive maintenance, fault detection, quality control, energy optimization, and production forecasting, leading to higher productivity, reduced downtime, improved product quality, and lower operational costs. By integrating iiot with advanced analytics, smart manufacturing analytics supports the development of intelligent, autonomous, and sustainable manufacturing systems for the next generation of smart factories.
Iyengar P.K· International Journal of Int...· 0 citations
The rapid advancement of Industry 4.0 has transformed conventional manufacturing into intelligent smart factories by integrating Industrial Internet of Things (IIoT), cyber-physical systems, cloud computing, and artificial intelligence (AI). As manufacturing environments become increasingly complex, traditional human-driven decision-making is insufficient for real-time production optimization. Autonomous Decision Support Systems (ADSS) address this challenge by combining AI, machine learning, digital twins, edge computing, and predictive analytics to enable intelligent, data-driven decision-making with minimal human intervention. This paper presents a scalable ADSS framework that integrates IIoT, edge-cloud computing, and digital twin technology for real-time monitoring, predictive maintenance, dynamic scheduling, and autonomous production optimization. The proposed architecture includes data acquisition, preprocessing, feature engineering, predictive analytics, decision optimization, autonomous execution, and continuous learning. Reinforcement learning and explainable AI improve decision accuracy, adaptability, and transparency, while federated learning enhances data privacy and reduces communication latency. Experimental results demonstrate significant improvements in production efficiency, equipment utilization, predictive maintenance, energy efficiency, quality control, and manufacturing responsiveness compared to conventional decision support systems. The proposed framework provides a scalable foundation for Industry 5.0, enabling sustainable, resilient, and intelligent manufacturing through seamless collaboration between human expertise and autonomous AI systems.
Jose Fernandez, Marta Silva· International Journal of Int...· 0 citations
Manufacturing systems increasingly require real-time performance monitoring and data-driven optimization to reduce downtime, stabilize quality, and support flexible production. Although Internet of Things (IoT) and Industrial Internet of Things (IIoT) technologies have been widely discussed in smart manufacturing, existing studies often treat sensing, key performance indicators (KPIs), analytics, and decision support as separate concerns. This paper presents a structured literature review and conceptual synthesis of IoT-enabled performance monitoring and optimization in manufacturing systems, with emphasis on recent work in IIoT architectures, edge and cloud analytics, digital twins, predictive maintenance, and manufacturing KPIs. The main contribution is an integrated five-layer conceptual framework that connects physical sensing and data acquisition, edge computing and connectivity, data management and integration, analytics and intelligence, and application-level decision support. The framework clarifies how shop-floor data can be transformed into KPI-oriented insights and optimization actions while accounting for cybersecurity, interoperability, data governance, scalability, and human-in-the-loop decision-making. An illustrative automotive parts/CNC manufacturing scenario demonstrates the framework's potential application; however, no simulation, pilot deployment, or quantitative validation is claimed. The review concludes by outlining implementation considerations and a validation roadmap for future empirical studies, including digital-twin simulation, pilot testing, baseline KPI comparison after implementation, and cost-benefit assessment.
Sami Gazem Abdullah Thabet, M. Amrani· 2026 6th International Confe...· 0 citations
Findings indicate that AI-enabled digital twins significantly improve equipment reliability, reduce unexpected failures, enhance resource utilization, and enable proactive manufacturing strategies, however, challenges related to interoperability, cybersecurity, computational complexity, data quality, and governance remain critical barriers to widespread industrial adoption.
H. Mahmood· European International Journ...· 0 citations
Accurate production has been facilitated as a pillar in the contemporary industrialization, prompted by the growing desire of quality products, decreasing production expenses, minimal wastes, and accelerated time-to-market. The technology behind Internet of Things (IoT) has converged with Big Data analytics which has drastically changed conventional manufacturing paradigms that have permitted real time monitoring, intelligent decision-making and predictive control of manufacturing processes. IoT makes it easy to pervasively sense and interconnect machines, tools, products and human operators, creating large volumes of heterogeneous data from the manufacturing lifecycle. The computation and analytical resources needed to store, process and extract actionable information out of this data are available through the use of big data technologies. The following paper demonstrates an in-depth study of the methods of integrating IoT and Big Data to achieve precision manufacturing. It examines system architecture, data acquisition, architecture, analytics, and decision-support models that promote accuracy and efficiency in the processes and quality in the products. An extensive literature review identifies areas of recent innovations and research lag in the field of smart manufacturing, Industrial IoT (IIoT) and data-driven manufacturing. The suggested methodology gives a description of an end-to-end system that includes the deployment of sensors, data ingestion, data preprocessing, analytics, and feedback control. The experimental findings and discussion illustrate how the Big Data analytics based on IoTs enhance predictive maintenance, quality assurance and optimization processes. The paper also ends with a note on the major challenges, research directions and the use of new technologies like artificial intelligence and digital twins in enhancing precision manufacturing.
Liam Walker, Grace Young· International Journal of Mod...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
