The industrial sector is currently undergoing a transformative era of intelligent automation driven by Artificial Intelligence (AI) capabilities. This synergy greatly enhances efficiency and seamlessly enables data-driven decision-making processes. These advantages enable more efficient resource allocation and enhance production planning precision. This paper aims to provide state-of-the-art and ongoing developments in the AI landscape within the manufacturing industry. In addition, the review explores the key areas where AI is being applied in manufacturing, such as predictive maintenance, quality control, process optimization, supply chain management, robotics and automation, and intelligent decision support systems. The review also encompasses an exploration of the challenges encountered by the manufacturing sector, alongside an investigation into the potential of AI to mitigate these challenges. Furthermore, this work thoroughly reviews recent AI advancements, including explainable AI, human-robot collaboration, edge computing, and the Internet of Things (IoT) integration. The review concludes by providing recommendations, highlighting best practices, and providing insights into potential collaborative opportunities.

Predictive maintenance is a crucial component of smart manufacturing in Industry 4.0, utilizing data from IoT sensor networks and machine learning algorithms to predict equipment failures before they happen. This proactive approach enables timely maintenance of equipment and machinery, reducing unplanned downtime, extending equipment lifespan, and enhancing overall system reliability, ultimately leading to more efficient and cost-effective operations. Conventional machinery and equipment maintenance approaches often rely on periodic manual inspections, human observations, and monitoring, which can be time-consuming, inefficient, and resource-intensive. Therefore, implementing automation through predictive models based on IoT and machine learning techniques is crucial for optimizing the maintenance of machinery and equipment. This paper aims to leverage machine learning techniques to develop predictive maintenance models, including electric motor temperature and vibration prediction, using data from established sensor networks and production data from ERP systems. The models are designed to predict potential issues within the next ten minutes, such as whether temperature or vibration levels will exceed predefined thresholds.

The meat food manufacturing industries play a crucial role in delivering various meat products to global consumers. However, one of the significant challenges within this industry is optimizing food processing efficiency across various stages, as it directly affects both product quality and production costs. Drying is one of the crucial stages, wherein moisture is extracted from the meat to reach the desired moisture levels. This prevents spoilage and influences product quality, safety, and overall production efficiency. The drying time is variable, contingent on factors such as the type of meat, quantity, environmental factors, and the desired product characteristics. This variability contributes to the complexity and multifaceted nature of the issue. Conventional approaches for estimating drying times often depend on empirical rules or manual observations, which can be time-consuming, subjective, and susceptible to human error. Therefore, implementing an automation solution by developing a predictive model for drying times in meat manufacturing is essential for optimizing the production lifecycle. Recognizing the potential of advanced computational techniques, machine learning algorithms have demonstrated promising results across various predictive tasks in recent years. Building on this, this research paper aims to explore the utilization of machine learning methods in predicting the drying time of meat-based food products incorporating multiple factors including structure and properties of food, environmental factors, food mass, and physical parameters of food containers. Furthermore, the paper explores correlations, performs feature importance analysis, and addresses the challenges and limitations within this context.