UTILIZING MACHINE LEARNING TO ASSESS DATA COLLECTION METHODS IN MANUFACTURING AND MECHANICAL ENGINEERING

Abstract

This study explores the significant impact of machine learning (ML) on data collection methods within the manufacturing and mechanical engineering sectors, emphasizing its superiority over traditional techniques. By analyzing data from 20 case studies and 15 industry reports, the research highlights how ML models such as neural networks and support vector machines enhance accuracy, efficiency, and reliability. The findings reveal that ML-based methods excel in handling large datasets, automating processes, and reducing human error, thereby improving data quality and operational performance. Applications in predictive maintenance and quality control demonstrate substantial reductions in equipment downtime and defect detection errors, alongside streamlined workflows and cost savings. Additionally, the study shows that ML can optimize process parameters and identify bottlenecks more effectively, leading to enhanced overall efficiency in industrial operations. These results underscore the transformative potential of ML in optimizing data collection practices, marking a significant advancement in industrial operations and paving the way for more innovative and efficient practices across the sector.