Machine Learning in Industrial IoT Applications for Safety, Security, Asset Localization, Quality Assurance, and Sustainability in Smart Production

Machine Learning in Industrial IoT Applications for Safety, Security, Asset Localization, Quality Assurance, and Sustainability in Smart Production

Srinivasa Reddy Vempati, Sai Prasanna Kumar J. V., D. Apparao, B. Ramesh, Ramya Maranan, P. Varaprasada Rao
Copyright: © 2024 |Pages: 18
DOI: 10.4018/979-8-3693-7842-7.ch004
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

This study explores the integration of machine learning techniques, notably Support Vector Machines (SVM) and Convolutional Neural Networks (CNN), with industrial production processes for quality assurance. The emphasis is on examining the performance of SVM and CNN through a rigorous assessment of precision, recall, and F1 score in the Performance Metrics Evaluation. Additionally, the study tests the algorithms against existing baseline approaches, evaluating their accuracy and efficiency in fault identification. The results reveal the consistent and strong performance of SVM and CNN, highlighting their revolutionary potential in revolutionizing quality control systems. The findings provide essential insights into the properties of each algorithm, demonstrating their ability to outperform existing methods and contribute to a more versatile and efficient approach to quality assurance in industrial settings.
Chapter Preview

Metaheuristic and Machine Learning Optimization Strategies for Complex Systems

Top

The background of quality assurance in industrial production processes covers a rich history defined by evolving methodologies and the ongoing search of perfection (Palaniyappan et al., 2022; Sathish et al., 2021). In the conventional setting, quality control has been equated with arduous manual inspection, when professional operators methodically evaluated things for defects (Muthiya et al., 2022; Natrayan, Sivaprakash, et al., 2018; Natrayan & Kumar, 2020). While effective to a certain extent, this approach inherently suffered from limits in scalability, speed, and the capacity to find minor deviations within enormous datasets (Natrayan, Senthil Kumar, et al., 2018; Natrayan & Merneedi, 2020; Yogeshwaran et al., 2020). As industries progressed and production sizes rose, the limitations of human inspection were more clear, encouraging a shift towards more complex and technologically driven solutions (Natrayan et al., 2020).

Complete Chapter List

Search this Book:
Reset