Optimizing Manufacturing Processes With Neural Network-Based Quality Control

View Sample PDF

Author(s): Mandeep Kaur (Department of Electronics and Communication Engineering, Punjabi University, Patiala, India)and Munikrishnaiah Sundararamaiah (Independent Researcher, USA)
Copyright: 2025
Pages: 24
Source title: Expert Artificial Neural Network Applications for Science and Engineering
Source Author(s)/Editor(s): Lingala Syam Sundar (Prince Mohamamd Bin Fahd University, Saudia Arabia), Deepanraj Balakrishnan (Prince Mohammad Bin Fahd University, Saudi Arabia)and Antonio C.M. Sousa (University of Aveiro, Portugal)
DOI: 10.4018/979-8-3693-7250-0.ch012

Keywords: Computer Science & IT / Engineering Science / Engineering Science Reference / Neural Networks

Purchase

View Optimizing Manufacturing Processes With Neural Network-Based Quality Control on the publisher's website for pricing and purchasing information.

Abstract

This chapter discusses how progress made in the area of neural networks has helped to revolutionize the issue of quality assurance in manufacturing systems. It starts by reviewing some of the past approaches to quality control with a view of showing how they fail to meet today's manufacturing demands. The availability of neural networks (deep learning and reinforcement learning) is put forward as a realistic solution to increasing the efficiency of defect detection and improving the process. The chapter also gives an outline of neural network systems with the emphasis of data acquisition, data preprocessing, and choice of the neural network architecture of the implementation tools and platforms, such as TensorFlow and PyTorch. Quantitative findings derived from the case analysis show better enhancement in the defects rate and quality scores when using neural networks instead of traditional techniques.

The IRMA Community

Research IRM

Optimizing Manufacturing Processes With Neural Network-Based Quality Control

Purchase

Abstract

Related Content

IRMA Sponsors