Intelligent monitoring and diagnosis of manufacturing process using an integrated approach of neural network ensemble and genetic algorithm Online publication date: Wed, 10-Dec-2008
by Jianbo Yu, Lifeng Xi
International Journal of Computer Applications in Technology (IJCAT), Vol. 33, No. 2/3, 2008
Abstract: In this paper, a hybrid learning-based model is developed for online intelligent monitoring and diagnosis of manufacturing processes. In this model, a Genetic Algorithm (GA)-based selective Neural Network (NN) ensemble (GASENN) is developed for monitoring the manufacturing process and recognising faulty quality categories of products being produced. In addition, a GA-based Rule (GARule) extraction algorithm is developed to discover the causal relationship between manufacturing parameters and product quality. These extracted rules are applied for fault diagnosis of the manufacturing process to reveal why this has occurred and how to recover from the abnormal condition with the specific guidelines on process parameter settings. Therefore, the seamless integration of GASENN and GARule provides abnormal warning, reveals assignable cause(s) and helps operators optimally set the process parameters. This model is conducted in an Ethernet network environment with various sensors, PLCs, computers, etc. The whole system is successfully applied into a japanning-line, which improves the product quality and saves manufacturing cost.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computer Applications in Technology (IJCAT):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com