Deep Learning-based System for Quality Control of Coatings in Recess Punch Manufacturing
Turcsanyi, Balint Newton and Saeed, Faisal and Cooper, Emmett (2023) Deep Learning-based System for Quality Control of Coatings in Recess Punch Manufacturing. Lecture Notes on Data Engineering and Communications Technologies. ISSN 2367-4520
|
Text
ICACIN_2022_Paper 3.pdf - Accepted Version Download (1MB) |
Abstract
Increasing efficiency of the quality inspection process is an on-going pursuit in all manufacturing-related industries. The research was proposed by Tooling international ltd – a company situated in the UK – in an attempt to solve a decade-long problem faced when undertaking quality inspection of their coated products. The main objective of this research is to develop a model that detects faulty products with unsatisfactory coating. In this re-search, several convolutional neural network (CNN) architectures were tested in order to find the most suitable one for this particular task. The best performing CNN model delivered 97.68% accuracy which exceed-ed the company’s requirements, providing superior accuracy to when com-pared to current company methods. This study will be used to develop an automated quality inspection machine, thus enhancing the company’s productivity, and will potentially be used as the foundation of further AI-based developments in similar manufacturing-related tasks.
| Item Type: | Article | ||||||
|---|---|---|---|---|---|---|---|
| Identification Number: | https://doi.org/10.1080/08982112.2021.2001828 | ||||||
| Dates: |
|
||||||
| Subjects: | CAH11 - computing > CAH11-01 - computing > CAH11-01-01 - computer science CAH11 - computing > CAH11-01 - computing > CAH11-01-05 - artificial intelligence |
||||||
| Divisions: | Faculty of Computing, Engineering and the Built Environment > School of Computing and Digital Technology | ||||||
| Depositing User: | Faisal Saeed | ||||||
| Date Deposited: | 29 Nov 2022 11:12 | ||||||
| Last Modified: | 05 Oct 2023 14:19 | ||||||
| URI: | https://www.open-access.bcu.ac.uk/id/eprint/13964 |
Actions (login required)
 |
View Item |
Tools
Tools