Abstract
Currently, expert knowledge is sometimes the only way to predict the duration of the manufacturing process in relation to conformity. While expert knowledge is difficult to come by and often limited to experience. This paper aims to predict the duration of the manufacturing process by utilizing machine learning and big data. This paper utilizes a real industrial case with the use of neural network regression model that aims to expand the body of knowledge available in the area of predictive manufacturing research. The result of the model suggests the neural network regression model can result in a feasible outcome, while in the meantime overfitting did occur. Mean-squared error, relative squared error, relative absolute error and the correlation coefficient was computed. The paper also addresses the limitations and limited scope of findings and makes suggesting moving forwards.
Original language | English |
---|---|
Title of host publication | Advances in Manufacturing Technology XXXV |
Subtitle of host publication | Proceedings of the 19th International Conference on Manufacturing Research, Incorporating the 36th National Conference on Manufacturing Research, 6-8 September 2022, University of Derby, UK |
Editors | Mahmoud Shafik, Keith Case |
Publisher | IOS Press BV |
Pages | 261-268 |
Number of pages | 8 |
ISBN (Electronic) | 9781643683317 |
ISBN (Print) | 9781643683300 |
DOIs | |
Publication status | Published - 8 Nov 2022 |
Event | 19th International Conference on Manufacturing Research, ICMR 2022 - Derby, United Kingdom Duration: 6 Sept 2022 → 8 Sept 2022 |
Publication series
Name | Advances in Transdisciplinary Engineering |
---|---|
Volume | 25 |
ISSN (Print) | 2352-751X |
ISSN (Electronic) | 2352-7528 |
Conference
Conference | 19th International Conference on Manufacturing Research, ICMR 2022 |
---|---|
Country/Territory | United Kingdom |
City | Derby |
Period | 6/09/22 → 8/09/22 |
Bibliographical note
Funding Information:This project is supported by an Italian company, Gruppo Fabbricazione Meccanica (GFM) SrlGroup. They provided data for this research as raw data; they work with many small independent machine shops. For each order that GFM receives from customers, a decision must be made on how these orders are allocated to these workshops. A very important task of GFM is to decide how to distribute these tasks in order to achieve the best performance indicators such as shortest lead time, cost and quality. The dataset used in this study contains information on 100,000 orders, including requested delivery date, actual production start date, machine code, product code, work location, etc. This data includes all GFM orders from 2015 to 2017.
Publisher Copyright:
© 2022 The authors and IOS Press.
Keywords
- Machine Learning
- Neural Network
- Predictive Manufacturing
- Predictive Scheduling
ASJC Scopus subject areas
- Computer Science Applications
- Industrial and Manufacturing Engineering
- Software
- Algebra and Number Theory
- Strategy and Management