|
Title:
|
POTENTIALS, LIMITS AND CHALLENGES OF USING DATA SCIENCE METHODS TO IMPROVE QUALITY PROCESSES IN MANUFACTURING INDUSTRY |
|
Author(s):
|
Jens Kiefer, Lisa Ollinger, Melina Precht and Kai Beer |
|
ISBN:
|
978-989-8704-50-4 |
|
Editors:
|
Piet Kommers, Mário Macedo, Guo Chao Peng and Ajith Abraham |
|
Year:
|
2023 |
|
Edition:
|
Single |
|
Keywords:
|
Data Science, Artificial Intelligence (AI), Quality Processes, Manufacturing Industry |
|
Type:
|
Full |
|
First Page:
|
269 |
|
Last Page:
|
276 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
This paper presents potentials, limits and challenges of using data science methods to improve quality processes in manufacturing industry. Apart from scientific discussions, this paper focuses on the specific application of data science methods based on real conditions and data from manufacturing industry. The application data, processes and all technical and organizational conditions originate from the foundry sector. As a first step, all necessary terms are explained and the most important processes and characteristics of the considered application scenario 'quality processes of a contract manufacturer for cast components' are illustrated. By means of two practical examples, potentials, limits and challenges of using data science methods in operational practice are critically evaluated. In terms of a socio-technical overall view, not only methodical issues but also information-technical and organizational aspects are discussed. The collected findings ultimately lead to recommendations for action, which are intended to give companies a kind of framework for a meaningful economic use of data science methods in operational practice. |
|
|
|
|
|
|
