Selmaier A, Robitzch P, Mayr A, Fürst J, Franke J (2019)
Publication Type: Book chapter / Article in edited volumes
Publication year: 2019
Publisher: Springer Vieweg
Edited Volumes: Production at the leading edge of technology
City/Town: Berlin, Heidelberg
Pages Range: 513-522
ISBN: 978-3-662-60417-5
URI: https://link.springer.com/chapter/10.1007/978-3-662-60417-5_51
DOI: 10.1007/978-3-662-60417-5_51
X-rays have a large range of medical applications and play an important role in imaging diagnostics. However, the ionized radiation that the patient is exposed to during its application is harmful. In order to keep the radiation exposure as low as possible and at the same time improve image quality, the development of X-ray tubes is being pushed to physical limits. These increased requirements create new challenges not only for product development, but also for the production of X-ray tubes. In addition to the chemical composition of the raw material, the manufacturing processes play a significant role in the quality and service life of the products. In order to obtain updated cause and effect relations and knowledge about the product from the quantity of influencing factors, a cross-process analysis of the manufacturing data is necessary. While classical statistical methods reach their limits in this task, machine learning (ML) algorithms seem promising in the analysis of high-dimensional data. However, according to today's state of the art, such analyses are accompanied by a considerable amount of pre-processing and data cleansing. This paper presents an approach with which the cross-process analysis of product quality can be realized in an efficient manner by creating a standardized procedure. The validation of the approach is based on a prototypical implementation for two product lines.
APA:
Selmaier, A., Robitzch, P., Mayr, A., Fürst, J., & Franke, J. (2019). Cross-Process Quality Analysis of X-ray Tubes for Medical Applications Using Machine Learning Techniques. In Wulfsberg J., Hintze W., Behrens BA. (Eds.), Production at the leading edge of technology. (pp. 513-522). Berlin, Heidelberg: Springer Vieweg.
MLA:
Selmaier, Andreas, et al. "Cross-Process Quality Analysis of X-ray Tubes for Medical Applications Using Machine Learning Techniques." Production at the leading edge of technology. Ed. Wulfsberg J., Hintze W., Behrens BA., Berlin, Heidelberg: Springer Vieweg, 2019. 513-522.
BibTeX: Download