Journal
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
Volume 225, Issue -, Pages -Publisher
ELSEVIER
DOI: 10.1016/j.chemolab.2022.104563
Keywords
Industry 4; 0; Design space; Model inversion; Partial least squares; Prediction uncertainty; Raw material multivariate specifications; Industry 4; 0; Design space; Model inversion; Partial least squares; Prediction uncertainty; Raw material multivariate specifications
Categories
Funding
- Valencian Regional Government: Direccion General de Ciencia e Investigacion [AICO/2021/111]
- Spanish Ministry of Economy, Industry and Competitiveness [DPI2017-82896-C2-1-R]
- European Social Fund [ACIF/2018/165]
Ask authors/readers for more resources
A novel methodology is proposed for defining multivariate raw material specifications to ensure the quality of the manufactured product, which can be used to accept or reject supplier raw material batches.
A novel methodology is proposed for defining multivariate raw material specifications providing assurance of quality with a certain confidence level for the critical to quality attributes (CQA) of the manufactured product. The capability of the raw material batches of producing final product with CQAs within specifications is estimated before producing a single unit of the product, and, therefore, can be used as a decision making tool to accept or reject any new supplier raw material batch. The method is based on Partial Least Squares (PLS) model inversion taking into account the prediction uncertainty and can be used with historical/happenstance data, typical in Industry 4.0. The methodology is illustrated using data from three real industrial processes.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available