Abstract
The use of data-based models is a favorable way to optimize existing industrial processes. Estimation of these models requires data with sufficient information content. However, data from regular process operation are typically limited to single operating points, so industrially applicable design of experiments (DoE) methods are needed. This paper presents a stepwise DoE and modeling methodology, using Gaussian process regression that incorporates expert knowledge. This expert knowledge regarding an appropriate operating point and the importance of various process inputs is exploited in both the model construction and the experimental design. An incremental modeling scheme is used in which a model is additively extended by another submodel in a stepwise fashion, each estimated on a suitable experimental design. Starting with the most important process input for the first submodel, the number of considered inputs is incremented in each step. The strengths and weaknesses of the methodology are investigated, using synthetic data in different scenarios. The results show that a high overall model quality is reached, especially for processes with few interactions between the inputs and low noise levels. Furthermore, advantages in the interpretability and applicability for industrial processes are discussed and demonstrated, using a real industrial use case as an example.
Highlights
Modern industrial companies are facing several challenges that are caused by legislation and the market
To identify strengths and weaknesses of the proposed methodology, first computer simulation experiments are performed. These experiments mainly focus on the achievable model quality and the interpretation of model hyperparameters, compared to a classical design of experiments (DoE) and modeling methodology
In the last regarded step, p∗, the model quality is assessed on separate test data sets, each consisting of Nt = 1000 data points
Summary
Modern industrial companies are facing several challenges that are caused by legislation and the market. Since production lines are typically operated for decades, methods for improving such existing industrial processes are needed. These improvements could be, for example, to determine the optimal process parameters for an individual product or to predict a need for maintenance of a production plant [1]. Collecting representative data sets for model estimation is a challenging task for real-world industrial processes. These challenges include the availability of data, variations of external influences on a process and the detection of system boundaries [2]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
