Model-based engineering for the integration of manufacturing systems with advanced analytics

Published

July 10, 2016

Author(s)

David Lechevalier, Anantha Narayanan Narayanan, Sudarsan Rachuri, Sebti Foufou, Yung-Tsun Lee

Abstract

To employ data analytics effectively and efficiently on manufacturing systems, engineers and data scientists need to collaborate closely to bring their domain knowledge together. In this paper, we introduce a domain-specific modeling approach to integrate a manufacturing system model with advanced analytics, in particular, neural networks to model the predictions. This approach combines a set of meta-models and transformation rules based on the domain specific knowledge from manufacturing engineers and data scientists. This approach uses a model of a manufacturing process and its associated data as inputs, and generates a trained neural network model as an output for predicting a quantity of interest. This paper presents 1) the domain- specific knowledge that the approach should employ, 2) the formal workflow of the approach, and 3) a milling process use case to illustrate the proposed approach. We also discuss potential extensions of the approach.

Proceedings Title

13th IFIP International Conference on Product Lifecycle Management (PLM16)

Conference Dates

July 11-13, 2016

Conference Location

Columbia, SC, US

Pub Type

Conferences

Download Paper

Local Download

Keywords

data analytics, meta-model, neural network, manufacturing process, predictive modeling

Citation

Lechevalier, D. , Narayanan, A. , Rachuri, S. , Foufou, S. and Lee, Y. (2016), Model-based engineering for the integration of manufacturing systems with advanced analytics, 13th IFIP International Conference on Product Lifecycle Management (PLM16), Columbia, SC, US, [online], https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=920876 (Accessed October 17, 2025)