Analysis and Optimization in Smart Manufacturing based on a Reusable Knowledge Base for Process Performance Models

Published

November 1, 2015

Author(s)

Alexander Brodsky, Guodong Shao, Mohan Krishnamoorthy, Anantha Narayanan Narayanan, Daniel Menasce?, Ronay Ak

Abstract

In this paper, we propose an architectural design and software framework for fast development of descriptive, predictive, diagnostic, and prescriptive analytics solutions for dynamic production processes. The proposed architecture and framework are based on a reusable, modular, and extensible Knowledge Base (KB) of process performance models. The approach requires solving the technical challenge of automatic translation methods from a high-level uniform representation of performance models in the Reusable KB into low-level specialized models required by each of the underlying tools, including data manipulation, optimization, statistical learning, estimation, and simulation. We also propose organization and key structure of the reusable KB, composed of atomic and composite process performance models and domain-specific dashboards. Furthermore, we illustrate the use of the proposed design and framework by performing diagnostic tasks on a composite performance model.

Proceedings Title

Proceedings of the IEEE International Conference on Big Data (IEEE BigData 2015)

Conference Dates

October 29-November 1, 2015

Conference Location

Santa Clara, CA, US

Conference Title

2015 IEEE International Conference on Big Data (IEEE Big Data 2015)

Pub Type

Conferences

Keywords

smart manufacturing, data analytics, optimization, reusable knowledge base, process performance models

Citation

Brodsky, A. , Shao, G. , Krishnamoorthy, M. , Narayanan, A. , Menasce?, D. and Ak, R. (2015), Analysis and Optimization in Smart Manufacturing based on a Reusable Knowledge Base for Process Performance Models, Proceedings of the IEEE International Conference on Big Data (IEEE BigData 2015), Santa Clara, CA, US (Accessed December 14, 2024)