S. Nannapaneni, S. Mahadevan, A. Dubey, D. Lechevalier, A. Narayanan, S. Rachuri
Smart and Sustainable Manufacturing Systems 2017
Manufacturing system optimization requires understanding how multiple uncertainty sources affect key performance indicators. Manual uncertainty analysis is labor-intensive and error-prone. This work is innovative because it automates Bayesian network construction from domain-specific models, enabling practitioners to incorporate uncertainty in design decisions.
This paper presents automated uncertainty quantification for manufacturing processes using hierarchical Bayesian networks. The work develops methodology for constructing Bayesian networks from semantic system models and physics-based models, enabling automated propagation of multiple uncertainty sources through manufacturing systems. The approach is demonstrated on injection molding processes.
The paper demonstrates automated uncertainty quantification for injection molding processes, successfully identifying key uncertainty sources and their effects on final product quality. The methodology enables systematic analysis of manufacturing performance under uncertainty.
@article{Nannapaneni2017a,
author = {Nannapaneni, S. and Mahadevan, S. and Dubey, A. and Lechevalier, D. and Narayanan, A. and Rachuri, S.},
journal = {Smart and Sustainable Manufacturing Systems},
title = {Automated Uncertainty Quantification Through Information Fusion in Manufacturing Processes},
year = {2017},
issn = {25206478},
number = {1},
pages = {153-177},
volume = {1},
abstract = {Evaluation of key performance indicators (KPIs) such as energy consumption is essential for decision-making during the design and operation of smart manufacturing systems. The measurements of KPIs are strongly affected by several uncertainty sources such as input material uncertainty, the inherent variability in the manufacturing process, model uncertainty, and the uncertainty in the sensor measurements of operational data. A comprehensive understanding of the uncertainty sources and their effect on the KPIs is required to make the manufacturing processes more efficient. Towards this objective, this paper proposed an automated methodology to generate a hierarchical Bayesian network (HBN) for a manufacturing system from semantic system models, physics-based models, and available data in an automated manner, which can be used to perform uncertainty quantification (UQ) analysis. The semantic system model, which is a high-level model describing the system along with its parameters, is assumed to be available in the generic modeling environment (GME) platform. Apart from semantic description, physics-based models, if available, are assumed to be available in model libraries. The proposed methodology was divided into two tasks: (1) automated hierarchical Bayesian network construction using the semantic system model, available models and data, and (2) automated uncertainty quantification (UQ) analysis. A metamodel of an HBN was developed using the GME, along with a syntax representation for the associated conditional probability tables/distributions. The constructed HBN corresponding to a system was represented as an instance model of the HBN metamodel. On the metamodel, a model interpreter was written to be able to carry out the UQ analysis in an automated manner for any HBN instance model conforming to the HBN metamodel. The proposed methodologies are demonstrated using an injection molding process.},
contribution = {minor},
file = {:Nannapaneni2017a-Automated_Uncertainty_Quantification_through_Information_Fusion_in_Manufacturing_Processes.pdf:PDF},
keywords = {uncertainty quantification, Bayesian networks, manufacturing, semantic models, automated analysis},
language = {eng}
}