TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Knowledge-based artificial neural network (KB-ANN) in engineering: Associating functional architecture modeling, dimensional analysis and causal graphs to produce optimized topologies for KB-ANNs

Tutkimustuotosvertaisarvioitu

Standard

Knowledge-based artificial neural network (KB-ANN) in engineering : Associating functional architecture modeling, dimensional analysis and causal graphs to produce optimized topologies for KB-ANNs. / Coatanéa, Eric; Wu, Di; Tsarkov, Vadim; Gary Wang, G.; Modi, Siddhant; Jafarian, Hesam.

38th Computers and Information in Engineering Conference. Vuosikerta 1B-2018 The American Society of Mechanical Engineers ASME, 2018.

Tutkimustuotosvertaisarvioitu

Harvard

Coatanéa, E, Wu, D, Tsarkov, V, Gary Wang, G, Modi, S & Jafarian, H 2018, Knowledge-based artificial neural network (KB-ANN) in engineering: Associating functional architecture modeling, dimensional analysis and causal graphs to produce optimized topologies for KB-ANNs. julkaisussa 38th Computers and Information in Engineering Conference. Vuosikerta. 1B-2018, The American Society of Mechanical Engineers ASME, Quebec City, Kanada, 26/08/18. https://doi.org/10.1115/DETC201885895

APA

Coatanéa, E., Wu, D., Tsarkov, V., Gary Wang, G., Modi, S., & Jafarian, H. (2018). Knowledge-based artificial neural network (KB-ANN) in engineering: Associating functional architecture modeling, dimensional analysis and causal graphs to produce optimized topologies for KB-ANNs. teoksessa 38th Computers and Information in Engineering Conference (Vuosikerta 1B-2018). The American Society of Mechanical Engineers ASME. https://doi.org/10.1115/DETC201885895

Vancouver

Coatanéa E, Wu D, Tsarkov V, Gary Wang G, Modi S, Jafarian H. Knowledge-based artificial neural network (KB-ANN) in engineering: Associating functional architecture modeling, dimensional analysis and causal graphs to produce optimized topologies for KB-ANNs. julkaisussa 38th Computers and Information in Engineering Conference. Vuosikerta 1B-2018. The American Society of Mechanical Engineers ASME. 2018 https://doi.org/10.1115/DETC201885895

Author

Coatanéa, Eric ; Wu, Di ; Tsarkov, Vadim ; Gary Wang, G. ; Modi, Siddhant ; Jafarian, Hesam. / Knowledge-based artificial neural network (KB-ANN) in engineering : Associating functional architecture modeling, dimensional analysis and causal graphs to produce optimized topologies for KB-ANNs. 38th Computers and Information in Engineering Conference. Vuosikerta 1B-2018 The American Society of Mechanical Engineers ASME, 2018.

Bibtex - Lataa

@inproceedings{712e3b334e804b209038106862e6d61f,
title = "Knowledge-based artificial neural network (KB-ANN) in engineering: Associating functional architecture modeling, dimensional analysis and causal graphs to produce optimized topologies for KB-ANNs",
abstract = "This article documents a study on artificial neural networks (ANNs) applied to the field of engineering and more specifically a study taking advantage of prior domain knowledge of engineering systems to improve the learning capabilities of ANNs by reducing the dimensionality of the ANNs. The proposed approach ultimately leads to training a smaller ANN, offering advantage in training performances such as lower Mean Squared Error, lower cost and faster convergence. The article proposes to associate functional architecture, Pi numbers, and causal graphs and presents a design process to generate optimized knowledge-based ANN (KB-ANN) topologies. The article starts with a literature survey related to ANN and their topologies. Then, an important distinction is made between system behavior centered topologies and ANN centered topologies. The Dimensional Analysis Conceptual Modeling (DACM) framework is introduced as a way of implementing the system behavior centered topology. One case study is analyzed with the goal of defining an optimized KB-ANN topology. The study shows that the KB-ANN topology performed significantly better in term of the size of the required training set than a conventional fully-connected ANN topology. Future work will investigate the application of KB-ANNs to additive manufacturing.",
keywords = "Additive Manufacturing, Artificial Neural Networks, Classifiers, Dimensional Analysis, Empirical learning, Knowledge Based Artificial Neural Network",
author = "Eric Coatan{\'e}a and Di Wu and Vadim Tsarkov and {Gary Wang}, G. and Siddhant Modi and Hesam Jafarian",
note = "INT=mei,{"}Jafarian, Hesam{"}",
year = "2018",
doi = "10.1115/DETC201885895",
language = "English",
volume = "1B-2018",
booktitle = "38th Computers and Information in Engineering Conference",
publisher = "The American Society of Mechanical Engineers ASME",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Knowledge-based artificial neural network (KB-ANN) in engineering

T2 - Associating functional architecture modeling, dimensional analysis and causal graphs to produce optimized topologies for KB-ANNs

AU - Coatanéa, Eric

AU - Wu, Di

AU - Tsarkov, Vadim

AU - Gary Wang, G.

AU - Modi, Siddhant

AU - Jafarian, Hesam

N1 - INT=mei,"Jafarian, Hesam"

PY - 2018

Y1 - 2018

N2 - This article documents a study on artificial neural networks (ANNs) applied to the field of engineering and more specifically a study taking advantage of prior domain knowledge of engineering systems to improve the learning capabilities of ANNs by reducing the dimensionality of the ANNs. The proposed approach ultimately leads to training a smaller ANN, offering advantage in training performances such as lower Mean Squared Error, lower cost and faster convergence. The article proposes to associate functional architecture, Pi numbers, and causal graphs and presents a design process to generate optimized knowledge-based ANN (KB-ANN) topologies. The article starts with a literature survey related to ANN and their topologies. Then, an important distinction is made between system behavior centered topologies and ANN centered topologies. The Dimensional Analysis Conceptual Modeling (DACM) framework is introduced as a way of implementing the system behavior centered topology. One case study is analyzed with the goal of defining an optimized KB-ANN topology. The study shows that the KB-ANN topology performed significantly better in term of the size of the required training set than a conventional fully-connected ANN topology. Future work will investigate the application of KB-ANNs to additive manufacturing.

AB - This article documents a study on artificial neural networks (ANNs) applied to the field of engineering and more specifically a study taking advantage of prior domain knowledge of engineering systems to improve the learning capabilities of ANNs by reducing the dimensionality of the ANNs. The proposed approach ultimately leads to training a smaller ANN, offering advantage in training performances such as lower Mean Squared Error, lower cost and faster convergence. The article proposes to associate functional architecture, Pi numbers, and causal graphs and presents a design process to generate optimized knowledge-based ANN (KB-ANN) topologies. The article starts with a literature survey related to ANN and their topologies. Then, an important distinction is made between system behavior centered topologies and ANN centered topologies. The Dimensional Analysis Conceptual Modeling (DACM) framework is introduced as a way of implementing the system behavior centered topology. One case study is analyzed with the goal of defining an optimized KB-ANN topology. The study shows that the KB-ANN topology performed significantly better in term of the size of the required training set than a conventional fully-connected ANN topology. Future work will investigate the application of KB-ANNs to additive manufacturing.

KW - Additive Manufacturing

KW - Artificial Neural Networks

KW - Classifiers

KW - Dimensional Analysis

KW - Empirical learning

KW - Knowledge Based Artificial Neural Network

U2 - 10.1115/DETC201885895

DO - 10.1115/DETC201885895

M3 - Conference contribution

VL - 1B-2018

BT - 38th Computers and Information in Engineering Conference

PB - The American Society of Mechanical Engineers ASME

ER -