Combinatory finite element and artificial neural network model for predicting performance of thermoelectric generator

Ravi Anant Kishore, Roop L. Mahajan, Shashank Priya

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Thermoelectric generators (TEGs) are rapidly becoming the mainstream technology for converting thermal energy into electrical energy. The rise in the continuous deployment of TEGs is related to advancements in materials, figure of merit, and methods for module manufacturing. However, rapid optimization techniques for TEGs have not kept pace with these advancements, which presents a challenge regarding tailoring the device architecture for varying operating conditions. Here, we address this challenge by providing artificial neural network (ANN) models that can predict TEG performance on demand. Out of the several ANN models considered for TEGs, the most efficient one consists of two hidden layers with six neurons in each layer. The model predicted TEG power with an accuracy of ±0.1 W, and TEG efficiency with an accuracy of ±0.2%. The trained ANN model required only 26.4 ms per data point for predicting TEG performance against the 6.0 minutes needed for the traditional numerical simulations.

Original languageEnglish (US)
Article numberen11092216
JournalEnergies
Volume11
Issue number9
DOIs
StatePublished - Jan 1 2018

Fingerprint

Neural Network Model
Artificial Neural Network
Generator
Finite Element
Neural networks
Thermal energy
Neurons
Computer simulation
Energy
Optimization Techniques
Neuron
Figure
Manufacturing
Predict
Numerical Simulation
Module

All Science Journal Classification (ASJC) codes

  • Renewable Energy, Sustainability and the Environment
  • Energy Engineering and Power Technology
  • Energy (miscellaneous)
  • Control and Optimization
  • Electrical and Electronic Engineering

Cite this

@article{3fb87d9befc34bd88399a08c2cfe6d2d,
title = "Combinatory finite element and artificial neural network model for predicting performance of thermoelectric generator",
abstract = "Thermoelectric generators (TEGs) are rapidly becoming the mainstream technology for converting thermal energy into electrical energy. The rise in the continuous deployment of TEGs is related to advancements in materials, figure of merit, and methods for module manufacturing. However, rapid optimization techniques for TEGs have not kept pace with these advancements, which presents a challenge regarding tailoring the device architecture for varying operating conditions. Here, we address this challenge by providing artificial neural network (ANN) models that can predict TEG performance on demand. Out of the several ANN models considered for TEGs, the most efficient one consists of two hidden layers with six neurons in each layer. The model predicted TEG power with an accuracy of ±0.1 W, and TEG efficiency with an accuracy of ±0.2{\%}. The trained ANN model required only 26.4 ms per data point for predicting TEG performance against the 6.0 minutes needed for the traditional numerical simulations.",
author = "Kishore, {Ravi Anant} and Mahajan, {Roop L.} and Shashank Priya",
year = "2018",
month = "1",
day = "1",
doi = "10.3390/en11092216",
language = "English (US)",
volume = "11",
journal = "Energies",
issn = "1996-1073",
publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",
number = "9",

}

Combinatory finite element and artificial neural network model for predicting performance of thermoelectric generator. / Kishore, Ravi Anant; Mahajan, Roop L.; Priya, Shashank.

In: Energies, Vol. 11, No. 9, en11092216, 01.01.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Combinatory finite element and artificial neural network model for predicting performance of thermoelectric generator

AU - Kishore, Ravi Anant

AU - Mahajan, Roop L.

AU - Priya, Shashank

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Thermoelectric generators (TEGs) are rapidly becoming the mainstream technology for converting thermal energy into electrical energy. The rise in the continuous deployment of TEGs is related to advancements in materials, figure of merit, and methods for module manufacturing. However, rapid optimization techniques for TEGs have not kept pace with these advancements, which presents a challenge regarding tailoring the device architecture for varying operating conditions. Here, we address this challenge by providing artificial neural network (ANN) models that can predict TEG performance on demand. Out of the several ANN models considered for TEGs, the most efficient one consists of two hidden layers with six neurons in each layer. The model predicted TEG power with an accuracy of ±0.1 W, and TEG efficiency with an accuracy of ±0.2%. The trained ANN model required only 26.4 ms per data point for predicting TEG performance against the 6.0 minutes needed for the traditional numerical simulations.

AB - Thermoelectric generators (TEGs) are rapidly becoming the mainstream technology for converting thermal energy into electrical energy. The rise in the continuous deployment of TEGs is related to advancements in materials, figure of merit, and methods for module manufacturing. However, rapid optimization techniques for TEGs have not kept pace with these advancements, which presents a challenge regarding tailoring the device architecture for varying operating conditions. Here, we address this challenge by providing artificial neural network (ANN) models that can predict TEG performance on demand. Out of the several ANN models considered for TEGs, the most efficient one consists of two hidden layers with six neurons in each layer. The model predicted TEG power with an accuracy of ±0.1 W, and TEG efficiency with an accuracy of ±0.2%. The trained ANN model required only 26.4 ms per data point for predicting TEG performance against the 6.0 minutes needed for the traditional numerical simulations.

UR - http://www.scopus.com/inward/record.url?scp=85054088948&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054088948&partnerID=8YFLogxK

U2 - 10.3390/en11092216

DO - 10.3390/en11092216

M3 - Article

AN - SCOPUS:85054088948

VL - 11

JO - Energies

JF - Energies

SN - 1996-1073

IS - 9

M1 - en11092216

ER -