Artificial neural network enabled accurate geometrical design and optimisation of thermoelectric generator
Artificial neural network enabled accurate geometrical design and optimisation of thermoelectric generator
The ever-increasing demand for renewable energy and zero carbon dioxide emission have been the driving force for the development of thermoelectric generators with better power generation performance. Alongside with the effort to discover thermoelectric materials with higher figure-of-merit, the geometrical and structural optimisation of thermoelectric generators are also essential for maximized power generation and efficiency. This work demonstrates for the first time the application of artificial neural network, a deep learning technique, in forward modelling the maximum power generation and efficiency of a thermoelectric generator and its application in the generator design and optimisation. After training using a dataset containing 5000 3-D finite element method based simulations, the artificial neural networks with 5 layers and 400 neurons per layer demonstrate extremely high prediction accuracy over 98% and are able to operate under both constant temperature difference and heat flux conditions while taking into account of the contact electrical resistance, surface heat transfer and other thermoelectric effects. Coupling with genetic algorithm, the trained artificial neural networks can optimise the leg height, leg width, fill factor and interconnect height of the thermoelectric generator for different operating and contact resistance conditions. With almost identical optimised values obtained, our neural networks can realise geometrical optimisation within 40 s for each operating condition, which is averagely over 1,000 times faster than the optimisation performed by finite element method. The up-front computational time for the neural network can be recovered when more than 2 optimisations are needed. The successful application of this data-driven approach in this work clearly represents a new and cost-effective avenue for conducting system level design and optimisation of thermoelectric generators and other energy harvesting technologies.
Artificial neural network, Genetic algorithm, Optimisation, Thermoelectric generator
Zhu, Yuxiao
0dd2c99f-c036-41dd-817d-4db9ecb051e4
Newbrook, Daniel W
8eb26553-e1e2-492d-ad78-ce51a487f31f
Dai, Peng
1150a00a-e54b-438b-bf51-4e8521c07f66
De Groot, Kees
92cd2e02-fcc4-43da-8816-c86f966be90c
Huang, Ruomeng
c6187811-ef2f-4437-8333-595c0d6ac978
1 January 2022
Zhu, Yuxiao
0dd2c99f-c036-41dd-817d-4db9ecb051e4
Newbrook, Daniel W
8eb26553-e1e2-492d-ad78-ce51a487f31f
Dai, Peng
1150a00a-e54b-438b-bf51-4e8521c07f66
De Groot, Kees
92cd2e02-fcc4-43da-8816-c86f966be90c
Huang, Ruomeng
c6187811-ef2f-4437-8333-595c0d6ac978
Zhu, Yuxiao, Newbrook, Daniel W, Dai, Peng, De Groot, Kees and Huang, Ruomeng
(2022)
Artificial neural network enabled accurate geometrical design and optimisation of thermoelectric generator.
Applied Energy - Elsevier, 305, [117800].
(doi:10.1016/j.apenergy.2021.117800).
Abstract
The ever-increasing demand for renewable energy and zero carbon dioxide emission have been the driving force for the development of thermoelectric generators with better power generation performance. Alongside with the effort to discover thermoelectric materials with higher figure-of-merit, the geometrical and structural optimisation of thermoelectric generators are also essential for maximized power generation and efficiency. This work demonstrates for the first time the application of artificial neural network, a deep learning technique, in forward modelling the maximum power generation and efficiency of a thermoelectric generator and its application in the generator design and optimisation. After training using a dataset containing 5000 3-D finite element method based simulations, the artificial neural networks with 5 layers and 400 neurons per layer demonstrate extremely high prediction accuracy over 98% and are able to operate under both constant temperature difference and heat flux conditions while taking into account of the contact electrical resistance, surface heat transfer and other thermoelectric effects. Coupling with genetic algorithm, the trained artificial neural networks can optimise the leg height, leg width, fill factor and interconnect height of the thermoelectric generator for different operating and contact resistance conditions. With almost identical optimised values obtained, our neural networks can realise geometrical optimisation within 40 s for each operating condition, which is averagely over 1,000 times faster than the optimisation performed by finite element method. The up-front computational time for the neural network can be recovered when more than 2 optimisations are needed. The successful application of this data-driven approach in this work clearly represents a new and cost-effective avenue for conducting system level design and optimisation of thermoelectric generators and other energy harvesting technologies.
Text
Artificial neural network enabled accurate geometrical design and optimisation of thermoelectric generator
- Accepted Manuscript
More information
Accepted/In Press date: 2 September 2021
e-pub ahead of print date: 26 September 2021
Published date: 1 January 2022
Additional Information:
Funding Information:
This work was supported by the UK STFC project (ST/P00007X/1) and EPSRC ADEPT project (EP/N035437/1). The authors acknowledge the use of the IRIDIS High Performance Computing Facility, and associated support services at the University of Southampton, in the completion of this work. DWN would like to thank both BAE and EPSRC for funding the iCASE studentship (EP/R512096/1). All data supporting this study are openly available from the University of Southampton repository at DOI: https://doi.org/10.5258/SOTON/D1903.
Funding Information:
This work was supported by the UK STFC project (ST/P00007X/1) and EPSRC ADEPT project (EP/N035437/1). The authors acknowledge the use of the IRIDIS High Performance Computing Facility, and associated support services at the University of Southampton, in the completion of this work. DWN would like to thank both BAE and EPSRC for funding the iCASE studentship (EP/R512096/1). All data supporting this study are openly available from the University of Southampton repository at DOI: https://doi.org/10.5258/SOTON/D1903.
Publisher Copyright:
© 2021 Elsevier Ltd
Keywords:
Artificial neural network, Genetic algorithm, Optimisation, Thermoelectric generator
Identifiers
Local EPrints ID: 451864
URI: http://eprints.soton.ac.uk/id/eprint/451864
ISSN: 0306-2619
PURE UUID: f7846cca-4e30-419d-9e5b-b665e64663e6
Catalogue record
Date deposited: 02 Nov 2021 17:30
Last modified: 30 Nov 2024 05:06
Export record
Altmetrics
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
