Abstract
Neural network models have a long history in fuel cell and battery modeling. With the recent advent of deep learning, there is potential for further improvements in these models. Conversely, deep learning is primarily designed for image detection and classification using large data sets and its performance on typical regression tasks in fuel cell and battery modeling remains largely unexplored. In this article, we present a new method for applying deep learning to general vector outputs from battery and fuel cell models and investigate the use of different deep learning architectures. We compare these methods to equivalent Gaussian process (GP) models on a range of regression tasks. We further provide the first rigorous error and asymptotic analysis of the multivariate GP model. For scalar outputs, deep networks are found to be less accurate on small data sets, but for large data sets, convolutional and recurrent networks are able to marginally exceed the accuracy of GP models.
Issue Section:
Research Papers
References
1.
Shah
, A. A.
, Luo
, K.
, Ralph
, T. R.
, and Walsh
, F. C.
, 2011
, “Recent Trends and Developments in Polymer Electrolyte Membrane Fuel Cell Modelling
,” Electrochim. Acta
, 56
(11
), pp. 3731
–3757
. 2.
Ramadesigan
, V.
, Northrop
, P. W. C.
, De
, S.
, Santhanagopalan
, S.
, Braatz
, R. D.
, and Subramanian
, V. R.
, 2012
, “Modeling and Simulation of Lithium-Ion Batteries From a Systems Engineering Perspective
,” J. Electrochem. Soc.
, 159
(3
), pp. R31
–R45
. 3.
Xing
, W.
, Razi
, M.
, Kirby
, R. M.
, Sun
, K.
, and Shah
, A. A.
, 2020
, “Greedy Nonlinear Autoregression for Multifidelity Computer Models at Different Scales
,” Energy AI
, 1
, p. 100012
. 4.
Cai
, L.
, and White
, R. E.
, 2010
, “An Efficient Electrochemical-Thermal Model for a Lithium-Ion Cell by Using the Proper Orthogonal Decomposition Method
,” J. Electrochem. Soc.
, 157
(11
), pp. A1188
–A1195
. 5.
Moccoteguy
, P.
, Pellegrino
, S.
, Ludwig
, B.
, Esposito
, A.
, Iwanschitz
, B.
, and Mai
, A.
, 2019
, “A Novel Approach to Analyse Incomplete Design of Experiments—Application to the Study of the Influence of Operational Parameters on the Performance of a Solid Oxide Fuel Cell Based Micro-Combined Heat and Power System
,” Int. J. Hydrogen Energy
, 44
(2
), pp. 1151
–1165
. 6.
Zhang
, W.
, Cho
, C.
, Piao
, C.
, and Choi
, H.
, 2016
, “Sobol’s Sensitivity Analysis for a Fuel Cell Stack Assembly Model With the Aid of Structure-Selection Techniques
,” J. Power Sources
, 301
, pp. 1
–10
. 7.
Vazquez-Arenas
, J.
, Gimenez
, L. E.
, Fowler
, M.
, Han
, T.
, and Chen
, S.
, 2014
, “A Rapid Estimation and Sensitivity Analysis of Parameters Describing the Behavior of Commercial Li-Ion Batteries Including Thermal Analysis
,” Energy Convers. Manage.
, 87
, pp. 472
–482
. 8.
Wang
, X.
, Li
, M.
, Liu
, Y.
, Sun
, W.
, Song
, X.
, and Zhang
, J.
, 2017
, “Surrogate Based Multidisciplinary Design Optimization of Lithium-Ion Battery Thermal Management System in Electric Vehicles
,” Struct. Multidiscip. Optim.
, 56
(6
), pp. 1555
–1570
. 9.
Radaideh
, M. I.
, Radaideh
, M. I.
, and Kozlowski
, T.
, 2020
, “Design Optimization Under Uncertainty of Hybrid Fuel Cell Energy Systems for Power Generation and Cooling Purposes
,” Int. J. Hydrogen Energy
, 45
(3
), pp. 2224
–2243
. 10.
Du
, W.
, 2013
, “Multi-Scale Modeling, Surrogate-Based Analysis, and Optimization of Lithium-Ion Batteries for Vehicle Applications
,” Ph.D. thesis, University of Michigan
, MI
11.
Maheshwari
, A.
, Dumitrescu
, M. A.
, Destro
, M.
, and Santarelli
, M.
, 2016
, “Inverse Parameter Determination in the Development of an Optimized Lithium Iron PhosphateaGraphite Battery Discharge Model
,” J. Power Sources
, 307
, pp. 160
–172
. 12.
Chun
, H.
, Kim
, J.
, and Han
, S.
, 2019
, “Parameter Identification of n Electrochemical Lithium-Ion Battery Model With Convolutional Neural Network
,” IFAC-PapersOnLine
, 52
(4
), pp. 129
–134
, IFAC Workshop on Control of Smart Grid and Renewable Energy Systems CSGRES 2019. 13.
Dolenc
, B.
, Vrecko
, D.
, Juricic
, D.
, Pohjoranta
, A.
, and Pianese
, C.
, 2017
, “Online Gas Composition Estimation in Solid Oxide Fuel Cell Systems With Anode Off-Gas Recycle Configuration
,” J. Power Sources
, 343
, pp. 246
–253
. 14.
Peksen
, M.
, Blum
, L.
, and Stolten
, D.
, 2012
, “Optimisation of a Solid Oxide Fuel Cell Reformer Using Surrogate Modelling, Design of Experiments and Computational Fluid Dynamics
,” Int. J. Hydrogen Energy
, 37
(17
), pp. 12540
–12547
. 15.
Pohjoranta
, A.
, Halinen
, M.
, Pennanen
, J.
, and Kiviaho
, J.
, 2015
, “Solid Oxide Fuel Cell Stack Temperature Estimation With Data-Based Modeling—Designed Experiments and Parameter Identification
,” J. Power Sources
, 277
(1
), pp. 464
–473
. 16.
Miao
, J.-M.
, Cheng
, S.-J.
, and Wu
, S.-J.
, 2011
, “Metamodel Based Design Optimization Approach in Promoting the Performance of Proton Exchange Membrane Fuel Cells
,” Int. J. Hydrogen Energy
, 36
(23
), pp. 15283
–15294
. 17.
Lobato
, J.
, Canizaresa
, P.
, Rodrigo
, M. A.
, Linares
, J. J.
, Piuleac
, C. G.
, and Curteanu
, S.
, 2009
, “The Neural Networks Based Modeling of a Polybenzimidazole-Based Polymer Electrolyte Membrane Fuel Cell: Effect of Temperature
,” J. Power Sources
, 192
(1
), pp. 190
–194
. 18.
Chang
, K.-Y.
, 2011
, “The Optimal Design for PEMFC Modeling Based on Taguchi Method and Genetic Algorithm Neural Networks
,” Int. J. Hydrogen Energy
, 36
(21
), pp. 13683
–13694
. 19.
Razbani
, O.
, and Assadi
, M.
, 2014
, “Artificial Neural Network Model of a Short Stack Solid Oxide Fuel Cell Based on Experimental Data
,” J. Power Sources
, 246
, pp. 581
–586
. 20.
Pourrahmani
, H.
, Siavashi
, M.
, and Moghimi
, M.
, 2019
, “Design Optimization and Thermal Management of the PEMFC Using Artificial Neural Networks
,” Energy
, 182
(7
), pp. 443
–459
. 21.
Ding
, R.
, Ding
, Y.
, Zhang
, H.
, Wang
, R.
, Xu
, Z.
, Liu
, Y.
, Yin
, W.
, Wang
, J.
, Li
, J.
, and Liu
, J.
, 2021
, “Applying Machine Learning to Boost the Development of High-Performance Membrane Electrode Assembly for Proton Exchange Membrane Fuel Cells
,” J. Mater. Chem. A
, 9
(11
), pp. 6841
–6850
. 22.
Yuan
, Z.
, Wang
, W.
, Wang
, H.
, and Ashourian
, M.
, 2020
, “Parameter Identification of PEMFC Based on Convolutional Neural Network Optimized by Balanced Deer Hunting Optimization Algorithm
,” Energy Reports
, 6
(44
), pp. 1572
–1580
. 23.
Huo
, W.
, Li
, W.
, Zhang
, Z.
, Sun
, C.
, Zhou
, F.
, and Gong
, G.
, 2021
, “Performance Prediction of Protonexchange Membrane Fuel Cell Based on Convolutional Neural Network and Random Forest Feature Selection
,” Energy Convers. Manage.
, 243
(2
), p. 114367
. 24.
Ma
, R.
, Yang
, T.
, Breaz
, E.
, Li
, Z.
, Briois
, P.
, and Gao
, F.
, 2018
, “Data-Driven Proton Exchange Membrane Fuel Cell Degradation Predication Through Deep Learning Method
,” Appl. Energy
, 231
, pp. 102
–115
. 25.
Wang
, F.
, Cheng
, X.
, and Hsiao
, K.
, 2020
, “Stacked Long Short-Term Memory Model for Proton Exchange Membrane Fuel Cell Systems Degradation
,” J. Power Sources
, 448
(6
), p. 227591
. 26.
Li
, W.
, Sengupta
, N.
, Dechent
, P.
, Howey
, D.
, Annaswamy
, A.
, and Uwe Sauer
, D.
, 2021
, “One-Shot Battery Degradation Trajectory Prediction With Deep Learning
,” J. Power Sources
, 506
(1
), p. 230024
. 27.
Zhang
, X.
, Zhou
, J.
, and Chen
, W.
, 2020
, “Data-Driven Fault Diagnosis for PEMFC Systems of Hybrid Tram Based on Deep Learning
,” Int. J. Hydrogen Energy
, 45
(24
), pp. 13483
–13495
. 28.
Liu
, J.
, Li
, Q.
, Yang
, H.
, Han
, Y.
, Jiang
, S.
, and Chen
, W.
, 2019
, “Sequence Fault Diagnosis for PEMFC Water Management Subsystem Using Deep Learning With T-SNE
,” IEEE Access
, 7
, pp. 92009
–92019
. 29.
Li
, H.
, Xu
, B.
, Du
, C.
, and Yang
, Y.
, 2020
, “Performance Prediction and Power Density Maximization of a Proton Exchange Membrane Fuel Cell Based on Deep Belief Network
,” J. Power Sources
, 461
, p. 228154
. 30.
Liu
, X.
, Zhou
, S.
, Yan
, Z.
, Zhong
, Z.
, Shikazono
, N.
, and Hara
, S.
, 2022
, “Correlation Between Microstructures and Macroscopic Properties of Nickel/yttria-Stabilized Zirconia (ni-ysz) Anodes: Meso-Scale Modeling and Deep Learning With Convolutional Neural Networks
,” Energy AI
, 7
, p. 100122
. 31.
Richardson
, R. R.
, Osborne
, M. A.
, and Howey
, D. A.
, 2017
, “Gaussian Process Regression for Forecasting Battery State of Health
,” J. Power Sources
, 357
(23
), pp. 209
–219
. 32.
Yang
, D.
, Zhang
, X.
, Pan
, R.
, Wang
, Y.
, and Chen
, Z.
, 2018
, “A Novel Gaussian Process Regression Model for State-of-Health Estimation of Lithium-Ion Battery Using Charging Curve
,” J. Power Sources
, 384
(1
), pp. 387
–395
. 33.
Tagade
, P.
, Hariharan
, K. S.
, Ramachandran
, S.
, Khandelwal
, A.
, Naha
, A.
, Kolake
, S. M.
, and Han
, S. H.
, 2020
, “Deep Gaussian Process Regression for Lithium-Ion Battery Health Prognosis and Degradation Mode Diagnosis
,” J. Power Sources
, 445
(15
), p. 227281
. 34.
Conti
, S.
, and O’Hagan
, A.
, 2010
, “Bayesian Emulation of Complex Multi-Output and Dynamic Computer Models
,” J. Stat. Plann. Inference
, 140
(3
), pp. 640
–651
. 35.
Higdon
, D.
, Gattiker
, J.
, Williams
, B.
, and Rightley
, M.
, 2008
, “Computer Model Calibration Using High-Dimensional Output
,” J. Am. Stat. Assoc.
, 103
(482
), pp. 570
–583
. 36.
Xing
, W. W.
, Triantafyllidis
, V.
, Shah
, A. A.
, Nair
, P. B.
, and Zabaras
, N.
, 2016
, “Manifold Learning for the Emulation of Spatial Fields From Computational Models
,” J. Comput. Phys.
, 326
, pp. 666
–690
. 37.
Shah
, A. A.
, 2017
, “Surrogate Modeling for Spatially Distributed Fuel Cell Models With Applications to Uncertainty Quantification
,” ASME J. Electrochem. Energy Convers. Storage
, 14
(1
), p. 011006
. 38.
Xing
, W. W.
, Yu
, F.
, Leung
, P. K.
, Li
, X.
, Wang
, P.
, and Shah
, A. A.
, 2021
, “A New Multi-Task Learning Framework for Fuel Cell Model Outputs in High-Dimensional Spaces
,” J. Power Sources
, 482
(3
), p. 228930
. 39.
Goodfellow
, I.
, Bengio
, Y.
, and Courville
, A.
, 2016
, Deep Learning
, MIT Press
, http://www.deeplearningbook.org40.
Shawe-Taylor
, J.
, Williams
, C. K. I.
, Cristianini
, N.
, and Kandola
, J.
, 2005
, “On the Eigenspectrum of the Gram Matrix and the Generalization Error of Kernel-PCA
,” IEEE Trans. Inf. Theory
, 51
(7
), pp. 2510
–2522
. 41.
Blanchard
, G.
, Bousquet
, O.
, and Zwald
, L.
, 2007
, “Statistical Properties of Kernel Principal Component Analysis
,” Mach. Learn.
, 66
(2–3
), pp. 259
–294
. 42.
Reiß
, M.
, and Wahl
, M.
, 2020
, “Nonasymptotic Upper Bounds for the Reconstruction Error of PCA
,” Ann. Stat.
, 48
(2
), pp. 1098
–1123
.43.
Kanagawa
, M.
, Hennig
, P.
, Sejdinovic
, D.
, and Sriperumbudur
, B. K.
, 2018
, “Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences
,” arXiv preprint arXiv:1807.02582.
44.
Schaback
, R.
, 1999
, “Improved Error Bounds for Scattered Data Interpolation by Radial Basis Functions
,” Math. Comput.
, 68
(225
), pp. 201
–216
. 45.
Mendelson
, S.
, 2006
, “Improving the Sample Complexity Using Global Data
,” IEEE Trans. Inf. Theory
, 48
(7
), pp. 1977
–1991
. 46.
Srinivas
, N.
, Krause
, A.
, Kakade
, S. M.
, and Seeger
, M. W.
, 2012
, “Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting
,” IEEE Trans. Inf. Theory
, 58
(5
), pp. 3250
–3265
. 47.
Chowdhury
, S.
, and Gopalan
, A.
, 2017
, “On Kernelized Multi-Armed Bandits
,” Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research
, International Convention Centre, Sydney, Australia
, Aug. 6–11
, D.
Precup
, and Y. W.
Teh
, eds., pp. 844
–853
.48.
De Freitas
, N.
, Smola
, A. J.
, and Zoghi
, M.
, 2012
, “Exponential Regret Bounds for Gaussian Process Bandits With Deterministic Observations
,” Proceedings of the 29th International Conference on Machine Learning, ICML’12
, Edinburgh, Scotland
, June
, pp. 955
–962
.49.
Wang
, W.
, Tuo
, R.
, and Wu
, C. F. J.
, 2020
, “On Prediction Properties of Kriging: Uniform Error Bounds and Robustness
,” J. Am. Stat. Assoc.
, 115
(530
), pp. 920
–930
. 50.
Lederer
, A.
, Umlauft
, J.
, and Hirche
, S.
, 2019
, “Uniform Error Bounds for Gaussian Process Regression With Application to Safe Control
,” Conference on Neural Information Processing Systems (NIPS)
, Vancouver, Canada
, Dec. 10–12
, pp. 659
–669
.51.
Xing
, W. W.
, Shah
, A. A.
, Wang
, P.
, Zhe
, S.
, Fu
, Q.
, and Kirby
, R. M.
, 2021
, “Residual Gaussian Process: A Tractable Nonparametric Bayesian Emulator for Multi-Fidelity Simulations
,” Appl. Math. Model.
, 97
(3
), pp. 36
–56
. 52.
Adler
, R. J.
, and Taylor
, J. E.
, 2009
, Random Fields and Geometry
, Springer Science & Business Media
.53.
Doyle
, M.
, Newman
, J.
, Gozdz
, A. S.
, Schmutz
, C. N.
, and Tarascon
, J.
, 1996
, “Comparison of Modeling Predictions With Experimental Data From Plastic Lithium Ion Cells
,” J. Electrochem. Soc.
, 143
(6
), pp. 1890
–1903
. 54.
Shah
, A. A.
, Tangirala
, R.
, Singh
, R.
, Wills
, R. G. A.
, and Walsh
, F. C.
, 2011
, “A dynamic Uunit Cell Model for the All-Vanadium Flow Battery
,” J. Electrochem. Soc.
, 158
(6
), p. A671
. Copyright © 2022 by ASME
You do not currently have access to this content.
