Heat and weight optimization methodology of thermal batteries by using deep learning method with multi-physics simulation

Park, Tae Ryong; Park, Hyunseong; Kim, Kiyoul; Im, Chae-Nam; Cho, Jang-Hyeon

doi:10.1016/j.enconman.2021.114033

Cited by 14 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because of their excellent learning capacity, these approaches could comprehend the battery's internal dynamics via several charging and discharging cycles. The emergence of the latest deep-learning algorithms has led to a gradual improvement in learning accuracy thanks to the accumulation of previously learned data that enable precise SOC estimates [38]. These methods do, however, have significant drawbacks.…”

Section: Literature Reviewmentioning

confidence: 99%

Parameter Identification of Lithium-Ion Battery Model Based on African Vultures Optimization Algorithm

et al. 2023

View full text Add to dashboard Cite

This paper establishes a study for an accurate parameter modeling method for lithium-ion batteries. A precise state space model generated from an equivalent electric circuit is used to carry out the proposed identification process, where parameter identification is a nonlinear optimization process problem. The African vultures optimization algorithm (AVOA) is utilized to solve this problem by simulating African vultures’ foraging and navigating habits. The AVOA is used to implement this strategy and improve the quality of the solutions. Four scenarios are considered to take the effect of loading, fading, and dynamic analyses. The fitness function is selected as the integral square error between the estimated and measured voltage in these scenarios. Numerical simulations were executed on a 2600 mAhr Panasonic Li-ion battery to demonstrate the effectiveness of the suggested parameter identification technique. The proposed AVOA was fulfilled with high accuracy, the least error, and high closeness with the experimental data compared with different optimization algorithms, such as the Nelder–Mead simplex algorithm, the quasi-Newton algorithm, the Runge Kutta optimizer, the genetic algorithm, the grey wolf optimizer, and the gorilla troops optimizer. The proposed AVOA achieves the lowest fitness function level of the scenarios studied compared with relative optimization algorithms.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Parameter Identification of Lithium-Ion Battery Model Based on African Vultures Optimization Algorithm

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The multi-physics model can effectively predict temperature; however, it requires higher computational time and is hard to implement to the optimization processes. To address this problem, a DNN (deep NN) model trained using a small set of simulation data was applied to the BTMS by Park et al [21]. They found that the DNN model produced an accurate estimate with a total error of less than 1%.…”

Section: Introductionmentioning

confidence: 99%

Modelling and Computational Experiment to Obtain Optimized Neural Network for Battery Thermal Management Data

et al. 2021

View full text Add to dashboard Cite

The focus of this work is to computationally obtain an optimized neural network (NN) model to predict battery average Nusselt number (Nuavg) data using four activations functions. The battery Nuavg is highly nonlinear as reported in the literature, which depends mainly on flow velocity, coolant type, heat generation, thermal conductivity, battery length to width ratio, and space between the parallel battery packs. Nuavg is modeled at first using only one hidden layer in the network (NN1). The neurons in NN1 are experimented from 1 to 10 with activation functions: Sigmoidal, Gaussian, Tanh, and Linear functions to get the optimized NN1. Similarly, deep NN (NND) was also analyzed with neurons and activations functions to find an optimized number of hidden layers to predict the Nuavg. RSME (root mean square error) and R-Squared (R2) is accessed to conclude the optimized NN model. From this computational experiment, it is found that NN1 and NND both accurately predict the battery data. Six neurons in the hidden layer for NN1 give the best predictions. Sigmoidal and Gaussian functions have provided the best results for the NN1 model. In NND, the optimized model is obtained at different hidden layers and neurons for each activation function. The Sigmoidal and Gaussian functions outperformed the Tanh and Linear functions in an NN1 model. The linear function, on the other hand, was unable to forecast the battery data adequately. The Gaussian and Linear functions outperformed the other two NN-operated functions in the NND model. Overall, the deep NN (NND) model predicted better than the single-layered NN (NN1) model for each activation function.

show abstract

Joint prediction of the capacity and temperature of Li-ion batteries by using ConvLSTM Network

Wang,

Li,

Ding

et al. 2024

J. Power Electron.

View full text Add to dashboard Cite

Heat and weight optimization methodology of thermal batteries by using deep learning method with multi-physics simulation

Cited by 14 publications

References 12 publications

Parameter Identification of Lithium-Ion Battery Model Based on African Vultures Optimization Algorithm

Parameter Identification of Lithium-Ion Battery Model Based on African Vultures Optimization Algorithm

Modelling and Computational Experiment to Obtain Optimized Neural Network for Battery Thermal Management Data

Joint prediction of the capacity and temperature of Li-ion batteries by using ConvLSTM Network

Contact Info

Product

Resources

About