Temperature‐Field Sparse‐Reconstruction of Lithium‐Ion Battery Pack Based on Artificial Neural Network and Virtual Thermal Sensor Technology

Zheng, Fang; Wang, Mengyi; Hu, Weifeng; Chang, Kejing; Zhang, Bijiao

doi:10.1002/ente.202100258

Cited by 7 publications

(2 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unfortunately, SOC cannot be measured directly but must go through indirect measurement. This indirect measurement causes SoC measurement to be inaccurate and have many errors [9] . The most common method for estimating SOC is Coulomb Counting.…”

Section: Introductionmentioning

confidence: 99%

The State of Charge Estimation of LiFePO4 Batteries Performance Using Feed Forward Neural Network Model

Dyartanti,

Jamaluddin,

Akshya

et al. 2024

AMM

View full text Add to dashboard Cite

Lithium-ion batteries like LiFePO4 become a new choice for electrical energy sources in the world and can be used on electric vehicles. Battery packs monitoring by Battery Management System in electric vehicles require accurate monitoring. The inaccuracy of monitoring such property can lead to low safety, low efficiency and battery’s life reduction. Estimating state of charge (SoC) to prevent battery damage from overcharging and over discharging. Some of the methods used to estimate SoC such as Coulomb Counting have errors during the charge and discharge process. This research proposes a counting method for measuring SoC with the artificial neural networks (ANN) to provide more precise estimation. Feed Forward Neural Network (FFNN) is an ANN model that can give an accurate estimation of SoC by learning data of the charge-discharge process performed on sample batteries. The sample batteries are tested with a battery analyzer to get its charging-discharging data consisting of variables such as voltage, current, capacity, and time with C-Rate variations. These variables data are then learned by the modeled FFNN to predict SoC value. The FFNN model consisted of 16 neurons in the first layer, 8 neurons in the second layer, and 4 neurons in the third layer. The predicted SoC value from FFNN has a similar value with its real SoC value. The relationship between SoC and battery voltage is plotted in a curve and shows an identical characteristic with how the SoC-Voltage curve of a battery should be and have a low mae value. This FFNN model can be applied further such as in electric vehicles to maintain its safety and for longer use.

show abstract

Section: Introductionmentioning

confidence: 99%

The State of Charge Estimation of LiFePO4 Batteries Performance Using Feed Forward Neural Network Model

Dyartanti,

Jamaluddin,

Akshya

et al. 2024

AMM

View full text Add to dashboard Cite

show abstract

“…In comparison to typical air BTMS, this newly created technique with intelligent control was capable of keeping the cell temperature well within the acceptable limit while consuming significantly less energy. Zheng et al 29 constructed ANN to record the cell temperature more precisely with as minimal sensors as necessary. They also compared their model with linear regression (LR).…”

Section: Introductionmentioning

confidence: 99%

Machine learning prediction and study of hotspots and hotspots location for sustainable battery energy system

Afzal

Alahmadi

Razak

et al. 2022

Intl J of Energy Research

View full text Add to dashboard Cite

Summary Analysis of hotspots in battery system is important as it indicates the thermal stresses arising and the occurrence of thermal runways. The battery heat generation and coolant flow system are together studied in this work using finite volume method. The role of different class of coolants like nanofluids, gases, oils, and liquid metals combined with the variations in spacings between the battery cells is specifically focused. In addition, effect of battery aspect ratio, coolant velocity, and their thermal conductivity are analysed in detail. The hotspots intensity and their locations are accessed for all the factors mentioned above. Later, using modern algorithms like X‐gradient boosting (XGB) and decision tree (DT) the predictions of hotspots and their locations is performed. From the numerical analysis, it is found that the hotspots get affected by changes in the chosen parameters except aspect ratio. It is found that, in an operating range of battery system with different heat generations and coolants, there is always a limiting value above/below which simply increasing/decreasing the parameter, does not reduce battery hotspots for sustainable performance. Both the algorithms used, predict the hotspot with a low accuracy of R2 value 0.55 and 0.53 using DT and XGB algorithm. The hotspots location is predicted with high accuracy having R2 value close to 0.92 from both the models.

show abstract

Storage of weights and retrieval method (SWARM) approach for neural networks hybridized with conformal prediction to construct the prediction intervals for energy system applications

Ashraf,

Dua

2024

Int J Data Sci Anal

View full text Add to dashboard Cite

The prediction intervals represent the uncertainty associated with the model-predicted responses that impacts the sequential decision-making analytics. Here in this work, we present a novel model-based data-driven approach to construct the prediction intervals around the model-simulated responses using artificial neural network (ANN) model. The loss function is modified with least mean square error and standard deviation between the model-simulated and actual responses for the online-training mode of ANN model development. The parameters (weights and biases) stored during the model development are extracted and are deployed to construct the prediction intervals with 95% confidence level for the test datasets of the three energy systems-based case studies including: crease recovery angle, energy efficiency cooling & energy efficiency heating and gas turbine power plant & coal power plant which are taken from literature, benchmark datasets and industrial-scale applications, respectively. The developed ANN models present root-mean-squared error of 1.20% and 0.52% on test dataset for energy efficiency cooling and energy efficiency heating, respectively. The width of prediction intervals made by the proposed approach, called as Storage of Weights And Retrieval Method (SWARM), incorporates the information available for each test observation during the model training and the SWARM-based prediction intervals are compared to those of inductive conformal prediction (ICP) technique. It is noted that SWARM technique offers better locally adaptive prediction intervals than those of ICP, highlighting the effectiveness of the SWARM technique for the estimation of prediction intervals for the case studies. This research presents a novel data-driven approach to construct the prediction intervals using the model-based information that can be applied on different real-life applications.

show abstract

Temperature‐Field Sparse‐Reconstruction of Lithium‐Ion Battery Pack Based on Artificial Neural Network and Virtual Thermal Sensor Technology

Cited by 7 publications

References 41 publications

The State of Charge Estimation of LiFePO4 Batteries Performance Using Feed Forward Neural Network Model

The State of Charge Estimation of LiFePO4 Batteries Performance Using Feed Forward Neural Network Model

Machine learning prediction and study of hotspots and hotspots location for sustainable battery energy system

Storage of weights and retrieval method (SWARM) approach for neural networks hybridized with conformal prediction to construct the prediction intervals for energy system applications

Contact Info

Product

Resources

About