Backpropagation neural network models for LiFePO4 battery

Primadusi, Ungu; Cahyadi, Adha Imam; Prasetyo, Dani; Wahyunggoro, Oyas

doi:10.1063/1.4958527

Cited by 3 publications

(4 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the multilayer perceptron neural network trained with BPNN is the most popular and widely used network paradigm employed by engineering applications to solve practical problems, and it has demonstrated exceptional performance [53,54,56,59,60]. Inevitably, the traditional BPNN algorithm has some shortcomings, such as low convergence speed and an easy fall to the local minimum, but some remedies have been proposed to solve these problems [61].…”

Section: Methodsmentioning

confidence: 99%

Optimization Based on Computational Fluid Dynamics and Machine Learning for the Performance of Diffuser-Augmented Wind Turbines with Inlet Shrouds

Hwang,

Wu,

Chang

2024

Sustainability

View full text Add to dashboard Cite

A methodology that could reduce computational cost and time, combining computational fluid dynamics (CFD) simulations, neural networks, and genetic algorithms to determine a diffuser-augmented wind turbine (DAWT) design is proposed. The specific approach used implements a CFD simulation validated with experimental data, and key parameters are analyzed to generate datasets for the relevant mathematical model established with the backpropagation neural network algorithm. Then, the mathematical model is used with the non-dominant sorting genetic algorithm II to optimize the design and improve the DAWT design to overcome negative constraints such as noise and low energy density. The key parameters adopted are the diffuser’s flange height/angle, the diffuser’s length, and the rotor’s axial position. It was found that the impact of the rotor’s axial position on the power output of the DAWT is the most significant parameter, and a well-designed diffuser requires accelerating the airflow while maintaining high-pressure recovery. Introducing a diffuser can suppress the wind turbine’s noise, but if the induced tip vortex is too strong, it will have the opposite effect on the noise reduction.

show abstract

Section: Methodsmentioning

confidence: 99%

Optimization Based on Computational Fluid Dynamics and Machine Learning for the Performance of Diffuser-Augmented Wind Turbines with Inlet Shrouds

Hwang,

Wu,

Chang

2024

Sustainability

View full text Add to dashboard Cite

show abstract

“…The former transmits the output values layer by layer, while the latter sums the error derivatives for weights in the reverse direction until all the data are run through the network once (Dong et al, 2020). This constitutes an epoch, and the weights are updated after each epoch such that the model error decreases (Primadusi et al, 2016).…”

Section: Bpnnmentioning

confidence: 99%

“…This partitioning is unique for each tree in the forest and hence provides a significant internal validation. As a result, RF can overcome the disadvantages of overfitting and instability and has good robustness and high interpretability (Khoshgoftaar et al, 2007;Primadusi et al, 2016). More specific details of RF algorithm can be found in Breiman' article (Breiman, 2001).…”

Section: Rfmentioning

confidence: 99%

Application of machine learning algorithms for prediction of ultraviolet absorption spectra of chromophoric dissolved organic matter (CDOM) in seawater

Wang

et al. 2023

Front. Mar. Sci.

View full text Add to dashboard Cite

The ultraviolet absorption spectra of chromophoric dissolved organic matter (CDOM) can be used to trace its sources and to explore the dynamic of the CDOM pool. In previous studies, only the spectra above 240 nm can be used directly to characterize the CDOM in seawater, due to the overlapping of CDOM absorption spectra below 240 nm with inorganic chemicals such as NO3−, NO2−, Cl- and Br-. In this study, three different machine learning models, back propagation neural network (BPNN), random forest (RF) and extreme gradient boosting (XGBoost), were built to predict the CDOM ultraviolet absorption spectra between 215 and 350 nm after being trained with the raw absorption spectra of seawater. The optimal input wavelength range of the raw seawater spectra is 250-350 nm, and the optimal model parameters of machine learning algorithms were determined by using five-fold cross validation. The results show that the three models can well predict the CDOM absorption spectra. Comparatively, the XGBoost model gave the best prediction results. The reasons might be related to the fact that the XGBoost algorithm focuses on the residuals generated by the last iteration, which can reduce both variance and bias, especially for datasets with small sample sizes. Based on the predicted spectra by XGBoost algorithm, we calculated the spectra slopes of short wavelengths between 215 and 240 nm (S215-240) and between 215 and 275 nm (S215-275). The results show that the S215-240 and S215-275 are ~2 times the widely used spectra slopes between 275 and 295 nm (S275-295) obtained by traditional method based on the raw spectra. Moreover, the S215-240 and S215-275 are more relavant with salinity for marine CDOM than S275-295, suggesting spectra slopes of shorter wavelengths might be the better proxies for marine CDOM than that of longer wavelengths.

show abstract

“…A typical BPNN has a simple network topology consisting of three layers: input layer, hidden layer, and output layer as shown in Figure 11. The learning process is divided into two phases: the forward signal propagation phase and the reverse error propagation phase [48].…”

Section: Chaptermentioning

confidence: 99%

Remaining Useful Life Prediction of Proton Exchange Membrane Fuel Cells Using Genetic Algorithm Based Nonlinear Autoregressive Exogenous Network

Shen¹

View full text Add to dashboard Cite

The proton exchange membrane fuel cell (PEMFC) is one of the most promising clean energy sources with characteristics like high energy conversion, no electrolyte leakage, and low operational temperature. However, it is difficult to build a mathematical model because the system consists of a complex nonlinear system. In the meantime, accurate estimation of the remaining useful life (RUL) of fuel cells plays an important role in improving the safety and lifetime of fuel cells. A joint prediction method based on genetic algorithm (GA) and nonlinear autoregressive neural network with external input (NARX) is proposed. The method was designed to predict the RUL of the proton exchange membrane fuel cell. GA is used to optimize the initial weights and biases of the NARX neural network. Then, the historical voltage evolution under rated current conditions is used to train the NARX network, where the trained model is used to predict the voltage evolution under ripple conditions. Integrating the GA-NARX algorithm leads to the improvement of convergence speed and the prediction accuracy of the algorithm. This integrated algorithm obtains better estimation accuracy compared to the NARX network by itself. The proposed method was compared with the genetic algorithm-based backpropagation neural network (GA-BPNN) and genetic algorithm-based time delay neural network (GA-TDNN). The proposed method is validated with the IEEE PHM 2014 Data Challenge dataset and the results showed that the method has better prediction accuracy compared to other ANN algorithms.

show abstract

Backpropagation neural network models for LiFePO4 battery

Cited by 3 publications

References 4 publications

Optimization Based on Computational Fluid Dynamics and Machine Learning for the Performance of Diffuser-Augmented Wind Turbines with Inlet Shrouds

Optimization Based on Computational Fluid Dynamics and Machine Learning for the Performance of Diffuser-Augmented Wind Turbines with Inlet Shrouds

Application of machine learning algorithms for prediction of ultraviolet absorption spectra of chromophoric dissolved organic matter (CDOM) in seawater

Remaining Useful Life Prediction of Proton Exchange Membrane Fuel Cells Using Genetic Algorithm Based Nonlinear Autoregressive Exogenous Network

Contact Info

Product

Resources

About