scholarly journals Integration of Semi-Empirical and Artificial Neural Network (ANN) for Modeling Lithium-Ion Electrolyte Systems Dynamic Viscosity

2022 ◽  
Author(s):  
Fadhel Azeez ◽  
Abdalrahman Refaie
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Empirical Model ◽  
Relative Viscosity ◽  
Lithium Ion ◽  
Electrolyte Solutions ◽  
Ann Model ◽  
Li Ion ◽  
Artificial Neural Network Ann ◽  
Semi Empirical

Abstract Dynamic viscosity is a key characteristic of electrolyte performance in lithium-ion battery. This work introduces a one parameter semi-empirical model and artificial neural network (ANN) to predict the viscosity of salt-free solvent mixtures and relative viscosity of Li-ion electrolyte solutions (lithium salt + solvent mixture), respectively. Data used in this study were obtained experimentally, in addition to data extracted from literature. There are seven inputs of the ANN model: salt concentration, electrolyte temperature, salt anion size, solvent melting and boiling temperatures, solvent dielectric constant, and solvent dipole moment. Different configuration of the ANN was tested and the configuration with least error was chosen. The results show the capability of the semi-empirical model to predict the viscosity with an overall mean absolute percentage error (MAPE) of 2.05% and 3.17% for binary and tertiary mixtures, respectively. The ANN model predicted the relative viscosity of electrolyte solutions with MAPE of 4.86%. The application of both models in series, resulted predicted the viscosity with MAPE 2.3%, although the ANN MAPE alone is higher than this value. Thus, this work highlights the promise of using predictive models to complement physical approaches and to provide an effective way to perform initial screening on Li-ion electrolytes.

scholarly journals Lithium-Ion batteries modeling and state of charge estimation using Artificial Neural Network

2019 ◽  
Vol 9 (5) ◽  
pp. 3415
Author(s):  
Younes Boujoudar ◽  
Hassan Elmoussaoui ◽  
Tijani Lamhamdi
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Lithium Ion ◽  
State Of Charge ◽  
Battery Cell ◽  
Present Sample ◽  
Previous Sample ◽  
Li Ion ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

<span class="fontstyle0">In This paper, we propose an effective and online technique for modeling nd State of Charge (SoC) estimation of Lithium-Ion (Li-Ion) batteries using Feed Forward Neural Networks(FFNN) and Nonlinear Auto Regressive model with eXogenous input(NARX). The both Artificial Neural Network (ANN) are rained using the data collected from the batterycharging and discharging pro ess. The NARX network finds the needed battery model, where the input ariables are the battery terminal voltage, SoC at the previous sample, and the urrent, temperature at the present sample. The proposed method is imple mented on a Li-Ion battery cell to estimate online SoC. Simulation results show good estimation of the<br />SoC.</span>

Modeling of lime production process using artificial neural network

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Abolghasem Daeichian ◽  
Rana Shahramfar ◽  
Elham Heidari
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Production Process ◽  
High Energy ◽  
Ann Model ◽  
Artificial Neural ◽  
Rotary Kilns ◽  
Input Variables ◽  
Artificial Neural Network Ann ◽  
Lime Production

Abstract Lime is a significant material in many industrial processes, including steelmaking by blast furnace. Lime production through rotary kilns is a standard method in industries, yet it has depreciation, high energy consumption, and environmental pollution. A model of the lime production process can help to not only increase our knowledge and awareness but also can help reduce its disadvantages. This paper presents a black-box model by Artificial Neural Network (ANN) for the lime production process considering pre-heater, rotary kiln, and cooler parameters. To this end, actual data are collected from Zobahan Isfahan Steel Company, Iran, which consists of 746 data obtained in a duration of one year. The proposed model considers 23 input variables, predicting the amount of produced lime as an output variable. The ANN parameters such as number of hidden layers, number of neurons in each layer, activation functions, and training algorithm are optimized. Then, the sensitivity of the optimum model to the input variables is investigated. Top-three input variables are selected on the basis of one-group sensitivity analysis and their interactions are studied. Finally, an ANN model is developed considering the top-three most effective input variables. The mean square error of the proposed models with 23 and 3 inputs are equal to 0.000693 and 0.004061, respectively, which shows a high prediction capability of the two proposed models.

scholarly journals Modeling the concentration of carbonyl of ethylene propylene diene monomer during the thermal aging using artificial neural network

2021 ◽  
Vol 03 (01) ◽  
pp. 45-52
Author(s):  
Hadjira Maouz ◽  
◽  
Asma Adda ◽  
Salah Hanini ◽  
◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Thermal Aging ◽  
Training Data ◽  
Ethylene Propylene Diene Monomer ◽  
Ann Model ◽  
Ethylene Propylene ◽  
Artificial Neural ◽  
Input Variables ◽  
Artificial Neural Network Ann

The concentration of carbonyl is one of the most important properties contributing to the detection of the thermal aging of polymer ethylene propylene diene monomer (EPDM). In this publication, an artificial neural network (ANN) model was developed to predict concentration of carbenyl during the thermal aging of EPDM using a database consisting of seven input variables. The best fitting training data was obtained with the architecture of (7 inputs neurons, 10 hidden neurons and 1 output neuron). A Levenberg Marquardt learning (LM) algorithm, hyperbolic tangent transfer function were used at the hidden and output layer respectively. The optimal ANN was obtained with a high correlation coefficient R= 0.995 and a very low root mean square error RMSE = 0.0148 mol/l during the generalization phase. The comparison between the experimental and calculated results show that the ANN model is able of predicted the concentration of carbonyl during the thermal aging of ethylene propylene diene monomer

scholarly journals Penerapan Algoritma Artificial Neural Network untuk Klasifikasi Opini Publik Terhadap Covid-19

2021 ◽  
Vol 5 (2) ◽  
pp. 109-118
Author(s):  
Euis Saraswati ◽  
Yuyun Umaidah ◽  
Apriade Voutama
Keyword(s):  
Neural Network ◽  
Social Media ◽  
Artificial Neural Network ◽  
Text Mining ◽  
Ann Model ◽  
Rapid Spread ◽  
Backpropagation Method ◽  
Artificial Neural ◽  
The Government ◽  
Artificial Neural Network Ann

Coronavirus disease (Covid-19) or commonly called coronavirus. This virus spreads very quickly and even almost infects the whole world, including Indonesia. A large number of cases and the rapid spread of this virus make people worry and even fear the increasing spread of the Covid-19 virus. Information about this virus has also been spread on various social media, one of which is Twitter. Various public opinions regarding the Covid-19 virus are also widely expressed on Twitter. Opinions on a tweet contain positive or negative sentiments. Sentiments of sentiment contained in a tweet can be used as material for consideration and evaluation for the government in dealing with the Covid-19 virus. Based on these problems, a sentiment analysis classification is needed to find out public opinion on the Covid-19 virus. This research uses Artificial Neural Network (ANN) algorithm with the Backpropagation method. The results of this test get 88.62% accuracy, 91.5% precision, and 95.73% recall. The results obtained show that the ANN model is quite good for classifying text mining.

scholarly journals Artificial Neural Network Trained to Predict High-Harmonic Flux

2018 ◽  
Author(s):  
Ana Maria Mihaela Gherman ◽  
Katalin Kovács ◽  
Mircea Vasile Cristea ◽  
Valer Tosa
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
High Harmonic ◽  
Ann Model ◽  
Gas Cell ◽  
Dimensional Parameter ◽  
High Order Harmonic ◽  
Cell Position ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

In this work we present the results obtained with an artificial neural network (ANN) which we trained to predict the expected output of high-order harmonic generation (HHG) process, while exploring a multi-dimensional parameter space. We argue on the utility and efficiency of the ANN model and demonstrate its ability to predict the outcome of HHG simulations. In this case study we present the results for a loose focusing HHG beamline, where the changing parameters are: the laser pulse energy, gas pressure, gas cell position relative to focus and gas cell length. The physical quantity which we predict here using ANN is directly related to the total harmonic yield in a specified spectral domain (20-40 eV). We discuss the versatility and adaptability of the presented method.

scholarly journals A Study on Correlation of Subjects on Electrical Engineering Course Using Artificial Neural Network (ANN)

2021 ◽  
Vol 17 (2) ◽  
pp. 144
Author(s):  
Fathiah Zakaria ◽  
Siti Aishah Che Kar ◽  
Rina Abdullah ◽  
Syila Izawana Ismail ◽  
Nur Idawati Md Enzai
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Electrical Engineering ◽  
Electric Circuit ◽  
Time Correlation ◽  
Ann Model ◽  
Core Subject ◽  
History Of ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Abstract: This paper presents a study of correlation between subjects of Diploma in Electrical Engineering (Electronics/Power) at Universiti Teknologi MARA(UiTM) Cawangan Terengganu using Artificial Neural Network (ANN). The analysis was done to see the effect of mathematical subjects (Pre-calculus and Calculus 1) and core subject (Electric Circuit 1) on Electronics 1. Electronics 1 is found to be a core subject with the history of high failure rate percentage (more than 25%) in previous semesters. This research has been conducted on current final semester students (Semester 5). Seven (7) models of ANN are developed to observe the correlation between the subjects. In order to develop an ANN model, ANN design and parameters need to be chosen to find the best model. In this study, historical data from students’ database were used for training and testing purpose. Total number of datasets used are 58 sets. 70% of the datasets are used for training process and 30% of the datasets are used for testing process. The Regression Coefficient, (R) values from the developed models was observed and analyzed to see the effect of the subject on the performance of students. It can be proven that Electric Circuit 1 has significant correlation with the Electronics 1 subject respected to the highest R value obtained (0.8100). The result obtained proves that student’s understanding on Electric Circuit 1 subject (taken during semester 2) has direct impact on the performance of students on Electronics 1 subject (taken during semester 3). Hence, early preventive measures could be taken by the respective parties.    Keywords: Artificial neural network, Diploma in Electrical Engineering, Graduate on time, Correlation.

Best Architecture of an Artificial Neural Network to Model Prefilming Airblast Atomization: Not So Deep Learning

2021 ◽  
Author(s):  
Geoffroy Chaussonnet ◽  
Sebastian Gepperth ◽  
Simon Holz ◽  
Rainer Koch ◽  
Hans-Jörg Bauer
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Feature Space ◽  
Middle Layer ◽  
Ann Model ◽  
Deformation Velocity ◽  
The Mean ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Domain Of Parameters

Abstract A fully connected Artificial Neural Network (ANN) is used to predict the mean spray characteristics of prefilming airblast atomization. The model is trained from the planar prefilmer experiment from the PhD thesis of Gepperth (2020). The output of the ANN model are the Sauter Mean Diameter, the mean droplet axial velocity, the mean ligament length and the mean ligament deformation velocity. The training database contains 322 different operating points. Two types of model input quantities are investigated and compared. First, nine dimensional parameters are used as inputs for the model. Second, nine non-dimensional groups commonly used for liquid atomization are derived from the first set of inputs. The best architecture is determined after testing over 10000 randomly drawn ANN architectures, with up to 10 layers and up to 128 neurons per layer. The striking results is that for both types of model, the best architectures consist of only 3 hidden layer in the shape of a diabolo. This shape recalls the shape of an autoencoder, where the middle layer would be the feature space of reduced dimensionality. It was found that the model with dimensional input quantities always shows a lower test and validation errors than the one with non-dimensional input quantities. In general, the two types of models provide comparable accuracy, better than typical correlations of SMD and droplet velocity. Finally the extrapolation capability of the models was assessed by a training them on a confined domain of parameters and testing them outside this domain.

Capacity Loss Estimation For Li-Ion Batteries Based On A Semi-Empirical Model

2021 ◽  
Author(s):  
Mohammed Rabah ◽  
Eero Immonen ◽  
Sajad Shahsavari ◽  
Mohammad-Hashem Haghbayan ◽  
Kirill Murashko ◽  
...  
Keyword(s):  
Lithium Ion Batteries ◽  
Empirical Model ◽  
Lithium Ion ◽  
Average Error ◽  
Li Ion Batteries ◽  
Capacity Loss ◽  
Capacity Degradation ◽  
Battery Capacity ◽  
Li Ion ◽  
Semi Empirical

Understanding battery capacity degradation is instrumental for designing modern electric vehicles. In this paper, a Semi-Empirical Model for predicting the Capacity Loss of Lithium-ion batteries during Cycling and Calendar Aging is developed. In order to redict the Capacity Loss with a high accuracy, battery operation data from different test conditions and different Lithium-ion batteries chemistries were obtained from literature for parameter optimization (fitting). The obtained models were then compared to experimental data for validation. Our results show that the average error between the estimated Capacity Loss and measured Capacity Loss is less than 1.5% during Cycling Aging, and less than 2% during Calendar Aging. An electric mining dumper, with simulated duty cycle data, is considered as an application example.

Sign in / Sign up

Export Citation Format

Share Document