Electric vehicles survey and a multifunctional artificial neural network for predicting energy consumption in all-electric vehicles

Results in Engineering, Год журнала: 2023, Номер 19, С. 101283 - 101283

Опубликована: Июль 18, 2023

This study contains a survey on the architecture of electric vehicles and an artificial neural network application for prediction energy consumption in all-electric vehicles. In this study, term “electric vehicles” (EVs) refers to various types electrified The technologies behind these were also discussed. focuses hybrid (HEVs), pure (PEVs), plug-in (PHEVs). presents design simulation typical HEV. A vehicle was designed using ADVISOR, it compared with another car known as targeted car. fuel found be lower than that introduced multifunctional model predicting electrical proposed has nine input variables, which are virtual functions calculated from selected parameters function formula. number variables made equal output so could simulate unique solution. multi-output inverse network. accuracy 1.24–6.85 times higher case studies considered terms mean square error.

Язык: Английский

---

State of charge prediction of lithium-ion batteries for electric aircraft with swin transformer

IEEE/CAA Journal of Automatica Sinica, Год журнала: 2024, Номер unknown, С. 1 - 3

Опубликована: Янв. 1, 2024

Dear Editor, As an important energy storage device, lithium-ion battery plays a vital role in electric aircrafts, which are new and promising equipment of transportation the future with low carbon emissions. Accurate prediction state charge (SOC) batteries is great importance reducing probability abnormal accidents ensuring flight safety. This paper proposes novel Swin Transformer-based method for predicting SOC batteries. Firstly, data reconstructed features extracted by using interpolation fitting to overcome noise generated during acquisition process practical industrial scenarios. Then, learned processed Transformer network achieve accurate letter conducts experiments verification based on actual aircrafts. The experimental results show that proposed has error accuracy.

Язык: Английский

---

A low-cost approach to on-board electrochemical impedance spectroscopy for a lithium-ion battery

Journal of Energy Storage, Год журнала: 2024, Номер 81, С. 110330 - 110330

Опубликована: Янв. 11, 2024

In this work, we describe the design and implementation of a low-cost acquisition system for electrochemical impedance spectroscopy on-board applications. The proof concept is based on commercial battery monitor lithium-ion batteries system-on-chip control unit, which can also be used to other devices, like stimulus generation unit. frequency range 0.1–500 Hz, bringing device its highest performance limits with low costs. We evaluate through measurement repeatability accuracy, making some statistical tests validated against data obtained laboratory instrumentation. order show operation within complete spectrum analyser application, embody sinusoidal generator in concept, integrating an easy way strategy into Such by changing charger.

Язык: Английский

---

A machine learning approach for detecting customs fraud through unstructured data analysis in social media

Decision Analytics Journal, Год журнала: 2024, Номер 10, С. 100408 - 100408

Опубликована: Фев. 2, 2024

Goods and services are sold through social media by individuals not authorized as legitimate dealers, resulting in lost taxes customs duties to governments. This study proposes a model called SHIELD for detecting these violations unstructured data media. The process involves collecting 2,373,570 records of commercial goods from platforms such Twitter Facebook three phases. In Phase 1, keywords labeling collected text classification. Three categories results defined: Red Line smuggled goods, unpaid duty, prohibited restricted goods; Green non-commercial Inspect that cannot be identified the require further investigation. 2 3 use detect smugglers grouped algorithms Logistic Regression (LR), Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), employed classify imported illegal products. all tests show LSTM technique had best accuracy 99.44% average F1 score 90.55%. Using techniques LR, GRU, demonstrates potential machine learning natural language processing activities promoting economic security.

Язык: Английский

---

Optimizing photovoltaic power plant forecasting with dynamic neural network structure refinement

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Янв. 27, 2025

Reliable prediction of photovoltaic power generation is key to the efficient management energy systems in response inherent uncertainty renewable sources. Despite advances weather forecasting, accuracy remains a challenge. This study presents novel approach that combines genetic algorithms and dynamic neural network structure refinement optimize prediction. methodology dynamically adjusts parameters during training, including number neurons, transfer functions, weights, biases, minimize root mean square error. Evaluation was performed on twelve representative days using annual, monthly, seasonal data, comparison made with multiple linear regression nonlinear autoregressive models, demonstrating approach's effectiveness. metrics such as error, R-value, percentage error reveal promising accuracy. MATLAB used for modeling, testing, real 4.2 kW PV plant validation. The results indicate significant improvements, errors low 20 W cloudy 175 sunny days. proposed achieves versus target regressions consistency, R values ranging from 0.95824 0.99980, highlighting its efficiency providing reliable predictions generation.

Язык: Английский

---

Design approaches for Li-ion battery packs: A review

Journal of Energy Storage, Год журнала: 2023, Номер 73, С. 109197 - 109197

Опубликована: Окт. 13, 2023

Nowadays, battery design must be considered a multi-disciplinary activity focused on product sustainability in terms of environmental impacts and cost. The paper reviews the tools methods context Li-ion packs. discussion focuses different aspects, from thermal analysis to management safety. aims investigate what has been achieved last twenty years understand current future trends when designing goal is analyze for defining pack's layout structure using modeling, simulations, life cycle analysis, optimization, machine learning. target concerns electric hybrid vehicles energy storage systems general. makes an original classification past works seven levels approaches final analyzes correlation between changes increasing demand outcome this allows reader evolutions practices packs developments.

Язык: Английский

---

Increasing the energy efficiency of an electric vehicle powered by hydrogen fuel cells

International Journal of Hydrogen Energy, Год журнала: 2024, Номер 85, С. 406 - 415

Опубликована: Авг. 25, 2024

Язык: Английский

---

Forecasting solar power generation using evolutionary mating algorithm-deep neural networks

Energy and AI, Год журнала: 2024, Номер 16, С. 100371 - 100371

Опубликована: Апрель 17, 2024

This paper proposes an integration of recent metaheuristic algorithm namely Evolutionary Mating Algorithm (EMA) in optimizing the weights and biases deep neural networks (DNN) for forecasting solar power generation. The study employs a Feed Forward Neural Network (FFNN) to forecast AC output using real plant measurements spanning 34-day period, recorded at 15-minute intervals. intricate nonlinear relationship between irradiation, ambient temperature, module temperature is captured accurate prediction. Additionally, conducts comprehensive comparison with established algorithms, including Differential Evolution (DE-DNN), Barnacles Optimizer (BMO-DNN), Particle Swarm Optimization (PSO-DNN), Harmony Search (HSA-DNN), DNN Adaptive Moment Estimation optimizer (ADAM) Nonlinear AutoRegressive eXogenous inputs (NARX). experimental results distinctly highlight exceptional performance EMA-DNN by attaining lowest Root Mean Squared Error (RMSE) during testing. contribution not only advances methodologies but also underscores potential merging algorithms contemporary improved accuracy reliability.

Язык: Английский

---

Exergo-economic analyzes of a combined CPVT solar dish/Kalina Cycle/HDH desalination system; intelligent forecasting using Artificial neural network (ANN) and Improved Particle Swarm Optimization (IPSO)

Renewable Energy, Год журнала: 2024, Номер 235, С. 121254 - 121254

Опубликована: Авг. 31, 2024

Язык: Английский

---

Design of a novel robust UIO estimator with predefined convergence time for the state of charge estimation for lithium-ion batteries

International Journal of Dynamics and Control, Год журнала: 2025, Номер 13(1)

Опубликована: Янв. 1, 2025

Язык: Английский

---