Optimizing electric vehicle powertrains peak performance with robust predictive direct torque control of induction motors: a practical approach and experimental validation

Scientific Reports, Год журнала: 2024, Номер 14(1)

Опубликована: Июнь 28, 2024

Enhancing the efficiency of electric vehicle's powertrain becomes a crucial focus, wherein control system for traction motor plays significant role. This paper presents novel vehicle based on robust predictive direct torque approach, an improved version conventional DTC, where traditional switching table and hysteresis regulators are substituted with block optimization algorithm. Additionally, speed loop regulator is employed instead proportional-integral regulator, which integrates new cost function finite horizon, incorporating integral action into law Taylor series expansion. technique's primary benefit its independence from necessity to measure observe external disturbances, as well uncertainties related parameters. The effectiveness suggested was confirmed through simulation experimental results under OPAL-RT platform. findings indicate that proposed approach outperforms method in terms rejecting exhibiting robustness variations parameters, minimizing ripple.

Язык: Английский

---

Data-Driven Approaches for State-of-Charge Estimation in Battery Electric Vehicles Using Machine and Deep Learning Techniques

Sustainability, Год журнала: 2024, Номер 16(21), С. 9301 - 9301

Опубликована: Окт. 26, 2024

One of the most important functions battery management system (BMS) in electric vehicle (BEV) applications is to estimate state charge (SOC). In this study, several machine and deep learning techniques, such as linear regression, support vector regressors (SVRs), k-nearest neighbor, random forest, extra trees regressor, extreme gradient boosting, forest combined with artificial neural networks (ANNs), convolutional networks, long short-term memory (LSTM) are investigated develop a modeling framework for SOC estimation. The purpose study improve overall performance by examining how BEV operation affects deterioration. By using dynamic response simulation lithium vehicles (BEVs) packs (LIBs), proposed research provides realistic training data, enabling more accurate prediction data-driven methods, which will have crucial effective impact on safe vehicles. paper evaluates algorithms various metrics, including R2 Score, median absolute error, mean square max error. All tests were performed MATLAB 2023, Anaconda platform, COMSOL Multiphysics.

Язык: Английский

---

Exploiting Artificial Neural Networks for the State of Charge Estimation in EV/HV Battery Systems: A Review

Batteries, Год журнала: 2025, Номер 11(3), С. 107 - 107

Опубликована: Март 13, 2025

Artificial Neural Networks (ANNs) improve battery management in electric vehicles (EVs) by enhancing the safety, durability, and reliability of electrochemical batteries, particularly through improvements State Charge (SOC) estimation. EV batteries operate under demanding conditions, which can affect performance and, extreme cases, lead to critical failures such as thermal runaway—an exothermic chain reaction that may result overheating, fires, even explosions. Addressing these risks requires advanced diagnostic strategies, machine learning presents a powerful solution due its ability adapt across multiple facets management. The versatility ML enables application material discovery, model development, quality control, real-time monitoring, charge optimization, fault detection, positioning it an essential technology for modern systems. Specifically, ANN models excel at detecting subtle, complex patterns reflect health performance, crucial accurate SOC effectiveness applications this domain, however, is highly dependent on selection datasets, relevant features, suitable algorithms. Advanced techniques active are being explored enhance improving models’ responsiveness diverse nuanced behavior. This compact survey consolidates recent advances estimation, analyzing current state field highlighting challenges opportunities remain. By structuring insights from extensive literature, paper aims establish ANNs foundational tool next-generation systems, ultimately supporting safer more efficient EVs robust safety protocols. Future research directions include refining dataset quality, optimizing algorithm selection, precision, thereby broadening ANNs’ role ensuring reliable vehicles.

Язык: Английский

---

A comprehensive review on artificial intelligence driven predictive maintenance in vehicles: technologies, challenges and future research directions

Deleted Journal, Год журнала: 2025, Номер 7(4)

Опубликована: Март 20, 2025

Язык: Английский

---

Artificial Interfacial Layers with Zwitterionic Ion Structure Improves Lithium Symmetric Battery Life and Inhibits Dendrite Growth

Symmetry, Год журнала: 2025, Номер 17(5), С. 652 - 652

Опубликована: Апрель 25, 2025

Lithium (Li) metal’s exceptional low electrode potential and high specific capacity for next-gen energy storage devices make it a top contender. However, the unregulated unpredictable proliferation of Li dendrites instability interfaces during repeated plating stripping cycles pose significant challenges to widespread commercialization metal anodes. We introduce creation hydrogen bond network solid electrolyte interphase (SEI) film that integrates zwitterionic groups, designed facilitate stability longevity lithium batteries (LMBs). Here, we design PVA/P(SBMA-MBA) (PSM) as an artificial SEI, integrating zwitterions polyvinyl alcohol (PVA) synergistically regulate Li⁺ flux. The distinctive effect in amplifies SEI film’s ionic conductivity 1.14 × 10−4 S cm−1 attains impressive Li+ ion transfer number 0.84. In situ Raman spectroscopy reveals dynamic reconfiguration under strain, endowing with self-adaptive mechanical robustness. These properties homogeneous flux exceptionally suppress dendritic growth. advanced anode may endure over 1200 h at 1 mA cm−2 current density mAh area Li|Li symmetric battery. And full cells paired LiFePO4 cathodes, 93.8% retention is reached after 300 1C. Consequently, this work provides universal strategy designing interphases through molecular dipole engineering, paving way safe durable batteries.

Язык: Английский

---

Reinforced performance control for automatic train operation with speed measurement deviation: a recollection observer approach

Nonlinear Dynamics, Год журнала: 2024, Номер unknown

Опубликована: Сен. 28, 2024

Язык: Английский

---

A Novel Method for Passengers’ Origin- Destination Distribution Prediction Over Metro Networks With Expansions Based on Automatic Fare Collection Data

IEEE Access, Год журнала: 2024, Номер 12, С. 137418 - 137426

Опубликована: Янв. 1, 2024

With the development of metro system, an increasing number new lines are being constructed. However, lack historical data on leads to challenge predicting origin-destination distribution whole network. Based advantage Automatic Fare Collection data, this study proposes a novel method predict over networks with expansions. Firstly, disaggregate model is built distributions network consideration passengers' destination choice behavior. Then, aggregate which can capture passenger patterns developed correct in existing lines. Finally, combines results and obtain distribution. This applies Guangzhou Metro network, show superiority proposed model. The help improve operation management urban rail transit.

Язык: Английский

---

Modeling of genetic algorithm tuned adaptive fuzzy fractional order PID speed control of permanent magnet synchronous motor for electric vehicle

Deleted Journal, Год журнала: 2024, Номер 6(10)

Опубликована: Сен. 27, 2024

Abstract This study presents a novel Genetic Algorithm-optimized Adaptive Fuzzy Fractional Order Proportional Integral Derivative (GA-AFFFOPID) controller for enhancing the speed control performance of permanent magnet synchronous motor (PMSM) drives in Electric Vehicles. The proposed GA-AFFFOPID controller, which combines advantages genetic algorithm optimization and adaptive fuzzy fractional-order PID control, represents unique innovative approach to address challenges associated with PMSM drives. Permanent technology, known its efficiency, compactness, reliability, versatility motion applications, is increasingly adopted electric vehicle drive systems. However, inherent non-linearity, dynamics, uncertainties motors pose significant challenges. exceptional demonstrated through superior system precise tracking, robustness against parameter variations sudden load disturbances, underscores advancements enabled by technique improving applications. Comparative analysis traditional methods demonstrates controller. These findings highlight improvements facilitated fractional order

Язык: Английский

---

Analyzing Locational Inequalities in the Placement of Electric Vehicle Charging Stations Using Machine Learning: A Case Study in Glasgow

Next research., Год журнала: 2024, Номер unknown, С. 100123 - 100123

Опубликована: Дек. 1, 2024

Язык: Английский

---