Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

29,922 Article Results

Fault diagnosis for inverter open circuit faults using DC-link signal and random forest-based technique

10.11591/ijpeds.v16.i4.pp2178-2185
Hoang-Giang Vu , Dang Toan Nguyen
Three-phase voltage source inverters based on insulated-gate bipolar transistors (IGBTs) are widely used in various industrial applications. Faults in IGBTs significantly affect the performance of the inverter and entire system. Robust and accurate fault detection are the key requirements of fault diagnosis methods. This paper explores a method for diagnosing power switch open circuit faults of a voltage source inverter based on machine learning algorithms. The diagnosis is performed in two steps, firstly the fault is detected by applying the Random Forest classifier algorithm with the DC-link signal. Next, the fault switch location is performed by additionally using the inverter output AC current signals. The diagnostic results based on simulation data show that the fault can be detected with maximum accuracy. Meanwhile, the accuracy in locating the fault switch is also significantly improved with the additional use of current signals measured at the DC-link. Potential application of electromagnetic field signal is also highlighted for the practical implementation of fault diagnosis.
Volume: 16
Issue: 4
Page: 2178-2185
Publish at: 2025-12-01

Arabic text classification using machine learning and deep learning algorithms

10.11591/ijai.v14.i6.pp5201-5217
Rawad Awad Alqahtani , Hoda A. Abdelhafez
The classification of Arabic textual content presents considerable challenges due to the language's rich morphological structure and the wide variation among its dialects. This study aims to enhance classification accuracy by leveraging ensemble learning techniques and a deep bidirectional transformer-based model, specifically the multilingual autoregressive BERT (MARBERT). To address linguistic variability, advanced preprocessing techniques were employed, including Farasa, Tashaphyne, and Assem stemming methods. The Al Khaleej dataset served as the basis for supervised learning, providing a representative sample of Arabic text. Furthermore, term frequency-inverse document frequency (TF-IDF) with bigram and trigram feature extraction was utilized to effectively capture contextual semantics. Experimental results indicate that the proposed approach, particularly with the integration of MARBERT, achieves a peak classification accuracy of 98.59%, outperforming existing models. This research underscores the efficacy of combining ensemble learning with deep transformer-based models for Arabic text classification and highlights the critical role of robust preprocessing techniques in managing linguistic complexity and improving model performance.
Volume: 14
Issue: 6
Page: 5201-5217
Publish at: 2025-12-01

Support vector machine performance: simulation and rice phenology application

10.11591/ijai.v14.i6.pp4878-4890
Hengki Muradi , Asep Saefuddin , I Made Sumertajaya , Agus Mohamad Soleh , Dede Dirgahayu Domiri
In the case of classification, model accuracy is expected to result in correct predictions. This study aims to analyze the performance of two kinds of support vector machine (SVM) methods: the support vector machine one versus one (SVM OvO) method and the generalized multiclass support vector machine (GenSVM) method. This method will compare to the generalized linear model, namely the multinomial logistic regression (MLR) method. Simulations were conducted using SVM OvO and GenSVM methods to get an overview of the parameters affecting both methods' performance. Furthermore, the three classification methods are implemented in the case of modelling the rice phenology and tested for performance. Simulation results show that, however, the SVM OvO and GenSVM machine learning methods are sensitive to the choice of model parameters. The empirical study results show that the SVM OvO and GenSVM methods can produce satisfactory model accuracy and are comparable to the MLR method. The best rice phenology model accuracy was obtained from the SVM OvO model, where 79.20 ± 0.21 overall accuracy and 70.69 ± 0.29 kappa were obtained. This research can be continued by handling samples, especially when class members are a minority, and can also add random effects to the SVM model.
Volume: 14
Issue: 6
Page: 4878-4890
Publish at: 2025-12-01

Bidirectional power converter for electrical vehicle with battery charging and smart battery management system

10.11591/ijpeds.v16.i4.pp2592-2604
Bodapati Venkata Rajanna , Kondragunta Rama Krishnaiah , Ganta Raghotham Reddy , Shaik Hasane Ahammad , Mohammad Najumunnisa , Syed Inthiyaz , Gouthami Eragamreddy , Ambarapu Sudhakar , Nitalaksheswara Rao Kolukula
In electric vehicles (EVs), efficient energy management is critical for reliable power transfer between the battery and motor. This paper presents the design and implementation of a bidirectional DC-DC converter equipped with a smart battery management system (BMS). The system supports bidirectional power flow, operating in boost mode during acceleration and buck mode during regenerative braking, thereby enhancing overall energy efficiency and vehicle performance. A PIC microcontroller governs the system, performing real-time monitoring of key battery parameters such as state of charge (SOC), state of health (SOH), voltage, and temperature. Safety features include automatic cooling fan activation when the temperature exceeds 45 °C and generator startup when battery voltage falls below 23 V. Real-time data is displayed via an LCD interface to improve user interaction and system transparency. The proposed system achieved a conversion efficiency of 90-93% during experimental testing, with stable switching, reliable automation, and effective thermal protection. The embedded energy management system optimizes charging and discharging cycles while preventing overcharging, deep discharge, and thermal stress. This intelligent, automated power converter enhances battery life, improves EV reliability, and contributes to sustainable transportation by enabling features like vehicle-to-grid (V2G) energy transfer. The proposed architecture is well-suited for integration into modern EV infrastructure. Although the system architecture supports future V2G integration, V2G functionality was not implemented or tested in the present experimental setup.
Volume: 16
Issue: 4
Page: 2592-2604
Publish at: 2025-12-01

Processor-in-the-loop performance validation of a three-phase NPC three-level inverter using a novel sinusoidal PWM technique for scalar control of an induction motor

10.11591/ijpeds.v16.i4.pp2257-2270
Badr N’hili , Souhail Barakat , Abdelouahed Mesbahi , Mohamed Khafallah , Ayoub Nouaiti
This paper presents the performance of a three-phase, three-level neutral point clamped inverter driving an induction motor for variable-speed applications, compared to a two-level inverter. The studied inverter operates using a novel sinusoidal pulse width modulation technique that improves the quality of voltage and current output signals while increasing efficiency. Motor speed control is achieved using the scalar control (V/Hz) method. Experimental validation of the simulation results is performed by executing the generated C code on the F28379D DSP LaunchPad within the MATLAB/Simulink and Code Composer Studio environment, applying the processor-in-the-loop (PIL) technique.
Volume: 16
Issue: 4
Page: 2257-2270
Publish at: 2025-12-01

Comparison of the discounted costs of controlled asynchronous electric drives with matrix and with DC link frequency converters

10.11591/ijpeds.v16.i4.pp2307-2320
Viktor Petrushyn , Juriy Plotkin , Vasily Horoshko , Rostyslav Yenoktaiev , Andrii Yakimets
A quality criterion based on discounted costs is proposed, which demonstrates a significant advantage of the variable frequency asynchronous motor drive with a matrix converter over the drive with a voltage source inverter, which contains a DC link. A MATLAB software simulation was conducted to ascertain the control characteristics. In light of the control range afforded by both drives, a criterion for discounted costs is proposed that is calculated as a mid-range within a specific rotational speed control range, or is determined based on a given tachogram. The aforementioned costs include the expense of the drive, the cost of losses, maintenance costs, amortization charges, and the cost of reactive power compensation due to phase shifts of the main harmonic current and voltage. In this study, we put forth a novel proposal for the incorporation of the cost of distortion power compensation resulting from the presence of harmonic components of the input current.  The latter costs characterize the electromagnetic compatibility of the drive with the network. For the first time, a quality criterion for a regulated electric drive is proposed, which has a cost component that takes into account the electromagnetic compatibility of the drive with the network. A significant reduction in this component in a drive with a matrix converter compared to a drive with a DC link predetermines a reduction in discounted costs. For a given payback period and annual inflation rate, it was determined that the mid-range discounted costs were reduced by more than 11 times and the tachogram based discounted costs were reduced by more than 10 times for a drive with a matrix converter in comparison to a drive with a DC link.
Volume: 16
Issue: 4
Page: 2307-2320
Publish at: 2025-12-01

Design and analysis of brushless permanent magnet motor for light electrically powered two-wheeler vehicle

10.11591/ijpeds.v16.i4.pp2296-2306
How Xuan Yu , Mohd Luqman Mohd Jamil , Nurul Ain Mohd Said
This study provides a comprehensive process of designing an electric motor that will be used for a small two-wheeled electric vehicle. Due to high performance capability in term of power and torque, brushless permanent magnet topology is chosen so that a compromise between size constraint and performance can be met. For an accurate motor design sizing, the design process is initially carried out by determination of power rating that derived from vehicle dynamic calculation. Based on winding factor calculation, fractional-slot 12-slot/10-pole and 9-slot/10-pole motors equipped with non-overlapping winding are chosen and analyzed using finite element analysis (FEA) software. For an optimum electromagnetic performance, parametric optimization is included, mainly on the stator dimension. Despite the performance of both designs improved, only 9-slot motor results a convincing performance as the rated torque is 18% higher than the 12-slot design. For verification purpose, 1-D analytical solution is also included and compared with results deduced by the FEA. According to the analysis, the proposed motor designs are adequately reliable for a light electrically powered electric vehicle application.
Volume: 16
Issue: 4
Page: 2296-2306
Publish at: 2025-12-01

Support-centric PSO-based fuzzy MPPT tuning for photovoltaic systems under uniform conditions

10.11591/ijpeds.v16.i4.pp2792-2803
Amel Smaili , El-Ghalia Boudissa , M’hamed Bounekhla
Several conventional maximum power point tracking (MPPT) algorithms have been applied to harvest the optimal power of a photovoltaic (PV) system. However, the main drawbacks of these algorithms are their fluctuations around the maximum power point (MPP) and their dependence on climatic conditions variation. To overcome these issues, a fuzzy logic controller (FLC) is proposed, where the system performance depends strongly on the choice of membership functions (MFs). They are typically selected by trial and error, which may not always yield the best results. This paper seeks to enhance the efficiency of the traditional FLC method by using the particle swarm optimization (PSO) algorithm for optimizing the supports of the triangular MFs. The simulation was performed using MATLAB-Simulink environment using the "1Soltech 1STH-215-P" PV module and a single-ended primary-inductor converter (SEPIC) converter, under ideal environmental conditions of 25 °C and 1000 W/m². A comparison is established between PSO-optimized FLC and the standard FLC-based MPPT method, as well as with several other state-of-the-art approaches reported in related research. The simulation data present that the PSO-optimized FLC approach outperforms other algorithms.
Volume: 16
Issue: 4
Page: 2792-2803
Publish at: 2025-12-01

Design and implementation of IoT-based soft starter for induction motor

10.11591/ijpeds.v16.i4.pp2170-2177
Laith Najem Abood Khudhur , Amer Abdulmahdi Jabbar Chlaihawi
The practical application of the induction motor is an essential part of electrical engineering. A direct connection of the motors to the mains voltage negatively affects both the motor itself and the mains system as a whole due to high starting current values, as a result, more accidents and shortening the drive system service life. This article discusses the development of designing and implementing of soft starter single-phase IM to reduce the inrush current using the firing angle reduction technique with remote monitoring and control using the ESP32 (node MCU) and Arduino Due microcontrollers. The integration of IoT-based tools software such as VS Code, enables the remote monitoring and control of motor features. Testing shows that the system effectively facilitates remote motor control, providing a flexible and accessible learning environment with minimum starting current, solving the inrush current problem facing IMs. The proposed soft starter gives three cases of firing angle reduction that show a percentage reduction in starting current for these cases (case I, case II, and case III) are 51%, 54% and 64%, respectively. Case III has a maximum starting current is 2.2 A compared to 6.2 A for direct connecting of IM to the power supply (DOL).
Volume: 16
Issue: 4
Page: 2170-2177
Publish at: 2025-12-01

Fuzzy logic-based adaptive PLL switching strategy for voltage control in DVR assisted grid tied PV systems

10.11591/ijpeds.v16.i4.pp2353-2368
R. Srilakshmi , V. Chayapathy
This study aims to enhance power quality in grid-connected photovoltaic (PV) systems by introducing an intelligent fuzzy logic-based adaptive control strategy for dynamic PLL switching in a DVR-supported configuration. A 100-kW grid-tied PV system is modeled with a digital phase-locked loop (DPLL), a conventional synchronous reference frame PLL (CTPLL), and a dynamic voltage restorer (DVR). A Mamdani-type fuzzy inference system (FIS) performs real-time PLL selection based on phase-wise real-time fault monitoring. The system was tested under symmetrical and asymmetrical 20% sag and swell conditions, evaluating voltage stability at both PCC and load, total harmonic distortion (THD), recovery time, and synchronization accuracy. Results show that the proposed method reduces unnecessary DVR voltage injection from ~50 V to ~5-6 V under healthy conditions, maintains a near-unity power factor (< 0.95), and achieves up to 15% THD reduction in inverter current and PCC currents compared to DPLL-only operation. Recovery times improved by up to 25%, with stable synchronization maintained in all fault cases. The integration of adaptive PLL switching and targeted DVR activation offers a novel, hardware-efficient approach to harmonic suppression, voltage stabilization, and fault resilience in medium-scale PV systems.
Volume: 16
Issue: 4
Page: 2353-2368
Publish at: 2025-12-01

The role of thermal insulation layers and the integration of solar energy in temporary heating systems

10.11591/ijpeds.v16.i4.pp2677-2687
Rexhep Selimaj , Sabrije Osmanaj
This paper examines thermal insulation strategies for building walls and the integration of solar heating systems to improve the performance of temporary heating systems in residential buildings in Kosovo. A two-story house was used as the case study, simulating four different scenarios of thermal insulation layer placement in the walls with different capacities of the heating system. The proposed thermal balance method of the building takes into account the arrangement of thermal insulation layers and their impact on the building’s energy savings. The results indicate that external insulation offers the best balance between heat retention and energy efficiency, while internal insulation enables faster heating and a shorter time to reach the desired temperature. Under low-temperature conditions, solar energy was analyzed and integrated as an additional source to enhance the heating system capacity and reduce electricity consumption. Simulation results demonstrate further improvement in system performance, enabling optimized operating schedules and a significant reduction in energy consumption.
Volume: 16
Issue: 4
Page: 2677-2687
Publish at: 2025-12-01

Comparative analysis of various rotor types BLDC motor for residential elevator application

10.11591/ijpeds.v16.i4.pp2224-2233
Nor Aishah Md. Zuki , Raja Nor Firdaus Kashfi Raja Othman , Fairul Azhar Abdul Shukor , Kunihisa Tashiro
Brushless DC (BLDC) motors are widely used in applications where high efficiency is crucial. With advancements in permanent magnet technology, BLDC motors are increasingly suitable for high-torque applications such as residential elevators. Known for their high efficiency, low maintenance, and excellent controllability, BLDC motors are ideal candidates for this research. However, the challenge lies in identifying the most efficient rotor structure that can deliver the required torque for residential elevator applications while maintaining cost-effectiveness and compact design. This paper addresses this problem by simulating various rotor types of BLDC motors using the finite element method (FEM), Ansys Maxwell. four different rotor structures have been analyzed to evaluate their back electromotive force (EMF) and torque. The model generating the highest torque will be selected for manufacturing as a motor for residential elevators. Among the models studied, BLDC-ERA rotor structures produced the highest torque of 28 Nm, while BLDC-HR type generates the lowest torque. To ensure practicality and cost-effectiveness of installing elevators in double-story houses or smaller residences, the selected motor must be compact and affordable, enabling senior citizen to maintain their independence. This research not only aids other researchers in designing suitable motors for elevator applications but also contributes to societal well-being by promoting accessibility and independence for the elderly.
Volume: 16
Issue: 4
Page: 2224-2233
Publish at: 2025-12-01

Supervised learning for fast inverse motor control mapping: a comparative study on SRM and BLDC motors

10.11591/ijpeds.v16.i4.pp2419-2428
S. Sudheer Kumar Reddy , J. N. Chandra Sekhar
This paper investigates the application of machine learning (ML) models, specifically artificial neural networks (ANN) and XGBoost, for real-time motor control, focusing on switched reluctance motors (SRM) and brushless DC motors (BLDC). Traditional inverse dynamics mapping for motor control is compared with ML approaches to highlight advantages in speed, accuracy, and deployment efficiency. Datasets simulating the input-output behavior of both motor types are used to train and test the models. Key performance metrics such as mean squared error (MSE), R² score, training time, and latency are evaluated, with the goal of replacing traditional control methods in real-time applications. Results indicate that ML models outperform traditional methods in terms of prediction accuracy and deployment speed, suggesting a promising path toward more efficient and adaptive motor control systems. The novelty of this work lies in applying supervised learning directly for inverse motor control mapping, thereby eliminating the need for explicit analytical models and enabling a unified, data-driven benchmarking framework across SRM and BLDC.
Volume: 16
Issue: 4
Page: 2419-2428
Publish at: 2025-12-01

A comprehensive review of efficient wireless power transfer for electric vehicle charging: advancements, challenges, and future directions

10.11591/ijpeds.v16.i4.pp2156-2169
Md. Ashraf Ali Khan , Kuber Kuber , Yusra Wahab , M. Saad Arif , Shahrin Md. Ayob , Norjulia Mohamad Nordin
Electric vehicles (EVs) have transformed the transportation sector, offering a sustainable alternative to fossil-fuel-powered vehicles. However, their widespread adoption faces challenges such as inadequate charging infrastructure, range anxiety, and concerns about user convenience. Wireless power transfer (WPT) technology provides an efficient, reliable, and user-friendly charging solution that eliminates physical connections, enabling both static and dynamic charging applications. This review explores key components of WPT systems, including wireless charging schemes, compensation circuits, coupling pad structures, and misalignment tolerance, emphasizing their impact on system efficiency and reliability. Findings highlight that WPT can enhance charging convenience, reduce dependence on large battery capacities, and support seamless EV integration into daily life. Additionally, WPT systems improve safety, lower maintenance needs, and create opportunities for autonomous charging. Key advancements in compensation topologies, coupling pad geometries, and misalignment-tolerant capabilities are discussed alongside their role in enhancing power transfer efficiency. By offering insights into the current state-of-the-art and future directions, this paper aims to support the development and deployment of WPT systems, contributing to the global transition toward sustainable transportation.
Volume: 16
Issue: 4
Page: 2156-2169
Publish at: 2025-12-01

Experimental validation of virtual flux concept in direct power control with dynamic performance

10.11591/ijpeds.v16.i4.pp2509-2520
Muhammad Hafeez Mohamed Hariri , Nor Azizah Mohd Yusoff , Muhammad Zaid Aihsan , Tole Sutikno
The virtual-flux direct power control (VFDPC) technique is a sensorless control approach aimed at improving the performance of grid-connected power converters. The approach involves simulating the grid voltage and AC-side inductors similar to an AC motor drive system, a principle deriving from direct torque control (DTC). The basic idea of VFDPC is to indirectly estimate the voltage at the converter's input through the concept of virtual flux, enabling the real-time calculation of instantaneous active and reactive power without necessitating direct voltage measurements. An essential element of the VFDPC approach is the implementation of a lookup table, used as a decision-making tool that identifies the most suitable voltage vector (a particular output state of the converter) in accordance with real-time power conditions. This provides instantaneous and smooth control of power flow, leading to enhanced operational stability. This approach allows for continual optimization of the converter's output, enabling VFDPC to significantly decrease total harmonic distortion (THD) while preserving reliable steady-state and dynamic performance. Experimental validation demonstrates that incorporating real-time feedback into virtual flux estimates improves the precision of voltage prediction and the responsiveness of the power control system. Consequently, VFDPC exhibits enhanced adaptability for various grid and load situations, presenting an appropriate choice for current power systems that demand efficient, reliable, and sensorless operation.
Volume: 16
Issue: 4
Page: 2509-2520
Publish at: 2025-12-01
1 2 3
...
1994 1995
Show 73 of 1995

Discover Our Library

Embark on a journey through our expansive collection of articles and let curiosity lead your path to innovation.

Explore Now
Library 3D Ilustration