Articles

Interleaved buck converter using a floating dual series-capacitor topology

10.11591/ijpeds.v16.i4.pp2538-2548

Chan Viet Nguyen , Dang Tai Nguyen , Thanh Phuong Ho

Interleaved buck converters (IBC) are widely utilized in step-down voltage applications due to their excellent performance and straightforward design. However, conventional IBCs require individual current sensors and feedback control circuits to maintain phase current balance, resulting in increased cost and design complexity. In this paper, a novel floating dual series capacitor (FDSC) converter based on an interleaved floating structure is proposed. The most distinctive aspect of this proposed converter is its ability to naturally balance the four inductor currents without the need for any current sensors or feedback control. Furthermore, the proposed converter also exhibits lower voltage stress on switching devices and inductors, contributing to improved efficiency and a reduction in overall magnetic volume. To validate the performance characteristics of the proposed converter, a 1.3 kW prototype of the FDSC topology was developed and tested to indicate the analytical results and demonstrate stable current balance even under different operating conditions. The experimental validation highlights the topology’s suitability for high step-down, compact, and efficient applications such as EV auxiliary power supply and voltage regulator modules.

Volume: 16

Issue: 4

Page: 2538-2548

Publish at: 2025-12-01

Nonlinear excitation control of multimachine systems via the invariant-set design

10.11591/ijpeds.v16.i4.pp2332-2341

Hisham M. Soliman , Ehab H. E. Bayoumi , Farag Ali El-Sheikhi , Fawzan Salem

Power grids are inherently vulnerable to many uncertainties. All power networks are prone to instability because of the uncertainties inherent in the operation of power systems. Rotor-angle instability is a challenging issue, and if not properly managed, could give rise to cascading failures and even blackouts. This paper addresses the generator excitation system’s state feedback sliding mode control (SMC). The global system is divided into multiple subsystems to achieve decentralized control. A disturbance is defined as the influence of the system as a whole on a specific subsystem. The state-feedback controller is to be designed taking into account the disturbance attenuation level, ensuring the closed-loop system's asymptotic stability. The SMC designing algorithm is described; it is based on precisely determining the sliding surface utilizing the invariant-set (ellipsoid) technique. The control structure ensures that mismatched disturbances in power systems have little impact on the system trajectory in the sliding mode. Moreover, the proposed controllers are represented in this paper using linear matrix inequalities (LMIs) and the Lyapunov theory approach. Finally, a multi-machine model is implemented to demonstrate the success of the suggested approach, and a comparison between the proposed SMC and the conventional one demonstrates its superiority.

Volume: 16

Issue: 4

Page: 2332-2341

Publish at: 2025-12-01

Early detection of tar spot disease in Zea mays using hyperspectral reflectance and machine learning

10.11591/ijai.v14.i6.pp4722-4730

Claudia Nohemy Montoya-Estrada , Oscar Cardona-Morales , Oscar López-Naranjo , Freddy Eliseo Hernandez-Jorge , Yeison Alberto Garcés-Gómez

Ensuring food security and meeting the economic needs of farmers and nations depend heavily on detecting and preventing crop yield losses. Early detection of tar spot caused by Phyllachora maydis is crucial to implementing efficient mitigation actions in the earliest stages of infestation. Currently, visual methods are used for detection, which require extensive training and experience from the operator. However, remote sensing techniques can be used to detect tar spot infestation through the selection of wavelengths present in the maize plant spectral signature. This research proposes using machine learning techniques and logistic regression to determine the first stage of tar spot infestation. The results show that the logistic regression model is the most suitable for detecting this first stage, and the K-Nearest Neighbors Classification and Random Forest Classification algorithms generate the best classification results. This approach can significantly reduce costs in terms of time, labor, and subjective analysis.

Volume: 14

Issue: 6

Page: 4722-4730

Publish at: 2025-12-01

ANN based speed control of switched reluctance motor using MATLAB-interfaced DSP controller

10.11591/ijpeds.v16.i4.pp2243-2256

Veena Wilson , Latha Padinjaredath Govindan

The switched reluctance motor (SRM) is gaining significance as a competitive motor in industries due to its prominent features such as absence of rare-earth elements, strong fault tolerance, and competitive efficiency. This paper presents a comprehensive framework to a novel and simplified hardware implementation of SRM drive, accompanied by a stepwise procedure to develop the control process that includes system modelling with simulation analysis and experimental validation, useful for the novice researchers. A precise hardware control environment is introduced, by integrating MATLAB/Simulink platform with digital signal processor (DSP) microcontroller - TMS320F280049C, which minimizes the complexities of traditional controller coding. The paper provides an in-depth explanation of deployment of artificial neural network (ANN) speed control block, offering valuable insights into the practical aspects of ANN-based control in MATLAB. The paper also compares closed-loop speed control using proportional-integral (PI) and ANN control in SRM, and the results demonstrate accurate and adaptive performance of ANN control for variable speed- load conditions.

Volume: 16

Issue: 4

Page: 2243-2256

Publish at: 2025-12-01

Modelling and analysis of linear DC motor with constant thrust characteristics

10.11591/ijpeds.v16.i4.pp2212-2223

Raja Nor Firdaus Kashfi Raja Othman , Siti Zulaika Mat Isa , Nor Aishah Md. Zuki , Suhairi Rizuan Che Ahmad , Fairul Azhar Abdul Shukor , Md. Nazri Othman

This paper introduces a portable and user-friendly innovation in food processing by replacing traditional molding methods with a linear DC motor (LDM). Traditional methods, which involve manual pressing, are energy-intensive and time-consuming, reducing productivity. The proposed LDM offers a simple, cost-effective, and robust solution capable of producing constant thrust, unlike conventional LDMs that require complex and expensive control methods and are limited to short displacements. The research focuses on modelling and analyzing an LDM with constant thrust characteristics for food processing applications. The primary objective is to model the thrust using the permeance analysis method (PAM), ensuring constant thrust capability. Verification was conducted using the finite element method (FEM) and measurement results, showing a percentage difference of 1.7% and 6.5%, respectively, between PAM and the other methods. The study provides valuable guidance for designing LDMs with constant thrust capabilities, enhancing the efficiency and practicality of food processing devices.

Volume: 16

Issue: 4

Page: 2212-2223

Publish at: 2025-12-01

Development of a PEM fuel cell equivalent circuit model with PINN-based parameter identification

10.11591/ijpeds.v16.i4.pp2804-2818

Ismail Ait Taleb , Zakaria Kourab , Souad Tayane , Mohamed Ennaji , Jaafar Gaber

This paper presents a novel equivalent electrical circuit model for proton exchange membrane fuel cells (PEMFCs) and introduces a physics-informed neural network (PINN) algorithm for parameter identification. The proposed model provides a more accurate representation of the fuel cell’s dynamic behavior while maintaining computational efficiency. Unlike conventional methods, the PINN framework integrates physical constraints with data-driven learning, ensuring physically consistent parameter estimation. To validate its effectiveness, the proposed model is compared with the widely used RC equivalent circuit and a generic PEMFC model. Experimental data from a 1.2 kW PEMFC test bench serve as a benchmark for evaluating the transient and steady-state performance of each modeling approach. Results demonstrate that the proposed circuit, combined with PINN-based identification, yields enhanced accuracy in predicting voltage response under various operating conditions. Additionally, the model exhibits improved adaptability to transient phenomena compared to conventional equivalent circuits. These findings highlight the potential of physics-informed machine learning for advancing fuel cell modeling and control strategies.

Volume: 16

Issue: 4

Page: 2804-2818

Publish at: 2025-12-01

Optimization of solar panel orientation and tracking systems for standalone PV applications

10.11591/ijpeds.v16.i4.pp2721-2730

Singgih Dwi Prasetyo , Yuki Trisnoaji , Misbahul Munir , Meirna Puspita Permatasari , Abram Anggit Mahadi , Marsya Aulia Rizkita , Zainal Arifin

The performance of photovoltaic (PV) systems is greatly influenced by the angle of arrival of sunlight and the geometric orientation of solar panels, especially in tropical regions with the potential for solar energy throughout the year. This study aims to evaluate the effect of tilt angle variation and tracking systems on energy output and performance indicators of standalone PV systems using PVsyst software. The simulation was conducted at the State University of Malang, Indonesia, by comparing four fixed-angle configurations (20°, 40°, 60°, and 80°) as well as a two-axis tracking system. The simulation results showed that the two-axis tracking system produced the highest normalized daily energy production of 6.8 kWh/kWp/day, with a performance ratio (PR) of 77.2% and a solar fraction (SF) of 97.1%, while a fixed configuration with an angle of 80° showed the lowest performance. These findings confirm the importance of selecting optimal panel orientation to maximize the efficiency of PV systems, as well as being the basis for the development of advanced research, such as field-based experiments, integration of adaptive MPPT algorithms, and economic feasibility studies in the application of PV systems in tropical and off-grid regions.

Volume: 16

Issue: 4

Page: 2721-2730

Publish at: 2025-12-01

Predictions of solar power using ensemble machine learning techniques

10.11591/ijpeds.v16.i4.pp2868-2878

Arangarajan Vinayagam , R. Mohandas , R. Jeyabharath , B. S. Mohan , Srinivasan Lakshmanan , C. Bharatiraja

Predicting solar power production accurately is becoming more and more crucial for efficient power management and the grid's integration of renewable energy sources. Using data from an Australian photovoltaic (PV) power station, this study employs a variety of machine learning (ML) ensemble techniques, such as gradient boosting (GB), random forest (RF), and extreme gradient boosting (XGBoost), to forecast solar power production. ML models are developed utilizing pertinent information from electricity and meteorological data in order to forecast solar power. The predictive performance of trained ML models is verified in terms of metrics like mean absolute error (MAE), root mean square error (RMSE), and correlation coefficient (R2). With higher R2 values and lower error results (MAE and RMSE), XGBoost performs better than GB and RF. Optimizing the hyperparameters of the XGBoost model significantly improves its performance. The tweaked XGBoost model shows a significant improvement in R2 (more than 5% to 10%) and error results (reduced MAE and RMSE by 0.01 to 0.06), when compared to other ensemble approaches. Compared to other ensemble approaches, the tuned XGBoost methodology is more robust and generates more accurate forecasts in solar power.

Volume: 16

Issue: 4

Page: 2868-2878

Publish at: 2025-12-01

Numerical and experimental state of identification battery pack lithium-ion

10.11591/ijpeds.v16.i4.pp2623-2633

Dewi Anggraeni , Budi Sudiarto , Eriko Nasemudin Nasser , Wahyudi Hasbi , Yus Natali , Purnomo Sidi Priambodo

Two key indicators of a battery management system (BMS) are the state of charge (SoC) and the state of health (SoH). Accurately estimating SoC is important to prevent potential issues. Additionally, space, computing time, and cost are important factors in hardware development. To address these considerations, the first-order extended Kalman filter (EKF) and adaptive extended Kalman filter (AEKF) models were selected due to their simpler data pre-processing and better accuracy. The study recommends using the first-order equivalent circuit model (ECM) method in conjunction with the EKF and AEKF algorithms due to their straightforward setup and efficient computational process. Analysis of the charge-discharge cycles shows that the AEKF method consistently outperformed the EKF method regarding SoC accuracy. Moreover, when given different initial SoC values, the AEKF method displayed superior SoC estimation accuracy compared to the EKF method. Moreover, while the accuracy of the EKF is diminished, the error value remains below 2.5% for up to 500 cycles. Additionally, the shorter computing time of the EKF method is a consideration for practical real-world implementation. Furthermore, experiments conducted over 500 cycles revealed that SoH estimation declined from 99.97% to 76.1947%, suggesting that the battery has reached the end of life (EOL) stage.

Volume: 16

Issue: 4

Page: 2623-2633

Publish at: 2025-12-01

Adaptive intelligent PSO-Based MPPT technique for PV systems under dynamic irradiance and partial shading conditions

10.11591/ijpeds.v16.i4.pp2841-2859

Muhammad Gul E. Islam , Mohammad Faridun Naim Tajuddin , Azralmukmin Azmi , Rini Nur Hasanah , Shahrin Md. Ayob , Tole Sutikno

This research introduces an adaptive improved particle swarm optimization (AIPSO) approach for maximum power point tracking (MPPT) approach designed to enhance energy harvesting from photovoltaic (PV) systems under dynamic irradiance conditions. The proposed AIPSO algorithm addresses the challenges associated with traditional MPPT methods, particularly in scenarios characterized by fluctuating solar irradiance, such as step changes and partial shading. By incorporating a robust reinitialization strategy along with updated velocity and position equations, the algorithm demonstrates superior performance in terms of convergence accuracy, tracking speed, and tracking efficiency. This modification enables the algorithm to effectively escape local maxima and explore a wider search space, leading to improved convergence and optimal power point tracking. Furthermore, the adaptive nature of the PSO enhances the algorithm’s ability to respond to real-time changes in environmental conditions, making it particularly suitable for large- scale PV systems subjected to varying atmospheric factors. Here, “adaptive” denotes coefficient scheduling (C3) and a re-initialization trigger that responds to irradiance regime changes; “intelligent” denotes robust regime shift detection and safe duty ratio clamping. Across uniform, step change, and partial shading conditions, the proposed AIPSO achieves fast reconvergence and high tracking efficiency with negligible steady state oscillations, as summarized in the results. Building on this contribution, future research will focus on evaluating its scalability across different PV architectures and large-scale grid integration with real hardware setup.

Volume: 16

Issue: 4

Page: 2841-2859

Publish at: 2025-12-01

Lithium-ion battery charge-discharge cycle forecasting using LSTM neural networks

10.11591/ijpeds.v16.i4.pp2831-2840

Vimala Channapatana Srikantappa , Seshachalam Devarakonda

An important component for the dependable and safe utilization of lithium-ion batteries is the ability to accurately and efficiently predict their remaining useful life (RUL). In this research, a long short-term memory recurrent neural network (LSTM RNN) model is trained to learn from sequential data on discharge capacities across different cycles and voltages. The model is also designed to function as a cycle life predictor for battery cells that have been cycled under varying conditions. By leveraging experimental data from the NASA battery dataset, the model achieves a promising level of prediction accuracy on test sets consisting of approximately 200 samples.

Volume: 16

Issue: 4

Page: 2831-2840

Publish at: 2025-12-01

A hybrid ARIMA and DNN approach with residual learning for electric vehicle charging demand forecasting

10.12928/telkomnika.v23i6.27219

Wahyu; National Research and Innovation Agency (BRIN) Cesar , Dwidharma; National Research and Innovation Agency (BRIN) Priyasta , Prasetyo; National Research and Innovation Agency (BRIN) Aji , Melyana; National Research and Innovation Agency (BRIN) Melyana , Agus; National Research and Innovation Agency (BRIN) Suprianto , Osen; National Research and Innovation Agency (BRIN) Fili Nami , Riza; National Research and Innovation Agency (BRIN) Riza

The rapid growth of electric vehicle (EV) adoption has created significant challenges for power grid management and charging infrastructure planning. Accurate forecasting of EV charging demand is therefore essential to ensure reliable electricity supply and effective station deployment. This study proposes a novel hybrid forecasting framework that combines autoregressive integrated moving average (ARIMA) with deep neural networks (DNN) through a residual learning strategy. In this approach, ARIMA models the linear temporal patterns, while DNN captures the nonlinear residuals, resulting in improved efficiency and predictive accuracy. The proposed hybrid model is one of the first applications of the residual learning approach for EV demand forecasting in Indonesia. Experimental evaluation using real-world daily consumption data shows that the hybrid method achieved the highest prediction accuracy of 98.22%, consistently outperforming single-model baselines. Beyond technical performance, the model can support stakeholders in planning charging infrastructure and help maintain grid stability in rapidly growing EV ecosystems.

Volume: 23

Issue: 6

Page: 1555-1565

Publish at: 2025-12-01

Predicting the severity of road traffic accidents Morocco: a supervised machine learning approach

10.11591/ijai.v14.i6.pp4461-4473

Halima Drissi Touzani , Sanaa Faquir , Ali Yahyaouy

Early prediction of road accidents fatality and injuries severity is one of the important subjects to road safety emphasizing the critical need to prevent serious consequences to reduce injuries and fatalities. This study uses real road accidents data set in Morocco. It represents the intersection between road safety and data science, aiming to employ machine learning techniques to provide valuable insights in accident’s severity prevention. The purpose of this paper is to study road accidents data in the country and combine results from statistical methods, spatial analysis, and machine learning models to determine which factors will mostly contribute to increase the accident’ severity in the country. A comparison of results obtained was also conducted in this paper using different metrics to evaluate the effectiveness of each method and determine the most important factors that contribute to increase the fatality or injuries severity in the specific context of accidents. The best prediction model was then injected into a proposed algorithm where more intelligent techniques are included to be implemented in a car engine to perform an early detection of severe accidents and therefore preventing crashes from happening.

Volume: 14

Issue: 6

Page: 4461-4473

Publish at: 2025-12-01

Metaheuristic optimization for sarcasm detection in social media with embedding and padding techniques

10.11591/ijai.v14.i6.pp5027-5037

Geeta Sahu , Manoj Hudnunkar

Sarcasm is a sophisticated mode of expression that allows speakers to express their opinions subtly. Stakeholders provide unstructured messages with extended phrases, making it difficult for computers and people to understand. This research aims to develop a sarcasm detection method to identify words in phrases as sarcastic or non-sarcastic from text, utilizing natural language processing appliances. The first step is pre-processing, when the padding and embedding are performed. Zero padding and end padding are used for the padding. At the same time, different embedding techniques, such as word2vec, Glove, and BERT, are used. Following pre-processing, the features are extracted from the pre-processed data, including "information gain, chi-square, mutual information, and symmetrical uncertainty-based features." Then, a hybrid optimization technique known as clan-updated grey wolf optimization (CU-GWO) is used for optimized features and weight selection. An ensemble technique was applied to extract optimal features. The classifiers in the proposed suggested ensemble technique with deep convolution neural network (DCNN). DCNN offers fine weight tuning and detection results.The performance analysis and its impact on the proposed model for sarcasm detection are classified with good accuracy into sarcastic and non-sarcastic categories. The results are also compared with against those of the GloVe and BERT techniques.

Volume: 14

Issue: 6

Page: 5027-5037

Publish at: 2025-12-01

Adaptive ANFIS-based MPPT for PV-powered green ships with high gain SEPIC converter

10.11591/ijpeds.v16.i4.pp2768-2779

G. Jegadeeswari , Rohini Govindaraju , D. Balakumar , D. Lakshmi , S. Marisargunam , M. Batumalay , B. Kirubadurai

To align with global climate goals, the International Maritime Organization (IMO) has enforced strict measures to reduce greenhouse gas emissions from the shipping industry by promoting energy efficiency and cleaner propulsion methods. Ship engines remain major contributors to environmental pollution due to their dependence on fossil fuels and inefficient propulsion systems, highlighting the need for clean and sustainable alternatives. This study aims to design a renewable energy-based marine power system that effectively stores and utilizes solar energy, improving overall efficiency and reducing emissions for process innovation. A hybrid setup was developed using photovoltaic (PV) panels, batteries, and a bidirectional DC-DC converter to enable flexible power flow during both charging and discharging cycles. An adaptive neuro-fuzzy inference system (ANFIS)-based maximum power point tracking (MPPT) algorithm was employed alongside a SEPIC converter to enhance energy extraction from the PV system under dynamic conditions. The integrated system achieved a power extraction efficiency of 97.12%, confirming the effectiveness of the ANFIS-based MPPT strategy and showcasing the viability of intelligent renewable energy solutions in maritime applications.

Volume: 16

Issue: 4

Page: 2768-2779

Publish at: 2025-12-01

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

Filters article

Years

Source Title

Authors

31,042 Article Results

Interleaved buck converter using a floating dual series-capacitor topology

Nonlinear excitation control of multimachine systems via the invariant-set design

Early detection of tar spot disease in Zea mays using hyperspectral reflectance and machine learning

ANN based speed control of switched reluctance motor using MATLAB-interfaced DSP controller

Modelling and analysis of linear DC motor with constant thrust characteristics

Development of a PEM fuel cell equivalent circuit model with PINN-based parameter identification

Optimization of solar panel orientation and tracking systems for standalone PV applications

Predictions of solar power using ensemble machine learning techniques

Numerical and experimental state of identification battery pack lithium-ion

Adaptive intelligent PSO-Based MPPT technique for PV systems under dynamic irradiance and partial shading conditions

Lithium-ion battery charge-discharge cycle forecasting using LSTM neural networks

A hybrid ARIMA and DNN approach with residual learning for electric vehicle charging demand forecasting

Predicting the severity of road traffic accidents Morocco: a supervised machine learning approach

Metaheuristic optimization for sarcasm detection in social media with embedding and padding techniques

Adaptive ANFIS-based MPPT for PV-powered green ships with high gain SEPIC converter

Discover Our Library