Journal of Applied Engineering Design and Simulation

Impact of ESDD-Standardised Pollution on Partial Discharge Inception and AC Breakdown Voltage of 11 kV Disc Insulators

Irdina Adriana Ibrahim, Nordiana Azlin Othman, Md Aris Nor Asyidi Md Nadzir — Mon, 30 Mar 2026 00:00:00 +0800

Outdoor porcelain insulators are significant in power distribution due to the fact that they offer insulation and mechanical support to overhead lines. Some of the environmental contaminants that may cause impairment of performance, especially under AC stress, are dust, salt, and moisture. The existence of moisture on the insulator surface can lead to the formation of soluble salts, creating a conductive layer that leads to increased leakage current, dry-band formation, and a reduction in flashover voltage. This experiment was designed to investigate the influence of the severity of pollution upon the AC breakdown voltage of 11 kV porcelain disc insulators based on the standard Equivalent Salt Deposition Density (ESDD). The conditions were controlled to simulate dry and wet states of clean, light, medium, and heavy pollution, as stipulated in IEC 60507. Besides, COMSOL Multiphysics, through the finite element simulation function, was used to imitate the electric field density and the leakage current for each level of pollution. The results showed that the breakdown voltage decreased with an increase in pollution, and the most meaningful outcome was that of wet conditions. It is also found through simulations that, in the case of heavy pollution, the strengthening of the electric field around the high-voltage electrodes becomes higher. The agreement between the experiment and simulation supports the modelling strategy and validates that the hybrid techniques are trustworthy in identifying the performance of the insulator in a polluted environment.

MLP Sliding-Window Forecasting for Electricity Load Prediction: A Multi-Scale Evaluation using an ONNX-based Java Framework

Farid Morsidi, Asma Hanee , Rohaizah — Mon, 30 Mar 2026 00:00:00 +0800

Deep learning models for time-series forecasting offer significant potential but face deployment challenges. This paper advances a modular framework for deploying ONNX models in Java, building on previous work. The research paper assesses the MLP sliding-window architecture through different time intervals which extends the previous LSTM-based system to establish primary performance standards that future research can use for comparison. The framework incorporates additional features for enhanced evaluation, including five metrics (MAE, RMSE, MAPE, SMAPE, R²), automated archiving, and high-quality graphical exports. Evaluations using electricity consumption data (ETTh1) and benchmark datasets show that the MLP sliding-window model outperforms LSTM in terms of R², MAE, and MAPE, achieving scores of 0.9895, 0.5907, and 7.19%, respectively, indicating high accuracy across various domain. The framework also implements a custom threshold (ε = 1e−10) to handle near-zero values in MAPE calculation, ensuring reliable result storage for reproducibility. The findings reveal that simpler MLP designs can either match or exceed LSTM performance in specific scenarios while offering faster processing and easier implementation. Detailed comparisons and guidelines for deployment are included, along with insights into model selection criteria

Prediction of Traffic Flow Time Series Data on Jakarta-Cikampek Toll Road Using a Chaotic Approach and Local Linear Approximation Method

Yessy Yusnita, Nur Hamiza Adenan, Angelalia Roza — Mon, 30 Mar 2026 00:00:00 +0800

The Jakarta–Cikampek Toll Road is widely recognised as a critical corridor linking Jakarta with major industrial centres and expanding residential areas in West Java. Traffic along this route is frequently dense and exhibits noticeable fluctuations over time. At certain periods, these variations reveal nonlinear patterns shaped not only by commuter movements and freight transport but also by broader economic activity. This study focuses on short-term traffic forecasting by modelling traffic flow as a nonlinear dynamical system rather than a purely stochastic process. A chaos-based framework is applied to the traffic flow time series through two main stages: first, the presence of chaotic behaviour is examined using the 0–1 test; second, short-term forecasting is performed using the Local Linear Approximation Method (LLAM), which utilises neighbouring trajectories in phase space. Hourly traffic flow data recorded over seven consecutive days are analysed, with 144 observations used for training and 24 for testing. The 0–1 test confirms the existence of chaotic dynamics within the series. During the forecasting stage, LLAM demonstrates reasonable agreement with observed traffic flow, achieving a Pearson correlation coefficient (r) of 0.8964, a Mean Absolute Error (MAE) of 159.41 vehicles per hour, and a Root Mean Squared Error (RMSE) of 203.42 vehicles per hour. These findings indicate that chaos-based modelling provides a dependable approach for short-term traffic forecasting. Beyond predictive accuracy, the framework offers practical value by supporting quicker operational responses, improved congestion management, and more effective short-term planning in dynamic toll-road environments.

Observation on Control and Navigation Capability Of a Tail-Less Blended Wing-Body UAV Equipped With 4G Internet Communication

Rizal E. M. Nasir, Nur Emileen Abdul Rashid, Shahrean Zainurin — Mon, 30 Mar 2026 00:00:00 +0800

This paper highlights the development of flight navigation system using 4G communication protocol for a transport unmanned aerial vehicle (UAV) based on a tail-less blended wing-body (BWB) UAV. Normal radio-based transceiver of 2.4GHz or 433MHz frequencies are limited, by regulation, to low power that limits their communication range to just merely one to two kilometres. Long-range navigation, while possible is automated mode, cannot be observed in real time due to limited communication distance. The objective of this research is to observe capabilities of a UAV navigation system utilizing 4G Internet communication specifically to the Blended Wing-Body type of configuration that requires sophisticated control and active stabilization. The UAV features six control surfaces with mixing strategy that enables these surfaces to act as elevators, ailerons, rudders and airbrakes. To achieve this, Navio2-Raspberry Pi4 IMU-controller-computer with Internet Protocol (IP) from cellular network is integrated into the BWB UAV in which the former controls propeller speed, four elevons and a pair of split drag flaps. The results show that good navigational accuracies of each waypoint is within 10 metres except for four waypoints which fall outside of aircraft’s manoeuvrability envelope, possibly due to manoeuvrability limitation. This successful integration opens promising possibilities for the future development and deployment of similar but larger UAV platforms, with improved efficiency and reliability in various applications.

AI-Enhanced Adaptive Flood Management: Integrating Multi-Objective Evolutionary Optimization and Real-Time SCADA for the Muda River Basin

Hapida Ghazali, Tajul Ariffin Norizan, Zulkifli Mohamed, Firdaus Mohamad — Mon, 30 Mar 2026 00:00:00 +0800

Mainly during the monsoon season, the Muda River Basin in northern Malaysia faces significant flood risks, threatening community safety, local infrastructure, and agricultural activities. Traditional flood management methods, which often rely on simplified empirical models, fall short in addressing the complex and dynamic nature of flood events in this region which prevents the hydromechanical infrastructure from being operated optimally. This study introduces an innovative AI-powered framework designed to enhance mechanical flood gates optimally in the Muda River Basin by integrating advanced machine learning techniques, real-time hydrological data, and automation technologies within an intelligent control system. The system features mechanical improvements such as automated hydraulic gate control for optimized discharge management and dynamic flood routing, all facilitated by a sophisticated SCADA architecture. These mechanical automation enhancements, combined with AI-driven models, improve the accuracy of flood predictions, enabling more effective, data-driven decision-making and adaptive flood control strategies. The results of this research demonstrate that AI-based flood management systems can significantly enhance operational resilience through optimal hydromechanical operation, improve flood prediction accuracy, and optimize water flow management, providing a scalable solution for mitigating flood risks in tropical river basins.

Prediction of Density and Surface Roughness in LPBF-Printed Parts from Recycled SS316L Powder Using Random Forest Regression Model

Mon, 30 Mar 2026 00:00:00 +0800

This paper use of machine learning algorithm to predict the density and surface roughness of 316L stainless steel parts manufactured using recycled powder based on the process parameter and powder characteristics. The advancement in Laser Powder Bed Fusion (LPBF), has enabled the production of complex and high-performance metallic components. However, the high cost of virgin powders and the substantial material waste generated during the AM process present economic and environmental challenges. The developed models with dedicated system interface built on the understanding of the effect of powder characteristics on the part properties included layer thickness, hatch spacing, laser power, and scanning speed. Feature relationships were analyzed using a correlation heatmap, highlighting strong interdependencies such as the inverse correlation between density and surface roughness (R = 0.98), and the alignment between laser power and scanning speed (R = 0.74). The RFR model was trained on datasets of varying sizes, and its performance was evaluated using standard error metrics (MAE, MSE, RMSE) and the coefficient of determination (R²). The model achieved high predictive accuracy, with an R² of 0.821 for density and 0.795 for surface roughness on a benchmark dataset. Error metrics were significantly lower than previous studies: MAE of 0.218 for density and 0.256 for surface roughness. Performance improved with larger datasets, reaching an R² of 0.973 for density and 0.942 for roughness at 250 samples, though a slight drop in accuracy was observed beyond this point due to potential data noise. The Random Forest model demonstrated strong capability in predicting quality outcomes in LPBF processes, outperforming earlier works in both accuracy and consistency. The developed system provides a model tool to inform AM optimization effectively, especially when supported by carefully selected features and appropriate dataset sizes.

Assessment of Heavy Metal Contaminants in Tomatoes Processed with Locally Fabricated Milling Machine

Mon, 30 Mar 2026 00:00:00 +0800

Tomatoes are a staple food in many diets worldwide, often processed using locally fabricated milling machines in sub-Saharan Africa. However, these machines may introduce metal contaminants into tomato products, posing health risks. This study assesses the levels of heavy metals (Fe, Cu, Pb, Cd, Mg, Ca, Mn,) in tomatoes milled with locally fabricated machines. Samples were analysed using atomic absorption spectroscopy (AAS). The analysis showed that the detected metals from Tomatoes sourced from South (TSS) are Fe, Mg and Ca with concentration that varies between 8.08 to 27.44 mg/kg, 112.81 to113.46 mg/kg, 0.66 to 0.75 mg/kg respectively. While for Tomatoes sourced from the North (TSN), the metals detected are Fe, Cu, Pb, Mg, and Ca with concentration varying from 7.56 to 29.28 mg/kg,11.65 to 11.84 mg/kg, 0.011 to 0.08 mg/kg, 140.62 to142.54 mg/kg, and 0.5 mg/kg, respectively. Result of the analysis revealed that some contaminants might have been introduced during the milling process. Both carcinogenic and noncarcinogenic risk analysis revealed that adult and child exposure to risk is below minimal. The findings highlight the need for improved locally fabricated milling machine design and stricter food safety regulations to mitigate metal contamination.