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

2026-03-02T14:49:43+08:00

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

2026-03-02T12:59:35+08:00

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

2026-03-02T12:57:10+08:00

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

2026-03-02T14:55:28+08:00

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

2025-12-30T17:29:18+08:00

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

2026-03-20T12:40:10+08:00

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

2026-02-27T09:20:09+08:00

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.

3D Printing Technology For Housing Construction Projects in Malaysia: The Perceptions of Construction Stakeholders

2026-03-06T09:49:20+08:00

The global construction landscape is undergoing a paradigm shift driven by Construction 4.0 and the Fourth Industrial Revolution (IR 4.0). Despite its potential for small-scale residential projects, Three-Dimensional Concrete Printing (3DCP) technology remains in its infancy within the Malaysian construction industry. This study investigates the readiness of the industry by assessing construction stakeholder’s perceptions of its potential, suitable technological approaches, and best implementation practices. Utilizing a mixed-methods questionnaire survey analysed through descriptive statistics and thematic coding, the research identifies critical drivers and barriers to adoption. The findings provide a strategic framework for best practices, offering a roadmap for stakeholders to integrate 3DCP into the Malaysian housing market effectively. The results show that the perception of respondents regarding the potential of 3DCP technology for housing construction project is very high in minimising time in construction and generally, high potential of enhancing housing project delivery in Malaysia, with moderate to high opinion on the potential to minimise waste, reliance on foreign labour, long-term costs and the better quality of housing. Hybrid applications gained by using 3D printed parts with traditional construction and low-rise housing are considered the most appropriate ones, and extrusion-based 3D concrete printing and modular 3D printing are also considered the most appropriate, but with lower confidence. Among the best practices emerging are the formulation of clear guidelines and standards, specialised training, government, industry and academia collaboration and the pilot housing project, but it seems that the lack of skilled personnel, unclear regulations, high initial equipment cost and low public awareness are seen as the key detractors. Malaysian stakeholders recognise 3DCP’s potential to save time, waste, and labour in housing construction project. However, they emphasize that mainstream success depends on better standards, specialized training, and the use of local materials.

Parameter Analysis of Gas Metal Arc Welding (GMAW) in Determining Defects by Comparing the Response Surface Method (RSM) and Artificial Neuron Network (ANN)

2026-02-12T15:38:35+08:00

Welding is a critical manufacturing process widely employed in industry for joining two or more materials through localized melting and subsequent solidification. Among the various welding techniques, Gas Metal Arc Welding (GMAW) is extensively used due to its high efficiency, versatility, and suitability for joining both ferrous and nonferrous materials. Optimizing GMAW process parameters is essential for improving weld quality, minimizing defects, and enhancing structural integrity in industrial applications. However, existing studies often rely on either statistical methods or machine learning approaches independently, with limited comparative analysis of their predictive capabilities, particularly within a simulation-based framework. This study aims to analyse and optimize key GMAW process parameters and to evaluate the predictive performance of Response Surface Methodology (RSM) and Artificial Neural Network (ANN) models. Finite element simulations are performed using Simufact Welding software to investigate the influence of welding current, arc voltage, and welding speed on output responses, including peak temperature, welding-induced deformation (distortion), and maximum residual stress. The simulated data are further analyzed using RSM to develop predictive mathematical models and examine interaction effects among input parameters, while an ANN model is implemented to enhance prediction and validation. The results indicate that both approaches are effective in modelling the process; however, RSM demonstrates superior predictive accuracy, as evidenced by a lower root mean square error (RMSE) compared to the ANN model. The key finding of this study highlights the effectiveness of RSM as a reliable and accurate tool for optimizing GMAW process parameters within a numerical simulation framework.

Simulation Study of Static and Fatigue Behaviour using Mesh-Free and Meshed FEM on a Bogie Frame

2026-03-27T11:36:52+08:00

This research is devoted to studying the simulation of fatigue behavior for bogie frames using the finite element method (FEM) and mesh-free. The bogie frame is the main structure that supports repeated loads from external forces on the railway car. This study used Altair SimSolid for static and fatigue analyses with a mesh-free method while Altair HyperLife simulated the fatigue analysis using meshed finite element methods (FEM) supported by Altair Hyperworks for static analysis results. This research has adopted this method because traditional models for calculating fatigue life have limitations that can lead to inaccuracies and unreliability. Cyclic loading is applied to the frame for simulating real-life conditions and determining its fatigue life. The frame is made of low-carbon steel and subjected to two vertical force loads of 196.2 kN each supported by four fixed points at the bogie frame's ends. The principal stress values obtained for the frame are 20.71 MPa for the FEM and 19.138 MPa for the mesh-free method. According to the fatigue life analysis, Altair HyperLife and Altair SimSolid yield fatigue life value for channel scale one, and channel scale 15 yields 100E cycles. A red contour shows the presence of damage.

Sustainability Readiness Assessment of Electric Vehicle Battery Recycling Industry in Indonesia: A Maturity Model Approach

2026-04-21T08:27:56+08:00

The rapid growth of electric vehicle (EV) adoption in Indonesia has raised concerns regarding end-of-life battery waste management. Although the government has established a roadmap targeting implementation by 2030, there is no structured instrument to assess the readiness of the EV battery recycling industry. This study proposes a maturity-based assessment instrument, namely the Sustainable EV Battery Recycling Maturity Model, to evaluate the readiness of the EV battery recycling industry in Indonesia. The model measures industry readiness through a set of defined indicators and maturity levels, adapted from existing maturity model concepts (e.g., CMM-based maturity levels) and contextualized to the Indonesian setting. The framework was developed through a systematic literature review and expert consultation, resulting in five dimensions: Technology, Governance, Economy, Social, and Environment, comprising a total of 15 sub-indicators. The indicators and sub-indicators were validated by three experts with relevant experience in the field using the Content Validity Index (CVI), while the weighting process was conducted using the Hesitant Fuzzy Analytic Hierarchy Process (HF-AHP). To demonstrate its practical applicability, the model was implemented in a hazardous waste management company to calculate a maturity index score. The results indicate that the current readiness level is at the “Defined” stage, with governance and regulatory alignment identified as key areas for improvement. Overall, this study provides a structured assessment framework to support the development of sustainable EV battery waste management systems, particularly in emerging economies.

Thermal Analyses on High and Medium Pressure Steam Flow in a Steam Conditioning Valve with a Steam Nozzle Using CFD

2026-04-10T07:49:20+08:00

An essential part of controlling steam flow and pressure in industrial systems is a pressure control valve which lowers and regulates steam pressure prior to its delivery process. Unplanned plant shutdowns and large operating losses could cause damage like a hairline crack near a valve diffuser on the inside surface of the control valve caused by high pressure steam. Experienced in chemical industry, a pressure control valve located in a utility area has exhibited signs of internal surface cracking might due to continuous operation in high and medium pressure steam, whereby a valve replacement is needed. This study is exploratory and not intended for quantitative prediction with a scope involving modelling of steam conditioning valve using 3D modelling software. Based on the valve specifications, the study analysed the cause of hairline crack due to steam flow within the valve using Computational Fluid Dynamics (CFD) simulation with appropriate boundary conditions in determining temperature distribution along the inner surface. The objective was to investigate the effect of temperature distribution of the valve with and without a steam nozzle at Point A-B as the hairline crack area is predicted to be initiated based on real life occurrence. The impact of flow temperature in Steam Conditioning Valve contributing to the cracking event in valve body might be due to rapid expansion of high-pressure steam, which induces cooling due to energy conversion from internal energy to kinetic energy during compressible flow. By comparing high-pressure steam (HPS) and medium-pressure steam (MPS) conditions, the nozzle inlet’s pressure was reduced to compare the flow behaviour of valve under MPS condition. The overall temperature difference was significantly lower for MPS which is only 38% reduction compared with under HPS conditions of 59%. However, the temperature drop for HPS from Point A to B exhibited immediate drop compared to MPS condition which may cause cracking due to rapid cooling. The identification of critical regions with elevated temperature values, which can be related to the actual problem of chemical industry, may contribute to the ongoing MPS letdown of control valve replacement project in chemical industry.