Association for Scientic Computing Electronics and Engineering (ASCEE): Open Journal Systems
Not a member yet
785 research outputs found
Sort by
Nonlinear Model Predictive Control of a Magnetic Levitation System Using Artificial Protozoa Optimizer
Full text linkA magnetic levitation system (Maglev) is a sensitive, multi-parameter, nonlinear, and unstable system that is utilized to levitate a ferromagnetic object in free space. Due to its vast applications, various research studies in the field of control strategy have become extremely important and challenging. This work proposes the design of a nonlinear model predictive (NMPC) control scheme for the object position control against the nonlinearities and uncertainties of a Maglev system. A novel bio-inspired Artificial Protozoa Optimization (APO) algorithm is used to fine-tune the NMPC parameters, which include best weighting matrices ( ), shorter prediction horizons ( ), and shorter time steps ( ) to minimize the objective cost function. The effective performance of the NMPC is verified using simulation-based results in MATLAB. The CasADi toolbox is utilized to solve nonlinear optimization problems and handle the nonlinearity of the Maglev system model. Simulations are implemented for three trajectories tracking (step, sine, and square) with 20% and without Maglev parameters perturbations. To prove the superiority of the proposed controller, comparisons are made with the conventional Linear Quadratic Regulator (LQR) and proportional-integral-derivative (PID) controllers. Two performance indices are introduced, Integral of Squared Error (ISE) and Integral of Absolute Error (IAE), to examine the tracking performances of the NMPC, LQR, and PID controller. The NMPC controller has shown more efficient performance and accurate results than other controllers. The contributions of this work include a new optimization technique of APO, a new engineering application of the APO integrated with NMPC to control a Maglev system, consideration of inherent nonlinearities and system constraints, and robustness improvement under perturbation
Comparative analysis of decision tree and random forest classifiers for structured data classification in machine learning
Full text linkThis study explores the application of machine learning techniques, specifically classification, to improve data analysis outcomes. The primary objective is to evaluate and compare the performance of Decision Tree and Random Forest classifiers in the context of a structured dataset. Using the Elbow Method for optimal clustering alongside decision tree and random forest for classification algorithms, this research investigates the effectiveness of each method in accurately categorizing data. The study employs K-Means clustering to segment the data and Decision Trees and Random Forests for classification tasks. Dataset used in this research was obtained from Kaggle consisting of 13 attributes and 1048575 rows, all of which are numeric. The key results show that Random Forest outperforms Decision Trees in terms of classification accuracy, precision, recall, and F1 score, providing a more robust model for data classification. The performance improvement observed in Random Forest, particularly in handling complex datasets, demonstrates its superiority in generalizing across varied classes. The findings suggest that for applications requiring high accuracy and reliability, Random Forest is preferable to Decision Trees, especially when the dataset exhibits high variability. This research contributes to a deeper understanding of how different machine learning models can be applied to real-world classification problems, offering insights into the selection of the most appropriate model based on specific data characteristics
Experimentation of BIM and AI software to support Adaptive Learning System in interior design course
Full text linkCurrent undergraduate students, particularly Generation Z, are digital natives who have grown up with digital technology and exhibit unique learning characteristics that necessitate new approaches in higher education. An Adaptive Learning System in education involves leveraging technology to accommodate individual students' unique needs and preferences. This research aims to enhance learning effectiveness and design processes in interior design courses, with the case study Interior Design II course at Telkom University, Indonesia. The course currently offers limited software options for interior layout design, which may hinder students' abilities and preferences. This study compares three software tools—Autodesk AutoCAD, Building Information Modeling (BIM) software Autodesk Revit, and Artificial Intelligence (AI)-based plugin PlanFinder—to determine which is most effective in improving students' understanding and simplifying the design process. The research methodology employs a mixed-method approach, integrating qualitative methods such as literature reviews and Focus Group Discussions (FGDs) with quantitative methods like experimentation workshops and pre-test and post-test questionnaires analyzed using SPSS software. The results demonstrate that Autodesk Revit, a BIM software, notably enhances the design process's effectiveness, particularly within the Interior Design II course context. Consequently, the study recommends the implementation of Adaptive Learning Systems that allow students to select software based on their capabilities and preferences. The three software tools/plugins examined in this study can be considered for integration into interior design courses. Furthermore, future research should seek to broaden the sample size and evaluate additional AI tools in interior design courses for comparative analysi
Bridging tradition and modernity: exploring patutan (the modal system) in Balinese music through the hybrid composition ‘cane’
Full text linkThis paper examines how the composer integrates traditional Balinese gamelan elements with Western musical concepts in the creation of the piece "Cane," focusing on two main aspects: the creative process and aesthetic analysis. Several strategies are employed, such as adopting, borrowing, transforming, elaborating, ornamenting, and combining musical elements from various genres and cultural traditions. The hybrid work "Cane" exemplifies this approach by blending motifs, patterns, and ornamentation from both Balinese and Western music. Additionally, the piece incorporates the processing of patutan/patet (modal system) from the Semar Pagulingan Saih Pitu gamelan ensemble. Rooted in research and experimentation, "Cane" is structured into five distinct parts, each utilizing one or more of these strategies. The music emphasizes melodic development intertwined with rhythmic, dynamic, and tempo variations. In the context of hybridization, the combination of musical elements includes: (1) Balinese traditions such as kekenyongan, nyongcag, ngempyung, and kekilitan motifs, and (2) Western elements like unison, harmony, dissonance, polyphony, and imitatio
Performance Enhancement of DC Motor Drive Systems Using Genetic Algorithm-Optimized PID Controller for Improved Transient Response and Stability
Full text linkSome systems require mechanical power, which can be used in many applications, including rotating vehicle wheels, pulling elevators, and moving robot limbs, etc. Mechanical or kinetic energy can be produced and generated from electrical machines, which can be represented by an electric motor, which is a machine that operates on electrical energy, i.e. input energy, and produces mechanical energy, i.e. output energy. One of the most common and widely used motors is the DC motor, which has features that make it a matter of interest to researchers, producing and manufacturing companies to develop and improve its performance. The motor is characterized by flexibility, low cost, durability, and the ability to control the speed and position of the rotating member using traditional, expert and intelligent control systems to achieve appropriate performance according to the field of application. In linear systems, traditional systems (Proportional-Integral-Derivative Controller (PID) have succeeded, while their performance is weak and unacceptable in nonlinear systems. Therefore, expert and intelligent control systems are relied upon to improve the performance of electric motors. It is proposed to implement and operate an electric motor control system using the genetic algorithm to verify its effectiveness in improving performance compared to the traditional one (PID). The genetic algorithm was chosen to address the optimization challenges because it is commonly used in artificial intelligence applications in various fields that are suitable for real time. Therefore, this study presented improving the performance of the traditional controller using the genetic algorithm. Through comparison, the possibility of improving the system performance with changing operating conditions was verified by adjusting the parameters of the traditional controller. The simulation was performed using Matlab, and the DC motor specifications included a rated voltage of 32.4 V, a rated current of 2 A, a rated speed of 536 rad/s, and a power of 54 watts. The conventional controller is responsible for the basic feedback control, while the GA-PID controller optimizes the control parameters to improve the system performance
Application of Artificial Neural Networks in Predicting Internal Combustion Engine Performance and Emission Characteristics: A Review of Key Methodologies and Findings
Full text linkThe global need for fuel-efficient coupled with minimizing the environmental impacts of ICEs. This review paper highlights how different ANN methodologies such as backpropagation, recurrent neural networks (RNNs), and long short-term memory (LSTM) networks have been applied to optimize engine calibration, improve fuel efficiency, and minimize emissions across a wide range of fuel blends, including hydrogen-gasoline and ethanol-gasoline mixtures. The research focuses on the application of ANN models to predict performance indicators such as brake thermal efficiency, brake-specific fuel consumption, and emissions, reducing reliance on costly and time-consuming experimental tests. The methodology involved a systematic review of peer-reviewed studies published between 2010 and 2024. Studies were selected based on criteria such as relevance to ICE performance and emission control, use of ANN methodologies, and the availability of experimental or simulation data for validation. involves the use of advanced ANN architectures, including backpropagation, RNNs, and LSTM networks, to establish nonlinear relationships between input parameters such as engine speed, load, and fuel type, and output performance indicators. Findings show that comparison between real model and developed program enhanced from ANN model make a difference prediction capability for engine performance enhanced by at least 10 to 15 % of the traditional modeling. techniques, provide better calibration method of ICEs for better fuel consumption. efficiency and reduced emissions. This present study seeks to establish itself in matters that have not been explored in other papers or researches as follows. integration of Hybrid ANN models, which are better than conventional methods in two major trends, one of which is the improvement of the predictive accuracy and the other is the achievement of increased computational efficiency. It is found that the ANN methodologies presents a strong armory in improving the performance of ICE coupled with lowering of emissions with the possibilities of additions for further enhancements of the technology through the incorporation of other machines use of learning techniques in the future studies
Lightning Risk Assessment, Control and Protection Scheme Design for a Rooftop Photovoltaic System in the New Capital of Egypt
Full text linkThe absence of an effective lightning protection system for photovoltaic (PV) systems can hinder their integration into networks. Outdoor PV installations are vulnerable to direct or indirect lightning strikes, resulting in damaging overvoltages that harm the PV structure. These systems, often situated on rooftops or open fields, face increased lightning strike risks due to their exposure compared to more sheltered setups. Lightning-induced surges can harm sensitive electrical components like panels, inverters, and wiring, leading to potential damage and downtime. The complexity of PV systems, with interconnected components, makes designing protection strategies challenging. Compliance with lightning protection standards is crucial to prevent damage, downtime, and financial losses. Implementing effective protection measures involves grounding, surge protection, and adherence to regulations. Lightning protection systems intercept strikes and safely direct electrical energy to the ground, safeguarding sensitive components and ensuring continuous power generation. The IEC 62305-2 standard guides lightning risk assessment and mitigation, aiding in evaluating risks, calculating damage likelihood, and designing protective measures. A case study focusing on the Arab African International Bank's rooftop PV system in Egypt illustrates the importance of lightning risk management in financial, operational, and regulatory contexts for solar projects. Risk assessment aims to identify vulnerabilities, implement mitigation strategies, and ensure safe, reliable system operation. By addressing lightning risks effectively, stakeholders can enhance system safety, reliability, and longevity while minimizing downtime and revenue loss associated with lightning strikes
Comparative Analysis of Path Planning Algorithms for Multi-UAV Systems in Dynamic and Cluttered Environments: A Focus on Efficiency, Smoothness, and Collision Avoidance
Full text linkThis study evaluates the performance of various path planning algorithms for multi-UAV systems in dynamic and cluttered environments, focusing on critical metrics such as path length, path smoothness, collision avoidance, and computational efficiency. We examined several algorithms, including A*, Genetic Algorithm, Modified A*, and Particle Swarm Optimization (PSO), using comprehensive simulations that reflect realistic operational conditions. Key evaluation metrics were quantified using standardized methods, ensuring the reproducibility and clarity of the findings. The A* Path Planner demonstrated efficiency by producing the shortest and smoothest paths, albeit with minor collision avoidance limitations. The Genetic Algorithm emerged as the most robust, balancing path length, smoothness, and collision avoidance, with zero violations and high feasibility. Modified A* also performed well but exhibited slightly less smooth paths. In contrast, algorithms like Cuckoo Search and Artificial Immune System faced significant performance challenges, especially in adapting to dynamic environments. Our findings highlight the superior performance of the Genetic Algorithm and Modified A* under these specific conditions. We also discuss the potential for hybrid approaches that combine the strengths of these algorithms for even better performance. This study's insights are critical for practitioners looking to optimize multi-UAV systems in challenging scenarios
Designing play mats as a tool for gross motor stimulation for early childhood using design thinking
Full text linkThe development of gross motor skills in early childhood is an important aspect of their initial growth stage. However, in the process of guidance, parents often face difficulties and limitations in stimulating their child's motor skills due to the lack of effective and adaptive play equipment. This research aims to address that gap by designing a practical play mat that can assist parents or institutions in supporting and stimulating the gross motor skills of early childhood children through design thinking steps. Qualitative research methods with a practice-based design approach were applied to develop a play tool that not only stimulates children's gross motor skills through movement but also supports social interaction and collaboration. The research results show that this tool facilitates parents and institutions in meeting children's gross motor development needs more effectively. These findings contribute in the form of practical and functional play mats, based on user-centered design, which can be applied in early childhood education institutions and family communities
A Review of Advanced Force Torque Control Strategies for Precise Nut-to-Bolt Mating in Robotic Assembly
Full text linkAchieving precise alignment in high-precision robotic assembly is critical, where even minor misalignments can cause significant issues. Various control strategies have been developed to tackle these challenges, including passive compliance control (PCC), active control (AC), and manual teaching method (MTC). While AC is valued for its real-time adaptability, PCC and MTC offer advantages in simpler, cost-effective applications. Â Â This review evaluates these strategies, emphasizing the integration of AI and machine learning to address the limitations of traditional AC methods, such as spiral and tilt searches, which are rigid, slow, and computationally demanding, making them unsuitable for dynamic environments. Machine Learning (ML) and Artificial Intelligence (AI) offer data-driven improvements in performance and adaptability over time. Techniques like Linear Regression, Artificial Neural Networks (ANNs), and Reinforcement Learning (RL) are explored for enhancing precision and real-time adaptability in complex tasks. These AI methods are applied in real-world industries, such as automotive and electronics manufacturing. The review compares control strategies and AI techniques, analyzing trade-offs in accuracy, speed, computational efficiency, and cost. It also discusses future directions, including hybrid control systems, advanced sensor integration, and more sophisticated AI algorithms. Ethical and safety considerations are highlighted, particularly in industrial settings where reliability and human-robot interaction are critical. This comprehensive review demonstrates AI's potential to enhance precision, reduce manual intervention, and improve performance in high-precision robotic assembly while guiding the selection of appropriate methods for specific applications