Association for Scientic Computing Electronics and Engineering (ASCEE): Open Journal Systems
Not a member yet
785 research outputs found
Sort by
Long Short-Term Memory vs Gated Recurrent Unit: A Literature Review on the Performance of Deep Learning Methods in Temperature Time Series Forecasting
Get PDFTemperature forecasting is a crucial aspect of meteorology and climate change studies, but challenges arise due to the complexity of time series data involving seasonal patterns and long-term trends. Traditional methods often fall short in handling this variability, necessitating more advanced solutions to enhance prediction accuracy. LSTM and GRU models have emerged as promising alternatives for modeling temperature data. This study is a literature review comparing the effectiveness of LSTM and GRU based on previous research in temperature forecasting. The goal of this review is to evaluate the performance of both models using various evaluation metrics such as MSE, RMSE, and MAE to identify gaps in previous research and suggest improvements for future studies. The method involves a comprehensive analysis of previous studies using LSTM and GRU for temperature forecasting. Assessment is based on RMSE values and other metrics to compare the accuracy and consistency of both models across different conditions and temperature datasets. The analysis results show that LSTM has an RMSE range of 0.37 to 2.28. While LSTM demonstrates good performance in handling long-term dependencies, GRU provides more stable and accurate performance with an RMSE range of 0.03 to 2.00. This review underscores the importance of selecting the appropriate model based on data characteristics to improve the reliability of temperature forecasting
Optimizing Single-Inverter Electric Differential System for Electric Vehicle Propulsion Applications
Get PDFThe increasing demand for electric vehicles (EVs) is driven by the urgent need for environmentally friendly transportation. This paper addresses the challenge of optimizing EV drivetrain efficiency by proposing a novel single-inverter electronic differential system for distributed EV drivetrains. The research focuses on reducing system cost and complexity while maintaining high performance. The methodology involves a detailed simulation using MATLAB/Simulink to validate the theoretical soundness of the proposed connection method. The results demonstrate that the proposed system achieves a minimum accuracy rate of 97.5%, marking a significant improvement over traditional dual-inverter systems. This approach not only enhances drivetrain efficiency but also contributes to more compact and cost-effective vehicle designs. Additionally, the findings underscore the potential for further refinement and exploration, suggesting that continued advancements in ED systems could lead to even greater performance gains in the future. This research lays the groundwork for future innovations in EV technology, particularly in the areas of cost reduction and system efficiency
Utilize the Prediction Results from the Neural Network Gate Recurrent Unit (GRU) Model to Optimize Reactive Power Usage in High-Rise Buildings
Get PDFThe growing urbanization and the construction sector, efficient use of electric energy becomes important, especially the use of reactive power. If excessive use causes decreased efficiency and increased operational costs. Decreased efficiency contributes to increasing exhaust gas volumes and greenhouse emissions. Efficient energy can achieved if planning and predictions are correct. This research applies the GRU neural network method with grid search initialization as a novelty predictive model for energy-use high-rise buildings in form fast training without multiple iterations because optimal hyperparameters are obtained. Experimental show the MAE and RMSE performance metrics of the GRU better than LSTM in predicting energy consumption data peak loads, off-peak loads and reactive power. The accuracy of GRU predictions can optimize the use of energy to contribute to saving the environment from exhaust emissions and the greenhouse effect in urban systems. Experimental results demonstrate the superiority of GRU over LSTM, proof of the much lower MAE and RMSE values. This metric shows the accuracy of GRU in generalizing data both during peak and off-peak hours, as well as in reactive power usage. By Utilizing GRU's capabilities, building management can manage reactive power usage effectively, allocate reactive power resources appropriately, and mitigate peak load times and the power factor within the threshold, thus avoiding additional costs and electrical system efficiency and contributing to reducing the carbon footprint and gas emissions greenhouse. Research on GRU is widely open in the high-rise building sector, including its integration with sensors to automatically control energy use
Design and Implementation of Crowbar and STATCOM for Enhanced Stability of Grid-Tied Doubly Fed Induction Wind Generators
Get PDFThese days, one of the most used layouts in the wind power industry is a variable-speed doubly-fed induction wind generator (DFIWG). For providing active power (P) and reactive power (Q) control during grid failures, this research examines the DFIWG. The system's transient behavior is examined under normal and abnormal circumstances. Through control of rotor side (RSC) and grid side (GSC) converters, Q assistance for the grid, and power converter stress reduction, the suggested control approach achieves system stability while enabling DFIWG to operate smoothly during grid failures. The DFIWG is exposed to three- and two-phase faults to analyze the machine's performance. The crowbar and STATCOM tools are implemented to enhance the system performance under faults and compared with the base case. The implemented tools successfully suppress rotor and stator overcurrent, over voltage at the DC link (DCL), and power oscillations, as well as supporting the grid voltage understudied cases. The obtained results prove that both STATCOM and crowbar not only enhance the system's effectiveness and performance but also enable the system to achieve the fault ride-through capacity (FRTC). MATLAB/SIMULINK 2017b is used for time-domain computer simulations
Accurate Robot Navigation Using Visual Invariant Features and Dynamic Neural Fields
Get PDFRobot navigation systems are based on Simultaneous Localization and Mapping (SLAM) and obstacle avoidance. We construct maps for the robot using computer vision methods requiring high repeatability for consistent feature tracking. Also, the obstacle avoidance method needs an efficient tool for fusing data from multiple sensors. This research enhances SLAM accuracy and obstacle avoidance using advanced visual processing and dy namic neural fields (DNF). We propose two key methods: (1) an enhanced multiscale Harris detector using steerable filters for robust feature extrac tion, achieving around 90% repeatability; and (2) a dynamic neural field algorithm that predicts the optimal heading angle by integrating visual de scriptors and LIDAR data. The first method’s experimental results show that the new feature detector achieves high accuracy, outperforming exist ing methods. Its invariance to the orientation of the image makes it insen sitive to the rotations of the robot. We applied it to the monocular SLAM and remarked that the positions of the robot were computed precisely. In the second method, the results showed that the dynamic neural fields algo rithm ensures efficient obstacle avoidance by fusing the gist of the image and LIDAR data, resulting in more accurate and consistent navigation than laser-only methods. In conclusion, the study presents significant advance ments in robot navigation through robust feature detection for SLAM and effective obstacle avoidance using dynamic neural fields. These advance ments significantly enhance precision and reliability in robot navigation, paving the way for future innovations in autonomous robotic applications
Applications of Multi-Objective OPF Solutions with Optimal Placement of Multiple and Multi-Type FACTS Units to IEEE System: Comparison of Different Approaches
Get PDFOptimal power flow (OPF) problem and its implications for power system stability and efficiency is investigated in this study. OPF, a restricted optimization query with non-linearity and non-convexity, is one of the most challenging and fascinating problems in the recent power system. Based on these parameters, researchers have been working hard over the past few decades to identify the best solutions to the OPF issue that maintain system stability. This work presents multi-objective OPF solutions utilizing Newton's technique with numerous multi-type FACTS units. First, the GA is applied to identify the perfect size and location of the FACTS units. Next, the generator and FACTS settings are optimized. In this instance, four scenarios are taken into consideration and three OFs are employed to see how the OFs affect the positioning and dimensions of FACTS devices. The OF is suggested to consider the reduction of both generation costs and transmission losses while also optimizing the power transfer capacity of designated corridors. A full analysis relating to the IEEE-30 bus system is presented and analyzed
Control of a Multimode Double-Pendulum Overhead Crane System Using Input Shaping Controllers
Get PDFThis paper investigates the impact of higher derivative input shaping for minimizing both oscillations, namely hook and payload of a multimode double-pendulum overhead crane (MDPOC) system. The MDPOC has greater nonlinearities and stronger internal couplings, especially when involving two oscillation frequencies with multimode dynamic effects. With a suitable system’s natural frequency and damping ratio of the hook and payload oscillations, multimode zero-vibration (ZV-ZV), multimode zero-vibration derivative (ZVD-ZVD) and multimode zero-vibration derivative-derivative (ZVDD-ZVDD) shapers are successfully designed. More interestingly, two scenarios under a fixed cable length and a payload hoisting are considered which are closer to the real practical crane.  Thus, an average travel length (ATL)-based shaper method is also considered to further verify the effectiveness and robustness of efficient hook and payload oscillation control under payload hoisting. All the multimode input shaping is simulated using the Matlab software. The simulation results of multimode ZVDD-ZVDD shaper successfully reduced in the overall hook and payload oscillations by 97.9% and 97.2%, respectively, compared to the unshaped system, whereas the multimode ATL-ZVDD shaper reduced hook and payload oscillations by 94.8% and 94.0%, respectively. In fact, the multimode ZVDD-ZVDD and multimode ATL-ZVDD shapers demonstrate the superiority in minimizing the hook and payload oscillations compared to the multimode ZV-ZV, multimode ZVD-ZVD, ATL-ZV and ATL-ZVD shapers. This significant reduction in oscillations enhances the precision and safety of real-world crane operations in industrial settings. It has been proven that considering the additional derivative of input shaping results in a higher level of hook and payload oscillations reduction
Analysis of Drone Wireless Communication System Performance Affected by Vibration based on 1DCNN
Get PDFDevelopments in drone technology have made them crucial in various fields. Vibrations caused by external conditions or mechanical failures in a drone's design can significantly affect the efficiency of the drone's communication systems. The drone's antenna generates phase noise, which can degrade the performance of drone communications systems. This work presents an analysis and computational model of how drone vibration affects system performance. by using two steps. The first one uses the simulation Monte-Carlo in MATLAB when the iteration algorithm processes with various variable values as the frequency carriers and the order of the quadrature-amplitude-modulation (M-QAM) system and evaluates the performance of the communication system by measuring the symbol error rate. The second step uses the one-dimensional convolutional neural network to predict the symbol error rate. After creating the dataset in the first stage, reprocess it and split it into 70% training and 30% testing. Then, by MATLAB App Designer created a graphical user interface (GUI) for friendly use. The result appears to be that the performance of the drone communication system decreased when frequency carriers and modulation order for M-QAM increased due to the impact of a vibrating antenna. Our contribution to this work is using 1DCNN, unlike other works that only use simulation to evaluate the performance, because 1DCNN can automatically extract useful features from the input dataset to evaluate the effect. This study provides a valuable method to evaluate the efficiency of a communication system on the UAV, which is particularly important for drone wireless system planning. In our next work, we propose investigating other factors affecting UAV communication systems, including humidity and temperature
Community Resilience based on Quality Family Village (Kampung KB) in Supporting Sustainable City Development in Indonesia (Evidence Banjar Municipality)
Get PDFCommunity Resilience (CR) has become a concern of world academics in urban and rural studies. The Covid-19 pandemic in addition to encouraging digitization also provides a new space for the community to innovate and move together, therefore community resilience is the key in facing every challenge both external and internal. The concept of community resilience based on KB villages is a strategy that prioritizes the concept of family resilience as the backbone of encouraging community resilience. The focus on handling stunting cases that have become a concern of the central government provides new thinking space in efforts to handle and overcome these problems in the future. The research was conducted in Banjar City to obtain a KB Village-based community resilience strategy where the innovativeness of the research lies in the integration of principles for building social-ecological resilience into the framework, and the provision of a step-by-step process in an effort to encourage community resilience. This research analyzes the concepts of family physical resilience, community social resilience and psychological resilience based on a literature review, and identifies key inhibiting variables through interviews with relevant parties
Enhanced Human Hitting Movement Recognition Using Motion History Image and Approximated Ellipse Techniques
Get PDFRecognition of human hitting movement in a more specific context of sports like boxing is still a hard task because the existing systems use manual observation which could be easily flawed and highly inaccurate. However, in this study, an attempt is made to present an automated system designed for this purpose to detect a specific hitting movement commonly known as a punch using video input and image processing techniques. The system employs Motion History Image (MHI) to model trajectories of motions and combine them with other parameters to reconstruct movements which tend to have a temporal component. Thus, CCTV cameras set at different positions (front, back, left and right) enable the system to identify several types of punches including Jab, Hook, Uppercut and Combination punches. The most important aspect of this work is the proposal of MHI and the Ellipse approximation which is quicker in the integration of both than other sophisticated systems which take a considerable duration in computations. Therefore, the system classifies C_motion, Sigma Theta, and Sigma Rho parameters to distress hitting from non-hitting movements. Evaluation on a dataset captured from multiple viewpoints establishes that the system performs well achieving the goal of 93 percent when detecting both the hitting and the non-hitting motion. These results demonstrate the system’s superiority to the system based such detection methods. This study paves the way for other applications in real-time such as sports analysis, security surveillance, and healthcare requiring greater efficiency in and accuracy of human movement assessment. The focus of future work may be in the direction of improving the recognition of slower movements, also modifying the system for more dynamic conditions in the future