Jurnal Rekayasa Elektrika
Not a member yet
345 research outputs found
Sort by
Web-Based Item Tracking System Using RFID
Full text linkNumerous tools, kits, and other items are utilized daily by many individuals in the college laboratories. Without a proper inventory record, there is a risk of missing and misplacing some items. The system for tracking items using Radio Frequency Identification (RFID) accessed via the website has been designed to track the location of each item in the laboratory using RFID technology. The primary objective of this system is to monitor and record inventory. Information regarding the inventory is stored in a database, which can be accessed to track inventory and review the history of specific items via the Internet. The designed system is capable of tracking and managing laboratory equipment inventory using RFID, accessible through a web-based platform
Hybrid Radio over Fiber with Radio over Free Space Optic for 5G Fronthaul Network Implementation in Urban Areas
Full text linkOptical fiber can meet the demand for fronthaul on 5G networks that offer high bandwidth, large capacity, high data rate and is free from electromagnetic interference. However, deploying infrastructure faces issues like permits and high costs. Hybrid Radio over Fiber (RoF) technology with Radio over Free Space Optic (RoFSO) can be a solution in urban areas, where the installation requires high costs. This research investigates a hybrid RoF-RoFSO scheme at a frequency of mmWave 26 GHz by considering atmospheric attenuation values arising from meteorological effects, such as rain, smog, and dust, using Optisystem. This research considers QPSK, 16-QAM, and 64-QAM modulation schemes, distance variations on the FSO and the meteorological data from the Indonesian Meteorology, Climatology and Geophysics Agency (BMKG) from March 2022 to May 2022. The results show that attenuation due to high rainfall is the main cause of signal quality degradation and limits the transmission distance on the FSO link. The maximum distance is 600 m using the QPSK and 16-QAM modulation schemes, while for the 64-QAM modulation scheme, the maximum transmission distance is 500 m. Meanwhile, damping values caused by foggy and dusty conditions can reach distances of up to 1000 m for the three modulation schemes
Control System Design for Water Pump Activation in PLC-based Smart Hydroponic Design
Full text linkFood security is one of the issues that is one of the concerns to the country government, and one of the independent efforts made by community on their awareness to meet and achieve food needs on a domestic scale in their respective households is through hydroponic for cultivation of vegetables. Hydroponics works by using water as growing medium instead of soil, however, the use of water as a planting medium requires special treatment thus the plants is able to grow optimally. To ensure that the air content in the water used as a hydroponic growing medium is properly available, a water regulation process is needed. The process of water regulation in the hydroponic system uses regulation of the activation of the water pump motor so that water can be regulated and electrical energy efficiency can still be achieved. This study aims to design and test a PLC-based automation system for the purposes of setting the activation of a water pump in a hydroponic system based on the sunlight conditions in the hydroponic installation being built. By using a light sensor (LDR) to measure the intensity of sunlight in the hydroponic system being built, the activation of the pump motor can be controlled through the use of a PLC device that processes the information obtained from the sensor used. The results of the tests carried out provide information that the designed system has proven effective for use in hydroponic systems with pump water regulation time from 08:00 AM to 04:00 PM
Power Consumption Predictive Analytics and Automatic Anomaly Detection Based on CNN-LSTM Neural Networks
Full text linkIn this modern era, electrical energy plays a crucial role in human life, as it is essential for most household appliances. The number of appliances requiring electrical energy increases each year, meeting the growing needs of users. However, electricity consumers tend to forget this fact and only realize its importance when they receive a significantly increased monthly electricity bill or face problems caused by anomalies in electricity use. Such anomalies can lead to substantial losses, especially when electrical equipment is damaged or left switched on without awareness. To make better decisions in such situations, real-time and accurate information is necessary, which can be achieved through data analytics utilizing machine-learning and predictive analytics. The purpose of this paper is to introduce the CNN-LSTM method of data analytic modeling for power consumption data collected through an electric data logger, which can help predict future power usage and detect real-time anomalies in the power network. The proposed model was tested using hourly electricity consumption data, and the results showed that the CNNLSTM method outperformed the LSTM model. The CNN-LSTM model had a 29% smaller Mean Squared Error (MSE) score than the LSTM method
Designing ANFIS Controller for MPPT on Photovoltaic System
Full text linkPhotovoltaics current and voltage output characteristics depend on the intensity of solar radiation and temperature. Maximum Power Point works with maximum energy output and has the highest efficiency. The maximum energy point tracking method (MPPT) keeps the solar cell operating point at its maximum point. This study uses the Adaptive Neuro-Fuzzy Inference System (ANFIS) method designed and used to maintain that point. The Perturb and Observe (PnO) method is used to test the results, often used in determining this tracking. Based on the test, it was found that the average power efficiency obtained was 84.79%, and using PnO was 83.87%. The transient response using ANFIS is relatively smoother than that of using PnO, which will cause chattering when there is a change in radiation and temperature
Multi-Class Heart Abnormalities Detection Based on ECG Graph Using Transfer Learning Method
Full text linkThe heart is one of the vital organs in the circulatory system. Regular checkups are very important to prevent heart disease. The most basic examination is blood pressure then further examination is related to the evaluation of the electrical activity of the heart using an electrocardiogram (ECG). The ECG carries important information regarding various abnormalities of heart function. Several automated classification techniques have been proposed to facilitate diagnosis. However, not all digital ECG devices provide raw data for analysis. ECG classification method based on images can be an alternative in classification. Therefore, in this study, it is proposed to classify ECG based on signal images. The proposed classification method uses transfer learning with VGG, AlexNet, and DenseNet architectures. The method used for the classification of multi-class ECG consists of normal, PVC, Atrial Fibrilation, AFL, Bigeminy, LBBB, and APB. The simulation results generate the best accuracy of 92% and F1-score of 92%. Best performance is achieved using DenseNet architecture at 60 epochs. This study is expected to be a new reference technique in the classification of ECG signals
Model dan Kendali Modular pada Pendulum Terbalik tipe Rotary
Full text linkRotary Inverted Pendulum (RIP) is a physical system that is often used as a theoretical platform and application of non-linear, unstable, and underactuated control systems so that it poses a challenge to design controls and realize them. The mechanical construction of the system consists of a pendulum arm that rotates horizontally on the RIP base shaft and a vertical pendulum arm that swings from a downward position to an upright equilibrium position. This paper presents a model and control scheme for RIP in a modular manner, in which three controller sections are constructed and realized using Multibody Matlab. The three controller parts include: a swing-up using a positive feedback Proportional Derivative controller, a switching mode controller that works to change swing up control scheme into stabilization control when the vertical pendulum arm reaches a position around its upright equilibrium, and stabilization controller to maintain vertical arm balanced using a Proportional Derivative controller. The trajectory of the motion of the pendulum arm and the 3D visualization of the pendulum system presented using Multibody Matlab show the effectiveness of the applied method
Optimizing Technical Losses of the PLN Distribution Network with Changes in Operational Patterns in 2023 at PLN ULP Lhokseumawe
Full text linkTechnical shrinkage is shrinkage caused by impedance in generation equipment or transmission equipment to the distribution network so that there is energy loss. There are several technical shrinkage problems at PT. Perusahaan Listrik Negara (PLN) especially in Customer Service Unit (ULP) Lhokseumawe City and for now the cause is still unsolved, because this technical shrinkage problem will harm and have an impact on consumers and PLN itself. The purpose of the study was to optimize technical shrinkage in the distribution network to reduce energy losses that occurred during the electrical power distribution process in the distribution network of PT. PLN (Persero) ULP Lhokseumawe City. This study uses the help of Electrical Transient Analyzer Program (ETAP) software to simulate the power flow so that the depreciation value that occurs is obtained, then re-load adjustment is carried out to simulate again to determine the change in the depreciation value obtained after load adjustment. The results of the ETAP simulation show the depreciation value that occurred before the load adjustment was made by 76.7 kW after the depreciation load adjustment was adjusted to 59.6 kW. This means that this technical shrinkage can be suppressed by changing the feeder operation pattern and voltage drop value in accordance with the limitation provisions set in SPLN 72:1987
Flood Early Warning System Prototype Based on Ultrasonic Sensor and Internet of Things
Full text linkFloods that come all of a sudden cause many people to be unable to prepare themselves to deal with it, so material losses to health problems cannot be avoided. Therefore, a system is needed to provide early warning to the public before a flood occurs. As technology develops, water levels in an area can be monitored to anticipate flooding using the Internet of Things (IoT). IoT can help to monitor and warn of floods in real-time and continuously. In this research, the system will be placed in areas that often cause flooding. Monitoring results from sensor readings will be stored in the cloud database. The water level category is divided into 4 levels, namely Safe, Standby, Careful, and Danger. The system uses IoT and a database to send water level status to users as notifications on applications. The buzzer will sound as a warning sign when the water level enters the Danger status. The system test results show that the sensor has a very good level of accuracy with an error percentage of 0.242131%, and IoT connectivity can reach a distance of up to 20 meters
Detection of Intermittent Oscillation in Process Control Loops with Semi-Supervised Learning
Full text linkOscillations in the control loops indicate the poor performance of the control loops. The occurrence of oscillations in the process control loop is quite high in the industry, so it needs to be reduced so that the control loop can work properly. The first step for oscillation reduction is oscillation detection. One type of oscillation that is difficult to detect is intermittent oscillation. The smart factory concept encourages the development of the intermittent oscillation detection system using machine learning by being implemented online. Therefore, in this study an online intermittent oscillation detection program is built using K-nearest neighbor (KNN)-based Semi-supervised learning (SSL) method. The SSL method applied is self-training. The training data was obtained by a simulation of the Tennessee Eastman Process. The data is segmented based on window size and extracted time series features. The extracted data is used to build a model to detect oscillations caused by stiction, tuning errors, and external disturbances in the reactor. The model is implemented online with sliding windows and MQTT. The best accuracy and F1-score of the model obtained are 96.15% and 95.15%. In online detection, the model detects the type of oscillation with an average time of 305 seconds