Jurnal Rekayasa Elektrika
Not a member yet
345 research outputs found
Sort by
Wood Species Identification Based on Gray Level Co-Occurrence Matrix (GLCM) Features on Macroscopic Images
Full text linkWood is an incredibly valuable resource, particularly for everyday living. To fully harness the advantages of wood, it must focus on two key considerations. Firstly, it is imperative to consistently utilize wood sourced from sustainably managed forests. Secondly, we must explore techniques that maximize the utilization of every part of the tree. One technique for meeting these considerations is to create a wood identification system. This system can be used for quickly inspecting wood species. In wood identification, it is essential to consider specific characteristics and physical properties of wood. Manual identification will depend on the examination of wood anatomists eye and will require a significant amount of time. In accordance with these situations, a computer vision-based system can address this condition. Therefore, feature extraction is necessary to extract the features of wood characteristics from the wood image. This research aims to propose a method for wood species identification based on Gray Level Co-occurrence Matrix (GLCM) features to extract important information about wood characteristics from macroscopic wood images. For the classifier, the Random Forest algorithm is proposed for the identification of the machine learning model. Five wood species images will be used in this research, with each wood sample being presented as a macroscopic image. The total dataset used was 750 images, with each wood species having 150 images. The result showed that the Model C (90/10) training data ratio demonstrates good performance in classifying wood species from the macroscopic images. The model achieved a peak accuracy of 0.81 and correctly predicted all test images. This study indicates that the Random Forest model can be an effective classifier for wood species identification
Implementation of IoT-based SCADA in MPS Processing Station Integrated With CtrlX Automation
Full text linkThe increasing complexity of industrial automation technology today requires industries to upgrade their existing systems, such as IoT-based SCADA, which allows for real-time production monitoring from anywhere. However, to achieve this, a system is needed that does not affect or halt the production process and does not require replacing the existing system during the upgrade process. Therefore, a system that can adapt to the existing one is necessary. This research aims to implement an IoT-based SCADA system in an existing plant by integrating the system with ctrlX Automation to address this issue. The implementation is carried out in several stages. The first stage involves integrating the plant controlled by the Omron CP1L PLC with ctrlX Automation. The second stage is creating tags for the SCADA system using tools installed on ctrlX Automation. The third stage involves developing the user interface. The fourth stage is the remote access communication process for the IoT system using the OpenVPN Cloud tool. The test results show that the integration between the Omron CP1L PLC and ctrlX Automation was successful, with a 100% tag retrieval rate from the Omron CP1L PLC, and the data could be visualized. The user interface can be accessed, and remote access can be performed on different networks and locations using the OpenVPN Cloud tool. During testing, the average data transfer write-read delay with one address/tag during remote access was 61.3ms, and for the write-read test with three addresses simultaneously, the average was 78.1ms. Based on these results, the data transfer process using ctrlX Automation integrated with the Omron CP1L PLC can be categorized as very good
Multi-Objective in Mapping the Optimal Distributed Generation Configuration through GWOA to Enhance Grid Performance Reliability
Full text linkIn electric power distribution systems, the distance between the load bus and the generating unitsignificantly affects grid efficiency and reliability, with longer distances causing greater voltage drops. To mitigatethis, Distributed Generation (DG) is increasingly being used, generating electricity closer to the point of consumption.Determining the optimal DG location requires advanced metaheuristic methods. This research proposes the Grey WolfOptimizer Algorithm (GWOA) to determine optimal DG placement, tested on the IEEE 14-bus distribution grid. Themethod generated two scenarios: In the first scenario, power losses were reduced by 98.1465% for real power and98.9538% for reactive power compared to the existing conditions, while voltage increased by an average of 0.0127 p.u.for all buses combined. The second scenario also showed a notable voltage increase of 0.0064 p.u. The GWOA methodproves to be an efficient and effective solution for DG placement, enhancing system reliability and protectinghousehold electronic devices
Design of Deep Learning-Based Pressure Injury Stage Classification Device
Full text linkPressure injury or pressure ulcers could occur due to continuous pressure on the bony prominence of the skin and tissue. Geriatric patients, especially those with limited mobility and several comorbidities, are more susceptible to pressure injury. Stage classification of pressure injury is currently carried out qualitatively and requires clear communication with the patient. This is often not possible in elderly patients due to lack perception of pain causing late detection of pressure injury until they have reached a severe level and can endanger the patient's life. This study proposes a non-contact device in the form of a camera integrated with a convolutional neural network (CNN) model with MobileNet architecture to classify the level of pressure injury. Testing showed a classification accuracy of 83.3% with an average classification duration of 2.24 s. This aiding device is considered to have great potential to improve faster and more accurate pressure injury assessment in clinical settings
Implementation of Eye-To-Text Morse Code Device to Help Speech Impairments People
Full text linkThis research aims to develop an Eye-to-Text Morse Code (ETT-MC) device as an assistive communication tool for individuals with speech disabilities, based on artificial intelligence image processing. The method used to detect speech codes is based on eye blink input, which is converted into Morse code and then translated into letters by utilizing a thresholding image processing technique that compares the pixel values when the eyes are open and closed. In Morse code, there are two main symbols combined to form a letter: the dash and the dot. The object of this research is the eye, where if the system detects the eye in an open state, it is converted into a dot code or value 1, while when the system detects the eye as closed, it is converted into a dash code or value 0. The results and hypotheses of this research show that the developed ETT-MC device can assist individuals with speech disabilities in communicating by utilizing eye blinks as an input medium to convey messages to others with an accuracy rate of up to 80%. This occurs because the accuracy of eye image detection processed by the system is significantly influenced by light intensity, the quality of the image detected by the camera, and the length of the translated text
A Low-Cost Salinity Meter Based On Ultrasonic Wave
Full text linkMonitoring the quality of shrimp pond water is crucial for shrimp growth, with salinity being one of the most significant parameters. Currently, salinity sensors for pond water are designed for momentary measurements, which are unsuitable for continuous monitoring. This study introduces a method for continuous salinity measurement using ultrasonic signals. The proposed approach utilizes a measuring chamber equipped with ultrasonic sensors to determine the Time-of-Flight (ToF). To ensure accuracy, four ToF methods were compared, with the cross-correlation method identified as the most accurate. This method was subsequently used to calculate the ToF, which was then applied to determine the acoustic speed. Since the acoustic speed in water is influenced by salinity, temperature, and pressure, changes in salinity cause detectable changes in the acoustic speed. The acoustic speed was further used as input for the modified Del Grosso equation to derive the salinity. Experimental results showed an average error of 4.83% for saline solutions and 1.81% for shrimp pond water. These findings demonstrate that the proposed method provides sufficient accuracy for water salinity measurement
A Comparative Study of the Implementation of 4G and 5G Networks in IIoT Process Automation Systems
Full text linkThe industrial internet-of-things (IIoT) has recently become an important requirement in the process industry. The factories must be able to integrate process automation devices such as programmable logic controllers and industrial computers with mobile devices, especially to support their maintenance and operations. Connectivity with mobile devices has the consequence that cellular networks must be specified to the needs of the industry itself. Comparative studies on using cellular networks in process automation systems are urgently needed. The research that has been conducted is a comparative study between the use of 4G and 5G cellular networks in IIoT process automation systems. It can be seen in the result that the 4G cellular network is sufficient to be used for industries that require mobile devices for monitoring functions, as seen from the results showing the latency obtained is 17.03 ms, jitter is 9.5 ms, packet loss is 6.67 %, and throughput is 192.73 Kbps. However, for the industry that needs to perform real-time control, mobile connectivity has to use a 5G network with better performance metrics with a latency of 15.21 ms, jitter of 5.43 ms, packet loss of 2.67 %, and throughput of 217.19 Kbps. The research results are needed by the process industry in Indonesia, which is widely spread on the island as an archipelago with quite varied cellular network connectivity quality
Bandwidth Enhancement on Microstrip Antenna with Dual Feed Line and Truncated for 5G Applications
Full text linkThe microstrip antenna is low-profile, meaning it has a narrow bandwidth. Additionally, the microstrip antenna is compact, making it highly suitable for implementation in small devices. Its low-profile nature is due to its thin thickness and flexibility, allowing it to be applied on curved surfaces. This study explores the combination of dual-feed and truncated methods to broaden the antenna's bandwidth. Truncation on the patch helps expand the bandwidth by altering the current distribution on the patch, which can affect the antenna's resonance. The antenna design is carried out using HFSS software. In this study, the author uses an RT/duroid 5880 substrate with a thickness of 1.575 mm and a dielectric constant of 2.2. The simulation and measurement results show the antenna's resonance and bandwidth alignment within the frequency range of 3.44 to 3.62 GHz with a simulated bandwidth of 180 MHz, and a measured bandwidth of 210 MHz within the frequency range of 3.42 GHz to 3.62 GHz
Optimization of Power Loss Reduction in IGBT-Based Three-Phase Rectifiers Using Discontinuous Pulse Width Modulation Method
Full text linkThe increasing demand for electricity supply is evident across various modern industrial sectors. Electrification advancements in the transportation industry aim to address environmental and energy issues and continue to evolve. Charging electric vehicles is one of the most important aspects of electrification in the transportation sector. This study develops and simulates a three-phase IGBT-based rectifier using the Discontinuous Pulse Width Modulation 60-degree (DPWM1) method to optimize power loss reduction in a 200-kW charging system. The use of the DPWM method has been shown to reduce power losses by up to 44% compared to the conventional Sinusoidal Pulse Width Modulation (SPWM) method under full load conditions, resulting in reduced heat and cooling requirements for the devices. Simulations show that with the appropriate use of filters, the total harmonic distortion of current (THDi) of the AC input side is reduced to 2.267%, minimizing the negative impacts on the grid. In addition, the implementation of feedforward control maintains DC voltage stability despite load variations, improving system efficiency and reliability
Integration of Multi-Modal Sensors and Robot Arm Vision for Monitoring and Assisting Elderly Activities
Full text linkThis research aims to develop an integration device combining Multi-Modal Sensors and Robot Arm Vision (MMS-RAV) for monitoring activities and assisting in healthcare services for the elderly at home. The method used to develop this device involves integrating MMS, which consists of PIR sensors for detecting the presence of the elderly, LDR sensors for detecting home light conditions, fire sensors for detecting flames, and DHT11 sensors for measuring temperature and humidity. Additionally, the RAV component assists and supports the activities of the elderly and includes a camera for vision-based object detection, ultrasonic sensors for robot navigation, Raspberry Pi as the data processing center, an arm for object retrieval and camera movement, LCD for displaying messages, omni-wheels for robot navigation, and buzzer for early warnings in case of anomalous conditions with the elderly. In this research, MMS functions to monitor elderly activities, while RAV supports healthcare services for the elderly, particularly in medication intake using image processing techniques. The software used to control the entire MMSRAV system is the robot operating system. The results of this study indicate that the developed MMS-RAV device is effective for monitoring elderly activities and assisting in providing healthcare services for medication intake