Garuda - Garba Rujukan Digital

Active Fault Tolerance Control For Sensor Fault Problem in Wind Turbine Using SMO with LMI Approach Mardiyah, Nuralif; Setyawan, Novendra; Retno, Bella; Has, Zulfatman
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 5: EECSI 2018
Publisher : IAES Indonesia Section

In this paper, we start to investigate the sensor fault problem in a Wind Turbine model with Fault Tolerant Control (FTC). FTC is used to allow the parameters of the controller to be reconfigured in accordance error information obtained online from sensors to improve the stability and overall performance of the system when an error occurs. The design is divided into two parts. The first part is designed Sliding Mode Observer (SMO) based Fault Detection Filter (FDF) to generate a residual signal to estimate fault. FDF is designed to maximize sensitivity fault. The second is a design output feedback control and Fault Compensation to guarantee the stability and performance system from disturbance by ignoring faults. Moreover, the function of fault compensation is to minimize effect fault of the system. The main contribution of this research is FTC proved to solve the sensor fault problem in a Wind Turbine model. The simulation showed the effectiveness of this method to estimate the fault and stabilized the system faster to a steady condition.

Object Detection of Omnidirectional Vision Using PSO-Neural Network for Soccer Robot Setyawan, Novendra; Mardiyah, Nuralif; Hidayat, Khusnul; Nurhadi, Nurhadi; Has, Zulfatman
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 5: EECSI 2018
Publisher : IAES Indonesia Section

The vision system in soccer robot is needed to recognize the object around the robot environment. Omnidirectional vision system has been widely developed to find the object such as a ball, goalpost, and the white line in a field and recognized the distance and an angle between the object and robot. The most challenging in develop Omni-vision system is image distortion resulting from spherical mirror or lenses. This paper presents an efficient Omni-vision system using spherical lenses for real-time object detection. Aiming to overcome the image distortion and computation complexity, the distance calculation between object and robot from the spherical image is modeled using the neural network with optimized by particle swarm optimization. The experimental result shows the effectiveness of our development in the term of accuracy and processing time.

A SIMPLE REAL-TIME ENERGY ANALYTICS MODEL FOR SMART BUILDING USING OPEN IOT PLATFORMS Nasar, Muhammad; Setyawan, Novendra; Faruq, Amrul; Sulistiyowati, Indah
Jurnal Elektronika dan Telekomunikasi Vol 19, No 2 (2019)
Publisher : Indonesian Institute of Sciences

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14203/jet.v19.83-90

Monitoring energy in buildings can ease us to have a better understanding of electricity consumption patterns to support efficiency and avoid potential damages. However, indoor installations are mostly unmonitored because their panel meters are usually difficult to access. Yet, indoor maintenance tends to be more difficult since the cables are inside the wall, ceiling, or concrete. Internet of Things and big data analytics can be used to track electricity usage either in residential, commercial, or industrial buildings. This paper presents how a simple real-time energy data analytics was built at a low cost and high accuracy to inspect energy fluctuations, anomaly, and its significant pattern. We proposed 3 layers of architecture namely acquisition, transportation, and application management. An electronic module named PZEM004T was used to sense voltage, current, and other electrical parameters. Through a microcontroller ESP8266, the data was processed and sent it to an application layer via an existing wireless network. The actual and historical data of electricity were visualized on high-resolution graphs. The experiment was conducted at our office building. The experimental results showed that data of electrical energy usage can be captured close to realtime and power anomaly and pattern can be figured. Performance and functionality testing showed acceptable use of this system with more than 99% accuracy. This system is intended to empower building managers in evaluating the electrical network balance as well as anticipating damage due to overload, overvoltage, and voltage drop. If this model is widely implemented it will produce big data that is useful for advanced analysis.

Signature PSO: A novel inertia weight adjustment using fuzzy signature for LQR tuning Achmad Komarudin; Novendra Setyawan; Leonardo Kamajaya; Mas Nurul Achmadiah; Zulfatman Zulfatman
Bulletin of Electrical Engineering and Informatics Vol 10, No 1: February 2021
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v10i1.2667

Particle swarm optimization (PSO) is an optimization algorithm that is simple and reliable to complete optimization. The balance between exploration and exploitation of PSO searching characteristics is maintained by inertia weight. Since this parameter has been introduced, there have been several different strategies to determine the inertia weight during a train of the run. This paper describes the method of adjusting the inertia weights using fuzzy signatures called signature PSO. Some parameters were used as a fuzzy signature variable to represent the particle situation in a run. The implementation to solve the tuning problem of linear quadratic regulator (LQR) control parameters is also presented in this paper. Another weight adjustment strategy is also used as a comparison in performance evaluation using an integral time absolute error (ITAE). Experimental results show that signature PSO was able to give a good approximation to the optimum control parameters of LQR in this case.

Kontrol Tegangan Self-Excited Induction Generator dengan Electronic Load Controller Terkontrol PID-GA Ermanu Azizul Hakim; Rahayu Pandunengsih; Diding Suhardi; Novendra Setyawan
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 10, No 1 (2020): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Induction generator operation requires reactive power with external contactor. One of induction generator types, SEIG reactive power supplied by capacitor bank connected to generator terminal. SEIG is alternative energy conversion in small area or rural, SEIG has the main disadvantage of poor voltage regulation under various load conditions. ELC combine PID control which is optimized using Genetic Algorithm in order to maintain the stability of the voltage when the load varies. The result shows the SEIG system using ELC with PID-GA control worked to stable voltage in accordance with the standard with voltage tolerance of 10% when load change. The addition of GA to determine the value of the PID parameter where response system better with difference overshoot value start is 70.48%, when decrease load in 5 second by 44.3% and in the 10 second when increase load of 2 kW is 5.96% compared system with PID control without GA optimization.

Klasifikasi Golongan Darah Menggunakan Artificial Neural Networks Berdasarkan Histogram Citra Lailis Syafaah; Yudawan Hidayat; Novendra Setyawan
IJEIS (Indonesian Journal of Electronics and Instrumentation Systems) Vol 11, No 2 (2021): Oktober
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijeis.64049

Blood type in the medical world can be divided into 4 groups, namely A, B, AB and O. To be able to find out the blood type, a blood type test must be done. So far, human blood type detection is still done manually to observe the agglutination process. This research applies a blood type identification process using image processing. This system works by reading the blood type card image that has been filled with blood samples, then it will be processed through a histogram process to get the minimum and maximum RGB values and pixel locations which are then classified by Artificial Neural Networks (ANN) to determine the blood type from the training results and data matching. From the test results using 12 samples, it was found that the average error in blood type identification was 16.67%.

Active Fault Tolerance Control For Sensor Fault Problem in Wind Turbine Using SMO with LMI Approach Nuralif Mardiyah; Novendra Setyawan; Bella Retno; Zulfatman Has
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 5: EECSI 2018
Publisher : IAES Indonesia Section

In this paper, we start to investigate the sensor fault problem in a Wind Turbine model with Fault Tolerant Control (FTC). FTC is used to allow the parameters of the controller to be reconfigured in accordance error information obtained online from sensors to improve the stability and overall performance of the system when an error occurs. The design is divided into two parts. The first part is designed Sliding Mode Observer (SMO) based Fault Detection Filter (FDF) to generate a residual signal to estimate fault. FDF is designed to maximize sensitivity fault. The second is a design output feedback control and Fault Compensation to guarantee the stability and performance system from disturbance by ignoring faults. Moreover, the function of fault compensation is to minimize effect fault of the system. The main contribution of this research is FTC proved to solve the sensor fault problem in a Wind Turbine model. The simulation showed the effectiveness of this method to estimate the fault and stabilized the system faster to a steady condition.

Object Detection of Omnidirectional Vision Using PSO-Neural Network for Soccer Robot Novendra Setyawan; Nuralif Mardiyah; Khusnul Hidayat; Nurhadi Nurhadi; Zulfatman Has
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 5: EECSI 2018
Publisher : IAES Indonesia Section

The vision system in soccer robot is needed to recognize the object around the robot environment. Omnidirectional vision system has been widely developed to find the object such as a ball, goalpost, and the white line in a field and recognized the distance and an angle between the object and robot. The most challenging in develop Omni-vision system is image distortion resulting from spherical mirror or lenses. This paper presents an efficient Omni-vision system using spherical lenses for real-time object detection. Aiming to overcome the image distortion and computation complexity, the distance calculation between object and robot from the spherical image is modeled using the neural network with optimized by particle swarm optimization. The experimental result shows the effectiveness of our development in the term of accuracy and processing time.

Pemantauan Physical Distance Pada Area Umum Menggunakan YOLO Tiny V3 Mohammad Chasrun Hasani; Fadhila Milenasari; Novendra Setyawan
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 6 No 1 (2022): Februari 2022
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Coronavirus disease in 2019 (Covid-19) is a phenomenon that become to the world concern because almost all countries experience the outbreak. One of attention to preventing the spread of Covid-19 is the physical distance in public areas. This study proposes human detection in public spaces by using image processing. The application of physical distance is intended to monitor the distance between people in public places. In this study, a human detection system is done by using the YOLO Tiny V3 method and the Euclidean algorithm to be developed to detect distances between humans. There are several stages in the research process: data collection, data preprocessing, data training, and physical distance detection. The system that has been designed can detect by getting an accuracy result of 78.43% for detecting human objects and an accuracy result of 87.82% for detecting distances between humans.

A Simple Real-Time Energy Analytics Model for Smart Building Using Open IoT Platforms Muhammad Nasar; Novendra Setyawan; Amrul Faruq; Indah Sulistiyowati
Jurnal Elektronika dan Telekomunikasi Vol 19, No 2 (2019)
Publisher : LIPI Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14203/jet.v19.83-90

Monitoring energy in buildings can ease us to have a better understanding of electricity consumption patterns to support efficiency and avoid potential damages. However, indoor installations are mostly unmonitored because their panel meters are usually difficult to access. Yet, indoor maintenance tends to be more difficult since the cables are inside the wall, ceiling, or concrete. Internet of Things and big data analytics can be used to track electricity usage either in residential, commercial, or industrial buildings. This paper presents how a simple real-time energy data analytics was built at a low cost and high accuracy to inspect energy fluctuations, anomaly, and its significant pattern. We proposed 3 layers of architecture namely acquisition, transportation, and application management. An electronic module named PZEM004T was used to sense voltage, current, and other electrical parameters. Through a microcontroller ESP8266, the data was processed and sent it to an application layer via an existing wireless network. The actual and historical data of electricity were visualized on high-resolution graphs. The experiment was conducted at our office building. The experimental results showed that data of electrical energy usage can be captured close to realtime and power anomaly and pattern can be figured. Performance and functionality testing showed acceptable use of this system with more than 99% accuracy. This system is intended to empower building managers in evaluating the electrical network balance as well as anticipating damage due to overload, overvoltage, and voltage drop. If this model is widely implemented it will produce big data that is useful for advanced analysis.

Title

Found 20 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 20 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 20 Documents
Search