scholarly journals Load Identification Using Harmonic Based on Probabilistic Neural Network

2019 ◽  
Vol 7 (1) ◽  
pp. 71-82
Author(s):  
Dimas Okky Anggriawan ◽  
Aidin Amsyar ◽  
Eka Prasetyono ◽  
Endro Wahjono ◽  
Indhana Sudiharto ◽  
...  
Keyword(s):  
Neural Network ◽  
Fourier Transform ◽  
Probabilistic Neural Network ◽  
Harmonic Distortion ◽  
Electrical Equipment ◽  
High Accuracy ◽  
Current Sensor ◽  
Harmonic Load ◽  
Load Identification ◽  
Current Waveform

Due to increase power quality which are caused by harmonic distortion it could be affected malfunction electrical equipment. Therefore, identification of harmonic loads become important attention  in the power system. According to those problems, this paper proposes a Load Identification using harmonic based on probabilistic neural network (PNN). Harmonic is obtained by experiment using prototype, which it consists of microcontroller and current sensor. Fast Fourier Transform (FFT) method to analyze of current waveform on loads become harmonic load data. PNN is used to identify the type of load. To load identification, PNN is trained to get the new weight. Testing is conducted To evaluate of the accuracy of the PNN from combination of four loads. The results demonstrate that this method has high accuracy to determine type of loads based on harmonic load

Real Time Harmonic Load Identification Based on Fast Fourier Transform and Artificial Neural Network

2021 ◽  
Vol 16 (3) ◽  
pp. 220
Author(s):  
Dimas Okky Anggriawan ◽  
Aidin Amsyar ◽  
Aji Akbar Firdaus ◽  
Endro Wahjono ◽  
Indhana Sudiharto ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fourier Transform ◽  
Fast Fourier Transform ◽  
Real Time ◽  
Harmonic Load ◽  
Load Identification ◽  
Time Harmonic ◽  
Artificial Neural

scholarly journals Inrush Current Based on Fast Fourier Transform

2021 ◽  
Vol 8 (2) ◽  
pp. 114
Author(s):  
Mochamad Ilham Zamzami ◽  
Eka Prasetyono ◽  
Dimas Okky Anggriawan ◽  
Mike Yuliana
Keyword(s):  
Fourier Transform ◽  
Fast Fourier Transform ◽  
System Modeling ◽  
Harmonic Distortion ◽  
Electrical Equipment ◽  
Transient Condition ◽  
Inrush Current ◽  
Simulation Data ◽  
Electrical Components ◽  
Incandescent Lamps

Advances in technology have caused the use of electricity to increase rapidly. With advances in technology, this is followed by the use of increasingly efficient electrical components or equipment. This more efficient electrical equipment causes the impedance of the component to be smaller, causing a surge in current when it is turned on. This current surge, if not followed by appropriate safety precautions, will be damage other components. Each load has different waveform characteristics and current transient peaks. For this reason, it is necessary to analyze the transient condition of a load to overcome this. This paper will explain the characteristics of the inrush current of the load due to ignition. There are three loads used in this study, namely resistive, capacitive and inductive loads. Then the use of this load is simulated by giving different ignition angle values, namely 0, 60, and 90 degrees. The analysis used is the Fast Fourier Transform (FFT) method which is a derivative of the Discrete Fourier Transform. The inrush current spectrum in this simulation is simulated using Simulink MATLAB with switching system modeling using TRIAC. This inrush current simulation data collection uses a sampling frequency of 100 Khz and will be analyzed in the first of 5 cycles. For each load in this paper, the harmonic values for each ignition angle will be presented. The simulation results show that the inrush current is caused by the ignition angle value used and because of components that can deviate energy such as inductors and capacitors as well as components which at the time of starting have a low impedance value such as incandescent lamps. The simulation also shows that the use of switching components for setting the ignition angle causes an increase in the value of Total Harmonic Distortion (THD) but the peak current in the first cycle when the ignition angle is set decreases.

On the Shape of the Leaves

2013 ◽  
Vol 798-799 ◽  
pp. 1053-1060
Author(s):  
Shu Jiang Ding
Keyword(s):  
Neural Network ◽  
Fourier Transform ◽  
Experimental Test ◽  
Classification Accuracy ◽  
Probabilistic Neural Network ◽  
External Environment ◽  
Shape Features ◽  
Leaf Vein ◽  
Color Features ◽  
Leaf Distribution

In this paper, we study the shape of the leaves. More specifically, we show that leaf shapes are affected by genes and external environment in different species; and affected by leaf vein and leaf distribution In the same species. Based on shape features, color features and vein features, aProbabilistic Neural Network (PNN) Modelis established by using Polar Fourier Transform. Finally, our experimental test shows that the total classification accuracy is 85.7%.

scholarly journals Klasifikasi Data Berat Bayi Lahir Menggunakan Weighted Probabilistic Neural Network (WPNN) (Studi Kasus di Rumah Sakit Islam Sultan Agung Semarang)

2017 ◽  
Vol 10 (1) ◽  
pp. 61
Author(s):  
Hasbi Yasin ◽  
Dwi Ispriyansti
Keyword(s):  
Neural Network ◽  
Low Birthweight ◽  
Probabilistic Neural Network ◽  
High Accuracy ◽  
Training Data ◽  
World Health ◽  
Model Accuracy ◽  
Health Organization ◽  
Very High ◽  
Length Of Gestation

Low Birthweight (LBW) is one of the causes of infant mortality. Birthweight is the weight of babies who weighed within one hour after birth. Low birthweight has been defined by the World Health Organization (WHO) as weight at birth of less than 2,500 grams (5.5 pounds). There are several factors that influence the BWI such as maternal age, length of gestation, body weight, height, blood pressure, hemoglobin and parity. This study uses a Weighted Probabilistic Neural Network (WPNN) to classify the birthweight in RSI Sultan Agung Semarang based on these factors. The results showed that the birthweight classification using WPNN models have a very high accuracy. This is shown by the model accuracy of 98.75% using the training data and 94.44% using the testing data.Keywords:Birthweight, Classification, LBW, WPNN.

Online Terrain Classification for Mobile Robots

2005 ◽  
Author(s):  
Edmond M. DuPont ◽  
Rodney G. Roberts ◽  
Majura F. Selekwa ◽  
Carl A. Moore ◽  
Emmanual G. Collins
Keyword(s):  
Neural Network ◽  
Control Strategy ◽  
Autonomous Vehicles ◽  
Probabilistic Neural Network ◽  
Detection Algorithm ◽  
High Accuracy ◽  
Vibration Frequencies ◽  
Terrain Classification ◽  
Ground Vehicles ◽  
Human Driver

Today’s autonomous vehicles operate in an increasingly general set of circumstances. In particular, unmanned ground vehicles (UGV’s) must be able to travel on whatever terrain the mission offers, including sand, mud, or even snow. These terrains can affect the performance and controllability of the vehicle. Like a human driver who feels his vehicle’s response to the terrain and takes appropriate steps to compensate, a UGV that can autonomously perceive its terrain can also make necessary changes to its control strategy. This article focuses on the development and application of a terrain detection algorithm based on terrain induced vehicle vibration. The dominant vibration frequencies are extracted and used by a probabilistic neural network to identify the terrain. Experimental results based on iRobot’s ATRV Jr (Fig. 1) demonstrate that the algorithm is able to identify with high accuracy multi-differentiated terrains broadly classified as sand, grass, asphalt, and gravel.

scholarly journals Identifikasi Gejala Penyakit Tanaman Jeruk Melalui Pengolahan Citra

2021 ◽  
Vol 3 (2) ◽  
pp. 104-113
Author(s):  
Maura Widyaningsih ◽  
Agus Harjoko
Keyword(s):  
Neural Network ◽  
Feature Extraction ◽  
Fourier Transform ◽  
Fast Fourier Transform ◽  
Local Binary Pattern ◽  
Probabilistic Neural Network

Pengolahan citra adalah trend terkini mendukung suatu pengenalan pola objek citra secara digital, dengan penerapan metode dan konsep dalam menginterprestasikan informasi menjadi pendukung data secara visual. Gejala penyakit pada tanaman dapat terlihat adanya noda pada area objek, sehingga dalam memudahkan pengenalan fitur yang digunakan adalah dengan tekstur, karena tanda penyakit dapat mengenai sekitar atau seluruh area obyek. Usulan yang dibangun diharapkan dapat memberikan solusi untuk melakukan identifikasi gejala suatu penyakit melalui pengolahan citra, dengan melibatkan konsep dan metode. Tahapan yang diterapkan dalam pengelolaan adalah preprocessing, feature extraction, dan identification Metode preprocessing dilakukan dengan resize, clipping, penajaman tekstur dengan usharp mask filter dan konversi RGB ke gray. Feature extraction dengan metode Fast Fourier Transform (FFT) dan Local Binary Pattern (LBP). FFT merupakan ekstraksi cepat pada transformasi fourier, sedangkan LBP merupakan ekstraksi ciri dengan diskripsi pola pada citra gray. Proses identifikasi dengan metode Probabilistic Neural Network (PNN) dalam melakukan klasifikasi yang mendukung proses identifikasi terhadap penyakit tanaman, jumlah data yang digunakan 233, terbagi dalam 157 data latih dan 76 data uji. Hasil klasifikasi terhadap data latih menunjukan hasil maksimal untuk semua citra batang, daun, dan buah. Sedang untuk data uji hasilnya tertinggi identifikasi pada penerapan ekstraksi ciri dengan FFT dibandingkan dengan LBP ataupun gabungan kedua ekstraksi ciri tersebut.

Estimating Pigment Concentrations from Spectral Images Using an Encoder‐Decoder Neural Network

2020 ◽  
Vol 64 (3) ◽  
pp. 30502-1-30502-15
Author(s):  
Kensuke Fukumoto ◽  
Norimichi Tsumura ◽  
Roy Berns
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Absorption Coefficient ◽  
Spectral Data ◽  
High Accuracy ◽  
Pigment Concentration ◽  
Scattering Coefficient ◽  
A Value ◽  
Input And Output ◽  
Pigment Concentrations

Abstract A method is proposed to estimate the concentration of pigments mixed in a painting, using the encoder‐decoder model of neural networks. The model is trained to output a value that is the same as its input, and its middle output extracts a certain feature as compressed information about the input. In this instance, the input and output are spectral data of a painting. The model is trained with pigment concentration as the middle output. A dataset containing the scattering coefficient and absorption coefficient of each of 19 pigments was used. The Kubelka‐Munk theory was applied to the coefficients to obtain many patterns of synthetic spectral data, which were used for training. The proposed method was tested using spectral images of 33 paintings, which showed that the method estimates, with high accuracy, the concentrations that have a similar spectrum of the target pigments.

Classification and Identification of Power System Disturbances Using Wavalet and Artificial Neural Network Technique

2005 ◽  
Vol 2 (2) ◽  
pp. 25
Author(s):  
Noraliza Hamzah ◽  
Wan Nor Ainin Wan Abdullah ◽  
Pauziah Mohd Arsad
Keyword(s):  
Neural Network ◽  
Power Quality ◽  
Probabilistic Neural Network ◽  
Microsoft Excel ◽  
Waveform Data ◽  
The Neural Network ◽  
Harmonic Voltage ◽  
Power Quality Disturbances ◽  
Electronic Load ◽  
Wavelet Technique

Power Quality disturbances problems have gained widespread interest worldwide due to the proliferation of power electronic load such as adjustable speed drives, computer, industrial drives, communication and medical equipments. This paper presents a technique based on wavelet and probabilistic neural network to detect and classify power quality disturbances, which are harmonic, voltage sag, swell and oscillatory transient. The power quality disturbances are obtained from the waveform data collected from premises, which include the UiTM Sarawak, Faculty of Science Computer in Shah Alam, Jati College, Menara UiTM, PP Seksyen 18 and Putra LRT. Reliable Power Meter is used for data monitoring and the data is further processed using the Microsoft Excel software. From the processed data, power quality disturbances are detected using the wavelet technique. After the disturbances being detected, it is then classified using the Probabilistic Neural Network. Sixty data has been chosen for the training of the Probabilistic Neural Network and ten data has been used for the testing of the neural network. The results are further interfaced using matlab script code.  Results from the research have been very promising which proved that the wavelet technique and Probabilistic Neural Network is capable to be used for power quality disturbances detection and classification.

Sign in / Sign up

Export Citation Format

Share Document