scholarly journals Solar PV Fault Classification using Back Propagation Neural Network

2020 ◽  
Vol 8 (6) ◽  
pp. 5568-5574
Keyword(s):  
Neural Network ◽  
Fault Detection ◽  
Short Circuit ◽  
Back Propagation ◽  
Error Rates ◽  
Fine Tuning ◽  
Solar Irradiation ◽  
Fault Classification ◽  
Photovoltaic Module ◽  
Solar Pv

Solar energy is that the foremost abundant, inexhaustible and clean of all renewable energy resources. Interest in electrical solar PV power generation has accumulated in recent years due to its benefits. This wide distribution of physical phenomenon panel production wasn't followed by watching, fault detection and designation functions to verify higher gain. In this paper, real time fault analysis and fault detection is done by using Back propagation. By simulating various fault conditions, the performances of a faulty electrical solar photovoltaic module have been compared with respect to its faultless model by quantifying the precise differential residue which can be associated with it. The deformations and faults induced on the I-V curves and P-V curves have been studied to generate data for neural network analysis for different types of faults. Five different fault cases like module to module fault, module - ground faults, short circuit fault, and different shading patterns of modules and solar cells are considered. The MATLAB simulation model’s results show the respective results for various fault conditions along with variation of different solar irradiation which commonly occur in the photovoltaic systems. The projected technique is often generalized and extended to additional sorts of faults. This faults condition was analyzed by using Backpropagation Based Neural Network (BPANN). Back propagation technique ensures fine tuning the weights of neural network to get lower error rates making the model more reliable, therefore the BP-ANN technique contributes in improving the overall accuracy for fault detection in the system using Artificial Neural Network.

scholarly journals Motor Fault Detection Using Wavelet Transform and Improved PSO-BP Neural Network

Processes ◽  
2020 ◽  
Vol 8 (10) ◽  
pp. 1322 ◽  
Author(s):  
Chun-Yao Lee ◽  
Yi-Hsin Cheng
Keyword(s):  
Neural Network ◽  
Wavelet Transform ◽  
Fault Detection ◽  
Bp Neural Network ◽  
Short Circuit ◽  
Back Propagation ◽  
Operating Environment ◽  
Cause Of Failure ◽  
Bearing Damage ◽  
Improved Pso

This paper proposes a motor fault detection method based on wavelet transform (WT) and improved PSO-BP neural network which is combined with improved particle swarm optimization (PSO) and a back propagation (BP) neural network with linearly increasing inertia weight. First, this research used WT to analyze the current signals of the healthy motor, bearing damage motor, stator winding inter-turn short circuit motor, and broken rotor bar motor. Second, features after completing the signal analysis were extracted, and three types of classifiers were used to classify. The results show that the improved PSO-BP neural network can effectively detect the cause of failure. In addition, in order to simulate the actual operating environment of the motor, this study added white noise with signal noise ratios of 30 dB, 25 dB, and 20 dB to verify that this model has a better anti-noise ability.

Integrated Navigation of Mobile Robot Based on Neural Network and Fault Detection

2012 ◽  
Vol 433-440 ◽  
pp. 3175-3180
Author(s):  
Hong Mei Wang ◽  
Ming Lu Zhang ◽  
Guang Zhu Meng
Keyword(s):  
Neural Network ◽  
Fault Detection ◽  
Global Positioning System ◽  
Navigation System ◽  
Inertial Navigation System ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Integrated Navigation ◽  
Global Positioning ◽  
Navigation Accuracy

When global positioning system (GPS) signal outages, the integrated navigation accuracy of GPS and strap-down inertial navigation system (SINS) will decline with time, and even navigation system cannot work. To avoid this, a new design is introduced. When GPS works normally, square root filter estimates the errors of position, velocity and attitude and compensates the outputs of SINS. When GPS is out of order, back propagation neural network (BPNN) will take the place of GPS to calculate the error parameters, thus the accuracy of navigation will enhance. And in this paper, the unit of fault detection is added to detect whether GPS signal outages or not. The simulation results show the effectiveness of this method

Research of Defect Detection Method Noise for Bevel Gear

2014 ◽  
Vol 889-890 ◽  
pp. 722-725 ◽  
Author(s):  
Feng Yan Dai ◽  
Zhao Yao Shi ◽  
Jia Chun Lin
Keyword(s):  
Neural Network ◽  
Fault Detection ◽  
Background Noise ◽  
Back Propagation ◽  
Noise Signal ◽  
Ensemble Empirical Mode Decomposition ◽  
Bevel Gear ◽  
Noise Characteristics ◽  
Useful Signal ◽  
Gear Fault

Noise signal analysis method is widely available for gearbox bevel gear fault detection. However, the noise from the gearbox is usually concealed by background noise, which leads to poor efficiency analysis. This paper reports an ensemble empirical mode decomposition (EEMD) and neural network method for bevel gear fault detection. To extract useful signal, EEMD algorithm was firstly applied to get rid of the background noise. Characteristics from a group of discriminating defect status were then chosen to build the eigenvector. Finally, the eigenvector was imported into a back propagation (BP) neural network classifier for defect diagnosis automatically. Experimental results show that the proposed approach is capable for signal denoising and providing distinguishing characteristics of founded fault. The developed method is an accurate approach to detect fault for tested bevel gear.

scholarly journals Characterization Performance of Monocrystalline Silicon Photovoltaic Module Using Experimentally Measured Data

2019 ◽  
Vol 25 (10) ◽  
pp. 1-19
Author(s):  
Mena Safaa Mohammed ◽  
Emad Talib Hashim
Keyword(s):  
Ambient Temperature ◽  
Solar Irradiance ◽  
Clean Energy ◽  
Monocrystalline Silicon ◽  
Solar Irradiation ◽  
Weather Data ◽  
Photovoltaic Module ◽  
Solar Pv ◽  
Solar Module ◽  
Pv Module

Solar photovoltaic (PV) system has emerged as one of the most promising technology to generate clean energy. In this work, the performance of monocrystalline silicon photovoltaic module is studied through observing the effect of necessary parameters: solar irradiation and ambient temperature. The single diode model with series resistors is selected to find the characterization of current-voltage (I-V) and power-voltage (P-V) curves by determining the values of five parameters ( ). This model shows a high accuracy in modeling the solar PV module under various weather conditions. The modeling is simulated via using MATLAB/Simulink software. The performance of the selected solar PV module is tested experimentally for different weather data (solar irradiance and ambient temperature) that is gathered from October 2017 to April 2018 in the city of Baghdad. The collected data is recorded for the entire months during the time which is limited between 8:00 AM and 1:00 PM. This work demonstrates that the change in a cell temperature is directly proportional with the PV module current, while it is inversely proportional with the PV module voltage. Additionally, the output power of a PV module increases with decreasing the solar module temperature. Furthermore, the Simulink block diagram is used to evaluate the influence of weather factors on the PV module temperature by connecting to the MATLAB code. The best value from the results of this work was in March when the solar irradiance was equal to 1000 W/m2 and the results were: Isc,exp=3.015, Isc,mod=3.25 , RE=7.79 and Voc,exp=19.67 ,Voc,mod=19.9 ,RE=1.1

Sign in / Sign up

Export Citation Format

Share Document