A Methodology to Evaluate Artificial Neural Network Training Used to Estimate Transformer Failure Probability

2007 ◽  
Author(s):  
Enrique A. Susemihl ◽  
Shuzhen Xu
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Failure Probability ◽  
Transformer Oil ◽  
Network Training ◽  
Insulation Degradation ◽  
Artificial Neural ◽  
Predicted Values ◽  
Artificial Neural Network Ann ◽  
Paper Insulation

In a previous paper [1] the authors presented a methodology to estimate the probability of failure of power transformers due to paper insulation degradation. The methodology was based on the identification of patterns in indirect measurements by means of an artificial neural network (ANN). The parameters measured were the amounts of dissolved gases and other chemical in the transformer oil. The failure probability was then estimated from the population life data. The methods presented in this paper are useful to estimate the quantitity of cases required for the training of the ANN to achieve acceptable predicted values, which is particularly important when the available data is limited.

A Prediction Model of Deflection of Fixing Thin Parts

2012 ◽  
Vol 217-219 ◽  
pp. 1526-1529
Author(s):  
Yu Mei Liu ◽  
Wen Ping Liu ◽  
Zhao Liang Jiang ◽  
Zhi Li
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Artificial Neural Network ◽  
Prediction Model ◽  
Simulated Data ◽  
Artificial Neural ◽  
Predicted Values ◽  
Artificial Neural Network Ann ◽  
Abaqus Software

A prediction model of deflection is presented. The Artificial Neural Network (ANN) is adopted, and ANN establishes the mapping relation between the clamping forces and the position of fixing and the value of deflection. The results of simulation of Abaqus software is used for Training and querying an ANN. The predicted values are in agreement with simulated data and experimental data.

scholarly journals Performance evaluation of natural esters and dielectric correlation assessment using artificial neural network (ANN)

2020 ◽  
Vol 10 (05) ◽  
pp. 2050025 ◽  
Author(s):  
Raymon Antony Raj ◽  
Ravi Samikannu ◽  
Abid Yahya ◽  
Modisa Mosalaosi
Keyword(s):  
Neural Network ◽  
Thermal Conductivity ◽  
Artificial Neural Network ◽  
Repetition Rate ◽  
Unsaturated Fatty Acids ◽  
Mineral Oil ◽  
Transformer Oil ◽  
International Electrotechnical Commission ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

The performance of correlation between the dielectric parameters of Baobab Oil (BAO) and Mongongo Oil (MGO) is evaluated using Artificial Neural Network (ANN). The BAO and MGO naturally own high Unsaturated Fatty Acids (UFAs) and are highly biodegradable. The temperature studies and dielectric studies are carried out and found that the Natural Esters (NEs) show a reliable performance over mineral oil-based Transformer Oil (TO). Further the endurance test, Partial Discharge Inception Voltage (PDIV) repetition rate and drop after 30 days, dielectric measurements are done as per the standards of IEC (International Electrotechnical Commission) and ASTM (American Society for Testing and Materials). The NEs show stable performance under PDIV and show minimum repetition rate when compared to the TO. The C[Formula: see text]H[Formula: see text] or Kerosene (KER) and NEs mixture prove that the NE-based transformer fluids show lesser tendency to hydro peroxidation. The C[Formula: see text]H[Formula: see text] acts as a thinning agent and reduces the ageing rate of the NEs, and this leads to slower rate of water saturation. This in turn increases the thermal conductivity of the oil and nearly a 30-days thermal ageing of the oil samples at 90[Formula: see text]C shows better strength of liquid insulation. The performance of association between the dielectric properties like breakdown voltage and water content, dissipation factor and thermal conductivity prove that the NEs show consistent performance and is a better substitute for the mineral oil-based TO.

Analysis of CHF Characteristics of Concentric-Tube Open Thermosyphon by Using Artificial Neural Network

2010 ◽  
Author(s):  
Ronghua Chen ◽  
Gunaghui Su ◽  
Suizheng Qiu
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Density Ratio ◽  
Outer Tube ◽  
Tube Length ◽  
Working Fluid ◽  
Optimum Diameter ◽  
Artificial Neural ◽  
Predicted Values ◽  
Artificial Neural Network Ann

An artificial neural network (ANN) for predicting critical heat flux (CHF) of concentric-tube open thermosyphon has been trained successfully based on the experimental data from the literature. The dimensionless input parameters of the ANN are density ratio, ρl/ρv, the ratio of the heated tube length to the inner diameter of the outer tube L/Di, the ratio of frictional area, di/(Di + do), and the ratio of equivalent heated diameter to characteristic bubble size, Dhe/[σ/g(ρl−ρv)]0.5, the output is Kutateladze number, Ku. The predicted values of ANN are found to be in reasonable agreement with the actual values from the experiments with a mean relative error (MRE) of 8.46%. For a particular outer tube, the CHF increases initially and then decreases with increasing inner tube diameter, and has a maximum at an optimum diameter of inner tube (do,opt). The do,opt is correlated with the working fluid and may decrease with the increase of ρl/ρv. CHF decreases with the increase of L/Di, and the decreasing rate decreases as L/Di increases. In the influence scope of pressure, the CHF decreases with increasing pressure for R22, while increases with increasing pressure for R113.

Application of the Artificial Neural Network (ANN) Method as MPPT Photovoltaic for DC Source Storage

2019 ◽  
Vol 12 (3) ◽  
pp. 145 ◽  
Author(s):  
Epyk Sunarno ◽  
Ramadhan Bilal Assidiq ◽  
Syechu Dwitya Nugraha ◽  
Indhana Sudiharto ◽  
Ony Asrarul Qudsi ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Random Forest (RF) and Artificial Neural Network (ANN) Algorithms for LULC Mapping

2020 ◽  
Vol 38 (4A) ◽  
pp. 510-514
Author(s):  
Tay H. Shihab ◽  
Amjed N. Al-Hameedawi ◽  
Ammar M. Hamza
Keyword(s):  
Neural Network ◽  
Remote Sensing ◽  
Artificial Neural Network ◽  
Random Forest ◽  
Satellite Image ◽  
Landsat 8 ◽  
Optical Remote Sensing ◽  
Data Set ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

In this paper to make use of complementary potential in the mapping of LULC spatial data is acquired from LandSat 8 OLI sensor images are taken in 2019.  They have been rectified, enhanced and then classified according to Random forest (RF) and artificial neural network (ANN) methods. Optical remote sensing images have been used to get information on the status of LULC classification, and extraction details. The classification of both satellite image types is used to extract features and to analyse LULC of the study area. The results of the classification showed that the artificial neural network method outperforms the random forest method. The required image processing has been made for Optical Remote Sensing Data to be used in LULC mapping, include the geometric correction, Image Enhancements, The overall accuracy when using the ANN methods 0.91 and the kappa accuracy was found 0.89 for the training data set. While the overall accuracy and the kappa accuracy of the test dataset were found 0.89 and 0.87 respectively.

Detection of Biomedical Images by Using Bio-inspired Artificial Intelligent

2020 ◽  
Vol 38 (2A) ◽  
pp. 255-264
Author(s):  
Hanan A. R. Akkar ◽  
Sameem A. Salman
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Mean Square Error ◽  
Average Rate ◽  
Mean Square ◽  
Performance Measurements ◽  
Artificial Intelligent ◽  
Average Mean Square Error ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Computer vision and image processing are extremely necessary for medical pictures analysis. During this paper, a method of Bio-inspired Artificial Intelligent (AI) optimization supported by an artificial neural network (ANN) has been widely used to detect pictures of skin carcinoma. A Moth Flame Optimization (MFO) is utilized to educate the artificial neural network (ANN). A different feature is an extract to train the classifier. The comparison has been formed with the projected sample and two Artificial Intelligent optimizations, primarily based on classifier especially with, ANN-ACO (ANN training with Ant Colony Optimization (ACO)) and ANN-PSO (training ANN with Particle Swarm Optimization (PSO)). The results were assessed using a variety of overall performance measurements to measure indicators such as Average Rate of Detection (ARD), Average Mean Square error (AMSTR) obtained from training, Average Mean Square error (AMSTE) obtained for testing the trained network, the Average Effective Processing Time (AEPT) in seconds, and the Average Effective Iteration Number (AEIN). Experimental results clearly show the superiority of the proposed (ANN-MFO) model with different features.

Sign in / Sign up

Export Citation Format

Share Document