Neural network of Gaussian radial basis functions applied to the problem of identification of nuclear accidents in a PWR nuclear power plant

Gomes, Carla Regina; Medeiros, J.A.C.C.

doi:10.1016/j.anucene.2014.10.001

Cited by 28 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The popularity of RBF neural networks compared to other kinds of neural networks concerns: (i) their capacity to approximate function problems, (ii) their simple and reduced architecture (composed only of three layers), (iii) their fast convergence properties and (vi) they have no local minima problems (Kasabov, 1998). Because of these advantages, RBF neural networks were applied in several disciplines, including in the photovoltaic process, to predict current-voltage characteristics and power-voltage (PeV) curves of a commercial PeV module (Bonanno et al, 2012), in medical diseases diagnosis (Qasem and Shamsuddin, 2011), in the identification of nuclear accidents (Gomes and Canedo Medeiros, 2015), in seismic inversions in petroleum exploration (Baddari et al, 2010), in image analysis (Cha and Kassam, 1996;Montazer and Giveki, 2015), in nanocomposite characterization of pore size measurement and wear model of a sintered CoppereTungsten (Leema et al, 2015), in the estimation of geotechnical parameters (Sinha and Wang, 2008;Mustafa et al, 2012), in geology to estimate the grade of an offshore placer gold deposit (Samanta and Bandopadhyay, 2009) and to assess rocky desertification in northwest Guangxi, China (Zhang et al, 2011).…”

Section: Introductionmentioning

confidence: 99%

A Preliminary study of relationships between thermal conductivity and petrophysical parameters in Hamra Quartzites reservoir, Hassi Messaoud field (Algeria)

Zerrouki

Géraud

Diraison

et al. 2019

Journal of African Earth Sciences

View full text Add to dashboard Cite

In geothermic studies, the thermal conductivity (TC) is an essential parameter needed to calculate heat flow in rocks. It is obtained generally with high accuracy from laboratory measurements. The methodology proposed in this paper is to estimate the TC, which depends on many parameters; such as mineralogy, porosity, shape of voids and nature of contact between grains, based on linear and nonlinear relationships. In order to predict the thermal conductivity from other petrophysical parameters in the Hamra Quartzites reservoir, we have measured porosity, density and permeability, for dry samples taken from core wells. The correlation coefficients (R) were calculated between thermal conductivity and other petrophysical parameters for all samples. The results show that, the correlation coefficient is moderate between TC and the porosity, weak between TC, density and permeability. To improve these correlations, samples were classified into cemented and uncemented sets. A minor improvement on the correlation coefficients is noted between TC, density and porosity in uncemented samples, with values equal 0.51 and 0.73, respectively. The application of Radial Basis Function (RBF) neural networks, using density, porosity and permeability as inputs and thermal conductivity as output, permit us to predict the thermal conductivity with high precision. The correlation coefficient between TC estimated by the RBF neural network is the same as that measured in laboratory equaling 0.983.

show abstract

Section: Introductionmentioning

confidence: 99%

A Preliminary study of relationships between thermal conductivity and petrophysical parameters in Hamra Quartzites reservoir, Hassi Messaoud field (Algeria)

Zerrouki

Géraud

Diraison

et al. 2019

Journal of African Earth Sciences

View full text Add to dashboard Cite

show abstract

“…If the problems frequently occur in these links and components, it will produce a significant influence on the regular operation of the system 21 . The fault probability of power system elements is a constant, while the state of system operation is changing, so the line vulnerability will also change 22 Important transmission channels will connect two important nodes, so the nodes' importance can also reflect the transmission function strength of the line connected. If the line between two important nodes in the power grid is disconnected, their electrical contact will be reduced, and the vulnerability of the power grid will increase 23 .…”

Section: Vulnerability Evaluation and Overload Identification Model Fmentioning

confidence: 99%

Research on line overload identification of power system based on improved neural network algorithm

Yang

Luo

Lin

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

Due to the continuous appearance of safety fault accidents in the practice process, operation safety has become the central task of various operation and management tasks of the power grid. Therefore, to establish a line overload identification and data control model for the power system, we first defined the vulnerability of complex power systems based on the analysis of each line and node. For finding the optimal parameters of this model, we proposed an improved optimization strategy by combining the genetic algorithm and BP neural network. To verified the effectiveness of our proposed method, we conducted experiments on a simulation on the IEEE 30-node power system environment. Experimental results demonstrate that the proposed algorithms can establish an optimized overload identification model with better performance. This study can help to conduct reasonable adjustment when overload happens to the power system, and then reduce similar failure as well as enhance the operation safety. K E Y W O R D S BP neural network, genetic algorithm, overload, power system 1 INTRODUCTION The power system is a combination of network space, physical space, and social space. Large-scale grid fault accidents will cause severe safety loopholes. Therefore, the operation safety of the power grid is an essential issue in the development of modern society. In practice, most power grid accidents originate from line overload of the power system, component failure, and similar problems. 1 To reduce such events, power grid enterprises should not only enhance daily maintenance but also need to improve the identification and survival ability of the power grid in emergencies. 2 With the development of information and communication technology, the Internet of Things has been extensively applied to the power grid, and the differential privacy protection policy can effectively protect the data security of power grid transfer. 3 Meanwhile, it would be better to detect corresponding important nodes and vulnerable lines and to reinforce the maintenance in advance before safety accidents happen, which can reduce economic losses and social disruption. 4 Many power safety management problems in power grid system can be converted into optimization problems through mathematical modeling. Some are multi-objective optimization problems, and high-performance computing at a faster speed is needed to solve these problems. 5 Line overload identification is still a difficulty for the safety of the power system. Therefore, we proposed an improved back propagation (BP) neural network based on the genetic algorithm (GA) to tackle the line overload problem in the power grid system. To establish a line overload identification and data control model for the power system, we first defined the vulnerability of complex power systems based on the analysis of each line and node. For optimizing this model, we take the advantages of combining the genetic algorithm and BP neural network. It is worth noting that the original BP neural network usually has the problem of s...

show abstract

“…The resulting value is passed to the neurons in the summation layer. Summation layer calculates the summation and computes arithmetic mean, Output layer neuron produces a binary output value corresponding to the best class choice for the specific sample, because that class has the maximum probability of being correct [15][18] [12].…”

Section: Probabilistic Neural Network (Pnn)mentioning

confidence: 99%

“…RBF learns with the help of hyperplane which is generated by a linear combination of functions from a given set of data points. Training in rbf is done with a set of input and output data pairs using which output layer weights are computed [18][8] [12].…”

Section: Radial Basis Function (Rbf)mentioning

confidence: 99%

Bank note authentication using decision tree rules and machine learning techniques

Kumar*

Dudyala

2015

2015 International Conference on Advances in Computer Engineering and Applications

View full text Add to dashboard Cite

Banknotes are currencies used by any nation to carry-out financial activities and are every countries asset which every nation wants it (bank-note) to be genuine. Lot of miscreants induces fake notes into the market which resemble exactly the original note. Hence, there is a need for an efficient authentication system which predicts accurately whether the given note is genuine or not. Exhaustive experiments have been conducted using different machine learning techniques and found that Decision tree and MLP techniques are effective for banknote authentication which efficiently classifies a given banknote data. The rules given by Decision Tree are also tested and found that they are accurate enough to be used for prediction.

show abstract

Neural network of Gaussian radial basis functions applied to the problem of identification of nuclear accidents in a PWR nuclear power plant

Cited by 28 publications

References 11 publications

A Preliminary study of relationships between thermal conductivity and petrophysical parameters in Hamra Quartzites reservoir, Hassi Messaoud field (Algeria)

A Preliminary study of relationships between thermal conductivity and petrophysical parameters in Hamra Quartzites reservoir, Hassi Messaoud field (Algeria)

Research on line overload identification of power system based on improved neural network algorithm

Bank note authentication using decision tree rules and machine learning techniques

Contact Info

Product

Resources

About