Faults Classification for Transmission Line using Wavelet and Radial Base Function

Nonlinear system optimization is always an issue that needs to be considered in engineering practices and management. In order to obtain optimal solutions without analysis formulas to nonlinear systems, we first construct a radial-base-function (RBF) neural network using the newrb() function in MALTAB 7.0, then train the neural network according to input and output, and finally obtain the solution using a genetic algorithm. Simulated experimental results show that the proposed algorithm is able to achieve optimal solutions with a relatively fast speed of convergence.

Download Full-text

ADAPTIVE BACKSTEPPING SLIDING MODE CONTROLLER FOR FLIGHT SIMULATOR BASED ON RBFNN

International Journal of Modeling Simulation and Scientific Computing ◽

10.1142/s1793962313420075 ◽

2013 ◽

Vol 04 (04) ◽

pp. 1342007 ◽

Cited By ~ 1

Author(s):

YUNJIE WU ◽

BAITING LIU ◽

WULONG ZHANG ◽

XIAODONG LIU

Keyword(s):

Controller Design ◽

Sliding Mode ◽

Flight Simulator ◽

Sliding Mode Controller ◽

Control Input ◽

Adaptive Backstepping ◽

External Disturbances ◽

Base Function ◽

System A ◽

Radial Base Function

For flight simulator system, a kind of Adaptive Backstepping Sliding Mode Controller (ABSMC) based on Radial Base Function Neural Network (RBFNN) observer is presented. The sliding mode control theory is famous by its characteristic that it is insensitive to the external disturbances and parameters uncertainties. Combining this characteristic with Backstepping method can simplifies the controller design. And the addition of the terminal attractor can make the arrival time shorten greatly. However, too large external disturbances and parameters uncertainties are still not allowed to the system, and the design process of ABSMC does not have the upper bound information of disturbance until a RBFNN observer is designed to solve the problems. The simulation results show that the proposed scheme can improve the tracking precision and reduce the chattering of the control input, and the system has a higher robustness.

Download Full-text

Response to “Comment on a recent sensitivity analysis of radial base function and multi-layer feed-forward neural network models”

Chemometrics and Intelligent Laboratory Systems ◽

10.1016/0169-7439(96)00018-4 ◽

1996 ◽

Vol 34 (2) ◽

pp. 299-301 ◽

Cited By ~ 4

Author(s):

E.P.P.A. Derks ◽

M.S. Sánchez Pastor ◽

L.M.C. Buydens

Keyword(s):

Neural Network ◽

Sensitivity Analysis ◽

Network Models ◽

Feed Forward Neural Network ◽

Neural Network Models ◽

Base Function ◽

Feed Forward ◽

Radial Base Function

Download Full-text

Analysis free surface of nonlinear seepage using the MQRBF method

E3S Web of Conferences ◽

10.1051/e3sconf/202123303042 ◽

2021 ◽

Vol 233 ◽

pp. 03042

Author(s):

Yan SU ◽

Zhi-ming ZHENG ◽

Cheng-yu GU ◽

Long-teng ZHANG

Keyword(s):

Free Surface ◽

Numerical Solution ◽

Solution Process ◽

Earth Dam ◽

Richards Equation ◽

Boundary Values ◽

Base Function ◽

Trefftz Method ◽

Transient Problem ◽

Radial Base Function

In order to solve the characteristics of low accuracy and slow efficiency in traditional numerical solution the free surface problem, the multiquardatic radial base function collocation method(MQ RBF) is used to analyze the constant seepage and unsteady seepage of the homogeneous earth dam. Computation of transient problem of free surface of earth dam by the linear derivation of Richards equation. The results show that the calculation accuracy of the MQRBF is higher than that of the traditional numerical method. The solution process does not involve numerical integral calculation and grid reorganization, which greatly reduces the calculation amount. Compared with the Trefftz method, it has the advantage of solving boundary values and internal values at the same time. It is not limited by the solution of the Laplace equation, and its application is wider and simpler.

Download Full-text

A Hybrid Fuzzy-RBFN Filter for Data Classification

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.1117.261 ◽

2015 ◽

Vol 1117 ◽

pp. 261-264 ◽

Cited By ~ 3

Author(s):

Balázs Tusor ◽

Annamária R. Várkonyi-Kóczy

Keyword(s):

Fuzzy Control ◽

Control Systems ◽

Data Classification ◽

Clustering Methods ◽

Base Function ◽

Output Layer ◽

Suggested Structure ◽

Radial Base Function

In this paper, a new filter network is presented that is based on Radial Base Function Networks (RBFNs). The output layer of the network is modified, in order to make it more effective in certain fuzzy control systems. The training of the network is solved by a clustering step, for which two different clustering methods are proposed. The suggested structure can efficiently be used for data classification.

Download Full-text

A New Support Vector Machine and Artificial Neural Networks for Prediction of Stuck Pipe in Drilling of Oil Fields

Journal of Energy Resources Technology ◽

10.1115/1.4026917 ◽

2014 ◽

Vol 136 (2) ◽

Cited By ~ 11

Author(s):

Habib Rostami ◽

Abbas Khaksar Manshad

Keyword(s):

Support Vector Machine ◽

Rbf Neural Network ◽

Drilling Fluid ◽

Oil Fields ◽

Support Vector ◽

Base Function ◽

Rock Formations ◽

Svm Model ◽

Fluid Properties ◽

Radial Base Function

Stuck pipe is known to be influenced by drilling fluid properties and other parameters, such as the characteristics of rock formations. In this paper, we develop a support-vector-machine (SVM) based model to predict stuck pipe during drilling design and operations. To develop the model, we use a dataset, including stuck and nonstuck cases. In addition, we develop radial-base-function (RBF) neural network based model, using the same dataset, and compare its results with the SVM model. The results show that the performance of both models for prediction of stuck pipe does not differ significantly and both of them have highly accurate and can be used as the heart of an expert system to support drilling design and operations.

Download Full-text