Stream Turbine Vibration Fault Diagnosis

2013 ◽  
Vol 340 ◽  
pp. 90-94 ◽  
Author(s):  
Hong Sheng Su
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Fault Diagnosis ◽  
Rbf Neural Network ◽  
Local Extremum ◽  
Decision Table ◽  
Rbf Neural Networks ◽  
Global Extremum ◽  
Artificial Fish Swarm Algorithm ◽  
Diagnosis Method

RBF neural networks possessed the excellent characteristics such as insensitive on the initial weights and parameters with artificial fish-swarm algorithm (AFSA) applied, which made it have abilities to get rid of the local extremum and obtain the global extremum, and called as AFSA-RBF neural networks. In this paper, a new stream turbine vibration fault diagnosis method was presented based on AFSA-RBF neural networks. After quantification and reduction of the diagnosis decision table, the simplified decision table served as the learning samples of AFSA-RBF neural network, and the well-trained neural network was then applied to diagnose stream turbine vibration faults. The diagnosis results show that the proposed method possesses higher convergence speed and diagnosis precision, and is a very effective turbine fault diagnosis method.

scholarly journals A Fault Diagnosis Method for Lithium-Ion Battery Packs Using Improved RBF Neural Network

2021 ◽  
Vol 9 ◽  
Author(s):  
Jia Wang ◽  
Shenglong Zhang ◽  
Xia Hu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Fault Diagnosis ◽  
Lithium Ion Battery ◽  
Electric Vehicles ◽  
Rbf Neural Network ◽  
Lithium Ion ◽  
Rbf Neural Networks ◽  
Battery Packs ◽  
Diagnosis Method

With the increasing demand for electric vehicles, the high voltage safety of electric vehicles has attracted significant attention. More than 30% of electric vehicle accidents are caused by the battery system; hence, it is vital to investigate the fault diagnosis method of lithium-ion battery packs. The fault types of lithium-ion battery packs for electric vehicles are complex, and the treatment is cumbersome. This paper presents a fault diagnosis method for the electric vehicle power battery using the improved radial basis function (RBF) neural network. First, the fault information of lithium-ion battery packs was collected using battery test equipment, and the fault levels were then determined. Subsequently, the improved RBF neural networks were employed to identify the fault of the lithium-ion battery pack system using the experimental data. The diagnosis test results showed that the improved RBF neural networks could effectively identify the fault diagnosis information of the lithium-ion battery packs, and the diagnosis accuracy was about 100%.

The Application of RBF Neural Networks in Curve Fitting

2012 ◽  
Vol 490-495 ◽  
pp. 688-692
Author(s):  
Zhong Biao Sheng ◽  
Xiao Rong Tong
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Rbf Neural Network ◽  
Engineering Application ◽  
Nonlinear Function ◽  
Rbf Neural Networks ◽  
Neural Network Approach ◽  
Rbf Network ◽  
Fast Learning ◽  
Nonlinear Processing

Three means to realize function approach such as the interpolation approach, fitting approach as well as the neural network approach are discussed based on Matlab to meet the demand of data processing in engineering application. Based on basic principle of introduction, realization methods to non-linear are researched using interpolation function and fitting function in Matlab with example. It mainly studies the RBF neural networks and the training method. RBF neural network to proximate nonlinear function is designed and the desired effect is achieved through the training and simulation of network. As is shown from the simulation results, RBF network has strong nonlinear processing and approximating features, and RBF network model has the characteristics of high precision, fast learning speed for the prediction.

Research of Fault Diagnosis Method Based on Improved Extreme Learning Machine

2015 ◽  
Vol 727-728 ◽  
pp. 872-875
Author(s):  
Wen Bo Na ◽  
Qing Feng Jiang ◽  
Zhi Wei Su
Keyword(s):  
Fault Diagnosis ◽  
Extreme Learning Machine ◽  
Rbf Neural Network ◽  
Wavelet Packet ◽  
Support Vector ◽  
Wavelet Packet Decomposition ◽  
Rbf Neural Networks ◽  
Diagnosis Method ◽  
Learning Machine ◽  
Better Than

In order to improve the accuracy of diagnosis pumping, and accelerate the speed of diagnosis, a fault diagnosis model based on improved extreme learning machine (RWELM) was proposed. Firstly, it extracted the energy characteristic eigenvector of dynamometer cards of an oilfield in northern Shanxi by using wavelet packet decomposition method. Then through simulation of fault diagnosis, and compare with the extreme learning machine (ELM), RBF neural networks and support vector machine (SVM). The experimental results show that the accuracy and the speed of fault diagnosis based on the RWELM are better than the ELM, RBF neural network and SVM.

Design of RBF Neural Networks Based on Adjustable Radius

2010 ◽  
Vol 439-440 ◽  
pp. 605-610
Author(s):  
Xiao Yong Liu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Function Approximation ◽  
Clustering Algorithm ◽  
Rbf Neural Network ◽  
Gaussian Function ◽  
Mean Square ◽  
Rbf Neural Networks ◽  
Data Points ◽  
Better Than

In this paper, a new RBF neural network (RBFNN) algorithm, called ar-RBFNN, is presented. In traditional RBFNNs based on clustering algorithm, called oRBFNN in this paper, the width of the basis function-Gaussian function, or called radius, ignored the effect of numbers in different clusters, or density of data points. New algorithm considers radius is effect to performance of algorithms in problem of function approximation. Mean Square Error is used to evaluate performances of two algorithms, oRBFNN and ar-RBFNN algorithms. Several experiments in function approximation show ar-RBFNN is better than oRBFNN.

Research of Automotive Glass Fog System Based on RBF Neural Network

2012 ◽  
Vol 588-589 ◽  
pp. 1441-1445
Author(s):  
Liu Zhang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Rbf Neural Network ◽  
Rbf Neural Networks ◽  
Matlab Software ◽  
New Type ◽  
New System

By describing a danger from driving vehicles with fog on windshield, we give a concept of a new type of automatic windshield defogging system applying traditional sensor and RBF neural networks. In terms of an analysis on the source of fogging on automatic windshield, applying traditional sensor, we design a RBF neural networks. Then, via RBF neural networks mode, training and testing 48 series of data from an experiment. A result of MATLAB software demonstrates that this new system defog from automatic windshield swiftly and precisely by applying RBF neural networks.

RBF Neural Network Model Training by Unscented Kalman Filter and its Application in Mechanical Fault Diagnosis

2014 ◽  
Vol 602-605 ◽  
pp. 2383-2386 ◽  
Author(s):  
Xu Sheng Gan ◽  
Hua Ping Li ◽  
Hai Long Gao
Keyword(s):  
Neural Network ◽  
Kalman Filter ◽  
Fault Diagnosis ◽  
Neural Network Model ◽  
Basis Function ◽  
Unscented Kalman Filter ◽  
Rbf Neural Network ◽  
Mechanical Equipment ◽  
Diagnosis Method ◽  
Model Training

To improve the ability of fault diagnosis for mechanical equipment, a Radial Basis Function Neural Network (RBFNN) diagnosis method based on Unscented Kalman Filter (UKF) algorithm is proposed. In the algorithm, at first, UKF algorithm is used to estimate the parameters of RBFNN, and then the proposed method is introduced into the fault diagnosis of mechanical equipment. The simulation indicates that the established model has a good diagnosis performance for mechanical fault diagnosis.

Fault Diagnosis of Cascaded Converter Based on Wavelet Packet RBF Neural Network

2013 ◽  
Vol 273 ◽  
pp. 300-304
Author(s):  
Xin Wang ◽  
Juan Xu ◽  
Guo Dong Zhang ◽  
Rui Min Qi
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Learning Algorithm ◽  
Rbf Neural Network ◽  
Wavelet Packet ◽  
Open Circuit ◽  
Learning Performance ◽  
Cascaded Converter ◽  
Diagnosis Method ◽  
Faults Diagnosis

To study the power component open circuit faults diagnosis method of the cascaded converter. Aiming at the insufficiency of the BP learning algorithm in the machinery fault diagnosis, such as the low learning convergence speed, the easily appearing local minimum, the instability learning performance caused by the initial value, to proposed a new method applied to the cascaded converter based on radial basis function (RBF) neural network. Experiments show that the method based on wavelet packet analysis and RBF neural network has better learning and fault identification capability, and it can meet the online real-time fault diagnosis of the cascaded converter.

Fault Diagnosis of CNC Machine Using Hybrid Neural Network

2011 ◽  
Vol 128-129 ◽  
pp. 865-869
Author(s):  
Juan Du ◽  
Xian Guo Yan ◽  
Na Sha Wei
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Fault Diagnosis ◽  
First Grade ◽  
Second Grade ◽  
Cnc Machine ◽  
Bp Network ◽  
Hybrid Neural Network ◽  
Neural Network System ◽  
Diagnosis Method

This paper proposed a technology of fault diagnosis for CNC machine based on hybrid neural network. Before the fault diagnosis was made, the fault patterns were firstly obtained from technical manuals and field experience to build a sample set, and then they were classified and coded according to the rule. In order to improve diagnosis speed, the fault diagnosis system was designed as a hybrid neural network system which consists of two-grade neural networks. When the fault pattern was input the system, the fault was first classified by the first-grade BP network, and according to the fault type, the corresponding second-grade ART network was activated to perform fault diagnosis. In this paper, the train algorithms of two kinds of neural networks were programmed by MATLAB. Comparing with the traditional diagnosis method, the presented technology possesses advantages of automatic fault diagnosis and ability for self-learning and self-organization.

Sign in / Sign up

Export Citation Format

Share Document