scholarly journals New Fault Recognition Method for Rotary Machinery Based on Information Entropy and a Probabilistic Neural Network

Sensors ◽  
2018 ◽  
Vol 18 (2) ◽  
pp. 337 ◽  
Author(s):  
Quansheng Jiang ◽  
Yehu Shen ◽  
Hua Li ◽  
Fengyu Xu
Keyword(s):  
Neural Network ◽  
Information Entropy ◽  
Probabilistic Neural Network ◽  
Recognition Method ◽  
Fault Recognition ◽  
Rotary Machinery

Fault Recognition of Gear Pump Based on EMD Neural Network

2013 ◽  
Vol 333-335 ◽  
pp. 1635-1639
Author(s):  
Shu Xiang Gao ◽  
Xiao Hu Chen ◽  
Yao Ding
Keyword(s):  
Neural Network ◽  
High Pressure ◽  
Working Conditions ◽  
Bp Neural Network ◽  
Gear Pump ◽  
Recognition Method ◽  
Vibration Acceleration ◽  
Fault Recognition ◽  
Network Method ◽  
Information Components

Aim at the non-stationary and time-variation characteristic of the gear-pump fault signal, proposing a condition recognition method for gear pump based on EMD and neural network. Take the vibration acceleration of case as the analysis object. Firstly,deal the signal with EMD, extract the main IMF components, containing the main information components. And then calculate its energy, and use the energy ratio to compose the feature vectors , which is used for BP neural network to identify the gear pump working state. The result reveals the EMD neural network method can recognize the working conditions of mesh-type high-pressure gear pump CB-KP63.

A novel fault diagnosis method based on improved adaptive variational mode decomposition, energy entropy, and probabilistic neural network

2020 ◽  
Vol 44 (1) ◽  
pp. 121-132 ◽  
Author(s):  
Shengjie Zhang ◽  
Huimin Zhao ◽  
Junjie Xu ◽  
Wu Deng
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Probabilistic Neural Network ◽  
Screening Method ◽  
Maximum Output ◽  
Variational Mode Decomposition ◽  
Bearing Fault ◽  
Energy Entropy ◽  
Mode Decomposition ◽  
Fault Recognition

To improve the accuracy of bearing fault recognition, a novel bearing fault diagnosis (PAVMD-EE-PNN) method based on parametric adaptive variational mode decomposition (VMD), energy entropy, and probabilistic neural network (PNN) is proposed in this paper. In view of the effect of VMD on signal decomposition effect affected by the number of preset decomposition modes, a central frequency screening method is proposed to determine the number of decomposition modes of the VMD method. The parametric adaptive VMD method is used to decompose the bearing fault signal into a series of intrinsic mode function (IMF) components. The energy entropy of IMF components is calculated to form an eigenvector, which is input into the PNN model for training to obtain a fault recognition model with maximum output probability. The actual bearing vibration data are obtained and used to test and verify the effectiveness of the PAVMD-EE-PNN method. The experimental results show that the PAVMD-EE-PNN method can effectively and accurately identify the fault type, and the fault recognition effect is better than contrast fault diagnosis methods.

scholarly journals Combined Classifier for Face Recognition using Legendre Moments

2012 ◽  
Vol 1 (2) ◽  
pp. 107-118 ◽  
Author(s):  
Sridhar Dasari ◽  
I.V. Murali Krishna
Keyword(s):  
Neural Network ◽  
Face Recognition ◽  
Discriminant Analysis ◽  
Dimensionality Reduction ◽  
Linear Discriminant Analysis ◽  
Probabilistic Neural Network ◽  
Recognition Method ◽  
Linear Discriminant ◽  
Face Images ◽  
Legendre Moments

In this paper, a new combined Face Recognition method based on Legendre moments with Linear Discriminant Analysis and Probabilistic Neural Network is proposed. The Legendre moments are orthogonal and scale invariants hence they are suitable for representing the features of the face images. The proposed face recognition method consists of three steps, i) Feature extraction using Legendre moments ii) Dimensionality reduction using Linear Discrminant Analysis (LDA) and iii) classification using Probabilistic Neural Network (PNN). Linear Discriminant Analysis searches the directions for maximum discrimination of classes in addition to dimensionality reduction. Combination of Legendre moments and Linear Discriminant Analysis is used for improving the capability of Linear Discriminant Analysis when few samples of images are available. Probabilistic Neural network gives fast and accurate classification of face images. Evaluation was performed on two face data bases. First database of 400 face images from Olivetty Research Laboratories (ORL) face database, and the second database of thirteen students are taken. The proposed method gives fast and better recognition rate when compared to other classifiers.DOI: 10.18495/comengapp.12.107118

Sign in / Sign up

Export Citation Format

Share Document