Rock hardness identification based on optimized PNN and multi-source data fusion

2021 ◽  
pp. 095440622110420
Author(s):  
Ying He ◽  
Muqin Tian ◽  
Jiancheng Song ◽  
Junling Feng
Keyword(s):  
Neural Network ◽  
Data Fusion ◽  
Probabilistic Neural Network ◽  
Wavelet Packet ◽  
Differential Evolution Algorithm ◽  
Vibration Signal ◽  
Optimization Method ◽  
Rock Wall ◽  
Rock Hardness ◽  
Source Data

To solve the problem that it is difficult to identify the cutting rock wall hardness of the roadheader in coal mine, a recognition method of cutting rock wall hardness is proposed based on multi-source data fusion and optimized probabilistic neural network. In this method, all kinds of cutting signals (the vibration signal of cutting arm, the pressure signal of hydraulic cylinders and current signal of cutting motor) are analyzed by wavelet packet to extract the feature vector, and the multi feature signal sample database of rock cutting with different hardness is established. To solve the problems of uncertain spread and complex network structure of probabilistic neural network (PNN), a PNN optimization method based on differential evolution algorithm (DE) and QR decomposition was proposed, and the rock hardness was identified based on multi-source data fusion by optimizing PNN. Then, based on the ground test monitoring data of a heavy longitudinal roadheader, the method is applied to recognize the cutting rock hardness, and compared with other common pattern recognition methods. The experimental results show that the cutting rock hardness recognition based on multi-source data fusion and optimized PNN has higher recognition accuracy, and the overall recognition error is reduced to 6.8%. The recognition of random cutting rock hardness is highly close to the actual. The method provides theoretical basis and technical premise for realizing automatic and intelligent cutting of heading face.

scholarly journals An Anti-Islanding Protection Technique Using a Wavelet Packet Transform and a Probabilistic Neural Network

Energies ◽  
2018 ◽  
Vol 11 (10) ◽  
pp. 2701 ◽  
Author(s):  
Masoud Ahmadipour ◽  
Hashim Hizam ◽  
Mohammad Lutfi Othman ◽  
Mohd Amran Mohd Radzi
Keyword(s):  
Neural Network ◽  
Shannon Entropy ◽  
Probabilistic Neural Network ◽  
Wavelet Packet ◽  
Wavelet Packet Transform ◽  
Detection Technique ◽  
Islanding Detection ◽  
Energy Entropy ◽  
Cost Parameters ◽  
Logarithmic Energy

This paper proposes a new islanding detection technique based on the combination of a wavelet packet transform (WPT) and a probabilistic neural network (PNN) for grid-tied photovoltaic systems. The point of common coupling (PCC) voltage is measured and processed by the WPT to find the normalized Shannon entropy (NSE) and the normalized logarithmic energy entropy (NLEE). Subsequently, the yield feature vectors are fed to the PNN classifier to classify the disturbances. The PNN is trained with different spread factors to obtain better classification accuracy. For the best performance of the proposed method, the precise analysis is done for the selection of the type of input data for the PNN, the type of mother wavelet, and the required transform level which is based on the accuracy, simplicity, specificity, speed, and cost parameters. The results show that, by using normalized Shannon entropy and the normalized logarithmic energy entropy, not only it offers simplicity, specificity and reduced costs, it also has better accuracy compared to other smart and passive methods. Based on the results, the proposed islanding detection technique is highly accurate and does not mal-operate during islanding and non-islanding events.

Fault Diagnosis of Large Rotors Based on Wavelet Packet Neural Network

2014 ◽  
Vol 722 ◽  
pp. 363-366
Author(s):  
You Juan Zheng ◽  
Ping Liao ◽  
Cai Long Qin ◽  
Yu Li
Keyword(s):  
Neural Network ◽  
Fault Diagnosis ◽  
Bp Neural Network ◽  
Test Bench ◽  
Feature Vector ◽  
Wavelet Packet ◽  
Vibration Signal ◽  
Network Method ◽  
Spectrum Characteristic ◽  
Fault Information

Using wavelet packet neural network method which is consist of wavelet packet and BP neural network to diagnose large rotors by vibration signal .Firstly , according to the spectrum characteristic of large rotors’ common vibration fault ,using the improved wavelet packet method to compute the energy of the spectrum that can reflect the fault information .And then make the feature vector as the input to establish a model of improved wavelet packet neural network for fault diagnosis . Collect the data of five working conditions from the test bench , establish a improved wavelet packet neural network model, and then use the model to diagnose fault. The experimental results show that this method improves the accuracy obviously and calculate fast.

scholarly journals Fault Identification of Gearbox Degradation with Optimized Wavelet Neural Network

2013 ◽  
Vol 20 (2) ◽  
pp. 247-262 ◽  
Author(s):  
Hanxin Chen ◽  
Yanjun Lu ◽  
Ling Tu
Keyword(s):  
Neural Network ◽  
Wavelet Packet ◽  
Back Propagation ◽  
Experimental System ◽  
Vibration Signal ◽  
Wavelet Neural Network ◽  
Acceleration Sensors ◽  
Gear Fault ◽  
Gear Crack

A novel intelligent method based on wavelet neural network (WNN) was proposed to identify the gear crack degradation in gearbox in this paper. The wavelet packet analysis (WPA) is applied to extract the fault feature of the vibration signal, which is collected by two acceleration sensors mounted on the gearbox along the vertical and horizontal direction. The back-propagation (BP) algorithm is studied and applied to optimize the scale and translation parameters of the Morlet wavelet function, the weight coefficients, threshold values in WNN structure. Four different gear crack damage levels under three different loads and three various motor speeds are presented to obtain the different gear fault modes and gear crack degradation in the experimental system. The results show the feasibility and effectiveness of the proposed method by the identification and classification of the four gear modes and degradation.

scholarly journals IDENTIFICATION OF OBSTRUCTIVE SLEEP APNEA USING ARTIFICIAL NEURAL NETWORKS AND WAVELET PACKET DECOMPOSITION OF THE HRV SIGNAL

2020 ◽  
Vol 17 (1) ◽  
pp. 24
Author(s):  
Abdulnasir Hossen ◽  
Sarah Qasim
Keyword(s):  
Neural Network ◽  
Obstructive Sleep Apnea ◽  
Sleep Apnea ◽  
Probabilistic Neural Network ◽  
Wavelet Packet ◽  
Back Propagation ◽  
Normal Subjects ◽  
University Hospital ◽  
Feedforward Network ◽  
Obstructive Sleep

The advancement of telecommunication technologies has provided us with new promising alternatives for remote diagnosis and possible treatment suggestions for patients of diverse health disorders, among which is the ability to identify Obstructive Sleep Apnea (OSA) syndrome by means of Electrocardiograph (ECG) signal analysis. In this paper, the standard spectral bands’ powers and statistical interval-based parameters of the Heart Rate Variability (HRV) signal were considered as a form of features for classifying the Sultan Qaboos University Hospital (SQUH) database for OSA syndrome into 4 different levels. Wavelet packet analysis was applied to obtain and estimate the standard frequency bands of the HRV signal. Further, the single perceptron neural network, the feedforward with back-propagation neural network and the probabilistic neural network have been implemented in the classification task. The classification between normal subjects versus severe OSA patients achieved 95% accuracy with the probabilistic neural network. While the classification between normal subjects versus mild OSA subjects reached accuracy of 95% also. When grouping mild, moderate and severe OSA subjects in one group compared to normal subjects as a second group, the classification with the feedforward network achieved an accuracy of 87.5%. Finally, when classifying subjects directly into one of the four classes (normal or mild or moderate or severe), a 77.5% accuracy was achieved with the feedforward network.

Damage Identification Using Wavelet Packet Transform and Neural Network Ensembles

2018 ◽  
Vol 18 (12) ◽  
pp. 1850148 ◽  
Author(s):  
Xiang Zhang ◽  
Renwen Chen ◽  
Qinbang Zhou
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Damage Identification ◽  
Probabilistic Neural Network ◽  
Wavelet Packet ◽  
Rotor Blades ◽  
Identification Accuracy ◽  
Vibration Responses ◽  
Neural Network Ensembles ◽  
Network Ensembles

This study presents a damage identification method that combines wavelet packet transforms (WPTs) with neural network ensembles (NNEs). The WPT is used to extract damage features, which are taken as the input vectors in the NNEs used for damage identification. An experiment was performed on a helicopter rotor blades structure to verify the proposed method. First, the vibration responses collected by different sensors are decomposed using the WPT. Second, the relative band energy of each decomposed frequency band is calculated and fused as the damage feature vectors. Third, two types of the NNEs are designed. One is based on the backward propagation neural networks (BPNNs) for detecting the damage locations and severities and the other one is based on the probabilistic neural network (PNN) to detect the damage types. Finally, the trained NNEs are employed in damage identification. From the identification outcomes, it is concluded that damage information can be extracted effectively by the WPT and the identification accuracy of the NNEs is better than that of individual neural networks (INNs).

scholarly journals THE PROBABILISTIC NEURAL NET NEURON’S NUMBER CALCULATIONS

2014 ◽  
pp. 137-144
Author(s):  
Galina Shcherbacova ◽  
Victor Krylov ◽  
Oleg Logvinov
Keyword(s):  
Neural Network ◽  
Gradient Method ◽  
Probabilistic Neural Network ◽  
Optimization Method ◽  
Neural Net ◽  
Noise Stability ◽  
Iterative Optimization ◽  
Hidden Layer ◽  
Classification Time

The sub-gradient method of estimation of the number of the hidden layer neurons of a probabilistic neural network is suggested. This method allows evaluating the data compactness violation in λ-space. This evaluation based on the noise stability sub-gradient iterative optimization method. This method allows reducing the number of the hidden layer neurons and classification time.

Sign in / Sign up

Export Citation Format

Share Document