Concrete Damage Identification based on Acoustic Emission and Wavelet Neural Network

2022 ◽  
Vol 80 (1) ◽  
pp. 48-57
Author(s):  
Yan Wang ◽  
Lijun Chen ◽  
Na Wang ◽  
Jie Gu
Keyword(s):  
Neural Network ◽  
Acoustic Emission ◽  
Source Identification ◽  
Basic Parameter ◽  
Damage Identification ◽  
Recognition Rate ◽  
Principal Component ◽  
Wavelet Neural Network ◽  
Tensile Data ◽  
Concrete Damage

In order to improve the accuracy of damage source identification in concrete based on acoustic emission testing (AE) and neural networks, and locating and repairing the damage in a practical roller compacted concrete (RCC) dam, a multilevel AE processing platform based on wavelet energy spectrum analysis, principal component analysis (PCA), and a neural network is proposed. Two data sets of 15 basic AE parameters and 23 AE parameters added on the basis of the 15 basic AE parameters were selected as the input vectors of a basic parameter neural network and a wavelet neural network, respectively. Taking the measured tensile data of an RCC prism sample as an example, the results show that compared with the basic parameter neural network, the wavelet neural network achieves a higher accuracy and faster damage source identification, with an average recognition rate of 8.2% and training speed of about 33%.

Identification of the concrete damage degree based on the principal component analysis of acoustic emission signals and neural networks

2020 ◽  
Vol 62 (5) ◽  
pp. 517-524
Author(s):  
Yan Wang ◽  
G. Jie ◽  
W. Na ◽  
Y. Chao ◽  
Z. Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Principal Component Analysis ◽  
Acoustic Emission ◽  
Principal Components ◽  
Principal Component ◽  
Damage Mechanism ◽  
Component Analysis ◽  
Damage Degree ◽  
Concrete Damage ◽  
Damage Process

Abstract This paper aims to improve the calculation efficiency and accuracy of concrete damage degree identification, and then to analyze the damage mechanism of concrete damage. First, the correlation analysis and principal component analysis of 15 characteristic parameters of acoustic emission signals accompanying concrete uniaxial compression and splitting damage process are performed through which the dimension is reduced into 5 non-correlated principal components. Then, based on the analysis of the relationship between each principal component and the damage and cracking mechanism of concrete, the damage degree of concrete is identified as an input variable of the BP neural network. The results show that the 5 principal components effectively eliminate redundant information and carry information on the failure mechanism of concrete damage and the damage process. Principal component analysis and the neural network are used to achieve the accurate recognition of acoustic emission parameters and the degree of concrete damage.

Predicting Complete Ground Reaction Forces and Moments During Gait With Insole Plantar Pressure Information Using a Wavelet Neural Network

2015 ◽  
Vol 137 (9) ◽  
Author(s):  
Taeyong Sim ◽  
Hyunbin Kwon ◽  
Seung Eel Oh ◽  
Su-Bin Joo ◽  
Ahnryul Choi ◽  
...  
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Plantar Pressure ◽  
Prediction Models ◽  
Pressure Sensors ◽  
Principal Component ◽  
Wavelet Neural Network ◽  
Human Gait ◽  
Ground Reaction Forces ◽  
Reaction Forces

In general, three-dimensional ground reaction forces (GRFs) and ground reaction moments (GRMs) that occur during human gait are measured using a force plate, which are expensive and have spatial limitations. Therefore, we proposed a prediction model for GRFs and GRMs, which only uses plantar pressure information measured from insole pressure sensors with a wavelet neural network (WNN) and principal component analysis-mutual information (PCA-MI). For this, the prediction model estimated GRFs and GRMs with three different gait speeds (slow, normal, and fast groups) and healthy/pathological gait patterns (healthy and adolescent idiopathic scoliosis (AIS) groups). Model performance was validated using correlation coefficients (r) and the normalized root mean square error (NRMSE%) and was compared to the prediction accuracy of the previous methods using the same dataset. As a result, the performance of the GRF and GRM prediction model proposed in this study (slow group: r = 0.840–0.989 and NRMSE% = 10.693–15.894%; normal group: r = 0.847–0.988 and NRMSE% = 10.920–19.216%; fast group: r = 0.823–0.953 and NRMSE% = 12.009–20.182%; healthy group: r = 0.836–0.976 and NRMSE% = 12.920–18.088%; and AIS group: r = 0.917–0.993 and NRMSE% = 7.914–15.671%) was better than that of the prediction models suggested in previous studies for every group and component (p < 0.05 or 0.01). The results indicated that the proposed model has improved performance compared to previous prediction models.

An Identification Method of Library Identifiers Based on Computer Vision

2013 ◽  
Vol 380-384 ◽  
pp. 3534-3537
Author(s):  
Li Ya Liu
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Network Model ◽  
Neural Network Model ◽  
Recognition Rate ◽  
Computation Time ◽  
Principal Component ◽  
Structural Features ◽  
Traditional Methods ◽  
Quantum Neural Network

For traditional methods of library identifies based on the two-dimensional code characteristics, these methods are time consuming and a lot of prior experience is required. A method of library identifies based on computer vision technology is proposed. In this method, a preprocessing, such as image equalization, binarization and wavelet change, is first performed on the acquired library label images. Then on the basis of the structural features of the character, the features of library identifiers are obtained by applying PCA for a principal component analysis. A quantum neural network model is designed to have an optimization analysis and calculation on the extracted features, to avoid the drawbacks which need a lot of prior knowledge for the traditional methods. At the same time, an optimization is carried out for the neural network model saving a large amount of computation time. The experimental results show that a recognition rate, up to 98.13%, is obtained by using this method. With a high recognition speed, the method can meet the actual needs to be applied in a practical system.

Fiber recognition with machine learning methods by fiber tensile fracture via acoustic emission method

2020 ◽  
Vol 90 (21-22) ◽  
pp. 2552-2563
Author(s):  
Xueyu Zhang ◽  
Binjie Xin ◽  
Yuansheng Zheng ◽  
Meiwu Shi ◽  
LanTian Lin ◽  
...  
Keyword(s):  
Acoustic Emission ◽  
Fiber Strength ◽  
Signal To Noise Ratio ◽  
Recognition Rate ◽  
Principal Component ◽  
Low Noise ◽  
Single Fiber ◽  
Tensile Fracture ◽  
Support Vector ◽  
Signal Acquisition

Energy release usually accompanies the single-fiber tensile fracture, and can be monitored using acoustic emission technology. Generated during the process of molecular structure fracture of various fibers, the acoustic emission signals can be extracted to identify different fracture types of fiber, which is especially important to the yarn formation process. In this study, a low-noise fiber-stretching device was employed to process the weak-intensity signal generated during fiber tensile fracture; in addition, the Hilbert–Huang transform (HHT), principal component analysis (PCA) and least squares support vector machine (LSSVM) algorithms were combined to identify the collected acoustic emission signals of polyester and cotton fibers. At the same time, it was verified that compared with the single-fiber breaking acoustic emission signal obtained by the electronic single-fiber strength tester, the signal acquisition device based on pneumatic components proposed in this paper can significantly improve the signal-to-noise ratio of the signal. According to the algorithm recognition results, the recognition rate of the two fibers increased from 74% to 95%.The experimental results indicate successful measurements of different fractures of two types of fiber.

scholarly journals Feedforward Chaotic Neural Network Model for Rotor Rub-Impact Fault Recognition Using Acoustic Emission Method

2018 ◽  
Vol 2018 ◽  
pp. 1-9
Author(s):  
Wei Peng ◽  
Weidong Liu ◽  
Xinmin Cheng ◽  
Liping Shi
Keyword(s):  
Neural Network ◽  
Acoustic Emission ◽  
Recognition Performance ◽  
Recognition Rate ◽  
Network Models ◽  
Normal Operation ◽  
Maximum Efficiency ◽  
Chaotic Neural Network ◽  
Bp Network ◽  
Fault Recognition

The rubbing faults caused by dynamic and static components in large rotatory machine are dangerous in manufacture process. This paper applies a feedforward chaotic neural network (FCNN) to recognize acoustic emission (AE) source in rotor rubbing and diagnose the rotor operational condition. This method adds the dynamic chaotic neurons based on logistic mapping into the multilayer perceptron (MLP) model to avoid the network falling into a local minimum, the delayed and feedback structure for maximum efficiency of recognition performance. The AE data was rotor rubbing process sampled from the test rig of rotatory machine, classification by fault degree. The experimental results indicate that the recognition rate is superior to the traditional BP network models. It is an effective method to recognize the rubbing faults for the machine normal operation.

Structural Damage Identification Based on Acceleration Response Vibration Transmissibility

2012 ◽  
Vol 236-237 ◽  
pp. 640-645
Author(s):  
Yan Song Diao ◽  
Qi Liang Zhang ◽  
Dong Mei Meng
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Structural Damage ◽  
Damage Identification ◽  
Back Propagation ◽  
Principal Component ◽  
Network Stability ◽  
Before And After ◽  
Vibration Transmissibility ◽  
Damage Characteristic

When the frequency response function (FRF) and Back-propagation (BP) neural network are used to identify the structural damage, problems such as the excitation information can not be got easily, the network is difficult to converge and the network stability is poor as the oversize input vectors. So, in this paper, two node acceleration responses of the structure under the white noise are directly used to construct the vibration transmissibility, and principal component analysis (PCA) is pursued to the amplitude of the vibration transmissibility for dimensionality reduction. The combinations of principal component variation before and after damage are used as the damage characteristic vectors, and which are input into the BP neural network for damage identification, the influences of the different degrees of noise during the damage identification are considered simultaneously. The results of numerical simulation and model experiment of offshore platform show that the method can identify the different degrees of structural damage.

Sign in / Sign up

Export Citation Format

Share Document