Crack Position Recognition of Metal Deep Drawing Parts Based on BP Neural Network

2013 ◽  
Vol 318 ◽  
pp. 108-113
Author(s):  
Ji Yong Xu ◽  
Jun Li Zhao ◽  
Bing Zhao ◽  
Ying Qing Shao
Keyword(s):  
Neural Network ◽  
Acoustic Emission ◽  
Bp Neural Network ◽  
Deep Drawing ◽  
Emission Characteristic ◽  
Characteristic Parameters ◽  
Forming Process ◽  
Crack Location ◽  
Location Identification ◽  
Crack Position

Crack position of metal drawing parts molding was analyzed by the BP neural network. First analysis of the drawing parts forming process may crack in different position. The BP neural network location identification was introduced in the basic process. 11 characteristic parameters from the drawing parts may crack position were gathered by acoustic emission signal acquisition system of deep drawing process. Then the BP neural network was designed rational, and carried out appropriate conduct to train and test. Establishing deep drawing parts of the relations between the different positions crack acoustic emission characteristic parameters and the corresponding position. Crack location was identified, in order to achieve the purpose of positioning the work piece forming process. The better method of acoustic emission location issues are resolved, metal deep drawing forming of crack location identification for basis. Provide the basis for metal drawing parts forming crack location identification.

Application of BP Neural Network to Extract AE Characteristic Parameters of the Crack in the Drawing Parts

2011 ◽  
Vol 181-182 ◽  
pp. 195-200
Author(s):  
Zhi Gao Luo ◽  
Xin He ◽  
Ai Cheng Xu ◽  
Qiang Chen
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Rise Time ◽  
Output Characteristic ◽  
Characteristic Parameters ◽  
Forming Process ◽  
Input Characteristic ◽  
Event Counter

Using BP Neural Network to optimize AE characteristic parameters of crack in drawing parts.By detecting the optimized characteristic parameters of crack, the crack in drawing parts are identified.According to the quality of drawing parts,the output of the network are crack signal and normal signal.Comparing the sensitivity of the input characteristic parameters on the output characteristic parameters,then pick the characteristic parameters which have bigger sensitivity values.Finally,the AE characteristic parameters such as Rise Time、AE Event Counter、Energy、Amplitude、Frequency Centroid can represent the signal of crack in the drawing parts better.These five characteristic parameters can identify the crack signal in the forming process of the drawing parts.

Optimization of Characteristic Parameters of Pipeline Crack Identification Based on BP Neural Network

2014 ◽  
Vol 926-930 ◽  
pp. 3442-3446 ◽  
Author(s):  
Ya Chun Dai ◽  
Dian Kai Huang ◽  
Jian Wei Xu
Keyword(s):  
Neural Network ◽  
Acoustic Emission ◽  
Bp Neural Network ◽  
Crack Identification ◽  
Characteristic Parameters ◽  
Emission Data ◽  
Bp Network ◽  
Emission Signal ◽  
Emission Parameter ◽  
Hidden Layer

Abstract. In this paper, we used three-layer BP network with a single hidden layer, and to design the structure of BP networks and set the parameters. We used the way of increasing the number of the hidden layer neurons and comparing the training errors and training number of the BP neural network to determine the number of the hidden layer neurons.Again, according to the acoustic emission data from the acquisition system and the designed BP neural network, we extract characteristic parameters of the corresponding crack acoustic emission signal,and to screen out seven acoustic emission parameter which the most represent crack characteristic by investigating each characteristic parameters' sensitivity of characterizing the crack condition, and according to the experiment data of the seven crack characteristic parameters to identify the crack state.

Fault Detection of Carbide Anvil Based on Hurst Exponent and BP Neural Network

2013 ◽  
Vol 805-806 ◽  
pp. 1881-1886 ◽  
Author(s):  
Li Han ◽  
Bin Chen ◽  
Bao Cheng Gao ◽  
Zhao Li Yan ◽  
Xiao Bin Cheng
Keyword(s):  
Neural Network ◽  
Fault Detection ◽  
Bp Neural Network ◽  
Hurst Exponent ◽  
Recognition Rate ◽  
Pulse Signal ◽  
Characteristic Parameters ◽  
Threshold Method ◽  
Fault Recognition ◽  
Bp Neural Network Model

This paper proposed a novel diagnosis algorithm based on Hurst exponent and BP neural network to detect carbide anvil fault in synthetic diamond industry. Firstly, a sort of preprocessing algorithm is proposed, which uses the sliding window and energy threshold method to separate the pulse from initial continuous signal. Then, some characteristic parameters which are based on Hurst exponent are extracted from the separated pulse signal. These characteristic parameters are used to construct fault characteristic vectors. Finally, the BP neural network model was established for fault recognition. Experimental results show that the proposed fault detection method has high recognition rate of 96.7%.

The selection of adaptive region of geomagnetic map based on PCA and GA-BP neural network

2020 ◽  
Author(s):  
Yang Chong ◽  
Dongqing Zhao ◽  
Guorui Xiao ◽  
Minzhi Xiang ◽  
Linyang Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Principal Component ◽  
Background Field ◽  
Characteristic Parameters ◽  
Positioning Accuracy ◽  
Matching Performance ◽  
Bp Neural Network Model ◽  
Selection Of

<p>The selection of adaptive region of geomagnetic map is an important factor that affects the positioning accuracy of geomagnetic navigation. An automatic recognition and classification method of adaptive region of geomagnetic background field based on Principal Component Analysis (PCA) and GA-BP neural network is proposed. Firstly, PCA is used to analyze the geomagnetic characteristic parameters, and the independent characteristic parameters containing principal components are selected. Then, the GA-BP neural network model is constructed, and the correspondence between the geomagnetic characteristic parameters and matching performance is established, so as to realize the recognition and classification of adaptive region. Finally, Simulation results show that the method is feasible and efficient, and the positioning accuracy of geomagnetic navigation is improved.</p>

A Time Series Analysis and Neural Network Based Scheme for Fault Diagnosis of Transformers

2015 ◽  
Vol 742 ◽  
pp. 412-418
Author(s):  
Jian Jun Zhang ◽  
Ye Xin Song ◽  
Yong Qu
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Fault Diagnosis ◽  
Time Series Analysis ◽  
Bp Neural Network ◽  
Back Propagation ◽  
Characteristic Parameters ◽  
Series Analysis ◽  
Diagnosis Accuracy ◽  
Artificial Neural Network Ann

This research presents a time series analysis and artificial neural network (ANN)-based scheme for fault diagnosis of power transformers, which extracts the characteristic parameters of the faults of the transformer from the results of time series analysis and bases on this basis establishes the corresponding back propagation (BP) neural network to detect the transformer operating faults. The simulation experimental results show that as compared to the related works, the proposed approach effectively integrates the superiority of time series analysis and BP neural network and thus can greatly improve the diagnosis accuracy and reliability.

Prediction of Forming Load for the Helical Gear Precision Forging by BP Neural Network

2013 ◽  
Vol 823 ◽  
pp. 170-174
Author(s):  
Wei Feng ◽  
Ji Chang Cao ◽  
Shu Ting Wu ◽  
Yang Fan Li
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Fem Simulation ◽  
Helical Gear ◽  
The Finite Element Method ◽  
Forming Process ◽  
Forming Load ◽  
Precision Forging ◽  
Metal Forming Process ◽  
Backward Propagation

Precision forging of the helical gear is a complex metal forming process under coupled effects with multi-factors. The high forming load is required to fill the teeth corner, which significantly causes failure, plastic deformation and wear of dies. The maximum forming load during precision forging helical gear is calculated by the finite element method (FEM). Combining the FEM simulation results with the artificial neural networks (ANN), backward propagation (BP) neural network is trained using the data of FEM simulation as learning sample. The trained BP neural network is validated using test samples and used to predict the maximum forming load under the different deformation conditions. The results show that the predicted results agree well with the simulated ones, the differences of prediction results exhibit low value, the predicted precision satisfy the request of industry.

Study on the Identification Method of Tool Wear State Based on BP Neural Network Optimized by Genetic Algorithm

2014 ◽  
Vol 602-605 ◽  
pp. 2458-2461 ◽  
Author(s):  
Zheng Qiang Li ◽  
Peng Nie ◽  
Shu Guo Zhao ◽  
Zhang Shun Ding
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Acoustic Emission ◽  
Tool Wear ◽  
Bp Neural Network ◽  
Solution Space ◽  
Optimal Solutions ◽  
Accurate Identification ◽  
Identification Method ◽  
Singular Spectrum

According to the un-stationary feature of the acoustic emission signals of tool wear, a tool wear state identification method based on genetic algorithm and BP neural network was proposed. The method reconstructed the acoustic emission signals and calculated the singular spectrum. And the feature vectors were reconstructed based on the singular spectrum. BP neural network was optimized by genetic algorithm. The weights of BP neural network and the thresholds were optimized originally to get more optimal solutions in solution space. Then the more optimal solutions were put into BP neural network to identify the tool wear state by the optimized classification machine. The study indicated that this method can make an accurate identification of tool wear state and should be widely used.

Hull Plate Bending Springback Prediction Based on Artificial Neural Network

2014 ◽  
Vol 988 ◽  
pp. 309-312
Author(s):  
Shao Juan Su ◽  
Yong Hu ◽  
Cheng Fang Wang ◽  
Bin Liu
Keyword(s):  
Neural Network ◽  
Bp Neural Network ◽  
Three Dimensional ◽  
Plate Bending ◽  
Forming Process ◽  
Cold Bending ◽  
Matlab Programming ◽  
Springback Prediction ◽  
Surface Plate

In the process of three-dimensional curved hull plate forming, springback caused serious influence on the forming accuracy, in order to ensure the forming quality of the asymmetric multiple pressure heads CNC bending machine of ship hull 3D surface plate, to achieve the automatic processing, it is necessary to solve the problem of springback in the hull plate forming process. It is rarely to see the research on the cold bending springback problem of middle-thickness hull plate now. To established nonlinear model of plate parameters and springback amount based on BP neural network, accurately analyzing the prediction of springback, and getting the sptringback prediction model based on the BP neural network in the Matlab programming.

The Characteristic Parameters Extraction of the Drawing Forming Cracks Based on Time-Series Analysis and ICA

2012 ◽  
Vol 239-240 ◽  
pp. 1259-1263
Author(s):  
Zhi Gao Luo ◽  
Jing Jing Zhang ◽  
Jun Li Zhao ◽  
Xu Dong Li
Keyword(s):  
Time Series ◽  
Acoustic Emission ◽  
Time Series Analysis ◽  
Deep Drawing ◽  
Characteristic Parameters ◽  
Distribution Maps ◽  
Part Quality ◽  
Series Analysis ◽  
Parameters Extraction ◽  
Ae Signals

The purpose of the study is to extract the characteristic parameters of the forming crack acoustic emission (AE) signals generated by the metal deep drawing. Time-series analysis and MATLAB were used to adopt independent component analysis (ICA) to isolate the crack AE signals and extracted the characteristic parameters of AE signals. This study isolate the crack AE signals of the drawing parts by the FastICA method based on the maximum negative entropy, the data was processed by MATLAB and the regression model of the various decomposition established by time-series analysis to extract the characteristic parameters of the crack AE signals. The results suggested that this method can isolate the crack AE signals of the deep drawing successfully and can extract the characteristic parameters and distribution maps of the crack AE signals of the metal drawing parts effectively, provide a favorable basis for the judgment of the molding part quality.

Sign in / Sign up

Export Citation Format

Share Document