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

Ya Chun Dai; Dian Kai Huang; Jian Wei Xu

doi:10.4028/www.scientific.net/AMR.926-930.3442

Paper Titles

Extract Soccer Video Highlights with Modified CRF
p.3426

Football Extraction Method Based on Image Segmentation Algorithm
p.3430

Image Processing Techniques and Application of Bilateral Filter Keeping Margin Random Noise Suppression
p.3434

Application of Improved Failure Modes and Effects Analysis in Product Reliability Analysis
p.3438

Optimization of Characteristic Parameters of Pipeline Crack Identification Based on BP Neural Network
p.3442

The Circle-End-Face Centering Device Based on Image Processing
p.3447

Interest Point Detection Based on Monogenic Signal Theory
p.3451

Mutil-Conditions Impress Nonsingular Dimensional Cellular Automaton on Traffic Flow
p.3455

Research and Application of the Methods for Irregular Graphics Recognition Based on VB
p.3459

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 926-930Optimization of Characteristic Parameters of...

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

Abstract:

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.