Method for reproducing two-dimensional defect of petroleum pipeline PSO-BP (Particle Swarm Optimization-Back-Propagation) neural network

A PSO-BP, neural network technology, applied in the field of pipeline defect detection, can solve problems such as slow convergence speed, oscillation effect, large amount of calculation, etc., to achieve the effect of improving convergence accuracy

Inactive Publication Date: 2012-02-29
HARBIN ENG UNIV
View PDF1 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The inverse problem is very complicated, and a commonly used method to solve the inverse problem is to use an iterative method, but this method is computationally intensive
[0003] BP neural network has the ability to approximate any nonlinear mapping through learning, but the standard BP neural network has the disadvantages of easy to fall into local minimum, slow convergence speed and cause oscillation effect.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for reproducing two-dimensional defect of petroleum pipeline PSO-BP (Particle Swarm Optimization-Back-Propagation) neural network
  • Method for reproducing two-dimensional defect of petroleum pipeline PSO-BP (Particle Swarm Optimization-Back-Propagation) neural network
  • Method for reproducing two-dimensional defect of petroleum pipeline PSO-BP (Particle Swarm Optimization-Back-Propagation) neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0045] The process of predicting the geometric parameters of defects according to the magnetic flux leakage signals generated by defects is essentially a process of establishing the mapping relationship between magnetic flux leakage signals and geometric parameters of defects.

[0046] (1) The measured value of the actual pipeline defect is used as the sample set for network training, and the acquired signal is used as the experimental data for defect reconstruction after preprocessing such as denoising. The magnetic flux leakage signal is used as the input of the PSO-BP neural network, and the defect contour (length and depth) is used as the output. There are 90 sets of sample data, the first 80 sets are used as training data, the last 10 sets are used as test data, and each set of data has 120 sampling points.

[0047] (2) Initialize the parameters of the particle swarm optimization algorithm, set the population size, inertia weight w, and learning factor c 1 c 2 , the num...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention aims at providing a method for reproducing a two-dimensional defect of a petroleum pipeline PSO-BP (Particle Swarm Optimization-Back-Propagation) neural network. Actually measured pipeline magnetic flux leakage data and pipeline defect data are used as experimental data of defect reconfiguration. The method comprises the steps of: with a magnetic flux leakage signal as input and a defect outline as outlet, setting a particle initial parameter, randomly initializing an initial position and an initial speed of each particle, calculating a particle fitness function numerical value , determining a past best value pbest of each particle and a global best value gbest of the whole particle swarm, updating the position and the speed of each particle, judging whether reaching the maximum iteration time or preset precision, if meeting the weight and the threshold of outputting a neutral network; and otherwise, re-comparing. The neutral network after the weight and the threshold are optimized by using a particle swarm algorithm is used for reproducing the two-dimensional defect of the pipeline and also reproducing a defect outline of the pipeline. According to the invention, the defect that the BP algorithm is easy to fall into a local minimum value can be effectively solved, and the convergence precision is improved, thus the defect of the pipeline is accurately reproduced.

Description

technical field [0001] The invention relates to a method for pipeline defect detection. Background technique [0002] With the rapid development of my country's oil and natural gas industry, pipeline transportation has become the main way of my country's land oil and gas transportation. However, with the increase of pipeline age, construction defects, man-made damage and corrosion, pipeline accidents occur frequently, which not only cause major economic losses, but also seriously pollute the environment and even endanger the lives of production personnel. Magnetic flux leakage detection technology is the most widely used method in pipeline defect detection. It uses ultrasonic, magnetic flux leakage, ray and other flaw detection principles. Without affecting normal production, through the intelligent detector walking in the pipeline, oil and gas Defects of the pipe wall or coating: such as deformation, damage, corrosion, perforation, weight loss of the pipe wall and thicknes...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/08
Inventor 刘胜傅荟璇王宇超郑秀丽陈明杰
Owner HARBIN ENG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products