Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Submarine pipeline corrosion grade classification method based on DBN and SVM

A technology for hierarchical classification and submarine pipelines, applied in the field of hierarchical classification, which can solve the problems of limited number of samples and unsatisfactory performance.

Inactive Publication Date: 2021-01-05
TIANJIN UNIV OF SCI & TECH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Traditional statistics research is the asymptotic theory when the number of samples tends to infinity, but in practical problems The number of samples is often limited. Therefore, some theoretically excellent learning methods perform unsatisfactory in practice.

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
  • Submarine pipeline corrosion grade classification method based on DBN and SVM
  • Submarine pipeline corrosion grade classification method based on DBN and SVM
  • Submarine pipeline corrosion grade classification method based on DBN and SVM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Step 1: Perform missing value data processing and invalid data processing, and divide the training set and test set;

[0023] In this example, the data used is the corrosion data of a certain pipeline in an oil field, with a total of 4015 valid data. Among them, some data are missing, and some are invalid. For these missing data, the invalid data is replaced by the mean value. The first 2018 pieces of data are selected as the training set for model training, and the rest of the data are used as the test set to verify the feasibility of the model and classify the pipeline corrosion level.

[0024] Step 2: Read the pipeline data through pandas, and convert the read data into a matrix for easy training;

[0025] For the original data read with pandas, the training set and test set are converted into matrices that can be used for input. Since the data size of each dimension varies greatly, it is necessary to normalize the data to reduce the error and improve the classific...

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 belongs to corrosion grade classification in the field of submarine pipelines, and relates to a submarine pipeline corrosion grade classification method based on DBN and SVM. The methodis mainly characterized in that a DBN and an SVM are used at the same time to adopt a processing mode of a pipeline pipeline mechanism, and a plurality of algorithm model algorithms can be connected in series through pipeline. Firstly, dbn is used for processing data, representative features are extracted from a data set, and the features serve as an important basis in the subsequent classification process; the specific unsupervised pre-training of the DBN enables the transmission weight of the network to be adjusted to a proper initial value. Then the SVM classifier is used to classify the pipeline corrosion levels. According to the pipeline corrosion grade classification, workers can know the corrosion condition of the pipeline, the pipeline is reasonably maintained, and unnecessary losses are reduced.

Description

technical field [0001] The invention belongs to the classification of corrosion grades in the field of submarine pipelines, and relates to a corrosion grade classification method for submarine pipelines based on DBN and SVM. Background technique [0002] After 30 years of exploration and development, my country's offshore oil has become a very important part of my country's petroleum industry. The submarine pipeline between offshore oil and gas fields and land terminals is the lifeline of offshore oil and gas transportation, and plays an important role in ensuring the safety and stability of my country's petroleum energy. At the same time, the construction of submarine pipelines has also reached its peak. As of the end of 2016, the total mileage of long-distance oil and gas pipelines in China was about 126,000 kilometers, including about 74,300 kilometers of natural gas pipelines, about 26,200 kilometers of crude oil pipelines, and about 26,200 kilometers of refined oil pipel...

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): G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/047G06N3/045G06F18/2411
Inventor 刘颖王立凡
Owner TIANJIN UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com