A Drilling Accident Early Warning Method Based on Time Recurrent Neural Network

A recursive neural network and accident technology, applied in neural learning methods, biological neural network models, predictions, etc., can solve the problem of inaccurate and comprehensive prediction of drilling accidents, achieve powerful parallel processing capabilities and practicality, and improve accuracy And timeliness, real-time requirements of high effect

Active Publication Date: 2022-04-29
SOUTHWEST PETROLEUM UNIV +1
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to address the above-mentioned deficiencies in the prior art, to provide a drilling accident early warning method based on time recursive neural network, to solve the problem that the existing drilling early warning method is not accurate and comprehensive in the prediction of drilling accidents

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
  • A Drilling Accident Early Warning Method Based on Time Recurrent Neural Network
  • A Drilling Accident Early Warning Method Based on Time Recurrent Neural Network
  • A Drilling Accident Early Warning Method Based on Time Recurrent Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The specific embodiments of the present invention are described below so that those skilled in the art can understand the present invention, but it should be clear that the present invention is not limited to the scope of the specific embodiments. For those of ordinary skill in the art, as long as various changes Within the spirit and scope of the present invention defined and determined by the appended claims, these changes are obvious, and all inventions and creations using the concept of the present invention are included in the protection list.

[0032] According to one embodiment of the present application, the method for early warning of drilling accidents based on time recurrent neural network of this program includes:

[0033] S1. First, use the autoregressive model analysis method to predict the drilling characteristic value at a certain moment, and measure the difference between the predicted characteristic value and the real drilling data at that moment, there...

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 discloses a drilling accident early warning method based on time recursive neural network. In the first step, the autoregressive model analysis method is used to predict the drilling eigenvalues ​​at a certain moment, and the difference between the predicted eigenvalues ​​and the real drilling data at that moment is measured, thereby obtaining the accident candidate set. Then use expert knowledge to judge the authenticity of the accidents in the accident candidate set, and classify the types of accidents; finally obtain the marked drilling time series data; on the premise of obtaining the marked data, train a supervised model, the second step, Based on deep learning, construct a temporal recurrent neural network model. First, randomly select part of the marked time series data as the training set. The specific input is the combination of each feature and the selection of the time window. Then the model is trained, and finally the probability of accident occurrence and the type of accident occurrence after one minute of output are predicted.

Description

technical field [0001] The invention belongs to the technical field of drilling early warning models, in particular to a drilling accident early warning method based on a time recursive neural network. Background technique [0002] In the drilling construction process, the possibility of engineering accidents exists at any time, and the occurrence of accidents will cause huge losses of funds and huge waste of time. Giving a certain degree of warning before the occurrence of engineering accidents is of great significance for preventing the occurrence of accidents, controlling the development of accidents, and minimizing losses. For a long time, safe drilling and optimized drilling have been one of the important research topics of drilling engineering. According to the parameter changes in the drilling process, the drilling data is analyzed and processed, and the accident warning model is established to predict and diagnose the accident phenomenon, and to know various possible...

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 Patents(China)
IPC IPC(8): G06Q10/04G06N3/08
CPCG06N3/08G06Q10/04
Inventor 蒋裕强陈雁黄嘉鑫文敏葛忆李平朱宇谢静程超付永红钟学燕蒋婵蒋增政钟原郑津
Owner SOUTHWEST PETROLEUM 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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap