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

Optimization method of pso drilling parameters based on neural network

A neural network and drilling parameter technology, applied in the field of drilling engineering, can solve problems such as uncertainty, random non-linearity, great practicability and limitations, and extremely complicated calculation process, and achieve strong anti-interference, stable operation, The effect of efficient search capabilities

Active Publication Date: 2022-04-05
BC P INC CHINA NAT PETROLEUM CORP +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the complexity of the drilling process, the drilling parameters are not only affected by multiple factors, but also there is correlation coupling between each parameter, which presents great uncertainty, randomness and nonlinearity. Optimizing the calculation by establishing a conventional mathematical model not only The calculation process is extremely complicated, and the model often ignores some actual conditions, resulting in the model being inaccurate, practicable and limited

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
  • Optimization method of pso drilling parameters based on neural network
  • Optimization method of pso drilling parameters based on neural network
  • Optimization method of pso drilling parameters based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0031] 1. Data collection and processing

[0032] With the development of automation and digital technology, many advanced real-time data acquisition and detection platforms have been introduced into the drilling process, accumulating massive drilling data. These data have the characteristics of huge quantity, rich sources, non-uniform data types, and high data redundancy. According to the known experience, the factors affecting the drilling efficiency are complicated. According to the data, the common target parameters affecting the ROP are: well depth, layer, suspension weight, weight on bit, torque, drilling time, displacement, pump pressure, Speed, drilling fluid density, drilling fluid viscosity, azimuth, well deviation, vertical depth, design well depth, etc. Since the designed vertical depth, designed well depth, azimuth and well deviation have been determined before drilling, they can be regarded as static data and not analyzed. According to the analysis, determining...

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 the technical field of drilling engineering, and in particular relates to a neural network-based PSO drilling parameter optimization method, which is characterized in that it comprises the following steps: (1) inputting the current design parameters into the drilling parameter optimization system database; (2) inquiring whether there is The historical data of adjacent wells of the current well, the data is transmitted to the system data analysis and processing module, the preprocessed data is input into the neural network for model training, and the pre-drilling parameter prediction model is output; (3) after drilling, the current data parameters while drilling are obtained synchronously , calculate the current ROP, update the model, and compare the ROP under the same formation lithology and hole size in the model with the current ROP. The present invention collects original parameter signals and processes them through software to analyze the information data of the entire drilling process, and then optimizes the key data, and realizes real-time and dynamic intelligent optimization and system synthesis of parameters through the integration of multiple technologies in the whole process of drilling parameter optimization. analyze.

Description

technical field [0001] The invention belongs to the technical field of drilling engineering, in particular to a neural network-based PSO drilling parameter optimization method. Background technique [0002] Drilling engineering is a key link in the field of oil and gas development, and one of the links with the largest economic investment and the highest risk in the exploration and development process. The efficiency and cost of the drilling process directly reflect the drilling level, which is of great significance to subsequent oil and gas production and operations. Due to the comprehensive influence of geological conditions, mechanical properties of drilling rigs, drilling fluid properties, bit types and other factors, the drilling process presents great uncertainty. For a long time, how to improve drilling efficiency, shorten drilling cycle and save development cost under the influence of complex factors has become an engineering difficulty and hot spot in drilling work...

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): G06F30/25G06F30/27G06N3/00G06N3/04G06Q10/04G06Q50/02
CPCG06N3/006G06Q10/04G06Q50/02G06N3/045
Inventor 郭修成夏泊洢李鹏娜白冬青李永钊匡涛常杨周超张青钟健邓旭庄纯才李果王西贵宋成坤池丽军解志亮李帅岐
Owner BC P INC CHINA NAT PETROLEUM CORP
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