Unlock instant, AI-driven research and patent intelligence for your innovation.

Multivariate Drilling Time Series Prediction Method Based on Mixed Leakage Integral Crj Network

A sequence prediction and drilling time technology, which is applied in drilling measurement, drilling equipment, neural learning methods, etc., can solve problems such as difficult to meet complex multivariate time series prediction tasks, weak model memory ability, etc., to improve dynamic characteristics and prediction performance Effect

Active Publication Date: 2021-01-12
BEIJING UNIV OF CHEM TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional CRJ network uses a single hyperbolic tangent neuron, the model memory ability is weak, and it is difficult to meet the requirements of complex multivariate time series prediction tasks

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
  • Multivariate Drilling Time Series Prediction Method Based on Mixed Leakage Integral Crj Network
  • Multivariate Drilling Time Series Prediction Method Based on Mixed Leakage Integral Crj Network
  • Multivariate Drilling Time Series Prediction Method Based on Mixed Leakage Integral Crj Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047]In this example, the leaky integral neuron with strong memory and the traditional hyperbolic tangent neuron are used to form a mixed leaky integral neuron model. After studying the combination of the mixed neuron model and the CRJ network structure, a hybrid leaky integral is proposed. CRJ network, also known as LI-HCRJ network. In the face of high-dimensional time series forecasting tasks, the forecasting accuracy not only depends on the network model, but also depends on the input information of the network model. This embodiment uses the gray relational algorithm as the processing algorithm for network input information. Different from the general relational algorithm, the gray relational analysis method is to quantitatively analyze the dynamic development process of the system to examine the degree of correlation between the variables of the system. Its core theory is According to the degree of similarity between curves to judge the degree of correlation between fact...

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 multivariate drilling time series prediction method based on a mixed leakage integral CRJ network. Firstly, time series data samples are obtained and the data samples are preprocessed; secondly, a gray correlation algorithm is used to select highly correlated variables of the prediction variables as network input. , and then optimize the traditional CRJ network model, use the hybrid leaky integral neuron with stronger memory to combine with the CRJ network, improve the dynamic characteristics and prediction performance of the network, and obtain the best combination method and leakage rate through comparative experiments , based on the experimental results to build a mixed leaky integral CRJ network model, and finally use the trained mixed leaky integral CRJ network to predict the key variables in the drilling process in time series, and understand the changes of parameters in advance through the prediction results, and take corresponding adjustment strategies in advance. So as to ensure safe and efficient drilling engineering.

Description

technical field [0001] The invention relates to the technical field of drilling time series prediction, in particular to a multivariate drilling time series prediction method based on mixed leakage integral CRJ network. Background technique [0002] Complex systems widely exist in many fields such as meteorology, hydrology, industry, and information science. They have multi-variable dynamic evolution behaviors and multi-level structures, and most of them present complex characteristics. It is usually difficult to obtain accurate analytical models. Therefore, it is of great practical significance to use data-driven technology to predict the multivariate complex time series observed in the system and analyze the evolution mechanism of the system. [0003] In the establishment of time series forecasting models, neural network models can approximate nonlinear functions with arbitrary precision, and only need less statistical knowledge to obtain ideal forecasting results, so they...

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): G06F30/27E21B45/00G06N3/08G06F119/14
CPCE21B45/00G06F30/20
Inventor 李宏光李金策王永健
Owner BEIJING UNIV OF CHEM TECH