A Method of Determining Mechanical Indexes of Double Bridge Static CPT Data Based on BP Neural Network

A technology of BP neural network and static penetration testing, which is applied in the fields of foundation structure test, on-site foundation soil survey, foundation structure engineering, etc., can solve the problems of lack of theory and method, difficulty of wide application, and limited scope of application, etc. Achieve the effects of reducing the number of drilling holes, ensuring accuracy and shortening the survey cycle

Active Publication Date: 2017-07-11
WUHAN SURVEYING GEOTECHN RES INST OF MCC
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, scholars at home and abroad have established a large number of regression equations or empirical formulas through the statistical analysis of the static penetration parameters and soil mechanical indicators, but these regression equations are subject to the static classification and identification of soil properties, the formation environment and regression analysis. The influence of the reliability of force penetration parameters is difficult to be widely used in engineering practice; some existing local codes and engineering geological manuals mainly list the empirical value relationship between single bridge static sounding data and foundation bearing capacity, and there is no specific Theories and methods, the scope of application is not wide

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 Method of Determining Mechanical Indexes of Double Bridge Static CPT Data Based on BP Neural Network
  • A Method of Determining Mechanical Indexes of Double Bridge Static CPT Data Based on BP Neural Network
  • A Method of Determining Mechanical Indexes of Double Bridge Static CPT Data Based on BP Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The following describes the implementation of the present invention by specific examples, please refer to figure 1 , a BP neural network-based method for determining the mechanical indexes of static penetration data of twin bridges:

[0027] ①. Collection and arrangement of Shuangqiao static sounding data and soil mechanical indicators: By collecting and arranging engineering geological survey reports and geotechnical test results in typical geological regions in the Yangtze River Delta region, the Shuangqiao static sounding data and The mechanical index of soil, a total of 89 groups, including Q 4 al Clay 28 groups, Q 4 al Silty clay 22 groups, Q 4 al Silt 27 groups, Q 4 al 12 groups of silt;

[0028] ②. Establish the BP neural network prediction model for the determination of the mechanical indicators of the double bridge static penetration penetration: Based on the BP neural network algorithm, use the data information in step ① to establish a prediction model...

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

Disclosed is a BP (back propagation) neural network based mechanic index determining method for twin-bridge static sounding data. The BP neural network based mechanic index determining method includes steps of firstly, collecting and ordering the twin-bridge static sounding data and mechanic indexes of soil; secondly, establishing a twin-bridge static sounding mechanic index determination BP neural network prediction model; thirdly, training the twin-bridge static sounding mechanic index determination BP neural network prediction model; fourthly, predicting the mechanic indexes of the soil by applying the trained twin-bridge static sounding mechanic index determination BP neural network prediction model. The BP neural network based mechanic index determining method for twin-bridge static sounding data has the advantages that a reliable theoretical method for determining the mechanic indexes of the soil layer through the static sounding data is provided; powerful support is provided for reliability of the mechanic index determination BP neural network prediction model by utilizing massive twin-bridge static sounding data and the mechanic indexes of the soil, and accuracy of the prediction results is guaranteed; the number of drilling holes during reconnaissance is greatly decreased, reconnaissance period is shortened, reconnaissance cost is saved, and engineering reconnaissance quality can be improved.

Description

technical field [0001] The invention relates to the application research field of in-situ testing of geotechnical engineering, in particular to a method for determining the mechanical index of the double-bridge static penetration testing data based on BP neural network. Background technique [0002] The traditional survey method is mainly based on drilling, and the static penetration test is used as an auxiliary measure to improve and improve the survey accuracy, while the new survey method emphasizes that the survey should be based on the static penetration test and targeted drilling, Indoor test and other in-situ tests, it also pays attention to the role of drilling and indoor test. This transformation of the survey method greatly reduces the number of drilling holes, shortens the survey cycle, saves survey costs, and improves the quality of survey. Using the static penetration test technology to replace the traditional survey method requires deep mining and full utilizati...

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): E02D33/00E02D1/00
Inventor 蔡清程江涛万凯军于沉香陈定安黄静
Owner WUHAN SURVEYING GEOTECHN RES INST OF MCC
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