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

Steel mechanical performance prediction method based on support vector machine quantile regression

A technique of quantile regression and support vector machine, which is applied in specific mathematical models, computer materials science, kernel methods, etc., and can solve problems such as factor nonlinearity that cannot simultaneously consider data heterogeneity modeling.

Pending Publication Date: 2020-07-17
WUHAN UNIV OF SCI & TECH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention is carried out in order to solve the above-mentioned problems. Aiming at the problem that the heterogeneity of data and the non-linearity between the factors of modeling cannot be considered at the same time in the current mechanical performance prediction, a quantile regression based on support vector machine is provided. Prediction method of mechanical properties of steel

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
  • Steel mechanical performance prediction method based on support vector machine quantile regression
  • Steel mechanical performance prediction method based on support vector machine quantile regression
  • Steel mechanical performance prediction method based on support vector machine quantile regression

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0353] Based on the LASSO variable selection support vector machine quantile regression to predict the mechanical properties of steel, the specific implementation steps are as follows:

[0354] 1. Use formula (1) to standardize the original collected hot rolling data, and part of the standardized data is shown in Table 1

[0355] Table 1. Some data structures

[0356]

[0357]

[0358] 2. Select the appropriate kernel function

[0359] Divide standardized data into training set and test set, based on (25) formula, adopt described training set data to carry out backtesting to the training model that has been substituted into different kernel functions, select the kernel function with the best fitting effect according to the result of backtesting, As a suitable kernel function, the final prediction model is obtained. The kernel function selected in this embodiment is a Gaussian kernel function.

[0360]

[0361] 3. Determine the impact factor and adjust parameters an...

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 provides a steel mechanical performance prediction method based on support vector machine quantile regression. The method includes following steps: data processing, model estimation value acquisition, variable selection, parameter acquisition, and model determination. The invention provides the steel mechanical performance prediction method and device based on support vector machinequantile regression and a storage medium, which are sued for solving the problem that in the mechanical performance prediction, the heterogeneity of data and the nonlinearity of factors in modeling cannot be considered at the same time. The invention provides the steel mechanical performance prediction method based on support vector machine quantile regression.

Description

technical field [0001] The invention relates to the field of prediction of mechanical properties of hot-rolled products of microalloy steel, in particular to a method for predicting the mechanical properties of steel materials based on support vector machine quantile regression, especially the tensile strength prediction method of hot-rolled products. Background technique [0002] In recent years, due to the wide application of steel in many industries such as construction and bridges, the demand for steel products has shown a trend of rapid growth; people have increasingly stringent requirements for the quality of steel products, not only requiring the mechanical properties of steel to meet standards, but also requiring steel to have Good surface quality. Metallurgists have been committed to reducing metallurgical costs and improving the quality of steel products, so it is necessary to predict the properties of steel before smelting; however, the performance of steel produc...

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
IPC IPC(8): G16C60/00G06N7/00G06N20/10G01N33/20
CPCG16C60/00G06N20/10G01N33/20G06N7/01
Inventor 何晓霞张信
Owner WUHAN 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