Machine learning-based asphalt dynamic viscoelastic characteristic prediction method

A viscoelastic property and machine learning technology, applied in the field of asphalt dynamic viscoelastic property prediction based on machine learning, can solve the problems of complex macro and micro properties of asphalt, difficult to establish correlation, etc., and achieve the effect of enriching evaluation methods.

Active Publication Date: 2021-10-22
HARBIN INST OF TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problem that the complex macro and micro properties of asphalt make it difficult to establish correlation

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
  • Machine learning-based asphalt dynamic viscoelastic characteristic prediction method
  • Machine learning-based asphalt dynamic viscoelastic characteristic prediction method
  • Machine learning-based asphalt dynamic viscoelastic characteristic prediction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0040] This embodiment provides a method for predicting dynamic viscoelastic properties of asphalt based on machine learning, such as figure 1 As shown, the specific implementation steps are as follows:

[0041]Step 1: Use the DHR-2 dynamic shear rheometer to scan the frequency of 50 kinds of asphalt samples in Table 1, measure the dynamic modulus of the material as a function of frequency, and establish a reference based on the time-temperature equivalent principle and the CAM model theory The main curve of dynamic modulus at a temperature of 20°C; the C, H, N, and S element data of asphalt were collected by Vario EL Cube elemental analyzer, and the O element data was obtained by difference method; the infrared data of asphalt was collected by Nicolet iS5 infrared spectrometer .

[0042] Table 1 Summary of Asphalt Samples

[0043]

[0044]

[0045] Note: L stands for low grade in the above asphalt numbers, B stands for binder, M stands for modified, and A stands for a...

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 machine learning-based asphalt dynamic viscoelastic characteristic prediction method, which comprises the following steps of: testing the dynamic viscoelastic characteristic of a sample by adopting a dynamic shear rheometer, and testing the microscopic composition structure of the sample by adopting an element analyzer and an infrared spectrometer; carrying out feature extraction on the microcosmic composition structure parameters by using a principal component analysis method; determining the mapping relation between the dynamic viscoelastic characteristic parameters and the microscopic composition structure parameters through adoption of a distance correlation coefficient method; and establishing an asphalt dynamic viscoelastic characteristic prediction model based on a support vector machine learning algorithm. The method disclosed by the invention reveals the corresponding relationship between the dynamic viscoelastic characteristic and the microscopic composition structure of the asphalt material, is beneficial to quickly obtaining the dynamic viscoelastic mechanical response of the asphalt, provides basic theoretical support for design and production of the asphalt material, and has positive significance for guiding on-demand design of the asphalt and other materials.

Description

technical field [0001] The invention belongs to the field of performance prediction of asphalt materials, and relates to a method for predicting dynamic viscoelastic properties of asphalt based on machine learning. Background technique [0002] Viscoelastic properties are the essential properties of asphalt materials, and their mechanical behavior has a direct impact on road performance. The use of viscoelasticity theory to study and analyze the mechanical response of asphalt provides positive guidance for solving the problems existing in the evaluation and use of asphalt and asphalt mixture. refer to. The dynamic modulus is one of the key characteristics that reflect the dynamic viscoelastic characteristics. This characteristic is closely related to the permanent deformation of the pavement, cracks, rutting and other diseases. It is also the key to the transformation of the asphalt pavement structural design system from static to dynamic. The microscopic composition of asp...

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): G01N11/00G01N21/35G06K9/62G06N20/00
CPCG01N11/00G01N21/35G06N20/00G06F18/214
Inventor 单丽岩王亚杰杨金龙王建杰
Owner HARBIN INST OF TECH
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