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

A Method for Predicting the Strength of High Performance Concrete Based on Memristor-Gradient Descent Neural Network

A high-performance concrete, gradient descent method, applied in neural learning methods, biological neural network models, instruments, etc., to achieve the effect of high strength prediction accuracy and low consumption

Active Publication Date: 2021-06-11
HOHAI UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Fortunately, the advent of memristors offers the possibility to solve this problem

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 for Predicting the Strength of High Performance Concrete Based on Memristor-Gradient Descent Neural Network
  • A Method for Predicting the Strength of High Performance Concrete Based on Memristor-Gradient Descent Neural Network
  • A Method for Predicting the Strength of High Performance Concrete Based on Memristor-Gradient Descent Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0086] The present invention excavates 104 groups from the literature (see literature C.H.Lim, Y.S.Yoon, J.H.Kim. Genetic algorithm in mixproportioning of high-performance concrete [J]. Cement and Concrete Research, 2004, 34 (3): 409-420.) Data, 92 groups are randomly selected as training samples, and the remaining 12 groups are used as prediction samples. The 104 groups of specific sample data values ​​are shown in Table 1.

[0087] Table 1 sample data

[0088]

[0089]

[0090]

[0091]

[0092] (1) In order to train the neural network established with the memristor, and considering the need to test the learned neural network, randomly select 12 groups (2, 10, 17, 30, 40, 48, 55, 63 , 75, 83, 93, 101 groups) as test data, and the remaining 92 data as training samples. For convenience, the screened test data are numbered 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, and 12 in sequence.

[0093] (2) Establish as figure 2 The memristor-gradient descent neural network show...

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 high-performance concrete strength prediction method based on memristor-gradient descent method neural network, including obtaining high-performance concrete experimental data, establishing a database, and obtaining training samples and prediction samples; combining memristor and traditional gradient A descent learning algorithm is used to establish a memristor-gradient descent method neural network; the obtained training samples are used to train the established memristor-gradient descent method neural network to obtain a trained memristor-gradient descent method neural network; The prediction samples are input into the trained memristor-gradient descent method neural network to predict the strength of high-performance concrete; output the strength value of high-performance concrete to be predicted, and perform performance evaluation on the prediction results. The method of the invention can accurately predict the strength of the high-performance concrete, meets the requirements of construction projects, and can be applied to the prediction of the strength of the high-performance concrete in actual projects.

Description

technical field [0001] The invention belongs to the field of high-performance concrete strength prediction, and in particular relates to a high-performance concrete strength prediction method based on a memristor-gradient descent method neural network. Background technique [0002] As one of the most widely used and consumed modern engineering structure building materials in the world, concrete plays an important role in the process of economic development and social progress. High-performance concrete is a building material with many special properties such as high workability, high strength, high volume stability and high durability. In the past ten years, high-performance concrete has been widely used in a large number of large-scale projects such as nuclear reactors, cross-sea bridges, nuclear waste containers, and submarine tunnels. Strength is an important mechanical property to measure the quality of high-performance concrete, how to accurately predict it has become ...

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): G16C60/00G06N3/08
CPCG06N3/084G16C60/00
Inventor 邱林梁英杰
Owner HOHAI UNIV
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