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

Online monitoring method for mechanical properties of 3D printing concrete based on neural network

A 3D printing and neural network technology, applied in the direction of measuring devices, scientific instruments, instruments, etc., can solve the problems of difficult monitoring and control of the mechanical properties of 3D printed concrete printed products, increase the amount of testing labor, etc., to save manpower and simplify the testing process Effect

Pending Publication Date: 2021-07-02
SHANGHAI CONSTR BUILDING MATERIALS TECH GRP CO LTD +1
View PDF4 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Ordinary pouring concrete specimens only need to test the mechanical properties of any one direction, while the mechanical properties of 3D printed concrete are different in three directions in three-dimensional space, so to fully test the mechanical properties of a 3D printed concrete specimen, at least Detect three sets of test pieces, which undoubtedly increases the amount of testing labor
[0003] The anisotropy of 3D printed concrete is affected by the printing material, construction process and construction environment. During a printing process, some of these influencing factors are constant, such as the length and diameter of the fibers in the printing material, the outlet of the printing nozzle Some of the shape and diameter will change with the printing process, such as the time elapsed after the printing material is mixed with water, extrusion pressure, ambient temperature, etc. Due to these complex influencing factors, it is difficult to rely on a specific formula to This relationship is expressed, which makes it difficult to monitor and control the mechanical properties of 3D printed concrete printed products.

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
  • Online monitoring method for mechanical properties of 3D printing concrete based on neural network
  • Online monitoring method for mechanical properties of 3D printing concrete based on neural network
  • Online monitoring method for mechanical properties of 3D printing concrete based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] This embodiment provides a neural network-based online monitoring method for the mechanical properties of 3D printed concrete, which performs online monitoring of the mechanical properties of 3D printed concrete during the printing process, including the following steps:

[0054] Step 1. The neural network model is trained and matured with the performance parameters of the printing material, system printing parameters and environmental parameters as the training data, and the mechanical properties of the 3D printed concrete as the output value. The input data of the neural network model includes:

[0055] Printing material performance parameters: exit yield stress, exit viscosity, exit fluidity, fiber content, fiber length, fiber diameter, fiber elastic modulus, material exit time, mechanical properties of pouring specimens, mechanical properties of 3D printed concrete ;

[0056] System printing parameters: printing layer height, nozzle outlet size, nozzle outlet shape...

Embodiment 2

[0067] This embodiment provides a neural network-based online monitoring method for the mechanical properties of 3D printed concrete, which is used to predict the mechanical properties of 3D printed concrete before printing, including the following steps:

[0068] Step 1. The neural network model is matured by using the performance parameters of the printing material and the printing parameters of the system as the training data, and the mechanical properties of the 3D printed concrete as the output value. The input data of the neural network model includes:

[0069] Printing material performance parameters: exit yield stress, exit viscosity, exit fluidity, fiber content, fiber length, fiber diameter, fiber elastic modulus, mechanical properties of pouring specimens, mechanical properties of 3D printed concrete;

[0070] System printing parameters: printing layer height, nozzle outlet size, nozzle outlet shape, overlapping rate of adjacent printing strips in the same layer, si...

Embodiment 3

[0074] This embodiment provides a neural network-based online monitoring method for the mechanical properties of 3D printed concrete, which is used to calculate the mechanical properties of 3D printed concrete after printing, including the following steps:

[0075] Step 1. The neural network model is trained and matured with the performance parameters of the printing material, system printing parameters and environmental parameters as the training data, and the mechanical properties of the 3D printed concrete as the output value.

[0076] Step 2. Transfer the actual printed constant eigenvalues, time-varying eigenvalues, eigenvalues ​​extracted from the printing path, and representative values ​​of changing eigenvalues ​​collected by the sensor to the mature neural network model trained in step 1 to calculate the finished product of 3D printed concrete Mechanical properties, draw the distribution map of mechanical properties of 3D printed concrete printed products.

[0077] Th...

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 an online monitoring method for mechanical properties of 3D printing concrete based on a neural network. The method comprises the following steps: step 1, neural network model training: training the neural network to be mature by taking the mechanical properties of the 3D printing concrete as output values; step 2, model input feature collection: inputting a constant feature value and collecting a change feature value in real time; step 3, monitoring mechanical properties on line: calculating the mechanical properties of the 3D printing concrete printing finished product through a mature neural network model based on the collected feature data; and step 4, monitoring result reaction: evaluating the mechanical property state of the 3D printing concrete printing finished product based on the monitoring result, drawing a mechanical property distribution diagram of the product, formulating an adjustment scheme and realizing man-machine interaction. According to the method, simulation and prediction of the mechanical property distribution of the printed finished product before 3D printing can be achieved, the mechanical property of the concrete 3D printed finished product is monitored and evaluated in the 3D printing process, the mechanical property distribution diagram of the product is drawn, and the method can be used for optimizing a product printing path and guiding use of the product.

Description

technical field [0001] The invention belongs to the technical field of 3D printing concrete, and in particular relates to an online monitoring method for the mechanical properties of 3D printing concrete based on a neural network. Background technique [0002] 3D printing concrete technology is a construction technology that extrudes strips by moving the extrusion head according to the set three-dimensional path, and superimposes the construction of the whole component layer by layer. Since the 3D printing concrete technology is stacked and formed along with the extrusion direction of the nozzle, the construction method, The physical structure of 3D printed concrete is directional, which further makes the mechanical properties, durability and microstructure of 3D printed concrete printed products directional, that is, anisotropic, which brings difficulties to the performance testing of 3D printed concrete. . Ordinary pouring concrete specimens only need to test the mechanic...

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 Applications(China)
IPC IPC(8): G01N33/38
CPCG01N33/383
Inventor 董赛阳朱敏涛吴杰朱峰卞成辉
Owner SHANGHAI CONSTR BUILDING MATERIALS TECH GRP CO LTD
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