Blunt device injury craniocerebral maximum principal strain prediction method and system based on convolutional neural network model

A technology of convolutional neural network and prediction method, which is applied in the field of rapid quantitative evaluation of craniocerebral injury caused by stick blows to the head, can solve the problems of reduced prediction accuracy of simplified models, inability to analyze and evaluate local brain tissue, etc. Accuracy, High Accuracy, Efficiency Enhanced Effects

Pending Publication Date: 2021-11-05
TIANJIN UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] 1. The finite element simulation experiment requires a lot of computing time and high-performance workstations, and requires operators to have certain professional knowledge
[0004] 2. For larger strain shocks and more complex injury factors, the prediction accuracy of the simplified model will be greatly reduced
[0005] 3. The existing technology model can only conduct an overall quantitative evaluation of the brain tissue, but cannot analyze and evaluate the local brain tissue

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
  • Blunt device injury craniocerebral maximum principal strain prediction method and system based on convolutional neural network model
  • Blunt device injury craniocerebral maximum principal strain prediction method and system based on convolutional neural network model
  • Blunt device injury craniocerebral maximum principal strain prediction method and system based on convolutional neural network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0043] 1) Prediction of the maximum principal strain when a hardwood round stick with a length of 400mm and a diameter of 55mm strikes the left forehead at 10m / s.

[0044] Figure 4 The speed curve of the round stick along the X, Y, and Z directions is shown. After mapping and zooming and importing into the convolutional neural network selected above, the prediction results of the brain, cerebellum, and corpus callosum are 0.515, 0.532, and 0.395, respectively. The real values ​​are 0.501, 0.529, 0.430 respectively.

[0045] 2) Prediction of the maximum principal strain when a round stick with a length of 400mm, a diameter of 40mm and made of cork strikes the left posterior parietal bone at 20m / s.

[0046] Figure 5 It shows the velocity curve of the round wooden stick along the X, Y, and Z directions. After mapping and zooming and importing into the convolutional neural network selected above, the prediction results of the brain, cerebellum, and corpus callosum are 0.682, 0...

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 method for predicting the maximum principal strain of the brain of a blunt device injury based on a convolutional neural network model. The method comprises the following steps: 1, carrying out finite element simulation on a blunt device hitting head; 2, extracting the maximum principal strain of the brain in the simulation data; 3, extracting speed curves of the blunt device in the simulation data in the X, Y and Z directions under the global coordinate system; cutting and filling the speed curve, and mapping and scaling the speed curve to obtain a mapping graph; wherein the mapping graph comprises an X axial speed, a Y axial speed and a Z axial speed; 4, constructing a convolutional neural network for training and predicting the maximum principal strain influence of the blunt device hitting the head on the brain; 5, taking the mapping graph and the maximum principal strain of the brain as input and output to train the convolutional neural network, and selecting an optimal model; 6, using the optimal model to predict the maximum principal strain of the brain.

Description

technical field [0001] The present invention relates to the technical field of deep learning and finite element simulation calculation, and in particular to a rapid quantitative evaluation method for craniocerebral injury caused by hitting the head with a stick based on convolutional neural network and finite element technology. Background technique [0002] The cranial brain is the most important life center of the human body, and the fatality rate and disability rate after injury are extremely high. Brain injury is one of the world's leading public health problems. According to the World Health Organization, more than 40 million people worldwide suffer from mild brain injuries each year. In forensic identification, blunt force trauma is one of the main factors leading to traumatic brain injury. Among them, sticks and blunt weapons accounted for the highest proportion. However, the current quantitative evaluation methods for blunt force-induced brain injury are extremely...

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): G16H50/50G06T17/20G06N3/04G06N3/08
CPCG16H50/50G06T17/20G06N3/08G06T2210/41G06N3/045
Inventor 李海岩李海防崔世海吕文乐贺丽娟
Owner TIANJIN UNIV OF SCI & 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