A Soft Tissue Penetration Force Modeling Method Based on Segmented Artificial Neural Network

A technology of neural network and modeling method, applied in the direction of biological neural network model, neural learning method, neural architecture, etc., can solve problems such as difficult time-consuming, poor real-time performance, complex biomechanics, etc., and achieve easy modeling and prediction The effect of small force error
CN109859849BActive Publication Date: 2022-05-20NANCHANG UNIV
5 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
NANCHANG UNIV
Publication Date
2022-05-20

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

A soft tissue puncture force modeling method based on a segmented artificial neural network, according to the following steps: 1) Select soft tissue samples to be modeled for puncture experiments to collect sample data; 2) Analyze and organize the sample data, and divide all data into The stage is divided into three groups: before the puncture, after the puncture until the deepest point, and pulling out, and then divide each group of data into a training group and a test group; 3) use the training group for neural network training, and then use the test group to evaluate the obtained Neural network; 4) The three neural networks obtained from the training are called in sections according to the puncture stage to complete the modeling. The prediction error of modeling in the present invention is small, within the range that is difficult to detect by human hands; it is easy to model, saves time and effort; it can perform mechanical modeling on the complete process of soft tissue puncture, and can be completed well even in the most nonlinear stage Modeling; the model has a certain general applicability to the same organization of different individuals, and the overall trend of predictive power is consistent with the experimental data.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention belongs to the field of information technology and relates to a biomechanical modeling method. Background technique

[0002] In recent years, as the development of virtual reality technology has been highly valued by the country, virtual surgery systems have gradually been accepted and applied in the medical field. Currently, virtual surgery systems on the market are relatively mature in terms of interactive equipment, cutting image modeling, and medical image processing. However, due to the complexity of biomechanics, most systems only stop at the visualization stage, and few have good results A complete system for haptic feedback. The lack of tactile force feedback makes virtual surgery different from clinical surgery, which is also the biggest drawback of the virtual surgery system, which directly causes the virtual surgery system to be ineffective in teaching doctors.

[0003] Most of the current soft tissue mechanics models use mas...

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