Digital twin modeling method based on multi-fidelity data
A modeling method and fidelity technology, applied in the direction of neural learning methods, electrical digital data processing, special data processing applications, etc., can solve problems such as model collapse and training difficulties, and achieve reduced demand, easy operation, and low cost Effect
Pending Publication Date: 2022-01-04
DALIAN UNIV OF TECH
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
In addition, in view of the difficulties in training and prone to model collapse in the traditional generative confrontation network, the present invention introduces the training technique of "supervised loss", which can significantly improve the stability and performance of the model
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0042] In order to make the method problem solved by the present invention, the method scheme adopted and the method effect achieved clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, but not to limit the present invention. In addition, it should be noted that, for the convenience of description, only parts related to the present invention are shown in the drawings but not all content.
[0043] The present invention provides implementation cases, such as figure 2 shown. The workpiece has three symmetrical holes and is 12mm thick. The way the workpiece is stressed is to fix it left and right, and apply different forces from top to bottom. The stress diagram reflects the stress on the surface and internal points of the workpiece when it bears different forces. . In this imple...
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
Login to View More Abstract
The invention provides a digital twin modeling method based on multi-fidelity data, and belongs to the technical field of industrial design. According to the digital twinborn modeling method, the generative adversarial network is used as a base model, and accurate digital twinborn modeling is given at relatively low cost for the problems of high precision, high cost and small quantity of high-fidelity data and low precision, low cost and large quantity of low-fidelity data in digital twinborn modeling. Compared with a traditional method, the method has the advantages that the internal distribution rule of data can be fully mined, the requirement of the method for high-fidelity point data is reduced, and problem setting is further met; meanwhile, excessive many assumptions are not made for the linear relation and data distribution of the high-fidelity data and the low-fidelity data, so that the application scene of the method is widened.
Description
technical field [0001] The invention belongs to the technical field of industrial design and relates to a digital twin modeling method based on variable fidelity data. Background technique [0002] The core concept of digital twin technology is to give an accurate digital description of the actual physical process, and to reflect the evolution of the physical process dynamically in real time. The earliest application field of digital twin technology is industrial manufacturing. For example, the construction of digital twins based on large-scale manufacturing equipment can comprehensively simulate and monitor the real-time status of equipment, play a major role in equipment management and risk investigation, and save unnecessary consumption such as manpower and material resources. [0003] However, one of the key issues in digital twin modeling is the need for sufficient data. Generally speaking, the sources of data are divided into two categories, one is theoretical data c...
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
Login to View More IPC IPC(8): G06F30/17G06F30/27G06N3/04G06N3/08G06F119/14
CPCG06F30/17G06F30/27G06N3/04G06N3/08G06F2119/14
Inventor 张超刘立雪宋学官
Owner DALIAN UNIV OF TECH