Unlock instant, AI-driven research and patent intelligence for your innovation.

3D printing multi-database sharing optimization algorithm based on homomorphic encryption technology

A secret sharing algorithm and 3D printing technology, applied in the field of 3D printing multi-database sharing optimization algorithm, which can solve the problems of high cost of 3D printing experiments and inability to exhaust 3D printing parameters.

Inactive Publication Date: 2020-12-29
CHENGDU AIRCRAFT INDUSTRY GROUP
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the implementation process of 3D printing, due to too many 3D printing related parameters, it is impossible to exhaust all 3D printing parameters during the experiment and judge whether these parameters can form suitable parts. Therefore, a 3D printing parameter learning and prediction method is needed. way to realize the prediction of 3D printing parameters
[0003] Due to the high cost of 3D printing experiments, it is impossible for one company or unit to complete all of them. Therefore, a technical solution for joint training of multiple databases to obtain more accurate model parameters is proposed, and this type of solution involves confidentiality among multiple databases. question

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
  • 3D printing multi-database sharing optimization algorithm based on homomorphic encryption technology
  • 3D printing multi-database sharing optimization algorithm based on homomorphic encryption technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0123] In this embodiment, the multi-party joint training of data vertical segmentation is taken as an example. Note: Ai and Aj are training members, N is the total number of training members, i, j=1,...,N and i≠j; A1, A2, ..., AN are the data owners in the joint training. Server C acts as the driving center for training.

[0124]This embodiment specifically includes the following steps.

[0125] Step 1: Data alignment and splitting

[0126] Multiple training members use the PSI protocol (Private Set Intersection) to perform intersection operations to obtain data intersections with the same ID, number the data intersections, and obtain data sets corresponding to Ai (i=1,...,N) , and each data set contains the training label data, record the label of the label data as Y;

[0127] Then, each data set is split to obtain the corresponding training set X trAi , validation set X valAi , test set X teAi ; and extract the training set X trAi The data dimension and the number of...

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 relates to the technical field of database sharing, and discloses a 3D printing multi-database sharing optimization algorithm based on a homomorphic encryption technology, and the algorithm comprises the steps: obtaining server-side input layer data through a secret sharing algorithm in a mode of center-driven multi-side training; obtaining the number of iterations corresponding to each training member and the number of central iterations corresponding to the server; each training member independently accumulates a first moment and a second moment to update the model; and finally, unifying the training progress of the multi-party training members by enabling the number of iterations of the training members to be consistent with the number of central iterations.

Description

technical field [0001] The invention relates to the technical field of multi-database sharing, in particular, it is a 3D printing multi-database sharing optimization algorithm based on homomorphic encryption technology. Background technique [0002] In the 1980s, 3D printing technology was born. 3D printing is a bottom-up manufacturing method, also known as additive manufacturing technology, which is different from traditional "removal" processing methods. 3D printing technology has been widely concerned by people since its birth, so it has developed rapidly. In recent decades, 3D printing technology has become the focus of attention and has been applied in industrial design, architecture, automobile, aerospace, dentistry, education and other fields. However, in the implementation process of 3D printing, due to too many 3D printing related parameters, it is impossible to exhaust all 3D printing parameters during the experiment and judge whether these parameters can form su...

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
IPC IPC(8): G06F21/60G06F21/62G06N3/04G06N3/08
CPCG06F21/602G06F21/6227G06N3/08G06N3/045
Inventor 隋少春荣鹏王大为高川云
Owner CHENGDU AIRCRAFT INDUSTRY GROUP