Title:
SAMPLE DATABASE SYSTEM, METHOD FOR TRAINING AND CHECKING PRINTING PARAMETER, AND COMPUTER
Document Type and Number:
WIPO Patent Application WO/2022/233206
Kind Code:
A1
Abstract:
Disclosed in the present application are a sample database system, a method for training and checking a printing parameter, a computer device, and a computer-readable storage medium. The sample database system comprises: a storage module, which stores sample data corresponding to a random 3D model, wherein the sample data comprises printing parameters, and printing material information and simulation data which correspond to the printing parameters, the printing parameters are used for describing a control mode of a 3D printing device for manufacturing the random 3D model, and the simulation data is used for describing molding characteristics of a corresponding printing material during the process of the 3D printing device executing printing according to the printing parameters; a data writing module, which is used for writing the sample data into the storage module; and a data reading module, which is used for reading the sample data from the storage module so as to be used by a prediction calculation model for training machine learning. In the present application, a random 3D model is generated, and sample data is generated by using the random 3D model, such that sample data with diversified model features is provided for the training of a prediction calculation model.
Inventors:
LUO XIAOFAN (CN)
WANG YIJIA (CN)
LONG JIELONG (CN)
HUANG YINGQIAO (CN)
HARTMANN DAVID SIMON (CN)
WANG YIJIA (CN)
LONG JIELONG (CN)
HUANG YINGQIAO (CN)
HARTMANN DAVID SIMON (CN)
Application Number:
PCT/CN2022/084257
Publication Date:
November 10, 2022
Filing Date:
March 31, 2022
Export Citation:
Assignee:
SUZHOU HELIO ADDITIVE INFORMATION TECH CO LTD (CN)
International Classes:
G06F30/27; B33Y50/00; G06F113/10
Domestic Patent References:
WO2019112655A1 | 2019-06-13 |
Foreign References:
CN110472355A | 2019-11-19 | |||
CN110110466A | 2019-08-09 | |||
CN111444559A | 2020-07-24 |
Other References:
ARND KOEPPE, HERNANDEZ PADILLA CARLOS ALBERTO, VOSHAGE MAXIMILIAN, SCHLEIFENBAUM JOHANNES HENRICH, MARKERT BERND: "Efficient numerical modeling of 3D-printed lattice-cell structures using neural networks", MANUFACTURING LETTERS, vol. 15, 1 January 2018 (2018-01-01), NL , pages 147 - 150, XP055685448, ISSN: 2213-8463, DOI: 10.1016/j.mfglet.2018.01.002
Attorney, Agent or Firm:
SHANGHAI DIANSHI PARTNERS, P.C. (CN)
Download PDF:
Previous Patent: SYSTEMS AND DEVICES FOR WASTE COLLECTION AND STORAGE
Next Patent: SURFACE LIGHT SOURCE APPARATUS AND FLAT PANEL DISPLAY APPARATUS
Next Patent: SURFACE LIGHT SOURCE APPARATUS AND FLAT PANEL DISPLAY APPARATUS