公开(公告)号：US20220214654A1

公开(公告)日：2022-07-07

申请号：US17170312

申请日：2021-02-08

Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE

Inventor： Jia-Cheng SUN ,  Ci-Rong HUANG ,  Yang-Lun LIU ,  Chen-Yu KAI

IPC: G05B17/02 ,  G06F30/10 ,  G06F30/20

Abstract: A processing method for automatically generating machining features is provided. A workpiece CAD file is obtained to perform a CAD numerical analysis on a blank body. With the workpiece CAD file being used as a target, a workpiece CAD appearance is compared with the blank body to obtain a feature identification result of a first to-be-processed blank body, which includes identifying data of a to-be-removed blank body and a feature of a first processing surface. A geometric analysis is performed on the first processing surface feature and a tool selection range is determined. A virtual cutting simulation is performed on the first processing surface to generate a processed area data and an unprocessed area data. A spatial coordinate mapping comparison between the unprocessed area data and a surface data of the workpiece CAD file is performed to obtain a feature identification result of a second to-be-processed blank body.

公开(公告)号：US20200184720A1

公开(公告)日：2020-06-11

申请号：US16225931

申请日：2018-12-19

Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE

Inventor： Yang-Lun LIU ,  Yu-Lin TSAI ,  Yao-Yang TSAI ,  Cheng-Chieh WU ,  Shuo-Peng LIANG

IPC: G06T17/10 ,  G06K9/62 ,  G06F17/50 ,  G06N3/08

Abstract: A machining parameter automatic generation system includes a geometric data capturing module, a feature recognition learning network and a machining parameter learning network. The geometric data capturing module captures a geometric shape of a workpiece to generate a candidate feature list. The feature recognition learning network trains the candidate feature list according to a first neural network model to obtain an applicable feature list. The machining parameter learning network trains the applicable feature list and the candidate machining parameter according to a second neural network model to obtain an applicable machining parameter. The applicable machining parameter is used to generate a machining program, and the machining program is read by a machine tool for processing.