公开(公告)号：US20230142578A1

公开(公告)日：2023-05-11

申请号：US17948443

申请日：2022-09-20

Applicant: Fulian Yuzhan Precision Technology Co.,Ltd

Inventor： XIONG-BO LI ,  TSUNG-JU LIN ,  DAO-LIANG ZHOU ,  CHENG-LUN LEE ,  CHEN-TING WU

IPC: G06T7/00 ,  G06T5/00 ,  G06T5/20 ,  G06V10/94

CPC classification number: G06T7/0004 ,  G06T5/002 ,  G06T5/20 ,  G06V10/95 ,  G06T2207/30136 ,  G06T2207/30164 ,  G06T2207/20081 ,  G06T2207/20032 ,  G06T2207/20028 ,  G06V2201/06

Abstract: A system and a method for detecting welding based on edge computing, the system includes at least one edge server, each edge server configured to obtain welding information of at least one welding machine, preprocess the welding information to generate processed data, input the processed data to a trained algorithm to generate a detecting result, and determine a welding quality of the welding machine according to the detecting result; and a data server coupled to the at least one edge server and configured to process and store the detecting result and the welding information uploaded by each edge server, generate display information, and visualizes the detecting result according to the display information.

公开(公告)号：US20230161842A1

公开(公告)日：2023-05-25

申请号：US17969426

申请日：2022-10-19

Applicant: Fulian Yuzhan Precision Technology Co., Ltd.

Inventor： CHEN-TING WU ,  XIN-DI LEI ,  HONG-WEI ZHANG ,  DENG-KUI TIAN ,  YING-YING NIE ,  CHENG-LUN LEE ,  QING-YU WANG

IPC: G06K9/62 ,  G06N20/00 ,  G05B13/02

CPC classification number: G06K9/6262 ,  G05B13/024 ,  G06N20/00

Abstract: A parameter setting method acquires historical processing data, pre-processes the historical processing data to obtain sample data, and creates a trained regression algorithm using the sample data, then acquires preliminary emulated processing data and predetermined objective parameters inputted, wherein the preliminary emulated processing data and the predetermined objective parameters constitute emulated processing data. A reinforcement learning algorithm is trained with the historical processing data, emulated processing data, and the reinforcement learning algorithm; an actual objective parameter are set according to the actual reference parameters and the reinforcement learning algorithm. Scale of the training data for the reinforcement learning algorithm is greatly increased by the trained regression algorithm, which improves the accuracy of the learning algorithm. A parameter setting device, an electronic device, and a storage medium are also disclosed.

公开(公告)号：US20230160811A1

公开(公告)日：2023-05-25

申请号：US17993180

申请日：2022-11-23

Applicant: Fulian Yuzhan Precision Technology Co., Ltd.

Inventor： CHEN-TING WU ,  HONG-WEI ZHANG ,  QING-YU WANG ,  LI YAN ,  DENG-KUI TIAN ,  CHENG-LUN LEE

IPC: G01N21/25

CPC classification number: G01N21/25

Abstract: A data analysis method for optimization of aluminum anodizing and dyeing process acquires a plurality of sample data groups, each sample data groups comprising dyeing result data and parameter data of multiple processing parameters. Contribution value of each processing parameter data relative to the dyeing result data in each of the plurality of sample data groups is determined, and the contribution values are used to determine at least one essential processing parameter. The essential processing parameters are then adjusted according to a data analysis result for improving quality of products. A computing device and storage medium are also provided.