公开(公告)号：US20220215246A1

公开(公告)日：2022-07-07

申请号：US17529311

申请日：2021-11-18

Applicant: GUANGDONG UNIVERSITY OF TECHNOLOGY

Inventor： Jiewu LENG ,  Weinan SHA ,  Zisheng LIN ,  Dewen WANG ,  Man ZHOU ,  Guolei RUAN ,  Qiang LIU ,  Hu ZHANG ,  Qianyi SU

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62 ,  G05B13/02

Abstract: A method for constructing and training a Decentralized Migration Diagram Neutral Network (DMDNN) model for a production process, including: determining a production task input management node, distributed management nodes and a granularity of each of the distributed management nodes, and constructing a production system network; constructing network calculation nodes on each of the distributed management nodes; constructing and training a DMDNN model; and applying the trained DMDNN model in management and control of the production process.

公开(公告)号：US20210286325A1

公开(公告)日：2021-09-16

申请号：US17072722

申请日：2020-10-16

Applicant: GUANGDONG UNIVERSITY OF TECHNOLOGY

Inventor： Qiang LIU ,  Jiewu LENG ,  Duxi YAN ,  Ding ZHANG ,  Hao ZHANG

IPC: G05B13/02 ,  G06F30/20 ,  B25J9/16 ,  G05B19/418

Abstract: Disclosed are a self-adaptive configuration method and system for linkage response of a construction type, a motion type, a control type and an optimization type. The disclosure aims to provide the self-adaptive configuration method and system for linkage response of quick adjustment and design of a workshop production line. The self-adaptive configuration method comprises the following steps of step A: construction type configuration; step B: motion type design; step C: control type design; and step D: optimization type evolution, wherein the step D comprises first-level iterative optimization, second-level iterative optimization and third-level iterative optimization. A closed optimization cycle is formed by the first-level iterative optimization, the second-level iterative optimization and the third-level iterative optimization jointly, and the multi-level iterative optimization is performed on the production line linkage design framework, so that the workshop production line can be self-adaptively and quickly adjusted and designed.

公开(公告)号：US20210256438A1

公开(公告)日：2021-08-19

申请号：US17060148

申请日：2020-10-01

Applicant: GUANGDONG UNIVERSITY OF TECHNOLOGY

Inventor： Jiewu LENG ,  Man ZHOU ,  Qiang LIU ,  Guolei RUAN ,  Shide YE ,  Jianbo JING ,  Hu ZHANG

IPC: G06Q10/06 ,  G16Y10/25 ,  G16Y40/35 ,  G06Q50/04

Abstract: Disclosed is a blockchain-enabled edge computing method for production scheduling. The method includes modeling a smart contract between a device and a manufacturing unit, and using the smart contract to perform production scheduling on the device inside the manufacturing unit; one of the manufacturing units includes multiple devices; mounting each device on the blockchain operating node, the MES issues production instructions to the nodes of each manufacturing unit, at the same time, the nodes acquire production data of the device through multiple data sources of the device, the operating state data and process parameter data of each device are acquired in real time, and the data is directly chained from the device level; according to the production instructions and device parameters obtained by the manufacturing unit, using edge computing to dynamically adjust the device load, efficiency, and utilization.