Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Distributed data-driven process modeling optimization method and system

A technology of distributed data and optimization methods, applied in data processing applications, neural learning methods, computing models, etc., to achieve the effect of saving manpower

Pending Publication Date: 2022-06-24
EAST CHINA UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a distributed data-driven process modeling optimization method and system to solve the problem of data security caused by collecting node data from different devices in the existing centralized data-driven modeling decision-making process

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
  • Distributed data-driven process modeling optimization method and system
  • Distributed data-driven process modeling optimization method and system
  • Distributed data-driven process modeling optimization method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0082] In order to make the objectives, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the invention, but not to limit the invention.

[0083] Federated machine learning is also known as federated learning, federated learning, and federated learning. Federated Machine Learning is a machine learning framework that can effectively help multiple agencies conduct data usage and machine learning modeling while meeting user privacy protection, data security, and government regulations. Federated learning, as a privacy-preserving distributed machine learning framework, protects user privacy by sharing update directions instead of private data, and has broad application prospects.

[0084] The invention proposes a distributed data-driven process...

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 field of industrial process optimization, in particular to a distributed data-driven process modeling optimization method and system. The method comprises the following steps: step S1, determining a used machine learning model according to task requirements and data set size, and issuing a model configuration file to each corresponding node; s2, performing data-driven modeling by the node to obtain a node model, and uploading the node model to a parameter server; s3, aggregating the node models by the parameter server to obtain a global model, and issuing the global model to each corresponding node; s4, selecting a carrier for decision optimization, and determining an optimization target number and an optimization strategy; s5, using the global model and the node model on a carrier, combining an optimization strategy to carry out evolutionary optimization, and searching to obtain a feasible solution; and step S6, the node evaluates the feasible solution until a termination condition is satisfied. According to the method, privacy protection modeling and decision optimization during data distributed storage are realized based on federated learning modeling, and the adaptability is relatively wide.

Description

technical field [0001] The invention relates to the field of industrial process optimization, and more particularly, to a distributed data-driven process modeling optimization method and system. Background technique [0002] With the rapid popularization of mobile edge devices and the rapid development of the Industrial Internet and 5G, the explosion of big data in the process industry has been accelerated. Process industry big data, including process status data, equipment operation and maintenance data, safety supervision and environmental protection image information and other heterogeneous data. [0003] Data-driven process modeling and decision optimization methods have been widely used in process industry intelligence, especially process industry modeling and decision optimization, because they are suitable for extracting knowledge contained in big data. [0004] figure 1 It is a schematic diagram of a typical centralized data-driven modeling and decision optimizatio...

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): G06Q10/04G06Q10/06G06N20/00G06N3/08G06N3/04G06N3/00G06K9/62
CPCG06Q10/04G06Q10/0633G06N20/00G06N3/084G06N3/006G06N3/045G06F18/214
Inventor 杜文莉钱锋杨明磊钟伟民王新杰徐金金
Owner EAST CHINA UNIV OF SCI & TECH
Features
  • Generate Ideas
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More