Supercharge Your Innovation With Domain-Expert AI Agents!

A manufacturing and assembling product quality prediction method based on a parallel long-short-term memory network

A long-short-term memory and product quality technology, applied in manufacturing computing systems, neural learning methods, biological neural network models, etc., can solve problems such as inability to accurately predict product quality

Active Publication Date: 2019-05-03
ZHEJIANG UNIV
View PDF2 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In order to solve the technical problem that the product quality cannot be accurately predicted in the manufacturing and assembly process, the present invention proposes a data-driven manufacturing and assembly process with cross-step quality parameter memory product quality prediction device and method, aiming at the possibility of parallel working steps in the manufacturing and assembly process Quantify and calculate the influence and effect between the manufacturing and assembly process across steps, analyze the inherent characteristics of the process parameter data generated by each step, obtain the relationship between it and the quality parameters of the final product, and finally predict the product quality

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
  • A manufacturing and assembling product quality prediction method based on a parallel long-short-term memory network
  • A manufacturing and assembling product quality prediction method based on a parallel long-short-term memory network
  • A manufacturing and assembling product quality prediction method based on a parallel long-short-term memory network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0083] The present invention will be further described below in conjunction with drawings and embodiments.

[0084] Such as figure 2 Shown, embodiment of the present invention and concrete implementation process thereof are as follows:

[0085] Step 1. Data Acquisition

[0086] The process parameter data in each station step in the rocket shell manufacturing and assembly process is obtained through multiple sensors as input characteristic data, including the process parameters and measurement parameters of each station step in the rocket shell component manufacturing or the entire assembly process. The input characteristics of each station step such as: manufacturing process: cutting speed, feed rate, depth of cut, spindle speed, workpiece speed, manufacturing time, back cutting amount, feed times, eccentricity, blank material type, tool material Category, geometric angle of the tool, fixture category number, cutting fluid category, measurement dimensional accuracy, measure...

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 discloses a manufacturing and assembling product quality prediction method based on a parallel long-short-term memory network. The method comprises the following steps: obtaining characteristics of each station step of the product; pre-processing the characteristics of each station step of the product; establishing a product quality prediction model based on a parallel long short-term memory network; performing parameter optimization training of a product quality prediction model based on a parallel long-short-term memory network; and predicting the quality characteristics of theto-be-tested sample based on the quality prediction model. The method is used for solving the problem of product quality prediction possibly existing in parallel working steps in the manufacturing and assembling process, can automatically obtain the influence between cross-working-step technological process parameters between the parallel working steps, and has higher product quality prediction precision, flexibility, prediction efficiency and model reusability.

Description

technical field [0001] The invention relates to a method for predicting product quality in a manufacturing assembly process that may have parallel working steps, in particular to a method for predicting product quality in a manufacturing assembly process based on a parallel long-short-term memory network. Background technique [0002] At present, in the development of enterprises in the machinery field, the quality of product manufacturing and assembly plays a decisive role. Therefore, product quality prediction in manufacturing assembly process, as the basis of product quality monitoring and control in manufacturing assembly process, has received extensive attention and research. However, in the manufacturing and assembly process, products usually go through different types of multiple station steps, and there are mutual influences between different station steps. There are many coupling features inside a single station step and between multiple station steps. with uncerta...

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): G06Q10/06G06Q50/04G06N3/08
CPCY02P90/30
Inventor 刘振宇张栋豪郏维强刘惠谭建荣
Owner ZHEJIANG UNIV
Features
  • R&D
  • 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com