Unlock instant, AI-driven research and patent intelligence for your innovation.

Separating state of mechanical press by analyzing training patterns in neural network

A technology of press and state, applied in the field of computer realization of state, can solve problems such as expensive calibration

Pending Publication Date: 2022-03-11
SIEMENS AG
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

These failures of the manufacturing process were not detected during the pressing process but only after a few pressing cycles during visual inspections carried out automatically or manually
In addition, micro-cracks may appear during the pressing process, which are not detected in visual inspection, but are only detected very late in the final assembly or even during operation
[0003] the later these faults in the manufacturing process are detected, the more expensive they will be to correct

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
  • Separating state of mechanical press by analyzing training patterns in neural network
  • Separating state of mechanical press by analyzing training patterns in neural network
  • Separating state of mechanical press by analyzing training patterns in neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0074] exist figure 1 , schematically depicts a computer-implemented method of indicating faults in a manufacturing process. Here, the manufacturing process is by pressing sheet or plate material (for example, made of steel) to form a workpiece.

[0075] The computer-implemented method comprises the steps of a) receiving 1 at least one input signal, b) transforming 2 the at least one input signal, c) deriving 3 latent features, d) mapping 4 the derived latent features, and e) optionally indicating 5 Faults in the manufacturing process.

[0076] In step a), at least one input signal is received. Here, five input signals I1..I5 are received. Four of the five input signals I1..I4 are time-varying force signals based on the time-varying pressing force of the plunger of the press on the die of the press as measured by four corresponding force transducers Measurement. The last of the five input signals I5 is a time-varying position signal based on the time-varying position of t...

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 present invention relates to a computer-implemented method, a data processing system and a computer program product for indicating a failure of a manufacturing process and a corresponding manufacturing machine, and also to a computer-implemented method for training a machine learning system (MLS) to indicate a state of a manufacturing process. An input signal of the sensor is converted into a parameter. The parameter is provided to an MLS that derives a potential feature. The potential features are mapped to one of several different clusters, each cluster representing a pattern of the manufacturing process. Finally, faults of the manufacturing process based on different states of the manufacturing process may be indicated.

Description

technical field [0001] The present invention relates to a computer-implemented method, data processing system, and computer program product for indicating faults in a manufacturing process, and corresponding manufacturing machines, and to a method of training a machine learning system (MLS) to indicate the state of a manufacturing process computer-implemented method. Background technique [0002] When pressing sheets or plates of different materials (e.g., steel, copper, polymers, etc.), cracks in the sheet / plate (or rather the manufactured workpiece) often occur, the sheet / plate or rather the manufactured waviness of the workpiece and other failures of the manufacturing process. These faults of the manufacturing process are not detected during the pressing process but only after a few pressing cycles during an automatically or manually carried out visual inspection. Furthermore, microcracks may appear during the pressing process, which are not detected in visual inspectio...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F2218/02G06F18/214G06N3/084B30B15/0094G05B23/0221G05B23/024G05B23/027B30B15/26G06N3/048
Inventor 托尔斯滕·赖曼
Owner SIEMENS AG