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

Process signal data extraction and storage method based on theory of two-dimensional convolution

A technology of signal data and two-dimensional convolution, which is applied in the direction of instrumentation, calculation, character and pattern recognition, etc., can solve problems such as unsatisfactory effects, technical solutions for signal data extraction in the processing process without special equipment, etc., and achieve process signal data The extraction and storage methods are simple and practical, meet the requirements of data accuracy, and improve efficiency

Inactive Publication Date: 2017-06-23
HUAZHONG UNIV OF SCI & TECH
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, relevant technical personnel in the field have done some research, but the effect is not very satisfactory, and there is no special technical solution for signal data extraction in the equipment processing 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
  • Process signal data extraction and storage method based on theory of two-dimensional convolution
  • Process signal data extraction and storage method based on theory of two-dimensional convolution
  • Process signal data extraction and storage method based on theory of two-dimensional convolution

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0022] see figure 1 and figure 2 , taking the extraction and classification automatic storage of process data in the engine cylinder head surface processing process as an example to illustrate the process signal data extraction and storage method based on the two-dimensional convolution theory provided by the first embodiment of the present invention, the engine cylinder head processing adopts a machining center For processing, two processes of milling and drilling are completed at one time. The process signal data extraction and storage method mainly includes the following steps:

[0023] Step 1: Establish a template image library of multiple single-process processing signals and full-process images corresponding to multi-process processing signals that need to extract data. Specifically include the following steps:

[0024] (1) Collect the data of the current signal of the X-axis screw of the horizontal machining center, and form the template image library of the milling...

Embodiment 2

[0038] see image 3 , taking the state monitoring of parts in the production process as an example to illustrate the process signal data extraction and storage method based on the two-dimensional convolution theory provided by the second embodiment of the present invention, in order to accurately extract the milling and The current data of the drilling process, here, according to the current data images of the milling process in three different states of new parts, normal operation and about to be replaced, the process data is cyclically extracted and stored, and the current data images are extracted and collected according to the given current data images The data mainly includes the following steps:

[0039] Step 1, image data collection. Specifically, firstly, sort out the sensor current data collected by the data collector, and extract 72,000 data collection points from the current data of each processing process; The current images (images of the whole process) are stored...

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 belongs to the technical field related to equipment machining process signal data extraction, and discloses a process signal data extraction and storage method based on the theory of two-dimensional convolution. The method comprises the following steps: building a template image library of multiple single-process machining signals and a whole-process image corresponding to a multi-process machining signal needing data extraction; matching the whole-process image with template images, using a correlation coefficient to indicate the matching degree between the whole-process image and the template images, and selecting a best template image according to the value of the correlation coefficient; locating the selected best template image and the whole-process image based on the theory of two-dimensional convolution to get locating pixels; and extracting signal data corresponding to a single-process machining signal according to the relationship of the locating pixels, the pixels of the whole-process image and corresponding signal data sampling points, and automatically storing the signal data in chronological order.

Description

technical field [0001] The invention belongs to the related technical field of signal data extraction in the equipment processing process, and more specifically relates to a signal data extraction and storage method based on two-dimensional convolution theory. Background technique [0002] In the process of industrial production, it is necessary to collect processing signal data of a single process in order to monitor and analyze the status of parts. However, the acquisition of processing signals in the actual processing process is mostly continuous collection of multiple processes, and the subsequent signal analysis and processing often require the use of signals from a certain process, which will need to be extracted from continuous multi-process signals. The corresponding single-process signal. At present, most of the manual methods are used to extract signal data, and it is extremely troublesome to use manual methods to extract signal data from a large amount of process...

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): G06K9/46G06K9/62G06K9/40
CPCG06V10/30G06V10/443G06F18/22
Inventor 武滢李斌彭芳瑜刘红奇罗博毛新勇谭波阳雪峰
Owner HUAZHONG UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products