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

Time sequence signal point anomaly detection method, system, equipment and medium

A time-series signal, anomaly detection technology, applied in manufacturing computing systems, neural learning methods, digital data information retrieval, etc., can solve the problems of low efficiency, hidden dangers in production, and high difficulty in abnormal discovery, and achieves the goal of improving discovery efficiency and reducing discovery difficulty. Effect

Pending Publication Date: 2022-04-01
中冶赛迪信息技术(重庆)有限公司
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In view of the above-mentioned shortcomings of the prior art, the present invention provides a method, system, equipment and medium for abnormal detection of timing signal points to solve the technical problems of hidden dangers in production, high difficulty in finding abnormalities, and low efficiency

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
  • Time sequence signal point anomaly detection method, system, equipment and medium
  • Time sequence signal point anomaly detection method, system, equipment and medium
  • Time sequence signal point anomaly detection method, system, equipment and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] With the rise of the Internet of Things technology and the concept of 5G Internet of Everything, the Internet of Things technology has been more and more widely used in the field of industrial production. Aiming at the time-series data collected by IoT sensors in a large number of production processes, if they can be used reasonably, the efficiency and intelligence of industrial production will be greatly improved. One of its application directions is production anomaly detection. Accurate capture of the timing signals fed back during the production process can assist relevant staff to discover and deal with abnormalities or hidden dangers in a timely manner, reduce the accident rate and improve the operation rate. In most large factories, this kind of data is often not paid enough attention, and it is only judged by the way of operator's naked eyes whether it is abnormal.

[0060] Aiming at the anomaly detection problem of time series data in the industrial production ...

Embodiment 2

[0169] see Image 6 , this embodiment provides a timing signal point anomaly detection system 600, the system includes:

[0170] A construction module 601, configured to construct an autoencoder model, where the autoencoder model includes an encoder and a decoder;

[0171] The training module 602 is used to obtain a plurality of sample industrial time series signal data, and use the sample industrial time series signal data to train the autoencoder model to obtain the trained autoencoder model, and the sample industrial time series signal data is collected through the time series data acquisition window ;

[0172] The error determination module 603 is used to obtain the industrial time series signal data to be detected, input the industrial time series signal data to be detected into the trained autoencoder model, and determine the dimension reconstruction error of each time series signal point in the industrial time series signal data to be detected , the industrial time-se...

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 provides a time sequence signal point anomaly detection method, system, device and medium, and the method comprises the steps: building an auto-encoder model in advance, training the auto-encoder model through employing a plurality of pieces of sample industrial time sequence signal data, obtaining the to-be-detected industrial time sequence signal data, and carrying out the detection of the to-be-detected industrial time sequence signal data; and inputting the to-be-detected industrial time sequence signal data into the trained auto-encoder model, determining the dimension reconstruction error of each time sequence signal point in the to-be-detected industrial time sequence signal data, and then determining the detection state, so that the difficulty in finding production hidden dangers, especially abnormal production data, is reduced, and the finding efficiency is improved.

Description

technical field [0001] The invention relates to the technical field of processing and analyzing industrial time series signals, in particular to a method, system, equipment and medium for detecting abnormality of time series signal points. Background technique [0002] In large-scale factories, the awareness and management of production safety are becoming more and more strict. However, due to factors such as numerous equipment and complicated procedures, the discovery of abnormalities in the production process often relies on manual visual inspection, which is inefficient and Because hidden dangers are often hidden and subtle, it is difficult to find them. Contents of the invention [0003] In view of the above-mentioned shortcomings of the prior art, the present invention provides a timing signal point anomaly detection method, system, equipment and medium to solve the technical problems of hidden dangers in production, high difficulty in finding anomalies, and low effic...

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): G06F16/2458G06N3/04G06N3/08G06Q10/00G06Q50/04
CPCY02P90/30
Inventor 邬小刚祝捷汤槟张晓辉毛尚伟潘谊
Owner 中冶赛迪信息技术(重庆)有限公司
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

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