Anomaly Monitoring System for Dynamic Production Environment Oriented to Real-time Data Flow
A technology for abnormal monitoring and production environment, applied in data processing applications, manufacturing computing systems, electrical digital data processing, etc., can solve problems such as interference and distinguish noise, and achieve good application prospects.
Active Publication Date: 2022-02-08
DONGHUA UNIV
View PDF7 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to solve the problem that it is difficult to distinguish noise interference from drift data in the prior art, and to provide a dynamic production environment anomaly monitoring system oriented to real-time data flow
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0047] The invention is further illustrated in conjunction with specific embodiments. It will be appreciated that these examples are intended to illustrate the scope of the invention and are not intended to limit the scope of the invention. It will be appreciated that after reading the present invention, those skilled in the art can make various modifications or modifications of the present invention, which also fall in the scope of the claims appended claims.
[0048] Dynamic production environment abnormal monitoring system for real-time data streams, such as figure 1 As shown, it includes a real-time data collection module, a single node sparse discrete encoder generating module, a single-node real-time abnormality monitoring module, a full process all nodes in real time monitoring modules and production mode update modules;
[0049] The real-time data collection module includes a number of numerical acquisition sensors deployed in real-time industrial production systems, 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
Login to View More PUM
Login to View More Abstract
The present invention relates to a dynamic production environment abnormality monitoring system oriented to real-time data streams, including a real-time data collection module (I), a single-node sparse discrete encoder generation module (II), a single-node real-time abnormality monitoring module (III), and a whole process All nodes parallel real-time monitoring module (Ⅳ) and production mode update module (Ⅴ); Ⅰ is used to collect the values of each node and integrate them into multi-dimensional samples; Ⅱ is used to generate multiple sparse discrete encoders, each sparse discrete code Ⅲ is used to judge whether the value is abnormal; Ⅳ is used to monitor all nodes in parallel in real time, and identify the noise interference and concept drift of each node according to the decision matrix; Ⅴ is used to determine the occurrence of concept drift. While drifting, change production mode. The real-time data flow-oriented dynamic production environment anomaly monitoring system of the present invention can monitor system anomalies in real time and distinguish whether it is noise interference or production mode change.
Description
Technical field [0001] The present invention belongs to the industrial automation and intelligent manufacturing technical field, to dynamic production environment abnormality monitoring system for real-time data stream. Background technique [0002] In the intelligent production process, the data is a core element of the monitoring and drive the production process, real-time production data noise is often caused by a variety of physical interference from external production systems, which usually does not cause a change in the overall trend of the data. Causing the data to change the overall trend is typically produced inside the production system mode is changed, the change is reflected in the trend of the data, generally comprises a mutation in both cases and gradients. Academic data on this phenomenon occurs the change of trend called concept drift. At present, research on the concept of drift drift detection and focused on two aspects of adaptive learning, and problem disting...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06F16/215G06F16/2455G06Q10/06G06Q50/04G06Q10/00G07C3/00
CPCG06F16/215G06F16/24568G06Q10/0639G06Q50/04G06Q10/20G07C3/005Y02P90/30
Inventor 郝矿荣王伟凯陈磊蔡欣唐雪嵩王彤
Owner DONGHUA UNIV