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

Controllable medium-high calender anomaly detection method based on spatial domain conversion independent tree

An anomaly detection and calender technology, applied in machine learning, measuring devices, computer components, etc., can solve the problems of low detection accuracy and achieve the effect of improving detection accuracy and broad application prospects

Pending Publication Date: 2021-08-13
ZAOZHUANG UNIV +1
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] However, the methods based on statistics and distance widely used at home and abroad have some shortcomings: the methods based on statistics are based on standard statistical principles. Detect the anomalies in the data set accurately, and use this to determine the cause of the anomalies
The above two methods are aimed at local abnormal data detection, and their detection accuracy is low

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
  • Controllable medium-high calender anomaly detection method based on spatial domain conversion independent tree
  • Controllable medium-high calender anomaly detection method based on spatial domain conversion independent tree
  • Controllable medium-high calender anomaly detection method based on spatial domain conversion independent tree

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] This embodiment discloses a controllable medium and high voltage optical machine anomaly detection method based on the independent tree of space domain conversion, such as figure 1 As shown, the flow of the method is: calender operation status data collection, historical data modeling, real-time data detection, data classification, calender fault maintenance.

[0048] Specifically, this method includes the following steps:

[0049] S01), deploying status monitoring sensors at important and prone to failure parts of the calender, the sensors monitor the status information of each important or failure-prone parts of the calender under the running state, and transmit the collected status information to the computer terminal , for data storage to form a time series data set.

[0050] In this embodiment, a torque sensor is installed on the rotary joint at the end of the hot roller to detect the torque of the rotary joint; a vibration sensor is installed on the bearing seats...

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 controllable medium-high calender anomaly detection method based on a spatial domain conversion independent tree, and the method comprises the steps of mapping the operation state data of a calender into a feature space through a Gaussian kernel function, and converting local anomaly into global anomaly; and on the basis, constructing an independent tree model to carry out anomaly detection on a coring data set. In order to solve the problem of how to select the optimal division feature and the division sample value, the system provides an optimal division feature and division sample value selection strategy. And on the basis of keeping the global anomaly detection capability, the detection precision of the local anomaly points of the operation state data of the calender is also improved.

Description

technical field [0001] The invention relates to the field of abnormal detection of calender equipment faults, in particular to a method for detecting abnormalities of controllable medium and high voltage optical machines based on a space domain conversion independent tree. Background technique [0002] Controllable medium and high pressure light machine series equipment (including soft roll calender, nonwoven hot rolling mill and embossing machine, hereinafter referred to as calender) is not only an important high-end equipment in the paper industry, but also an important high-end equipment for melt blown cloth (medical masks). Core materials), reverse osmosis membranes (seawater desalination, water purifiers) and other high-value core equipment in emerging industries, with complex technical structures and high value, are key nodes in the intelligent manufacturing industry chain. [0003] The structure of the calender consists of frame, soft roll, hot roll, scraper, threadin...

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): G06K9/62G06F17/18G06N20/00G01D21/02
CPCG06F17/18G06N20/00G01D21/02G06F18/213G06F18/214
Inventor 屈洪春胡安明刘光辉宋传东曹旨昊姜振凤
Owner ZAOZHUANG UNIV