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

Aluminum profile extrusion process flow data anomaly detection method and device based on isolated forest algorithm and storage medium

A forest algorithm, extrusion process technology, applied in computing, computer parts, instruments, etc., can solve the problems of inaccurate abnormal detection results and inaccurate abnormal detection of streaming data.

Active Publication Date: 2020-11-13
GUANGDONG UNIV OF TECH
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to overcome the inaccuracy of abnormality detection in the prior art, and provide an abnormality detection method, equipment and storage medium for aluminum profile extrusion process flow data based on the isolated forest algorithm, which can update the model in real time and solve the problem of flow data There are problems in noise and concept drift that lead to inaccurate anomaly detection results

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
  • Aluminum profile extrusion process flow data anomaly detection method and device based on isolated forest algorithm and storage medium
  • Aluminum profile extrusion process flow data anomaly detection method and device based on isolated forest algorithm and storage medium
  • Aluminum profile extrusion process flow data anomaly detection method and device based on isolated forest algorithm and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0079] This embodiment discloses a method for detecting anomalies in aluminum profile extrusion process flow data based on the isolated forest algorithm. The method is proposed on the basis of the half-space isolated forest (HS-Trees) model, wherein the half-space isolated forest (HS-Trees ) The establishment process of the model subtree is mainly divided into two stages: subtree construction and node quality calculation. In the subtree construction stage, the value boundary of each dimension of the data is obtained, a certain dimension is randomly selected, and the midpoint of the dimension is used as the dividing point to cut the subspace. The dimension information of the subspace is updated, and each subspace is divided again, and the half-space tree is obtained through the iterative division process, as shown in Algorithm 1.

[0080] Algorithm 1 HS-Trees Subtree Construction Algorithm-BuildTree

[0081]

[0082]

[0083] In the node quality calculation stage, record...

Embodiment 2

[0139] In this embodiment, the method, equipment and storage medium in Example 1 are used to carry out experiments on the extruder, and the experimental results prove that the method proposed by the present invention can not only detect in real time the abnormal state of the extruder during operation, And it has higher accuracy.

[0140] The experiment is as follows:

[0141] 1) Experimental environment and data

[0142] The environment used in the experiment of the present invention is Intel(R) Core(TM) i5-7300HQ@2.5GHz, 16GB RAM, Windows 10 64-bit system, and the algorithm is implemented using Python 3.7.

[0143] 2) Evaluation indicators

[0144] The present invention uses the three most commonly used indicators in the field of anomaly detection, namely accuracy rate, recall rate and precision rate, to verify the anomaly detection performance of the model. Among them, the correct rate indicates the proportion of the number of correct judgments by the model to the total d...

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 relates to the technical field of streaming data anomaly detection and more specifically relates to an aluminum profile extrusion process stream data anomaly detection method and devicebased on an isolated forest algorithm and a storage medium. The method comprises the following steps: S10, reading original stream data of an extrusion process of an extruder, and initializing a multi-feature semi-space isolated forest model through the original stream data; S20, entering a detection period, and using the multi-feature semi-space isolation forest model to perform anomaly detectionon the stream data in the current period; S30, judging whether the detection period is finished or not; if not, returning to the step S20, updating the detection period, and if so, entering the nextstep; S40, judging whether the abnormal rate of the current period is greater than a threshold value or not, if so, indicating that concept drift exists, updating the model by using the data of the current period; if not, returning to the step S20, and entering the next period for detection until all periods are detected. The model can be updated in real time, and the problem that abnormal detection results are inaccurate due to noise and concept drift existing in streaming data is solved.

Description

technical field [0001] The present invention relates to the technical field of flow data anomaly detection, and more specifically, to a method, device and storage medium for detecting flow data anomalies in an aluminum extrusion process based on an isolated forest algorithm. Background technique [0002] my country is a big country in the production, export and consumption of aluminum profiles. In 2015, the output of processed aluminum profiles in my country reached 26,000kt / a, and the output of aluminum alloy extrusions reached 14,000kt / a, ranking among the top in the world. Further statistics show that in 2017, the output of extruded aluminum in China continued to rise, reaching 19,500kt / a, accounting for 55% of the world's total output. There are about 1,850 modern hydraulic presses with various extrusion forces, accounting for about 10% of the global total. 70%. The scale of aluminum production and consumption continues to expand, and further analysis of the production...

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): G06K9/62
CPCG06F18/2433G06F18/24323Y02P90/30
Inventor 杨海东印四华徐康康朱成就许志城胡罗克
Owner GUANGDONG UNIV OF 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com