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

Multi-index anomaly detection method based on machine learning and application system thereof

An anomaly detection and machine learning technology, applied in the field of intelligent operation and maintenance, which can solve the problems of consuming storage space resources, unnecessary calculation, and high time cost

Pending Publication Date: 2021-06-01
中国信托登记有限责任公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The disadvantage of the existing technology is that the algorithm is complicated, a large number of unnecessary calculations are generated, the calculation speed is slow, the time cost is too high, and redundant storage space resources are consumed

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
  • Multi-index anomaly detection method based on machine learning and application system thereof
  • Multi-index anomaly detection method based on machine learning and application system thereof
  • Multi-index anomaly detection method based on machine learning and application system thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only Some, but not all, embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0065] The embodiment of the present invention provides a multi-indicator anomaly detection method based on machine learning. The method is based on the multi-indicator algorithm of RS-hash, and estimates the data of the local subspace area related to the point through random local parameters, bias parameters, and sub-dimensions. distribution, and average these distrib...

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 multi-index anomaly detection method based on machine learning and an application system thereof, the multi-index anomaly detection method is based on an RS-hash multi-index algorithm and depends on random hash, the randomness of the hash is reflected in three aspects of a detection distribution range, a detection sample and a subspace dimension, and the detection accuracy is improved. Abnormality is detected by analyzing data distribution of local subspace regions related to random local parameters, bias parameters and sub-dimension estimation points and averaging the distribution on local subspaces of different sizes.

Description

technical field [0001] The invention relates to the technical field of intelligent operation and maintenance, in particular to a multi-indicator anomaly detection method based on machine learning and an application system thereof. Background technique [0002] In recent years, the idea of ​​using machine learning methods to detect anomalies and faults has aroused great interest in the research community. Applying machine learning-based anomaly or fault detection methods to the direction of operation and maintenance monitoring has also become an important topic in the research of enterprises in the direction of operation and maintenance monitoring. Its methods can be roughly divided into supervised methods and unsupervised methods. [0003] Supervised methods rely on using labeled training data to accurately identify known anomalies that have occurred before. Unsupervised methods do not require labeled training data to discover problems, and are more suitable for the existi...

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): G06N20/20
CPCG06N20/20
Inventor 冯雪云史相冬宋文欣黄彬何斌陈坤
Owner 中国信托登记有限责任公司