Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Multidimensional data anomaly detection method and device based on XGBoost

A multi-dimensional data and anomaly detection technology, applied in data processing applications, instruments, calculations, etc., can solve problems such as low accuracy and slow speed of multi-dimensional data

Pending Publication Date: 2020-06-12
HUADIAN POWER INTERNATIONAL CORPORATION LTD
View PDF11 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problems existing in the prior art, the present invention is based on the real multi-dimensional measuring point data of thermal power plant equipment, and aims at the problems of slow speed and low accuracy when dealing with multi-dimensional data in the current equipment anomaly detection method, and proposes a multi-dimensional detection method based on XGBoost Time series data anomaly detection method and device

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
  • Multidimensional data anomaly detection method and device based on XGBoost
  • Multidimensional data anomaly detection method and device based on XGBoost
  • Multidimensional data anomaly detection method and device based on XGBoost

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] Such as figure 1 As shown, the multidimensional data anomaly detection method based on XGBoost includes:

[0058] Step 1: Data collection and cleaning. Most of the original multi-dimensional data comes from real-time data collected by thermal power plant equipment sensors. Due to the long-term deterioration of sensors or the influence of noise in the data transmission process, there may be some obvious differences in the original data that are measured by the sensors. Values ​​outside the range are either directly implemented as 0 or null. Such data (referred to as interference value in the present embodiment) cannot explain that the operation of the equipment is in an abnormal state, and when such data is input into the abnormal detection system for abnormal detection, it will often bring false positive results. Therefore, after obtaining the original data, it is necessary to perform preprocessing on the original data to remove these interference values.

[0059] 1-...

Embodiment 2

[0092] A detection device installed with the above method, including a memory, a processor, an I / O device and an alarm device that are electrically connected and stored with a program for realizing the above method, and the I / O device is connected to a computer and / or network that installs the monitoring software of the power plant, Access and obtain real-time measurement point data.

[0093] The processor is connected to the hand-held user terminal through wireless transmission. Remote monitoring and early warning through handheld devices.

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 belongs to the field of power plant safety control systems, and particularly relates to a multi-dimensional data anomaly detection method and device based on XGBoost. The method is characterized by comprising a first step of data acquisition and cleaning, a second step of performing standardization processing on cleaned data, and unifying dimensions between data of different dimensions; step 3, feature extraction and dimension reduction; step 4, exception detection model training: training the dimension reduction data by using an XGBoost method, and establishing a prediction model of equipment exception; and step 5, abnormity on-line detection is carried out, and if a given threshold value is exceeded, it is determined that abnormity occurs. The method is suitable for processing and predicting important abnormal events of equipment, the thought and technology of ensemble learning are fully utilized, important features in multi-dimensional data information detected by an equipment sensor are effectively utilized, and then online abnormal detection based on real-time measuring point data of a power plant is achieved. The method is large in collected data volume, small in analysis error and high in early warning result accuracy.

Description

technical field [0001] The invention belongs to the field of thermal power generation, and relates to a multidimensional data anomaly detection method and device derived from sensor measurement points, in particular to an XGBoost-based multidimensional data anomaly detection method and device. Background technique [0002] With the rapid development of thermal power plant information construction, equipment fault diagnosis and predictive maintenance are getting more and more attention. There are a large number of large-scale equipment in thermal power plants. The equipment structure is complex and the working environment is harsh, which is easy to cause various failures. If it cannot be found and repaired in time, it will seriously affect the safety and reliability of its operation. Moreover, once the key equipment of the power plant fails and shuts down, it will affect the stable operation of the thermal power plant system, cause huge economic losses, and even affect the st...

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): G06Q10/06G06Q10/00G06Q50/06G06K9/62
CPCG06Q10/0639G06Q10/20G06Q50/06G06F18/2148G06F18/2135G06F18/2433Y04S10/50
Inventor 葛凌峰杜彬田锐庄浩君王宝鑫刘茂明宋峰
Owner HUADIAN POWER INTERNATIONAL CORPORATION LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products