Real-time fault detection and real-time fault isolation of multi-dimensional signals

A real-time fault detection method technology, applied in the field of sensor detection, to achieve the effect of real-time fault detection and real-time fault isolation

Inactive Publication Date: 2019-03-15
HARBIN INST OF TECH
View PDF3 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 solve the real-time problem of fault detection and isolation of sensor multi-dimensional signals in equipment or instruments, and provide a method for real-time fault detection and real-time fault isolation of multi-dimensional signals

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
  • Real-time fault detection and real-time fault isolation of multi-dimensional signals
  • Real-time fault detection and real-time fault isolation of multi-dimensional signals
  • Real-time fault detection and real-time fault isolation of multi-dimensional signals

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0026] Specific implementation mode one: the following combination figure 1 This embodiment is described. The real-time fault detection method for multi-dimensional signals described in this embodiment extracts the approximate basis of the normal training set to form the approximate basis of the training samples in the normal state, and uses the approximate basis of the training samples in the normal state to construct the core. Component analysis fault detection model, kernel principal component analysis fault detection model When a fault is detected, a reconstruction-based contribution method is used to detect the locations of all faulty gas sensors.

[0027] In this embodiment, the Kernel Principal Component Analysis (KPCA) method is projected from the original data space to the high-dimensional space F, and the Principal Component Analysis (PCA) method is executed in F.

specific Embodiment approach 2

[0028] Embodiment 2: In this embodiment, Embodiment 1 is further explained. The approximate basis for extracting the normal training set is to use the minimum number of training samples to represent the features of the entire training sample set.

specific Embodiment approach 3

[0029] Specific embodiment three: this embodiment will further explain embodiment one or two, extract the approximate base of the normal training set, form the approximate base of the training sample under the normal state, and use the approximate base of the training sample under the normal state to construct the core The specific process of component analysis fault detection model is as follows:

[0030] X={x n}(n=1,2,...,N) represents the entire training sample set of kernel principal component analysis, where N represents the number of training samples;

[0031] is the entire training sample set X={x n}(n=1,2,…,N), where p(pB the sample size;

[0032] represents the approximate base X B Projection vector in high-dimensional space F;

[0033] per sample x n The projection vector of The approximate value of is expressed as: where θ n =(θ 1 ,θ 2 ,…,θ p ); p Represents the mapping value of the pth training sample in the high-dimensional space F; the projectio...

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

A method for real-time fault detection and isolation of multi-dimensional signals belongs to the field of sensor detection. The invention solves the real-time problem of fault detection and isolationof multi-dimensional signals of sensors in equipment or instruments. According to the invention, approximate basis of normal training set is extracted, The approximate basis of training samples in normal state is formed, and the fault detection model of KPCA is constructed by using the approximate basis of training samples in normal state. When the fault is detected by the fault detection model ofKPCA, the position of all the fault gas sensors is detected by the contribution method based on reconstruction. The real-time fault isolation method of multi-dimensional signals adopts the contribution method based on reconstruction to construct the fault direction candidate set of the fault information at the previous time and isolate the fault at the current time. The present invention is usedto determine the accuracy and reliability of a multidimensional signal of a sensor.

Description

technical field [0001] The invention relates to a multivariable real-time fault detection and real-time fault isolation method, which belongs to the field of sensor detection. Background technique [0002] Modern equipment and instruments can measure multiple parameters simultaneously and are widely used in more and more chemical processes. As a data acquisition device, if incorrect information is used in system decision-making, serious accidents will occur. Therefore, the accuracy and reliability of multi-dimensional sensor signals are particularly important for the entire system. [0003] Modern equipment or instruments make decisions based on the measured values ​​of sensors, and sensors, as information acquisition units, exist in large numbers in equipment or instruments. For some equipment or instruments with harsh working conditions (high temperature, high pressure, high humidity, high salinity), sensor failure is inevitable, and the frequency of failure is high, whic...

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
CPCG06F18/2135
Inventor 杨京礼陈寅生孙震刘晓东
Owner HARBIN INST OF TECH
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap