Tiny fault detection method based on Kolmogorov-Smirnov inspection

A kind of fault detection and micro technology, applied in the direction of comprehensive factory control, instruments, complex mathematical operations, etc., can solve the problems of insensitivity to micro faults, low fault false alarm rate, low fault detection rate, etc., to overcome the small fault detection performance. good, low false positive rate and low false positive rate, and the effect of reducing serious harm

Pending Publication Date: 2022-05-24
NANTONG UNIVERSITY
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] In view of this, the object of the present invention is to provide a micro-fault detection method based on the Kolmogorov-Smirnov test, in order to solve the problems that the traditional data-driven fault detection method is not sensitive to micro-faults, and the fault detection rate is low. This method has a high fault detection rate and a low fault false alarm rate when detecting small faults

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
  • Tiny fault detection method based on Kolmogorov-Smirnov inspection
  • Tiny fault detection method based on Kolmogorov-Smirnov inspection
  • Tiny fault detection method based on Kolmogorov-Smirnov inspection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] see Figure 1-Figure 7 , this embodiment provides a method for detecting tiny faults based on the Kolmogorov-Smirnov test, the method is oriented to the CSTH process, and CSTH is an experimental platform developed by the laboratory of the University of Alberta in Canada. The function of the stirring tank is to mix the hot and cold water together, and then the mixture is heated by steam, and the heated mixed water finally flows out from the bottom of the heating tank. Its process flow chart is as follows figure 2 shown. The cross section of the stirred tank is circular, with a volume of 8 liters and a height of 0.5 meters. Although the model of the CSTH process is small and has no actual reaction process, all sensors, valves and heat exchangers in the process have complete characteristics , thus simulating the process of exothermic chemical reaction.

[0054] In this embodiment, MATLAB is used as the simulation platform, and a simulation model is built in Simulink, a...

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 small fault detection method based on Kolmogorov-Smirnov inspection, which comprises the following steps of: after carrying out standardized preprocessing on a training sample, establishing a PCA model and obtaining a load matrix P, then collecting sample data on line in real time, calculating a principal component space of online data by utilizing the PCA model established in an offline process, and finally obtaining a load matrix P; and performing K-S test on the principal component space of the training data and the online data, and comparing the value of the K-S test statistic Dn with a control limit to realize online monitoring. According to the method, the problem that the detection performance of the small fault is poor due to the small amplitude of the small fault in a traditional PCA fault detection method is solved, and the detection rate of the small fault is high.

Description

technical field [0001] The invention relates to the technical field of micro-fault detection, in particular to a micro-fault detection method based on Kolmogorov-Smirnov test. Background technique [0002] With the rapid development of modern economy and the continuous improvement of scientific and technological level, industrial processes or equipment are becoming more and more complex and large. This presents a serious challenge to the engineers responsible for ensuring the reliable operation of the process. Once a minor fault occurs in the production process or equipment, if it cannot be discovered and handled properly, it will gradually develop into a serious fault or even cause a major accident over time, resulting in casualties and huge economic losses. [0003] A fault is an undesired feature or any abnormality manifested in a system. Therefore, in modern industry, fault detection is essential to improve system reliability, prevent severe system performance degradat...

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): G06K9/62G06F17/18G06F17/16
CPCG06F17/18G06F17/16G06F18/2135Y02P90/02
Inventor 商亮亮泮佳俊张帆蒋玮平顾银波唐一鸣华亮傅怀梁
Owner NANTONG UNIVERSITY
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