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

A method of industrial process fault diagnosis based on kpca

A fault diagnosis and industrial process technology, applied in the direction of instruments, electrical testing/monitoring, control/regulation systems, etc., can solve the problem of inability to effectively distinguish fault information from normal information, excessive reconstruction, and inability to reflect the nonlinear characteristics of data, etc. question

Active Publication Date: 2017-05-10
SHEN ZHEN FENGJING NETWORKS TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the traditional fault reconstruction method is a linear modeling method, which cannot reflect the nonlinear characteristics of the data; and this method only focuses on the internal relationship of the fault data, and cannot effectively distinguish the fault information from the normal information in the data. Fault reconstruction based on the fault feature direction extracted by the method will lead to excessive reconstruction

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
  • A method of industrial process fault diagnosis based on kpca
  • A method of industrial process fault diagnosis based on kpca
  • A method of industrial process fault diagnosis based on kpca

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0215] Real-time collection of 400 new data 1 of the smelting process of the fused magnesium furnace, the T of the new data 1 2 Statistical detection diagram and SPE statistical detection diagram such as Figure 6 As shown, among them, Figure 6 (a) T for the new data 2 Statistics check chart, Figure 6 (b) is the SPE statistic detection chart of the new data. It can be seen from the figure that the T of the new data 1 2 Both statistics and SPE statistics began to exceed the limit at about the 101st sampling point, and formed a stable alarm, indicating that a fault occurred.

[0216] For new data 1, use the historical fault data of type l for T 2 According to the fault characteristic direction reconstructed by statistics, the fault direction is reconstructed for the new data, and the fault direction is reconstructed for the new data according to the fault characteristic direction reconstructed by the SPE statistics by using the historical fault data of type l.

[0217] Fo...

Embodiment 2

[0221] Real-time collection of 400 new data 2 of the smelting process of the fused magnesium furnace, the T of the new data 2 2 Statistical detection diagram and SPE statistical detection diagram such as Figure 9 As shown, among them, Figure 9 (a) T for the new data 2 Statistics check chart, Figure 9 (b) is the SPE statistic detection diagram of the new data. It can be seen from the figure that the T of the new data 2 2 Both statistics and SPE statistics began to exceed the limit around the 150th sample, and formed a stable alarm, indicating that a fault occurred.

[0222] For the new data 2, use the l-type historical fault data for T 2 According to the fault characteristic direction reconstructed by statistics, the fault direction is reconstructed for the new data, and the fault direction is reconstructed for the new data according to the fault characteristic direction reconstructed by the SPE statistics by using the historical fault data of type l.

[0223] For class...

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 an industrial process fault diagnosis method based on KPCA. The KPCA method is used to extract the load direction of the principal component subspace and the load direction of the residual subspace from the historical normal data of the industrial production process. The historical faults of known faults are The data uses the KPCA method to extract the load direction of the pivot subspace and the load direction of the residual subspace. Historical fault data of known fault types are reconstructed based on T2 statistics and SPE statistics to extract historical faults. The fault characteristic direction reconstructed from the data for T2 statistics and the fault characteristic direction reconstructed for SPE statistics are obtained to obtain the reconstructed fault characteristic direction set, new data of the industrial production process are collected in real time, and the T2 statistics of the new data are calculated using the KPCA method. and SPE statistics to determine whether a fault occurs in the industrial production process collected in real time, and use the reconstructed fault characteristic direction set to reconstruct the fault direction of the new data to determine the fault type of the current industrial production process.

Description

technical field [0001] The invention belongs to the field of process control, and in particular relates to a KPCA-based industrial process fault diagnosis method. Background technique [0002] Using the data obtained in the industrial production process to model and detect and diagnose the faults in the production process is a very challenging problem, which has received extensive attention in recent years. Many scholars have studied the detection and diagnosis of faults in the production process by using multivariate statistical methods such as PCA and PLS. These methods are able to extract the latent characteristics of the measurement data, and use statistical principles to define detection statistics and their control limits under normal production conditions based on these characteristics. During on-line monitoring, the corresponding statistics are calculated through the new sampling data, and if the result exceeds the limit and an alarm is issued, it is considered that...

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 Patents(China)
IPC IPC(8): G05B23/02
CPCG05B23/0235
Inventor 张颖伟杜文友严启保王正兵
Owner SHEN ZHEN FENGJING NETWORKS TECH CO LTD
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