A Remaining Life Prediction Method for Multi-sensor System

A multi-sensor, life prediction technology, used in instruments, measuring electricity, measuring devices, etc.

Active Publication Date: 2021-03-23
SICHUAN UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The present invention provides a method for predicting the remaining life of a multi-sensor system, which has the advantage of accurate

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 Remaining Life Prediction Method for Multi-sensor System
  • A Remaining Life Prediction Method for Multi-sensor System
  • A Remaining Life Prediction Method for Multi-sensor System

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0114] see figure 1 , a method for predicting the remaining life of a multi-sensor system, the method for predicting the remaining life of the multi-sensor system mainly includes using a data fusion method to characterize the health index of the electromechanical equipment and using a particle filter method to realize the prediction of the health state of the electromechanical equipment, the data fusion method By fusing multiple sensor data, a health indicator with a good degradation trend and a small threshold variance is constructed to characterize the health status of the device. When the health indicator is constructed using the data fusion method, the health indicator will often have a greater improvement. Second-order arrangement Entropy, to make the health index have a good overall monotonic trend, thereby improving the prediction accuracy of the remaining life of electromechanical equipment, the specific implementation steps are as follows:

[0115] S1 calculates the i...

Embodiment 2

[0143] see figure 1 , the difference between this embodiment and the above-mentioned embodiment is that: the tasteless Kalman filter is used in this embodiment to select the suggested distribution of the particle filter, since the particle filter algorithm uses the prior distribution as the suggested density distribution function, when the prior distribution and When the coincidence degree of the posterior distribution is very small, the effect of the particle filter algorithm is poor, so that when the particle filter algorithm is used to predict the remaining effective life of the electromechanical equipment, the prediction accuracy will be reduced accordingly. Therefore, the tasteless Kalman filter is used in this embodiment to To choose the proposed distribution of particle filter, first in the sampling stage, calculate the mean and covariance of each particle with tasteless Kalman filter, and then use the mean and covariance to guide sampling, and use tasteless Kalman filte...

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 the technical field of electromechanical equipment health management and discloses a residual life prediction method for a multi-sensor system. The method comprises the following specific implementation steps: S1, calculating improved second order permutation entropy of sensor data; S2, according to the calculation method in the step S1, calculating improved second order permutation entropies of all the sensor data and comparing; and S3, selecting the improved second order permutation entropies and using data of sensors for data fusion. The residual life prediction method for the multi-sensor system provides an improved second order permutation entropy index for measuring a monotony trend of data, data of multiple sensors is fused by virtue of a data fusion method,a health index with a good degradation trend and smaller threshold variance is built for representing health status of equipment, then data of the health index is taken as a tasteless particle filtering observed value, the health status of the equipment is estimated and predicted, and residual life prediction on the multi-sensor system is finally realized.

Description

technical field [0001] The invention relates to the technical field of electromechanical equipment health management, in particular to a method for predicting the remaining life of a multi-sensor system. Background technique [0002] With the rapid development of modern science and technology and the continuous improvement of functional requirements, the complexity, comprehensiveness and intelligence level of a large number of electromechanical equipment continue to increase, making these electromechanical equipment a large and complex multi-sensing system. At the same time, these equipment Reliability and safe operation performance are becoming more and more important. However, complex operating conditions and harsh operating environments will lead to inevitable performance degradation of electromechanical equipment during operation. When the performance of electromechanical equipment degrades to When the equipment is not enough to complete its function, it will lead to equ...

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
IPC IPC(8): G01R31/00
CPCG01R31/00
Inventor 苗强张恒罗冲莫贞凌
Owner SICHUAN UNIV
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