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

Equipment residual life evaluation method based on continuous Weiner process damage

A technology for life evaluation and equipment, applied in computer-aided design, design optimization/simulation, biological neural network model, etc., can solve the problems of large error and damage in remaining life evaluation, and achieve the effect of accurate evaluation

Active Publication Date: 2021-06-15
NAVAL AERONAUTICAL UNIV
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical problem to be solved by the present invention is: a method for evaluating the remaining life of equipment based on continuous Weiner process damage to solve the problem of large errors in the evaluation of remaining life of equipment in the above-mentioned prior art

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
  • Equipment residual life evaluation method based on continuous Weiner process damage
  • Equipment residual life evaluation method based on continuous Weiner process damage
  • Equipment residual life evaluation method based on continuous Weiner process damage

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Embodiment 1: a kind of equipment remaining life assessment method based on continuous Weiner process damage, the method comprises the following steps:

[0055] Step 1: Initialize the monitoring data of the whole life cycle of n sample devices, and divide the data into multiple monitoring batches through sliding windows. Take the first two batches of data of each device, and mark the random number whose performance degradation is 0.01~0.05, take the last batch of data of each device, mark the random number whose performance degradation is 0.9~0.91, and mark the second last batch of data, Mark the random number whose performance degradation is between 0.89 and 0.9;

[0056] Step 2: Establish a general long-term short-term memory network (LSTM), and input the final batch monitoring data of each device and the corresponding performance degradation label value into the long-term short-term memory network (LSTM) for training;

[0057] Step 3: Input the trained long-short-te...

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 an equipment residual life evaluation method based on continuous Weiner process damage. The method mainly realizes conversion of continuous monitoring data of equipment into performance degradation indexes, evaluates reliability indexes of the equipment in each period based on a continuous Wiener process damage accumulation model in allusion to the fluctuation condition of a degradation physical process, and through overlong and short-term memory network training, full-life monitoring data of continuously operating equipment is converted into a single performance degradation index, and a reliability index and a performance index are fused through Bayesian information fusion to obtain a residual life prediction result of the equipment. The performance degradation index change in the early stage of equipment degradation is not obvious, and the performance degradation index change severely in the late stage of equipment degradation. Therefore, the method of combining continuous Wiener process damage accumulation and network training can greatly reduce the deviation of the residual life prediction of the equipment.

Description

technical field [0001] The invention relates to a method for evaluating the remaining life of equipment based on a continuous Wiener process damage accumulation model and a long-short-term memory network, belonging to the field of equipment reliability evaluation and failure prediction. Background technique [0002] At present, most of the reliability analysis adopts the traditional reliability theory. The traditional reliability analysis technology takes the failure time as the statistical analysis object. The method is to obtain the failure data of the product or its components through a large number of tests, and then use the statistical method, choose the most suitable statistical analysis model, and finally obtain the reliability of the product through the system reliability structure model and component life distribution model. However, in general, as the use time of the product increases, the characteristic parameters that characterize the performance of the product w...

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): G06F30/27G06N3/04G06F119/04
CPCG06F30/27G06F2119/04G06N3/044
Inventor 王瑞奇徐廷学顾钧元李海君
Owner NAVAL AERONAUTICAL UNIV
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com