Industrial equipment remaining useful life prediction model and construction method and application thereof

A technology of life prediction model and industrial equipment, applied in the direction of comprehensive factory control, comprehensive factory control, general control system, etc., can solve the problems that the data set processing method cannot effectively denoise, the prediction accuracy of the model is not high, and improve the prediction accuracy , the effect of improving the predictive ability

Active Publication Date: 2019-12-24
HUAZHONG UNIV OF SCI & TECH
View PDF11 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a prediction model for the remaining life of industrial equipment and its construction method and application, which are used to solve the problem that the construction of the remaining life p

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
  • Industrial equipment remaining useful life prediction model and construction method and application thereof
  • Industrial equipment remaining useful life prediction model and construction method and application thereof
  • Industrial equipment remaining useful life prediction model and construction method and application thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] A construction method 100 of a remaining life prediction model for industrial equipment, such as figure 1 shown, including:

[0045] Step 110, collecting a plurality of full-life multi-feature data sets of the same industrial equipment under different failure modes, and constructing a multi-dimensional matrix of each full-life multi-feature data set;

[0046] Step 120, using a sliding window to slice each multi-dimensional matrix in time series to obtain multiple time-sliced ​​matrices of the multi-dimensional matrix;

[0047] Step 130, classify all time slice matrices according to the type of failure mode;

[0048] Step 140 , based on all the time slice matrices corresponding to each failure mode, train the CNN-RNN hybrid remaining life prediction model of the failure mode, and obtain the remaining life prediction model library of industrial equipment.

[0049] The distributed sensor network is used to collect and record the data changes in multiple dimensions such a...

Embodiment 2

[0113] An industrial equipment remaining life prediction model library is constructed by using any method for constructing an industrial equipment remaining life prediction model described in the first embodiment above.

[0114] The relevant technical solutions are the same as those in Embodiment 1, and will not be repeated here.

Embodiment 3

[0116] A remaining life prediction method 200 of industrial equipment, such as figure 2 and image 3 shown, including:

[0117] Step 210, obtain the test data set of the industrial equipment to be tested and the above-mentioned predictive model library, and determine the construction method of the predictive model library;

[0118] Step 220, according to the processing operation of the full-life multi-feature data set in the construction method, process the test data set to obtain multiple time slice matrices;

[0119] Step 230, calculate the Euclidean distance between multiple time slice matrices and all time slice matrices required for training each prediction model in the prediction model library, and determine the prediction model with the closest distance;

[0120] Step 240: Based on multiple time slice matrices, use the prediction model with the closest distance to predict the remaining life of the industrial equipment under test under the test data set.

[0121] The...

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 industrial equipment remaining useful life prediction model and a construction method and application thereof. The method comprises the steps that full-life multi-feature datasets of multiple sets of identical industrial equipment under different fault modes are collected, and a multidimensional matrix of each full-life multi-feature dataset is constructed; a sliding window is adopted to perform time sequence slicing on each multidimensional matrix, and multiple time slice matrixes of each multidimensional matrix are obtained; according to the types of the fault modes, all the time slice matrixes are sorted; and based on all the time slice matrixes corresponding to each fault mode, a CNN-RNN (Convolutional Neural Network-Recurrent Neural Network) hybrid prediction model of each fault mode is trained to obtain the remaining useful life of the industrial equipment. According to the prediction model, by using the sliding window to perform time sequence slicing on multidimensional data, the diversity of hybrid model input is improved; a model base is constructed by use of pre-sorting, and the datasets containing the multiple fault modes are processed to improve the model prediction precision; and by constructing a CNN-RNN hybrid network, the end-to-end remaining useful life prediction model without self-definition of a failure threshold is realized.

Description

technical field [0001] The invention belongs to the field of modern industrial failure prediction and health management, and more specifically relates to a prediction model for the remaining life of industrial equipment and its construction method and application. Background technique [0002] Prognostic Health Management (PHM) technology is one of the most important core technologies in the development of modern industry. Due to the loss of machinery itself, external damage and other reasons, the equipment will have mechanical failures due to performance degradation, causing accidents, and even causing casualties or huge property losses in severe cases. PHM technology predicts the remaining service life of equipment, and on this basis, adopts appropriate means to manage health and improve the reliability and safety of equipment. Remaining Useful Life (RUL) technology is an important part of life prediction and health management. By accurately predicting the remaining life,...

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): G05B19/418
CPCG05B19/41885G05B2219/32339Y02P90/02
Inventor 董燕张馨云鲁放文龙
Owner HUAZHONG UNIV OF SCI & 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