Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Prediction method for residual life of gear based on LSTMPP

A prediction method and gear technology, applied in instruments, biological neural network models, calculations, etc., can solve problems such as wasting computing resources, unfavorable life prediction, affecting the training speed and accuracy of neural network models, and achieve good results

Active Publication Date: 2019-09-06
CHONGQING UNIV
View PDF9 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

First of all, the long-term information storage capacity of LSTM is also limited. The storage of redundant information is not conducive to life prediction and will waste computing resources in vain.
And the existence of irrelevant and / or redundant features will affect the speed and accuracy of neural network model training

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
  • Prediction method for residual life of gear based on LSTMPP
  • Prediction method for residual life of gear based on LSTMPP
  • Prediction method for residual life of gear based on LSTMPP

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0080] According to the LTSMPP neural network model and prediction method proposed above, the experiment will be carried out below. In this experiment, the first-stage transmission is accelerated and the second-stage transmission is decelerated, which just makes the transmission ratio of the experimental gearbox 1:1. The material used for the experimental gear is 40Cr, the machining accuracy is grade 5, the surface hardness is 55HRC, and the modulus is 5. In particular, the number of teeth of the large gear is 31, the number of teeth of the pinion is 25, and the width of the first stage transmission gear is 21mm. In this experiment, the torque is 1400N.m, the speed of the large gear is 500r / min, the amount of lubricating oil in the experimental gearbox is 4L / h, and the cooling temperature is 70 degrees. The mode of collecting data selects all data during the collection process. Due to the large torque, the gear of the first stage transmission broke teeth after running for 81...

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 a gear residual life prediction method based on LSTMPP, and belongs to the field of big data and intelligent manufacturing. The method comprises the steps of firstly, simplifying and fusing high-dimensional features of collected gear vibration signals; then using the fusion feature information subjected to dimension reduction for multi-step prediction of an eccentric longshort-term memory network LSTMPP, and performing eccentric processing on the fusion feature data by adopting an attention mechanism method according to the characteristic that different feature information contains different information amounts; and finally, amplifying the weights of the input data and the recursive data according to an eccentric processing result, and performing automatic and different degrees of processing on the fused feature data. The prediction speed and precision of the residual life of the gear can be improved while the calculated amount is reduced.

Description

technical field [0001] The invention belongs to the field of big data and intelligent manufacturing, and relates to a method for predicting the remaining life of gears based on LSTMPP. Background technique [0002] Gears are widely used in mechanical equipment and are one of the most widely used mechanical parts. Gears have unique advantages such as high transmission efficiency, compact structure, good transmission smoothness, large carrying capacity, and long service life, which make them have strong and lasting vitality. Under complex working conditions and environments, gears are prone to failure, which may lead to disasters in machine operation and even endanger personal safety. This is especially true for large or very large equipment, such as hydroelectric generators, mining conveying machinery, helicopter power transmission systems, heavy machine tools, etc. The life prediction of in-service gears can effectively determine the maintenance time of equipment, improve ...

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): G06F17/50G06N3/04
CPCG06N3/049G06F2119/04G06F30/17
Inventor 秦毅项盛金磊王阳阳
Owner CHONGQING 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
Eureka Blog
Learn More
PatSnap group products