Multi-sensor fusion convolutional neural network aero-engine bearing fault diagnosis method

A convolutional neural network, multi-sensor fusion technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as difficult to accurately identify, unclear fault characteristics, etc., to achieve the effect of information processing

Inactive Publication Date: 2021-10-01
ZHEJIANG UNIV CITY COLLEGE
View PDF10 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Aeroengine mechanical failures can generally be divided into gas path failures, accessory failures, and rotating machinery failures. Rotating machinery failures are analyzed and solved based on traditional physical mechanism dynamic models due to their various types of failures and

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
  • Multi-sensor fusion convolutional neural network aero-engine bearing fault diagnosis method
  • Multi-sensor fusion convolutional neural network aero-engine bearing fault diagnosis method
  • Multi-sensor fusion convolutional neural network aero-engine bearing fault diagnosis method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0043] Embodiment 1 of the present application provides a multi-sensor fusion convolutional neural network aeroengine bearing fault diagnosis method, including: data collection, data preprocessing, data storage, source domain 1D-CNN model offline training, target domain bearing online diagnosis, wherein :

[0044] Data acquisition part: Arrange vibration acceleration sensors according to actual needs, and collect acceleration signals at different positions and directions of the equipment.

[0045]Data preprocessing part: It is necessary to normalize, slice and label the collected original state parameters, and convert them into data types that can be recognized by 1D-CNN.

[0046] Further, the normalization process adopts maximum and minimum value normalization, and the formula is:

[0047]

[0048] Where: x max is the maximum value of the sample data, x min is the minimum value of the sample data, x` is the normalized result, and the value interval is [0, 1].

[0049] ...

Embodiment 2

[0071] Such as figure 2 Shown is a multi-sensor fusion convolutional neural network aero-engine bearing fault diagnosis method flow chart, including: data acquisition and preprocessing, offline training, online diagnosis. Specifically include the following steps:

[0072] S1. Data collection: Collect the relevant data of deep groove ball bearings tested on a helicopter transmission system test bench and the main reduction test bench. The sampling frequency is 10,000 Hz, and the sampling time is 3 minutes, that is, 1,800,000 data points are sampled for each fault type; Bearing fault types are outer ring fault, inner ring fault, rolling element fault, combined fault and normal bearing;

[0073] S2. Data preprocessing: normalize, slice, and label the data, and convert the data into a data type that can be used for supervised learning. The data structure is shown in Table 1:

[0074] Table 1 Labels of the gear dataset

[0075] Number of samples (training set / test set...

Embodiment 3

[0081] According to the 1D-CNN neural network model and the principle of multi-sensor information fusion, the specific structural parameters of the aeroengine bearing fault diagnosis model proposed by the present invention are shown in Table 2.

[0082] The 1D-CNN established by the present invention for aeroengine bearing fault diagnosis is composed of four sub-models with the same parameters, and each sub-model includes four sets of convolution-maximum pooling layers and one average pooling layer. The output of the last layer of each sub-model is aggregated and input to the same Flatten layer for flattening, and finally the recognition result is output in the Softmax layer. After the original bearing data passes through the convolutional layer, it is converted into a set of feature maps (multi-channel one-dimensional array), and then it is down-sampled by maximum pooling, thereby reducing the number of parameters. After these operations are repeated 3 times, the characterist...

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 multi-sensor fusion convolutional neural network aero-engine bearing fault diagnosis method. The method comprises the steps of S1, performing data acquisition; s2, performing data preprocessing; s3, taking the data acquired by the analogue simulation test platform as source domain data, and taking the data acquired by the online monitoring system as target domain data; s4, building a multi-sensor information fusion 1D-CNN model, and putting the source domain data into the source domain 1D-CNN model for training; s5, carrying out target domain bearing online diagnosis; s6, generating a fault diagnosis result. Vibration signals of different positions of aero-engine bearing in different fault states are collected, multi-channel input 1D-CNN model is adopted, data collected by vibration acceleration sensors at different positions are fused and put into model for training, and target domain bearing online diagnosis is carried out. Therefore, the fault diagnosis and analysis are carried out on the bearing of the rotating mechanical part of the aero-engine, so that fault type identification is accurately completed, and the process of manual feature mining in a traditional method is omitted.

Description

technical field [0001] The invention relates to the field of fault diagnosis of electromechanical systems, in particular to a multi-sensor fusion convolutional neural network aeroengine bearing fault diagnosis method. Background technique [0002] According to the statistical report on my country's civil aviation safety information in 2018, nearly 40% of the general aviation accidents that occur each year are caused by mechanical problems such as equipment system failures, failures, wear and tear of key parts, and the engine as an aviation aircraft. The key power components, due to their complex mechanical structure, high temperature and high pressure and other harsh operating environments, are more prone to mechanical damage to their internal components after a period of use. The failures of aeroengines are mostly caused by the shafting parts (such as gears, bearings, etc.) that constitute its rotating mechanism. Once the surface of the parts fails, breaks, etc., it is easy ...

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): G06K9/00G06K9/62G06N3/04G06N3/08G01M13/045
CPCG06N3/08G01M13/045G06N3/047G06N3/048G06N3/045G06F2218/12G06F2218/08G06F18/2415G06F18/241
Inventor 万安平杨洁王景霖单添敏缪徐黄佳湧杜翔
Owner ZHEJIANG UNIV CITY COLLEGE
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