Ship fault real-time diagnosis method based on CNN and RNN fusion

A real-time diagnosis and fault technology, applied in the field of ship systems, can solve problems such as not being able to meet the real-time diagnosis of multiple devices

Pending Publication Date: 2020-10-30
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Purpose of the invention: The purpose of the present invention is to overcome the problem that the existing technology cannot meet the real-time diagnosis...

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
  • Ship fault real-time diagnosis method based on CNN and RNN fusion
  • Ship fault real-time diagnosis method based on CNN and RNN fusion
  • Ship fault real-time diagnosis method based on CNN and RNN fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0058] The present invention will be further explained below in conjunction with the accompanying drawings.

[0059] The environment of the present invention is in the Anaconda experimental environment based on python 3.7 version.

[0060] First, using the historical data in the ship historical database, a correlation matrix that can characterize the relationship between attributes is obtained.

[0061] Subsequently, the collected multi-sensor raw data is preprocessed, and the preprocessing content includes:

[0062] (1) Add a sliding window to divide the collected multi-sensor raw data into multivariate time series of multiple window sizes;

[0063] (2) Multiply the multivariate time series of the window size with the correlation matrix to obtain the input variables of the network;

[0064] Subsequently, CNN and RNN fusion technology is used for fault diagnosis, and the method is as follows:

[0065] (1) Introduce n convolution kernels of the same size, and the width of th...

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 fault diagnosis method based on CNN and RNN fusion. The method can be used for ship real-time fault diagnosis. The method comprises the following steps: firstly, establishing a correlation matrix between ship characteristic parameters by utilizing historical ship data; the correlation matrix can represent the relationship between attributes; then adding multi-sensor original data in a sliding window acquisition window for correlation processing, taking the processed multivariable time sequence as the input of a convolutional neural network, automatically extracting fault features by the convolutional neural network, and finally, recombining the extracted feature vectors as the input of a recurrent neural network for fault classification. Experimental results showthat the method does not need to manually extract data features, and is high in fault diagnosis accuracy and short in response time. The advancement of the method is mainly reflected in that the method has a good effect in ship fault diagnosis and classification, is quick in time response, and can meet the use requirements of ship fault real-time diagnosis.

Description

technical field [0001] The invention belongs to the technical field of ship systems, in particular to a real-time fault diagnosis method for multiple sensor raw data. Background technique [0002] As the main tool of water transportation, the safety and stability of ship operation play a vital role in the water transportation industry. Due to the large number of ship equipment and the complex operating environment, the probability of equipment failure is greatly increased. If the equipment fails to be found in time, it will bring great danger to the navigation of the ship. Fault diagnosis is of great significance to the health management of ships by detecting and identifying faults. Effective fault detection can improve the safety of ships, so it is necessary for real-time online fault diagnosis of ship equipment. Contents of the invention [0003] Purpose of the invention: The purpose of the present invention is to overcome the problem that the existing technology cannot...

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): G06N3/04G06N3/08G06K9/62B63B79/00B63B79/10
CPCG06N3/08B63B79/00B63B79/10G06N3/045G06F18/2415
Inventor 曾友渝谢强
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
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