Unlock instant, AI-driven research and patent intelligence for your innovation.

A semi-supervised fault diagnosis method for the propulsion system of a semi-submersible ship

A technology for propulsion system and fault diagnosis, applied in the direction of ships, etc., can solve problems such as the working influence of semi-submersible ships, failure of main train, bearings, gear components, and multi-sensor fusion diagnosis.

Active Publication Date: 2022-04-22
SOUTH CHINA UNIV OF TECH
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The rotating parts of the propulsion system of the semi-submersible ship have been in service for a long time in a humid environment with high temperature and high pressure, and failures of the main shaft, bearings, gears and other components may occur, which will seriously affect the work of the semi-submersible ship
At present, the fault intelligent diagnosis of the overall system state of the semi-submersible propulsion system is still a challenge
Especially under different sea conditions, the problem of how to integrate multi-sensor fusion diagnosis has not been solved due to the difference in the damage characterization received by different sensors

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
  • A semi-supervised fault diagnosis method for the propulsion system of a semi-submersible ship
  • A semi-supervised fault diagnosis method for the propulsion system of a semi-submersible ship
  • A semi-supervised fault diagnosis method for the propulsion system of a semi-submersible ship

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0029] A semi-supervised fault diagnosis method for the main propulsion system of a semi-submersible ship, such as figure 1 shown, including the following steps:

[0030] S1. Use different sensors to monitor the status signals of the main propulsion system of the semi-submersible ship in real time, and obtain multi-sensor monitoring signal data;

[0031] The state signals of the main propulsion system of the semi-submersible ship monitored in real time include the vibration acceleration signal of the propulsion motor, the vibration acceleration signal of the reduction gearbox, the speed signal of the long shaft system, the temperature signal of the propulsion motor, the temperature signal of the reduction gearbox, the reduction gearbox The oil pressure signal, the input and output voltage and current signals of the propulsion motor;

[0032] Vibration acceleration signals are obtained by three-way acceleration sensors at the positions of the reduction gear box and the propuls...

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 a semi-supervised fault diagnosis method for the main propulsion system of a semi-submersible ship. The method includes the following steps: using different sensors to monitor the state signal of the main propulsion system of the semi-submersible ship in real time, and obtaining multi-sensor monitoring signal data; using a convolutional coding network to reconstruct and reduce the dimensionality of the multi-sensor monitoring signal to realize different sensor monitoring signal dimensions Alignment; the multi-sensor monitoring signal can be probabilistically reconstructed by using the variational autoencoder network, and the reconstruction error is used as the fault degree index of the overall operating state of the main propulsion system of the current semi-submersible ship. When the index is greater than the set threshold, it is regarded as a fault state. The invention can recognize the abnormal state of the overall operation state of the main propulsion system of the semi-submersible ship only by using the multi-sensor monitoring data in the normal state.

Description

technical field [0001] The invention belongs to the field of fault diagnosis, and in particular relates to a semi-supervised fault diagnosis method for the main propulsion system of a semi-submersible ship. Background technique [0002] The main purpose of semi-submersible ships is long-distance transportation of large cargo and equipment, so the safety and reliability of the propulsion system during long-distance voyages is an important monitoring indicator for semi-submersible ships in service. The propulsion system of a semi-submersible ship using a conventional shafting propeller is configured with a main propulsion system, a bow thruster and a tail thruster, wherein the main propulsion system includes a propulsion motor, a reduction gearbox, a long shafting and a fixed-pitch propeller. [0003] The rotating parts of the propulsion system of the semi-submersible ship have been in service for a long time in a humid environment with high temperature and high pressure, and ...

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 Patents(China)
IPC IPC(8): B63B79/10B63B79/30
CPCB63B79/10B63B79/30
Inventor 洪晓斌张斌
Owner SOUTH CHINA UNIV OF TECH