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

Ship power station fault diagnosis method based on data fusion

A technology for data fusion and power station faults. It is applied in the direction of measuring electricity, measuring electrical variables, measuring devices, etc., and can solve problems such as difficulty in establishing high-precision mathematical models.

Active Publication Date: 2013-11-27
WUXI PROFESSIONAL COLLEGE OF SCI & TECH
View PDF3 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The ship power station is an important part of the ship and the core of the ship's power system. The reliable operation of the ship power station is of great significance to ensure the safety of the ship. It is responsible for providing continuous, reliable and high-quality electrical energy for the entire ship's electrical equipment. , once a major accident occurs, the consequences are quite serious. With the development of large-scale, high-speed and automated ships, higher requirements are placed on ship power stations. At present, there are two main fault diagnosis methods for ship units at home and abroad. : The first is vibration analysis; the second is to judge the failure of the unit based on the electrical parameters. However, since the ship power station unit is a complex nonlinear system, its failure law is difficult to describe with a simple mathematical model. In fault diagnosis, it is difficult to establish a high-precision mathematical model

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 power station fault diagnosis method based on data fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] Such as figure 1 As shown, the present invention includes a plurality of sensors to monitor the fault information parameters separately, integrate the monitored data for the first level of fusion detection layer data, and eliminate the problem of unequal accuracy of the data collected by the sensors, and the data after the first level of fusion Carry out the second-level fusion to identify the dominant factors and non-dominant factors, so as to identify the dominant fault characteristic value, the data after the second-level fusion is carried out to the third-level fusion to remove uncertain information, and the fault diagnosis conclusion is obtained, then the third-level The fused diagnostic data is matched with the fault diagnosis knowledge base, and the fault diagnosis result is output.

[0026] The fault diagnosis method steps are:

[0027] a. The first level of fusion uses adaptive weighted data fusion, and the data detected by its n sensors is assumed to be , f...

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 provides a ship power station fault diagnosis method based on data fusion. The method comprises the steps of respectively adopting different data fusion algorithms on different levels of a fault diagnosis, using a plurality of sensors for detecting fault messages in multiple aspects, conducting stage treatment on multi-source messages, accurately and timely judging the state of a system, and giving the correct judgment on whether the system fails or not and the correct judgment on the fault mode. According to the ship power station fault diagnosis method based on the data fusion, intelligent monitor of a ship power station unit is effectively achieved, the reliability and safety of the operation of the unit are improved, and the phenomena of false alarms, misinformation and information missing are reduced. The sensors respectively monitor parameters of the fault messages and integrate the monitored data to conduct a first-stage fusion to detect layer data, a second-stage fusion is carried out on the data passing through the first-stage fusion, a third-stage fusion is carried out on the data passing through the second-stage fusion, the data after the three-stage fusion are matched with data inside a fault diagnosis knowledge database, and the fault diagnosis result is output.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence fault diagnosis, in particular to a method for fault diagnosis of a ship power station based on data fusion. Background technique [0002] The ship power station is an important part of the ship and the core of the ship's power system. The reliable operation of the ship power station is of great significance to ensure the safety of the ship. It is responsible for providing continuous, reliable and high-quality electrical energy for the entire ship's electrical equipment. , once a major accident occurs, the consequences are quite serious. With the development of large-scale, high-speed and automated ships, higher requirements are placed on ship power stations. At present, there are two main fault diagnosis methods for ship units at home and abroad. : The first is vibration analysis; the second is to judge the failure of the unit based on the electrical parameters. However, since the...

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): G01R31/00
Inventor 陈佳陈晶陆冬磊
Owner WUXI PROFESSIONAL COLLEGE 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
Eureka Blog
Learn More
PatSnap group products