Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Fault diagnosis method without mathematical modeling of underwater robot

An underwater robot, mathematical modeling technology, applied in the direction of instruments, electrical testing/monitoring, control/regulation systems, etc., can solve problems such as difficult to diagnose, difficult and impossible to accurately model, and achieve strong universality , high diagnostic accuracy, avoid the effect of mathematical modeling process

Active Publication Date: 2021-08-06
ZHEJIANG UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, underwater robots are complex nonlinear dynamic systems, and it is difficult to accurately describe some complex dynamic behaviors, noise, interference and other factors in the system, and it is almost difficult or even impossible to model them accurately, which means Difficult to make an accurate 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
  • Fault diagnosis method without mathematical modeling of underwater robot
  • Fault diagnosis method without mathematical modeling of underwater robot
  • Fault diagnosis method without mathematical modeling of underwater robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] First of all, it should be explained that the diagnosis method of the present invention does not construct a mathematical model for the underwater robot itself, but focuses on the potential relationship between the state data of the underwater robot and the type of failure. Directly learning patterns between state data and fault types is fundamentally different from model-based approaches. Therefore, the present invention adopts the relevant expression of "no model".

[0036] The invention relates to underwater robot technology, deep learning technology and fault diagnosis technology. During the implementation of the present invention, the application of multiple software function modules will be involved. The applicant believes that, after carefully reading the application documents and accurately understanding the realization principle and purpose of the present invention, combined with existing known technologies, those skilled in the art can fully implement the pre...

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 an underwater robot technology, and aims to provide a fault diagnosis method without mathematical modeling of an underwater robot. The method includes the steps that an underwater robot executes a specified task program, and corresponding behavior responses are generated according to different preset fault types; state data in the test process is stored as a data sample; multiple tests are repeatedly carried out to collect enough data samples, and a two-dimensional matrix is obtained after preprocessing and is used for generating an original training set; the obtained training set is used to train a diagnosis model in an off-line mode; the trained diagnosis model is loaded to the underwater robot, the real-time state data of the underwater robot in the task program execution period is taken as the input of the diagnosis model, and forward calculation is performed to achieve fault prediction and diagnosis. According to the method, a complex mathematical modeling process is avoided, so that the method has higher universality. A traditional double-stage diagnosis mode can be converted into a single-stage diagnosis mode, and high diagnosis accuracy is achieved.

Description

technical field [0001] The invention relates to underwater robot technology, in particular to a fault diagnosis method (of an underwater robot) that does not require mathematical modeling of the underwater robot itself. Background technique [0002] With the exploration and development of the ocean, underwater robots are playing an increasingly important role in marine applications. At the same time, the complex and unpredictable marine environment will increase the probability of failure of underwater robots, so underwater robots must have the ability to diagnose faults. When the underwater robot fails to meet the expected state, the fault diagnosis technology can help the underwater robot to obtain accurate fault information (including whether a fault occurs and the location of the fault source) in time, so as to take appropriate measures to reduce the fault. the impact. However, underwater robot systems are often complex in structure, with strong nonlinearity and uncert...

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): G05B23/02
CPCG05B23/0262G05B2219/24065
Inventor 冀大雄姚鑫
Owner ZHEJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products