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

Engine state monitoring method based on vibration and neural network technology

A neural network and vibration monitoring technology, applied in the direction of internal combustion engine testing, etc., can solve problems such as inability to accurately judge the running state of the engine, and achieve the effect of reducing the difficulty of layout

Inactive Publication Date: 2018-08-14
SHANDONG YUNSHUN INTELLIGENT TECH
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The technical task of the present invention is to solve the deficiencies of the prior art and provide a method for monitoring the state of the engine based on vibration and neural network technology, aiming to solve the problem that the existing fault analysis and processing methods cannot accurately judge the operating state of the engine

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The engine state monitoring method based on vibration and neural network technology of the present invention includes the step of extracting the vibration characteristic parameters of the engine and the step of utilizing neural network technology to analyze the engine state, wherein:

[0018] The extraction of the characteristic parameters of the engine vibration is to select the test points of the engine vibration monitoring test at the measuring points near the cylinder head cover, the cylinder block and the side wall of the crankcase.

[0019] The use of neural network technology for engine state analysis is to use neural network technology to perform nonlinear fitting, map complex nonlinear relationships with faults, and obtain a comprehensive evaluation model based on fuzzy reasoning synthesis rules.

[0020] Its specific steps include:

[0021] 1) Obtain the signal under no fault and fault state under specific working conditions, extract and normalize the fault sy...

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 an engine condition monitoring method based on vibration and neural network technology and belongs to the engine fault monitoring method field. The method includes the following steps of: extracting the vibration characteristic parameters of an engine and performing engine state analysis by using the neural network technology. Measuring point near a cylinder head cover, a cylinder block and a crankcase side wall are selected as the vibration monitoring experimental test points of the engine, and therefore, the arrangement difficulty of sensors can be decreased. The stepof performing the engine state analysis by using the neural network technology includes the following steps that: 1) signals in a fault-free state and a fault state under a specific operating condition are obtained, fault symptom data are extracted and normalized, and the normalized fault symptom data are adopted as the input of a BP neural network; 2) a BP neural network system is established, the characteristic parameters of known fault states are adopted as training samples to train the network, so that the network can achieve required diagnosis accuracy; and 3) the fault characteristic parameters of an unknown state are inputted into the trained neural network for testing the unknown state, and the output of the under the unknown state is obtained, and post-processing is carried out,a result is compared with failure modes for training the network, so that a diagnosis result, namely, a fault type, can be obtained.

Description

technical field [0001] The invention relates to an engine fault monitoring method, in particular to an engine state monitoring method based on vibration and neural network technology. Background technique [0002] For mechanical equipment, the engine is an important power machine and the core power component of the mechanical equipment. The engine fault diagnosis methods disclosed in the prior art mainly use fault tree analysis and multi-sensor fusion analysis and judgment methods, and none of these fault analysis and processing methods can accurately judge the operating state of the engine. Contents of the invention [0003] The technical task of the present invention is to solve the deficiencies of the prior art, and provide an engine state monitoring method based on vibration and neural network technology, aiming to solve the problem that the existing fault analysis and processing methods cannot accurately judge the engine running state. [0004] The technical solution...

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): G01M15/12
CPCG01M15/12
Inventor 黄斐杨东武文松
Owner SHANDONG YUNSHUN INTELLIGENT 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