Fan gear box fault diagnosis model establishing method and device
A technology for fault diagnosis model and establishment method, which is applied in the direction of machine gear/transmission mechanism testing, measuring device, neural learning method, etc., which can solve the problems of low diagnosis efficiency and poor accuracy of fan gearboxes
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0052] This embodiment provides a method for establishing a fault diagnosis model of a wind turbine gearbox, which is used to establish a fault diagnosis model of a wind direction gearbox, and the model is used for fault diagnosis of a wind turbine gearbox. The flow chart of the method is as figure 1 mentioned, including:
[0053] S1. Obtain the vibration signal of the fan gearbox. The vibration signal of the fan gearbox under normal and typical fault conditions is collected by the vibration sensor. The vibration signal can include normal vibration signal, vibration signal when the inner ring of the gearbox bearing is faulty, vibration signal when the outer ring of the gearbox bearing is faulty, and vibration signal when the tooth is broken. some or all of the .
[0054] In this embodiment, the vibration signal of the wind turbine gearbox is obtained through the vibration sensor installed on the wind turbine gearbox, which includes four kinds of vibration signals under four ...
Embodiment 2
[0089] A device for establishing a fault diagnosis model of a wind turbine gearbox, the structural block diagram is as follows figure 2 As shown, used to build a diagnostic model, which includes
[0090] The signal acquisition unit 01 is used to acquire the vibration signal of the fan gearbox;
[0091] A preprocessing unit 02, configured to perform smoothing and noise reduction processing on the vibration signal;
[0092] The feature vector extraction unit 03 is used to decompose the processed vibration signal and extract the feature vector of the vibration signal;
[0093] The data set setting unit 04 is used to divide the feature vector of the vibration signal into a training data set and a test data set;
[0094] The model generation unit 05 is used to optimize the parameters of the radial basis neural network model by using the fruit fly algorithm, input the eigenvector of the vibration signal in the training data set to obtain the optimal value of the parameters, and g...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com