Hydroelectric generating set fault diagnosis method and system based on DdAE (Difference Differential Algebraic Equations) deep learning model

A hydroelectric unit and fault diagnosis technology, applied in neural learning methods, biological models, computing models, etc., can solve cumbersome manual work and other problems, achieve the effects of improving anti-noise ability, avoiding gradient explosion, and improving feature learning ability

Active Publication Date: 2018-05-22
HUAZHONG UNIV OF SCI & TECH
View PDF6 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] The purpose of the present invention is to provide a method and system for fault diagnosis of hydropower units based on the DdAE deep learning ...

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
  • Hydroelectric generating set fault diagnosis method and system based on DdAE (Difference Differential Algebraic Equations) deep learning model
  • Hydroelectric generating set fault diagnosis method and system based on DdAE (Difference Differential Algebraic Equations) deep learning model
  • Hydroelectric generating set fault diagnosis method and system based on DdAE (Difference Differential Algebraic Equations) deep learning model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] The embodiment of the present invention is based on the fault diagnosis method flow of the deep denoising autoencoder (Deep denoising Autoencoder, abbreviated as DdAE) deep learning model is as follows figure 1 shown. Include the following execution steps:

[0046] In step 201, a data set is obtained, and n groups of data blocks are extracted from the data set as training data for the DdAE network model.

[0047] Taking the hydroelectric generating unit as an example, in step 201, the original data of the vibration of the hydroelectric unit is used as the input sample set x, and normalized processing is performed before being used as training data, even if the processed data is distributed according to the distribution ratio of the original data Between -1 and 1, a new input sample set x' is obtained; then the normalized sample set x' is equally divided into k groups of data blocks, considering the periodicity of the vibration fault of the hydroelectric unit, in order ...

Embodiment 2

[0090] The embodiment of the present invention is a composite solution that integrates many extended and preferred solutions in embodiment 1, wherein, refer to as Figure 6 The flow chart of the fault diagnosis method for hydroelectric units based on the DdAE deep learning model is shown. This embodiment mainly includes two processes of training and testing of the DdAE network model. The training process of the DdAE network model can be summarized as follows:

[0091] Step (1): Raw data preprocessing

[0092] In the embodiment of the present invention, the original data of the vibration of the hydroelectric unit is used as the input sample set x, and the normalization process is first adopted, even if the processed data is distributed between -1 and 1 according to the distribution ratio of the original data, a new input sample set is obtained x'; and then divide the normalized sample set x' into k groups of data blocks. Considering the periodicity of vibration faults of hydr...

Embodiment 3

[0158] The embodiment of the present invention also provides a hydroelectric unit fault diagnosis system based on the DdAE deep learning model, such as Figure 7 As shown, the system includes a training data processing module, a neural network model training module, a DdAE network model optimization module, a reconstruction feature vector generation module and a failure probability calculation module, and the above-mentioned modules are connected in sequence, specifically:

[0159] The training data processing module is used to obtain the data set, and extract n groups of data blocks from the data set as the training data of the DdAE network model;

[0160] Neural network model training module, for setting up DdAE network model, and utilize described training data to train DdAE network model, obtain the connection weight of DdAE network model;

[0161] The DdAE network model optimization module is used to use the structural parameters of DdAE and the hyperparameters in the err...

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 the technical field of hydroelectric generating set fault diagnosis, in particular to a hydroelectric generating set fault diagnosis method and system based on a DdAE (Difference Differential Algebraic Equations) deep learning model. The method and the system are established on the basis of the analysis of the original vibration data of the hydroelectric generating set, adeep learning characteristic extraction method based on a multilayer neural network model is adopted, a complex manual processing and feature extraction process is not required, an ASFA (Aquatic Sciences and Fisheries Abstracts) method based on random search is adopted to carry out the structural parameter adjustment and optimization of the DdAE to achieve a purpose of strategy optimization. A deep denoising automatic encoder model is used for realizing the distributed expression of original data, and reconstruction data subjected to feature extraction is input into a Softmax regression modelto judge the work state and the fault type of the hydroelectric generating set. The analysis of a network experiment result indicates that the method can be effectively applied to the hydroelectric generating set fault diagnosis.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis of hydroelectric units, and more specifically relates to a method and system for fault diagnosis of hydroelectric units based on a DdAE deep learning model. Background technique [0002] In a hydroelectric power generation system, the hydroelectric generating set is the most critical main equipment. Whether its operation status is safe and reliable is directly related to whether the hydropower station can safely and economically provide reliable power for the country's various economic departments and people's daily life. It is also directly related to the safety of the hydropower station itself. Continuously improving and optimizing the condition monitoring and fault diagnosis system can not only improve the economic and social benefits of hydropower stations, but also benefit the development of fault diagnosis technology for large hydropower units in China. With the increasing level of ...

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): G06K9/62G06N3/00G06N3/08
CPCG06N3/006G06N3/088G06F18/2415G06F18/214
Inventor 李超顺陈昊邹雯赖昕杰陈新彪
Owner HUAZHONG UNIV 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
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap