Inverter low-frequency noise fault diagnosis method based on wavelets and neural network
A neural network and fault diagnosis technology, applied in the fault diagnosis of inverters, the field of low-frequency noise fault diagnosis of inverters based on wavelets and neural networks, can solve the problems of difficult fault detection, complicated implementation process, single fault diagnosis, etc. Achieve the effect of fast speed, scientific and reasonable method, and accurate diagnosis
Active Publication Date: 2015-01-28
NORTHEAST DIANLI UNIVERSITY
View PDF5 Cites 12 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
The traditional method of manually detecting and judging the fault state is due to the lack of experience of maintenance personnel on the one hand, and the lack of detailed fault state information on the other hand, making it a big problem to quickly and accurately detect faults
In recent years, researchers have made many achievements in inverter fault diagnosis, such as bond graph theory fault diagnosis method, switching function model fault diagnosis method, fuzzy theory, expert system, particle swarm estimation, spectrum estimation and so on. Fault diagnosis methods, etc., but most of these methods are limited in application due to the complex implementation process and single fault diagnosis, and how to accurately describe the transition of the inverter fault level, so far there is no accurate diagnosis method
And there is no literature report and practical application of inverter low-frequency noise fault diagnosis method based on wavelet and neural network
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0020] see figure 1 , a kind of inverter low-frequency noise fault diagnosis method based on wavelet and neural network of the present invention, its steps are:
[0021] 1) Collect passive data from inverters in normal and faulty states, input the collected data into the PC, and perform low-pass filtering processing with a cutoff frequency of 100KHz to ensure that low-frequency noise data can be obtained, thereby obtaining Normal state data x n and fault status data x f,i , i is the number of faulty inverters;
[0022] 2) Perform wavelet transform on the data separately, and use multi-resolution analysis to decompose. Since the processing is low-frequency noise below 100KHz, the number of decomposition layers is not easy to be too many, and 4-5 layers are appropriate. Select an appropriate threshold function to process high-frequency Wavelet coefficients to eliminate white noise, and finally get the scale coefficient a j with wavelet coefficient d j , where j=1,2,...,J, j...
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
Login to View More Abstract
The invention discloses an inverter low-frequency noise fault diagnosis method based on wavelets and a neural network. The method is characterized by comprising the following steps that passive test data output is carried out on a normal inverter and a fault inverter, wavelet transformation and decomposition are carried out on output normal signals and fault signals, difference value treatment is carried out on a numerical value matrix obtained after energy transformation to obtain a characteristic quantity, the characteristic quantity is input into the neural network to be trained, output of the neural network is judged, and fault levels are judged. The method has the advantages of being scientific, reasonable, applicable, accurate in diagnosis, high in speed and the like.
Description
technical field [0001] The invention relates to an inverter fault diagnosis method, in particular to an inverter low-frequency noise fault diagnosis method based on wavelet and neural network, and belongs to the technical field of analog circuit fault diagnosis and detection. Background technique [0002] With the widespread application of inverters in people's production and life, people have higher and higher reliability requirements for them. The traditional method of manually detecting and judging the fault state is due to the lack of experience of the maintenance personnel on the one hand, and the lack of detailed fault state information on the other hand, making it a big problem to quickly and accurately detect faults. In recent years, researchers have made many achievements in inverter fault diagnosis, such as bond graph theory fault diagnosis method, switching function model fault diagnosis method, fuzzy theory, expert system, particle swarm estimation, spectrum esti...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06N3/02G06N3/08G06F19/00
Inventor 陈晓娟申雅茹陈东阳吴洁李建坡李楠姜万昌
Owner NORTHEAST DIANLI UNIVERSITY