A bearing fault diagnosis method based on pca_cnns
A fault diagnosis and bearing technology, applied in mechanical bearing testing, neural learning methods, biological neural network models, etc., can solve problems such as bearing fault diagnosis, and achieve the effects of high accuracy, reduced computational complexity, and strong generalization ability.
Active Publication Date: 2022-07-19
NANJING UNIV OF SCI & TECH
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] The purpose of the present invention is to provide a bearing fault diagnosis method based on PCA_CNNS to solve the problem of bearing fault diagnosis of key equipment in the production process
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
[0069] The PCA-CNNS-based fault diagnosis method of the present invention is used to conduct experiments and model simulation verification.
[0070] The experimental object of this experiment is the drive end bearing, the model to be diagnosed is the deep groove ball bearing SKF6205, and the sampling frequency of the system is 12kHz. There are 3 kinds of defect positions in the diagnosed bearing, namely rolling element damage, outer ring damage and inner ring damage. The damage diameters include 0.007inch, 0.014inch and 0.021inch respectively, a total of nine damage states.
[0071] Step 1: Use the principal component analysis method to extract the m-dimensional principal component data set w representing the characteristic information of the original n-dimensional data in the input bearing data set v, where mtrain and the test sample set w test , go to step 2.
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 a bearing fault diagnosis method based on PCA_CNNS, which is used for diagnosing the bearing fault of key components of production equipment. The invention combines the convolutional neural network with the principal component analysis method, and completes the data analysis according to the input bearing state characteristic data. Feature extraction is more in line with the fault diagnosis process in the actual processing and production process. The fault diagnosis process is divided into two parts: feature extraction and fault classification, the feature extraction of the data to be detected is completed by the improved convolutional neural network model based on principal component analysis, and the K-fold cross-validation is used to cyclically divide the data set for comparison. The model with strong generalization ability is solved, combined with the self-organizing mapping algorithm, the data after feature extraction is screened, and finally the fully connected neural network is used to complete the classification of faults and output the diagnosis results. The fault diagnosis method proposed by the invention has the advantages of strong robustness and high real-time performance.
Description
technical field [0001] The invention belongs to the field of fault diagnosis, in particular to a bearing fault diagnosis method based on a convolutional neural network (PCA_CNNS). Background technique [0002] At present, in the field of wooden door production, the fault diagnosis of wooden door production and processing equipment is a core point of research. The accuracy and timeliness of fault diagnosis are the criteria for measuring the health assessment of wooden door processing equipment, reflecting the current health status of the equipment, accurate and timely. The fault source can be judged quickly so that the wooden door manufacturer can respond quickly to ensure the production and operation efficiency. Therefore, the fault diagnosis of the key equipment of the wooden door production line is the key to the flexible and intelligent research of the wooden door production line. [0003] The mainstream fault diagnosis methods at this stage are mainly divided into metho...
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 Patents(China)
IPC IPC(8): G01M13/04G06N3/04G06N3/08
CPCG01M13/04G06N3/04G06N3/08
Inventor 陆宝春张劲飞葛超翁朝阳练鹏
Owner NANJING UNIV OF SCI & TECH