Rolling bearing fault diagnosis method based on 1-DCNN (1-Dimensional Convolutional Neutral Network) and LSTM (Long Short-Term Memory) fusion
A technology for fault diagnosis and rolling bearings, applied in character and pattern recognition, testing of mechanical components, testing of machine/structural components, etc., can solve the problem of loss of original signal integrity and spatial correlation, failure of deep learning network self-learning and Data processing capabilities, increasing data preprocessing and human interference, etc., to achieve powerful feature self-learning and data processing capabilities, improve recognition and diagnosis accuracy, and improve recognition accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0065] Example 1. A rolling bearing fault diagnosis method based on fusion of 1-DCNN and LSTM, such as Figure 7 shown, follow the steps below:
[0066] a. The original one-dimensional vibration signal is processed and expanded by sliding window overlapping sampling method to obtain the expanded signal;
[0067] b. Input the expanded signal into the two channels of 1-DCNN and LSTM for training and analysis, and extract the feature information; extract the spatial feature information in the 1-DCNN channel, and extract the temporal feature information in the LSTM channel;
[0068] c. Splicing the spatial feature information and time feature information through the concatenate layer to obtain the splicing feature;
[0069] d. Connect the splicing features to the fully connected layer, and classify the fault categories through the Softmax classifier.
[0070] Specifically, in step b, the spatial feature information extracted in the 1-DCNN channel is as follows:
[0071] For a ...
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