Phi-OTDR vibration signal identification algorithm based on STFT-CNN-RVFL
A technology of -OTDR and vibration signal, which is applied in the field of identification and classification of time-frequency diagram of Φ-OTDR vibration signal, can solve problems such as falling into local minimum, and achieve high accuracy and obvious signal identification effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0037] specific implementation plan
[0038] The present invention will be described in further detail below through examples of implementation.
[0039] In this implementation case, three typical intrusive vibration signals of knocking, climbing, and pedestrian passing and three non-invasive vibration signals of wind, rain, and animal touch were used for experiments. The initially collected Φ-OTDR vibration signal files are binary files, which need to be format converted. The number of acquisitions of each type of vibration signal is 30 times, and the sampling frequency is 10KHz, corresponding to 6 types of vibration signals. There are 180 sets of experimental data in total. Divide each group of data into 10 segments, divide 1 to 5 segments into one sample, 2 to 6 segments into one sample, and so on. Each group of signals can get 6 samples, and 30 groups of data can get 180 samples. 140 samples are randomly selected as training samples, and the rest are used as test samples...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


