All-optical fiber dynamic and static monitoring and trend prediction system and method for overhead transmission lines
An overhead transmission line and trend prediction technology, applied in the field of power system, can solve the problems of limited scope, easy to be disturbed by bad weather, high labor intensity, etc., to achieve the effect of convenient use and resource saving
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0067] A preferred embodiment of the present invention provides an all-fiber dynamic and static monitoring and trend prediction system for overhead transmission lines, such as figure 1 As shown, the system includes an optical fiber sensing probe for real-time measurement of static environmental data and a FBG demodulation system connected with the optical fiber sensing probe. It also includes a probe optical cable for real-time monitoring of dynamic wind and dance data of the transmission line, and a probe optical cable connected with the probe optical fiber. The connected P-OTDR demodulation system also includes a processing terminal connected to the signal output end of the FBG demodulation system and the signal output end of the P-OTDR demodulation system, such as a processing terminal such as a computer, and the processing terminal is used for the input quasi-static environment Data and transmission line dynamic wind dance data for analysis, processing and model prediction....
Embodiment 2
[0137] The preferred embodiment of the present invention is based on Embodiment 1, firstly, based on the quasi-static air temperature and air pressure data of the external environment collected by the FBG sensor, the LSTM model is trained, and long-term and short-term predictions are made respectively. The specific test process and results are as follows:
[0138] (1) Prediction test of temperature data
[0139] ① Long-term forecast of temperature
[0140] Considering the large amount of data over a long period of time, the five-year temperature data were averaged on a daily basis, that is, every 24 data were averaged, which was equivalent to obtaining long-term daily average temperature data. The first 5 / 7 data is used for model training, and the last 2 / 7 data is used for testing, that is, training set:test set=5:2. The long-term temperature data takes the year as the change cycle, the training set data contains about 3.5 change cycles, and the test set data contains about ...
Embodiment 3
[0154] The preferred embodiment of the present invention is based on the first embodiment, and for the dynamic wind dance data, the corresponding LSTM model is trained and predicted.
[0155] Due to the strong randomness of the wind dance signal change compared to the slowly and regularly changing temperature and air pressure, the prediction effect of directly using the ordinary LSTM model will not be very good. In order to improve the learning ability of the LSTM model, it can dig deeper information. , for dynamic wind dance data, use multi-layer LSTM model, and iterative prediction method should be used in prediction. Figure 10 The overall framework of the 3-layer LSTM network model is shown. The multi-layer LSTM model adds multiple hidden layers to the single-layer LSTM model, and the next hidden layer uses the output of the previous hidden layer as input. Change more complex input data.
[0156] Considering that the basic variation law of the wind dance signal is a kind...
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.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap