All-fiber dynamic and static monitoring and trend prediction system and method for overhead transmission line
An overhead transmission line and trend prediction technology, applied in the field of power system, can solve the problems of difficult power supply and maintenance of electrical components, easy to be interfered by bad weather, limited range, etc., to facilitate inspection and key protection, save resources, and use handy effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0067] An all-fiber dynamic and static monitoring and trend prediction system for overhead power transmission lines provided by a preferred embodiment of the present invention, such as figure 1 As shown, the system includes an optical fiber sensing probe for real-time measurement of quasi-static environmental data and an FBG demodulation system connected with the optical fiber sensing probe. The connected P-OTDR demodulation system also includes a processing terminal connected to the FBG demodulation system signal output terminal and the P-OTDR demodulation system signal output terminal, such as a processing terminal such as a computer, and the processing terminal is used for quasi-static environment input Data and transmission line dynamic wind dance data for analysis, processing and model prediction.
[0068] Further, the optical fiber sensing probe adopts a fiber sensing probe based on Bragg gratings.
[0069] The quasi-static environmental data includes environmental temp...
Embodiment 2
[0137] On the basis of Embodiment 1, the preferred embodiment of the present invention first trains the LSTM model based on the quasi-static air temperature and pressure data of the external environment collected by the FBG sensor, and makes long-term and short-term predictions respectively. The specific test process and results are as follows:
[0138] (1) Temperature data prediction test
[0139] ① Long-term forecast of temperature
[0140] Considering the large amount of data in the long-term period, the temperature data of 5 years are averaged on a daily basis, that is, every 24 data are averaged, which is equivalent to obtaining the long-term daily average temperature data. Use the first 5 / 7 data for model training, and the last 2 / 7 data for testing, that is, training set:test set=5:2. The long-term temperature data takes years as the change cycle, the training set data contains about 3.5 change cycles, and the test set data contains about 1.5 change cycles.
[0141] T...
Embodiment 3
[0154] In the preferred embodiment of the present invention, on the basis of Embodiment 1, the corresponding LSTM model is trained and predicted for the dynamic wind dance data.
[0155] Since the change of the wind dance signal is more random than the slowly changing air temperature and air pressure, the direct use of the ordinary LSTM model for prediction 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 a multi-layer LSTM model, and an iterative prediction method should be used for prediction. Figure 10 The overall framework of the 3-layer LSTM network model is shown. The multi-layer LSTM model adds multiple hidden layers on the basis of the single-layer LSTM model. The next hidden layer uses the output of the previous hidden layer as input, and is connected by a multi-layer network (a 3-layer network is used in this patent), and the model can adapt to Changes to more complex...
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