Power grid icing galloping risk prediction method and system, and storage medium
A risk prediction and icing technology, which is applied in prediction, neural learning methods, biological neural network models, etc., can solve problems such as unsatisfactory results, reduced objectivity of galloping prediction, and untimely galloping prediction time, so as to reduce galloping disasters, The effect of strong initiative and high degree of intelligence
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0059] see figure 1 , this embodiment discloses a method for predicting the risk of electrical grid icing galloping, including the following steps:
[0060] S1: Select historical ice-covered dancing related data to construct an initial sample data set, divide the initial sample data set into a training sample data set and a verification sample data set, and initialize the parameter values of the restricted Boltzmann machine algorithm according to the training sample data set .
[0061] Specifically, 36 sets of historical ice-covered dance-related data in China from 2010 to 2016 were selected as the initial sample data set, and each set of data included meteorological feature data, terrain and terrain data, and power grid line structure data. The first 32 sets of data are used as the training sample data set, and the last 4 sets of data are used as the verification sample data set. Among them, meteorological feature data include wind speed, angle between wind direction and ...
Embodiment 2
[0090] Corresponding to the above method, this embodiment also discloses a power grid icing galloping risk prediction system, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the program, the following is achieved: step:
[0091] S1: Select historical ice-covered dancing related data to construct an initial sample data set, divide the initial sample data set into a training sample data set and a verification sample data set, and initialize the parameter values of the restricted Boltzmann machine algorithm according to the training sample data set ;
[0092] S2: Repeatedly learn and update parameter values until the restricted Boltzmann machine algorithm meets the convergence of the training sample data set;
[0093] S3: Obtain the parameter values of the restricted Boltzmann machine algorithm after deep learning according to the logarithmic likelihood function of the algorithm in maxi...
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