A Hierarchical Localization Method for Forced Oscillations Based on Multi-Stage Transfer Learning
A technology of forced oscillation and transfer learning, which is applied in the field of forced oscillation hierarchical positioning based on multi-stage transfer learning, can solve the problems of changing system operation mode, immaturity, and low accuracy, so as to alleviate the burden of data processing and reduce data volume, the effect of reducing training volume
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0017] The present invention will be described in further detail below in conjunction with the accompanying drawings.
[0018] The general process of the multi-stage migration learning-based forced oscillation hierarchical localization method of the present invention includes an offline training process and an online localization process. The offline training process is roughly as follows: first, partition the entire power system according to the generator correlation, extract its oscillation principal components in each partition, and use smooth pseudo Wigner-Ville distribution (WVD) to transform, visualize it and get forced WVD image of the oscillation interval. Then, the first stage of migration learning is performed on the pre-trained convolutional neural network to obtain a first-layer partition localization model that can locate the partition where the disturbance source is located. Then input the WVD image of each unit in the partition, use the first-level positioning ...
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