Classification Method of Power Quality Disturbance Based on Bidirectional Gating Recurrent Neural Network
A technology of cyclic neural network and power quality disturbance, which is applied in the field of signal control, can solve problems such as the inability to classify and identify single elements in sequence data, and achieve the effects of improving judgment accuracy and judgment speed, simple gate structure, and improving training efficiency
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0049] On the sequence classification of power quality disturbance categories, traditional methods cannot identify single sequence element information, and it is difficult to establish a comprehensive feature description method for complex power quality disturbances, and it relies heavily on the experience and technical level of experts. Some power quality disturbance classification algorithms have low recognition accuracy for complex power quality disturbance types, and cannot correctly classify a single element in the sequence. At the same time, traditional algorithms, such as support vector machines or description function methods, cannot achieve real-time performance, and the accuracy of judgment is low. However, using the method of the present invention, for 48 kinds of power quality disturbances including single and composite power quality disturbances, the comprehensive judgment accuracy rate of 100,000 samples can be greatly increased to more than 99%, and the judgment ...
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