Layered multi-fork network structure efficient search method for rotating machine fault diagnosis
A technology for fault diagnosis and rotating machinery, which is applied in the testing of mechanical components, testing of machine/structural components, neural learning methods, etc. It can solve the problems of consuming large computing resources and the inability of network models to apply to diagnostic tasks, so as to improve search efficiency Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Examples
Example Embodiment
[0068] Such as figure 1 As shown, the present invention is a highly efficient search method for a spiral multi-aforementioned network structure, including the following steps:
[0069] S1, based on the length of the memory network, the memory network is built, and the decision is made according to the quantities of the primary structure, from the input node space and the operation space to create two types of metaded structural normal elements and dropwise;
[0070] S2, in accordance with the stack definition and stacking rules, two types of metallic structures are stacked into a monocrus model, utilizing divided training data and test data training and verifying the child model;
[0071] S3, taking the child model verification accuracy, according to the controller optimization logic, the training controller optimizes its parameters so that it can search for high precision sub-models;
[0072] S4, child models, and controller alternate training, eventually obtain a controller that ca
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