Multivariate drilling time sequence prediction method based on mixed leakage integral CRJ network
A drilling time and sequence prediction technology, which is applied in drilling measurement, drilling equipment, earthwork drilling and production, etc., can solve problems such as difficult to meet complex multivariate time series prediction tasks, weak model memory ability, etc., to improve dynamic characteristics and prediction performance Effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0047]In this example, the leaky integral neuron with strong memory and the traditional hyperbolic tangent neuron are used to form a mixed leaky integral neuron model. After studying the combination of the mixed neuron model and the CRJ network structure, a hybrid leaky integral is proposed. CRJ network, also known as LI-HCRJ network. In the face of high-dimensional time series forecasting tasks, the forecasting accuracy not only depends on the network model, but also depends on the input information of the network model. This embodiment uses the gray relational algorithm as the processing algorithm for network input information. Different from the general relational algorithm, the gray relational analysis method is to quantitatively analyze the dynamic development process of the system to examine the degree of correlation between the variables of the system. Its core theory is According to the degree of similarity between curves to judge the degree of correlation between fact...
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