Method and device for predicting operation stage and service life of grounding grid of substation
A technology of substation grounding grid and operation stage, which is applied in the field of substation grounding grid operation phase and operation life prediction field, can solve the problems of inability to accurately grasp the substation grounding grid operation phase, waste of manpower and material resources, lack of scientificity, etc., to ensure diversity, The effect of good scalability and high clustering accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment 1
[0062] Such as figure 1 and Figure 4 As shown, the embodiment of the present invention provides a substation grounding grid operation phase and operation life prediction method based on the improved random forest algorithm, including the following steps.
[0063] Step S1 is constructed to obtain various types of initial data and construct an original sample set. In this step, the various initial data may include maintenance results of the substation grounding grid, material of the grounding grid, soil condition data, and climate data. Among them, the maintenance results of the substation grounding grid, the material of the grounding grid, and the soil condition are obtained from the records of the substation, and the climate and other data are obtained from the regional meteorological department. data to form the original sample set. The embodiment of the present invention does not limit the total number of samples, which may be 120. The maintenance results of the substat...
specific Embodiment 2
[0089] Such as Figure 5 As shown, the embodiment of the present invention provides a substation grounding grid operation stage and operation life prediction device based on the improved random forest algorithm, including:
[0090] A construction module 201, configured to obtain various initial data and construct an original sample set;
[0091] The extraction module 202 is used to summarize and extract feature variables based on the characteristics of the original sample set;
[0092] The clustering module 203 is used to consider the existing data characteristics, and adopt the K-medoids method to cluster the original sample set;
[0093] The prediction module 204 is used to process various samples by using the random forest algorithm, extract training sets from various sample sets through bootstrap sampling technology, respectively establish classification regression trees and generate decision trees, and summarize and form random forest models; ground the substations to be...
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