Ground subsidence prediction system and method based on support vector machine
A support vector machine and land subsidence technology, which is applied in database management systems, computer components, character and pattern recognition, etc., can solve problems affecting ground subsidence, poor fault tolerance, construction risks, etc., to ensure smooth operation and improve storage capacity , to avoid the effect of abnormal operation
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0030] Shield construction needs to use machine operation data, construction geological data and construction environment data to predict the ground subsidence of the construction line. The traditional ground subsidence analysis method is to train the model in single machine and serial mode. When faced with massive data The exposed problems such as slow speed, low efficiency and poor fault tolerance directly affect the prediction accuracy of ground settlement, which in turn brings construction risks.
[0031] For this present situation and problem, the present invention launched research, proposed a kind of land subsidence prediction system based on support vector machine, see figure 1, comprising Hadoop big data analysis platform, data collection module, data preprocessing module, model construction module, subsidence prediction module in the land subsidence prediction system based on support vector machine of the present invention, data collection module, data preprocessing m...
Embodiment 2
[0034] The overall composition of the land subsidence prediction system based on support vector machine is the same as embodiment 1, see figure 1 , the data collection module of the present invention includes a data collection range determination sub-module and a data storage sub-module, the data collection range determination sub-module is to determine the characteristic variables through the mechanism analysis in the shield construction process, collect the corresponding machine operation data, and construct Geological data and construction environment data, and determine the characteristic data related to the settlement; the data storage sub-module of the data collection module is to store the collected land subsidence data, that is, the characteristic data, on the distributed file system of the Hadoop big data analysis platform .
Embodiment 3
[0036] The overall composition of the land subsidence prediction system based on support vector machine is the same as embodiment 1-2, see figure 1 , the data preprocessing module of the present invention includes a cleaning processing submodule, a denoising processing submodule, a normalization processing submodule and a dimensionality reduction processing submodule. The cleaning processing sub-module is to detect and fill the null values in the original data, so as to avoid abnormalities caused by missing data when building the model. The denoising processing sub-module is to eliminate the abnormal points in the data processed by the cleaning processing sub-module, so as to reduce the influence of "noise" data on the model accuracy. The normalization processing sub-module is to map the data processed by the cleaning processing sub-module and denoising processing sub-module to the [0,1] interval, eliminating the dimensional impact caused by the inconsistency of data units b...
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