Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Slope slide calamity forecast method based on RBF nerve network

A neural network and disaster technology, applied in neural learning methods, biological neural network models, alarms, etc., can solve problems such as slow convergence speed and long training time

Active Publication Date: 2017-06-09
XI'AN POLYTECHNIC UNIVERSITY
View PDF4 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a landslide disaster prediction method based on RBF neural network, which solves the problem that the convergence speed of BP is too slow and the training time is too long when the network is trained

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Slope slide calamity forecast method based on RBF nerve network
  • Slope slide calamity forecast method based on RBF nerve network
  • Slope slide calamity forecast method based on RBF nerve network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0155] 1) First construct the landslide disaster online monitoring and forecasting system, mainly including the wireless smart sensor module and the on-site forecasting terminal module. The data collected by the sensor acquisition module is standardized through the wireless smart sensor module, and the data is transmitted to the forecast terminal through the wireless communication module. The on-site forecast terminal then summarizes the data of each smart sensor to determine whether it reaches the forecast valve. value, and the data is uniformly processed and packaged and transmitted to the control center (PC side). And the data obtained from real-time monitoring are used as model input variables. And through the screening of MIV algorithm, the more important disaster factors relative to landslides are screened out, which helps to collect the main impact data in the case of such disaster prediction in the case of time constraints, so as to obtain more reliable prediction resu...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a slope slide calamity forecast method based on a RBF nerve network; the method comprises the following steps: building a slope slide calamity online monitoring forecast system, carrying out real time monitoring so as to obtain calamity forming factor data, using a MIV algorithm to screen the data, and using the calamity forming factor data obtained by monitoring as input variables; building a slope slide forecast model based on the RBF nerve network; inputting the calamity forming factor data into the slope slide forecast model, using the forecast model to process the inputted calamity forming factor data, thus finishing slope slide calamity forming probability prediction and forecast. The slope slide calamity forecast method based on the RBF nerve network can eliminate the influences caused by the factors irrelevant to a learning task in the inputted data on the learning performance in a data expression mode, and can keep the useful information in the learning task; the method can be applied to the slope slide calamity forecast, thus more accurately determining the slope slide calamity forming probability.

Description

technical field [0001] The invention belongs to the technical field of geological disaster forecasting methods, and in particular relates to a landslide disaster forecasting method based on an RBF neural network. Background technique [0002] Landslide is not only a natural disaster, but also a serious engineering geological disaster. In recent years, major geological disasters have occurred frequently, often causing damage to houses, interruption of communication facilities, collapse of roads, destruction of land, and even the destruction of villages. Moreover, accidents often occur in mountainous areas with complex geological structures and steep terrain. The time for the implementation of prevention and post-disaster recovery will be prolonged, causing inconvenience to the lives of residents. The scale and risk are far beyond what we can bear. Therefore, how to use technical means to monitor and forecast, to remind the affected people in real time, and to reduce disaster...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G08B21/10G06N3/08
CPCG06N3/082G08B21/10
Inventor 温宗周李璐李丽敏
Owner XI'AN POLYTECHNIC UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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