High and steep slope deformation trend prediction method based on multi-factor fuzzy time sequence

Abstract

The invention relates to a high and steep slope deformation trend prediction method based on a multi-factor fuzzy time sequence, and the method comprises the following steps: employing a type-2 fuzzytime sequence algorithm to determine main factors and secondary factors affecting slope deformation, the discourse domain division of the fuzzy time sequence is more reasonable by using an overall distribution optimization algorithm, the slope dynamic deformation prediction precision is improved, the prediction accuracy of small samples and fluctuation data is improved, and the data change of theslope in a certain period in the future can be predicted.

Description

technical field [0001] The invention belongs to the technical field of slope deformation monitoring in open-pit mines, and in particular relates to a method for predicting deformation trends of high and steep slopes based on multi-factor fuzzy time series. Background technique [0002] With the rapid development of my country's economy, the mining range and depth of open-pit mines are constantly increasing, thus forming many large-scale high and steep slopes. On the one hand, the high and steep slope greatly changes the stress conditions in the local area, which in turn affects the structures around the open-pit mine; on the other hand, once the deformation of the high and steep slope exceeds the limit, accidents such as landslides are likely to occur, which is harmful to the safety of the mining area. Production and people's life safety have posed a great threat. [0003] The traditional mine slope deformation data is mainly obtained through multi-period deformation monito...

AI Technical Summary

Problems solved by technology

Among them, the time series analysis highlights the time series and does not consider the influence of external factors for the time being. However, due to the complex and changeable mine environment and many uncertain factors, there are often large deviations in the time series analysis.

Due to complex and changeable mine slope conditions and numerous factors, the modeling accuracy of regression analysis will have a large deviation due to unreasonable selection of modeling factors

Due to the complexity of the original monitoring data sources of mine slopes, the gray prediction model with strict requirements on the original monitoring data will have low prediction accuracy

The prediction results of the BP neural network model are related to the selection of the initial value, but it is difficult to determine the most reasonable initial value in the complex mine slope environment

A type of fuzzy time prediction model can improve the prediction accuracy, but only considers the change of the variable itself, that is, it can only predict multiple variables separately

However, in practical problems, the development of variables is not only related to itself, but also related to factors affecting environmental variables, so the prediction effect of the first-type fuzzy time prediction model is often not very ideal

Images