Water inflow forecasting method based on wavelet transform and ARMA-SVM

Abstract

The invention belongs to the technical field of deposit hydrogeological exploration and relates to a water inflow forecasting method based on wavelet transform and ARMA-SVM (auto-regressive moving-average model-support vector machine). The water inflow forecasting method comprises the following steps: collecting and analyzing the water inflow account data of a mine, then selecting a modeling sample and an inspection sample, performing dyadic wavelet decomposition and reconstruction on the modeling sample, extracting a high-frequency signal and a low-frequency signal in an original time sequence, utilizing the ARMA model to build a high-frequency signal model, meanwhile, utilizing the SVM to build a low-frequency signal model, synthesizing the high-frequency signal model and the low-frequency signal model to obtain a final water inflow prediction model, and finally, utilizing the inspection sample to inspect the final prediction model to realize water inflow prediction. While the low-frequency signal is fully fit, over-fitting of the high-frequency signal is avoided, the working principle is reliable, the prediction method is simple, the prediction precision is high and the prediction environment is friendly.

Description

Technical field: [0001] The invention belongs to the technical field of ore deposit hydrogeological exploration, and relates to a water inflow prediction method, in particular to a water inflow prediction method based on wavelet transform and autoregressive moving average model-support vector machine (ARMA-SVM). Background technique: [0002] Mine water inflow is the amount of water poured into the mine pit (including wells, lanes and mining systems) per unit time. It is an important indicator to determine the complexity of the hydrogeological conditions of the mine deposit and mine construction and rational development. It is also the mine production department to formulate mining methods and determine The main basis for meeting the required drainage capacity and economical drainage facilities is of great significance to mine water prevention and control work. The prediction of mine water inflow is a relatively complicated and difficult task. At present, the commonly used m...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to overcome the defects existing in the existing water inflow prediction technology, and seek to provide a water inflow prediction method. In order to solve the problem of non-stationary time series prediction of water inflow, considering the impact of binary orthogonal wavelet decomposition on non-stationary The adaptability of time series, the separation effect on low frequency and the good generalization ability of support vector machine provide a water inflow prediction method based on wavelet transform and ARMA-SVM to improve the prediction accuracy

Images