Radial basis function (RBF) neural network parameter self-optimizing-based multi-step prediction method for water quality

Abstract

The invention discloses a radial basis function (RBF) neural network parameter self-optimizing-based multi-step prediction method for water quality. The method comprises the following steps of: first storing the data of each monitoring station into a database of a local server by using the remote transmission of an online water quality monitoring instrument; then performing normalization processing on a water quality sample sequence, calculating an autocorrelation coefficient to determine an input variable of an RBF neural network, and converting sample data into a standard dynamic sequence data format trained and predicted by the RBF neutral network; next searching for and determining an optimal value of a spreading coefficient spread of the RBF neural network by utilizing a differential evolution algorithm and taking a relative standard error as a target function to obtain an optimal prediction model; and finally sampling water quality data in real time, performing multi-step prediction by using the obtained optimal prediction model and adopting a single-point iteration method, and evaluating a water quality prediction result to realize an early warning function. The water quality can be intelligently warned.

Description

technical field [0001] The invention relates to a water quality prediction method, in particular to a multi-step water quality prediction method based on RBF neural network parameter self-optimization. Background technique [0002] Drinking water safety is related to the national economy and people's livelihood. Real-time prediction and analysis of water quality can effectively control and reduce the harm caused by water quality deterioration, and achieve the goal of effective cognition and control of water quality deterioration. In addition, timely and effective multi-step water quality prediction can win more emergency response time for water plants. [0003] At present, the main researches at home and abroad are on single-step water quality prediction methods. One-step water quality prediction includes two aspects: mechanism-based modeling and intelligence-based modeling. Due to the complexity and changeability of the water environment system, its detailed mechanism canno...

AI Technical Summary

Problems solved by technology

Neural network has powerful self-organization, self-learning, parallel processing information and nonlinear fault-tolerant capabilities, and is a research hotspot at home and abroad, but only knowing the predicted value at the next time point cannot provide a long enough emergency response for the water quality early warning system time, so it is necessary to introduce a multi-step forecasting method

Images