Water quality fluctuating range prediction method based on combination of deep learning algorithm and mixed integer linear programming

A mixed integer and linear programming technology, applied in forecasting, calculation, data processing applications, etc., can solve problems such as difficult to establish water quality prediction models

Active Publication Date: 2017-10-24
郑保宁 +1
View PDF6 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The water environment system is a complex system affected by many factors such as biology, chemistry, physics, and man-made, and the wa

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
  • Water quality fluctuating range prediction method based on combination of deep learning algorithm and mixed integer linear programming
  • Water quality fluctuating range prediction method based on combination of deep learning algorithm and mixed integer linear programming
  • Water quality fluctuating range prediction method based on combination of deep learning algorithm and mixed integer linear programming

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0031] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0032] The overall flow chart of the water quality fluctuation interval prediction method based on the combination of deep learning algorithm and mixed integer linear programming is as follows: figure 1 shown, including the following steps:

[0033] Step 1. Historical data preprocessing of water quality indicators

[0034] The prediction of water quality indicators is a time series prediction problem. The lack of data at any point in time will affect the accuracy of the overall prediction to a certain extent. Therefore, it is necessary to complete the historical data of water quality monitoring. According to the known data before and after the missing point, the fitting polynomial is constructed by the method of least squares, and then the missing value of the historical data of water quality indicators is supplemented according to thi...

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 water quality fluctuating range prediction method based on a combination of a deep learning algorithm and mixed integer linear programming, and belongs to the fields of water environmental protection and monitoring study. The method comprises the steps of firstly, introducing an LSTM (Long Short Term Memory) model architecture suitable for time series data prediction in the deep learning algorithm into modeling of water quality time series point prediction; and secondly, considering that the LSTM model has strong time series prediction performance but has common problems of deterministic prediction methods, namely cannot be used for estimating the indeterminacy of prediction, constructing a general range prediction model based on mixed integer linear programming according to the deviation of validation set sample LSTM point prediction and real values and a confidence parameter, thus giving a water quality fluctuating range prediction method under certain confidence. The method can provide a new solution for water quality prediction, and then provides reliable evaluation and early warning basis for water quality early warning.

Description

technical field [0001] The invention relates to a water quality fluctuation interval prediction method based on the combination of deep learning algorithm and mixed integer linear programming, which belongs to the research field of water environment protection and monitoring. Background technique [0002] Water is the source of life, and human beings cannot do without water in life and production activities. With the rapid development of my country's economy, the expansion of population, and the decline of the self-purification capacity of rivers and lakes, rivers and lakes in my country are generally polluted to varying degrees, and 75% of the lakes in the country have experienced eutrophication to varying degrees. Water pollution reduces the use function of water bodies, exacerbates the shortage of water resources, and has a negative impact on the implementation of my country's sustainable development strategy. Based on the historical data of water quality monitoring, a w...

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): G06N3/04G06Q10/04
CPCG06N3/04G06Q10/047
Inventor 郑保宁包哲静
Owner 郑保宁
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products