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

Series water conveyance canal water level prediction and control method based on fuzzy neural network

A technology of fuzzy neural network and control method, applied in the field of real-time control of channel water level, can solve the problems of difficulty in determining constant linear relationship parameters, limit the practicability of simplified linear control model, etc., and achieve the effect of accurate prediction and control of water level

Active Publication Date: 2020-07-31
CHINA INST OF WATER RESOURCES & HYDROPOWER RES
View PDF19 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, there are still a series of problems in the use of this simplified linear control model. First, it is difficult to determine the constant linear relationship parameters between the pond and water level and flow in the integral time-delay model; second, the integral time-delay model is too simplified, and its assumptions There is a constant linear relationship between the canal pond and the water level and flow. This basic assumption does not hold when the water delivery conditions of the canal pond change greatly. Third, the control action here is the gate flow, and it is necessary to further convert the gate flow into Spend
These issues limit the usefulness of simplified linear control models

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
  • Series water conveyance canal water level prediction and control method based on fuzzy neural network
  • Series water conveyance canal water level prediction and control method based on fuzzy neural network
  • Series water conveyance canal water level prediction and control method based on fuzzy neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0056] This embodiment provides a method for predicting and controlling the water level of series water delivery channels based on fuzzy neural network, such as Figure 9 shown, including the following steps:

[0057] S1, establish a fuzzy neural network with multiple inputs and single outputs, train the fuzzy neural network based on the operating data of the channel, and obtain a fuzzy neural network prediction model that can predict the water level of the canal pond based on the opening value of the gate and the initial water level;

[0058] S2, based on the fuzzy neural network prediction model in step S1, constructing a water level controller in front of the gate coupled with a predictive control algorithm;

[0059] S3, based on the control target of the water level controller in front of the gate constructed in step S2, the optimal control rate of the water level controller in front of the gate is solved by gradient optimization algorithm;

[0060] S4, based on the optim...

specific Embodiment approach

[0092] In this implementation mode, an 11-stage series canal pool is taken as an example. By controlling the opening of the control gate, the water level in front of the downstream control gate of each canal pool is guaranteed to be stable, that is, the control target is the water level in front of the 11 control gates. Assume that a large flow change occurs upstream, and the initial water level is much lower than the target water level in front of the gate. The target water levels in front of the 11 control gates are 73.8m, 72.6m, 71.8m, 70.5m, 69.4m, 68.3m, 65.9m, 65.4m, 64.4m, 63.2m, 62.2m. The control strategy is selected as once every 2 hours to ensure that the target water level is within 0.3m above and below the target water level. The method in Example 1 is used to regulate the gate to achieve the goal of regulation. Since this method is a real-time gate control algorithm, in this embodiment, a one-dimensional hydrodynamic model is used instead of an actual project to...

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 series water conveyance canal water level prediction and control method based on a fuzzy neural network, and relates to the technical field of water level prediction. The method comprises: conducting the relation between the gate opening degree and the open channel control water level through a fuzzy neural network, and constructing a pre-gate water level controller coupled with a predictive control algorithm; solving the optimal control rate of the water level controller in front of the gate by adopting a gradient optimization algorithm based on the control target ofthe water level controller in front of the gate; based on the solved optimal control rate, collecting and multiplying actually measured water level change information by the optimal control rate to generate a control strategy, and therefore the purposes of water level prediction and control are achieved.

Description

technical field [0001] The invention relates to the technical field of real-time control of channel water levels, in particular to a method for predicting and controlling water levels of serial water delivery channels based on a fuzzy neural network. Background technique [0002] The control goal of channel water delivery is to provide users with safe and reliable water supply services. The stability of water delivery is controlled by the water level at certain points. These points are usually referred to as channel operation control points, and maintaining a stable water level at the control points is the primary condition for safe channel operation. Water level control is mainly accomplished by the control buildings in the middle of the ditch pond and at the entrance. The water level control of the canal pond is mainly based on real-time water level information. The traditional canal operation control basically relies on manual operation, and the control process complete...

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): G05D9/12G05B13/02G05B13/04G06N3/04G06N3/08G06Q10/04
CPCG05D9/12G05B13/0285G05B13/042G05B13/048G06N3/08G06Q10/04G06N3/045G06Q50/06G06N3/043G06N3/063
Inventor 雷晓辉孔令仲田雨张召黄鑫王超王浩乔雨朱杰靳燕国
Owner CHINA INST OF WATER RESOURCES & HYDROPOWER RES
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