Unlock instant, AI-driven research and patent intelligence for your innovation.

Intelligent calibration method and system for reflection type water level gauge in front of gate based on edge calculation

An edge computing, reflective technology, applied in the field of intelligent calibration of reflective water level gauges in front of the gate, to reduce the impact

Pending Publication Date: 2021-10-29
NANJING AUTOMATION INST OF WATER CONSERVANCY & HYDROLOGY MINIST OF WATER RESOURCES
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to overcome the deficiencies of the prior art above, the present invention provides an intelligent calibration method and system for the reflective water level gauge in front of the gate based on edge computing to solve the problem of on-site calibration of the reflective water level gauge in front of the gate

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
  • Intelligent calibration method and system for reflection type water level gauge in front of gate based on edge calculation
  • Intelligent calibration method and system for reflection type water level gauge in front of gate based on edge calculation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] Such as Figure 1-2 As shown, this embodiment provides an intelligent calibration method and system for reflective water level gauges in front of gates based on edge computing, using on-site embedded computers, high-precision water level calibration platforms, multi-element sensors combined with thermal-mechanical coupling theory and machine learning methods, By sensing the output signal of the water level gauge and the environmental information at the same time, and adopting the strategy of establishing a measurement error correction model offline regularly and outputting it online in real time, the intelligent calibration of the water level in front of the gate is realized.

[0043] The method can be extended to occasions where reflective water level gauges are used behind gates, in front of dams, in channels, etc., to realize high-precision monitoring of water levels.

[0044] Self-check the system equipment to determine whether the system equipment is normal. If not...

Embodiment approach

[0054] As an implementation, the underwater tray is used as the reference plane for calibration, and after the optimal measurement error correction model is determined, the underwater tray is vertically put away until it is close to the wall where the upper and lower vertical guide rails are located, Then measure the water level in front of the gate online.

[0055] As an implementation, during the calibration process, the vertical movement of the water level measuring device and the bracket is within the range of the reflective water level gauge; mid-range of the meter.

[0056] As an implementation, correlation vector machine (SVM), long short-term memory (LSTM), encoding-decoding neural network model and gated recurrent unit (GRU) are selected as the measurement error correction model.

[0057]As an implementation, the method for comprehensively evaluating the trained measurement error correction model includes: by randomly selecting multiple sets of input combinations, ca...

Embodiment 2

[0063] Such as Figure 1-2 As shown, this embodiment provides a system for intelligent calibration of the reflective water level gauge in front of the gate based on edge computing. Device 4, leveling mark 5 and reinforced concrete pier surface 6, wherein the measuring device and support 1 are used to measure the water level in front of the sluice as well as meteorological and transparency data; the support precision lifting control device 2 is used to drive the water level measuring device and support to a fixed interval height Move up and down and fix it; the reference surface providing device 3 is used to provide a stable water surface reference during calibration and ensure that the water flow and water surface will not be affected during measurement; the measurement communication control device 4, the measurement device and the bracket 1, the bracket precision lifting control device 2 and the reference surface Provide device 3 connection for measuring sensors, controlling ...

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 an intelligent calibration method and system for a reflection type water level gauge in front of a gate based on edge calculation. The method employs a field embedded computer, a water level high-precision calibration platform and a multi-element sensor to combine with a thermal coupling theory and a machine learning method, employs a regular off-line building measured value error correction model and an online real-time error correction strategy, and realizes intelligent calibration of the water level in front of the gate. In off-line calibration, a water level reference surface is firstly fixed, then a water level measuring device and a support are controlled to move up and down on a high-precision lead screw at a preset height interval, meanwhile, a water level value, meteorological parameters and transparency between the water surface and the support are measured, and a measured value error correction model is constructed by using a sample. Real-time error correction is conducted by taking influence factors as input of a measured value error correction model during online measurement. The method is visual and rigorous, the system is advanced and reliable, and the method can be popularized to other application scenes with high requirements for water level measurement precision and long-term stability.

Description

technical field [0001] The invention relates to the field of water conservancy engineering, in particular to an intelligent calibration method and system for a reflective water level gauge in front of a gate based on edge computing. Background technique [0002] The water level in front of the sluice is an important parameter for sluice operation control, structural safety analysis and flow calculation. Due to the low water head of the sluice, the rapid change of water level, and the sensitivity of the calculation and analysis model to the water level, the sluice has high requirements for the accuracy of water level observation. The existing reflection water level gauge It is easy to be affected by ambient temperature, atmospheric humidity, water surface transpiration, water mist flow, etc., resulting in measurement error, plus the temperature drift and time drift of the water level gauge itself, so the error is relatively large, and there is a tendency to gradually develop 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): G01F25/00
Inventor 方卫华孙勇梅星蔡悦卢涛蒋涛张威
Owner NANJING AUTOMATION INST OF WATER CONSERVANCY & HYDROLOGY MINIST OF WATER RESOURCES