Method for controlling operation of complex pipeline based on deep learning

A technology of deep learning and operation control, applied in adaptive control, general control system, control/regulation system, etc., can solve problems such as high energy consumption, short reliable running time, frequent safety problems, etc., and achieve long reliable running time , reduced energy consumption, and fewer safety issues

Active Publication Date: 2018-04-06
NINGBO UNIV
View PDF7 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a complex pipeline operation control method based on deep learning to solve the problems that the existing technology canno

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
  • Method for controlling operation of complex pipeline based on deep learning
  • Method for controlling operation of complex pipeline based on deep learning
  • Method for controlling operation of complex pipeline based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0029] Specific implementation mode one: combine figure 1 , figure 2 , image 3 This embodiment is described. The complex pipeline operation control method based on deep learning given in this embodiment is as follows: image 3 As shown, the specific steps are as follows:

[0030] Step 1. For each section of the pipeline in the pipeline network, a control-oriented complex pipeline model is established in the SCADA system. A complex pipeline network usually consists of water source 1 (reservoir), flow meter 2, pressure gauge 5, pump 4 (pumping station), valve 3 and so on. Flow meter 2, pressure gauge 5, pump 4 (pump station), valve 3 are connected to the central control room through wired or wireless; the central control room dispatches and monitors the entire pipeline network in real time through SCADA system and powerful numerical calculation, information fusion, etc. information (a schematic diagram of a complex pipeline network such as figure 1 , figure 2 shown);

...

specific Embodiment approach 2

[0046] Embodiment 2: The difference between this embodiment and Embodiment 1 is that in step 3, the specific steps for determining whether to adopt the complex pipeline open-loop control strategy based on the deep learning method or to adopt the complex pipeline closed-loop control strategy based on the deep learning method include: :

[0047] Define the following toggle function:

[0048]

[0049] Among them, P e1 , P e2 is the switching function weight, is the flow value at the preset pipeline position or the flow value in the pipeline section, is the pressure value at the preset pipeline position or the pressure value in the pipeline section, q i Indicates the flow value measured by the i-th flowmeter in the pipe network, i∈[1,M], p j Indicates the pressure value measured by the jth pressure gauge in the pipe network, j∈[1,N], M is the number of flowmeters in the pipe network, and N is the number of pressure gauges in the pipe network;

[0050] Generally speaking...

specific Embodiment approach 3

[0052] Specific implementation mode three: as Figure 4 As shown, the difference between this embodiment and the specific embodiment 1 is that in step 41, the specific steps of the complex pipeline open-loop control strategy include:

[0053] A1. Starting from the mechanism model of complex pipelines, establish a control-oriented space-time evolution model, give boundary valves, and write them into the pipeline space-time evolution module;

[0054] A2. Set the performance index of complex pipeline open-loop control and write it into the performance index module of open-loop control;

[0055] A3. Introduce Lagrangian functions λ(l, t), μ(l, t) into the co-state module of open-loop control to obtain the performance index of extended open-loop control and obtain the performance of open-loop control by variational method Co-state model, write the co-state model of open-loop control into the co-state module of open-loop control, and write the obtained gradient form into the gradie...

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 provides a method for controlling the operation of a complex pipeline based on deep learning, belongs to the technical field of pipeline transportation, and especially relates to a method for controlling the operation of a complex pipeline. First, a control-oriented complex pipeline model is built in an SCADA system; the position or section needing operation control is determined according to the pipe network information monitored in real time and the user or industrial demand for the pipeline; then, whether to adopt a complex pipeline open-loop control strategy based on a deep learning method or a complex pipeline closed-loop control strategy based on a deep learning method is decided according to the obtained flow and pressure information of the position or section needingoperation control, and a strategy is performed according to the decision result; and finally, information is fused, and the operation control of the complex pipeline network is completed in a coordinated manner. In the prior art, the operation of a complex pipeline cannot be controlled effectively and reasonably, which leads to frequent occurrence of safety problems, high energy consumption and short reliable running time. The problem is solved by using the method of the invention. The method of the invention can be used in pipeline transportation.

Description

technical field [0001] The invention belongs to the technical field of pipeline transportation, in particular to a complex pipeline operation control method. Background technique [0002] A pipeline is a device used to transport gas, liquid or fluid with solid particles connected by pipes, pipe connectors and valves. In actual engineering, according to the layout and connection of pipelines, pipelines are divided into two types: simple pipelines and complex pipelines; simple pipelines refer to pipelines whose diameter and flow do not change along the way (equal-diameter pipelines without branches); complex pipelines refer to pipelines Pipelines whose diameter and flow rate change along the way (a pipeline system composed of more than two pipelines), complex pipelines can be divided into series, parallel pipelines, branched and ring pipe networks, etc. Worldwide, complex pipelines are widely used for the supply and transportation of materials such as water, petroleum, liquef...

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): G05B13/04
CPCG05B13/042
Inventor 陈特欢蔡振宇
Owner NINGBO UNIV
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