On-line identification and control method and system of rotation speed of dredge pump of dredger based on neural network

A technology of neural network and control method, which is applied in the field of online identification control method and system of dredger mud pump speed, and can solve problems such as inability to cope with offline identification and slow convergence speed

Active Publication Date: 2020-06-12
SHANGHAI JIAO TONG UNIV
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Aiming at the shortcomings of the existing neural network system such as slow convergence speed and inability to deal with uncertain systems in offline identification, the present invention proposes an online identification control method and system for dredger mud pump speed based on neural network, which solves the problem of cutter suction dredger The problem of precise control of the speed of the mud pump has achieved the goal of precise construction and energy-saving transportation

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
  • On-line identification and control method and system of rotation speed of dredge pump of dredger based on neural network
  • On-line identification and control method and system of rotation speed of dredge pump of dredger based on neural network
  • On-line identification and control method and system of rotation speed of dredge pump of dredger based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] In this embodiment, Matlab is used to simulate the physical model of the mud pump, and a required speed target is customized.

[0021] This embodiment relates to a neural network-based online identification control method for dredging equipment, which specifically includes the following steps:

[0022] Step 1, give the number of identification points N n and polynomial number N m and the number of terms in the Taylor expansion N a , N b

[0023] In this embodiment, the simulation object model expression is used: Objective function: y i =0.25sin[π(i-1) / 180] as an example, assign N n =N a =N b = 2,N m = 3;

[0024] Step 2: Give Top N m The input value and the corresponding output value at +1 control time point. In this example, the initial input value is assigned 1.9702 times the expected output value. The assignment is shown in Table 1 below.

[0025] Table 1, initial values

[0026] Simulation serial number Control input (u) output value (y) ...

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 an on-line identification and control method for directly determining rotation speed of a dredge pump of a dredger of a neural network based on weight. The on-line identification and control method includes the steps that firstly, a photoelectric encoder is used for detecting the actual rotation speed of the dredge pump and recording the input target rotation speed of a corresponding dredge pump driving converter; then, a forward neural network controller is established, the detected actual rotation speed of a plurality of steps of the dredge pump and the corresponding input target speed are taken as input and output data of the neural network, and the weight of the neural network is calculated and determined by a method for directly determining the weight; and finally, according to the target rotation speed under an actual working condition, the required rotation speed control amount of the dredge pump is determined by the trained forward neural network controller, and is converted into a rotation speed control instruction and sent to the driving converter to realize online control. According to the on-line identification and control method, the difficult problem of accurate control of the rotation speed of the dredge pump of the cutter suction dredger is solved, and the purpose of precise construction and energy saving transportation is achieved.

Description

technical field [0001] The invention relates to a technology in the field of artificial intelligence application, in particular to a method and system for online identification and control of the speed of a dredger dredge pump based on a neural network. Background technique [0002] Offline identification is obviously unable to deal with uncertain systems and systems whose system characteristics change with time. Especially for the dredger dredging system, as the excavation depth or width changes, the soil properties will change accordingly, the resistance characteristics of the pipeline will also change, and the characteristics of the dredge pump will also be affected. Therefore, the previous offline identification model has long been consistent with the actual production model. lost pair. Contents of the invention [0003] Aiming at the shortcomings of the existing neural network system such as slow convergence speed and inability to deal with uncertain systems in offli...

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
Patent Type & Authority Applications(China)
IPC IPC(8): F04D15/00
CPCF04D15/0066F05D2270/304F05D2270/709F05D2270/71
Inventor 李铭志何炎平谷孝利赵永生刘亚东黄超
Owner SHANGHAI JIAO TONG 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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap