CN111335388A - Full-intelligent cutter suction dredger - Google Patents

Full-intelligent cutter suction dredger Download PDF

Info

Publication number
CN111335388A
CN111335388A CN202010109232.6A CN202010109232A CN111335388A CN 111335388 A CN111335388 A CN 111335388A CN 202010109232 A CN202010109232 A CN 202010109232A CN 111335388 A CN111335388 A CN 111335388A
Authority
CN
China
Prior art keywords
yield
control
prediction model
pump
reamer
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010109232.6A
Other languages
Chinese (zh)
Inventor
张晴波
戴文伯
侯晓明
肖晔
林挺
陈新华
冯波
胡京招
王海荣
崔鹏飞
刘佳
沈彦超
王柳艳
王纲筛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
CCCC National Engineering Research Center of Dredging Technology and Equipment Co Ltd
Original Assignee
CCCC National Engineering Research Center of Dredging Technology and Equipment Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by CCCC National Engineering Research Center of Dredging Technology and Equipment Co Ltd filed Critical CCCC National Engineering Research Center of Dredging Technology and Equipment Co Ltd
Priority to CN202010109232.6A priority Critical patent/CN111335388A/en
Publication of CN111335388A publication Critical patent/CN111335388A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • E—FIXED CONSTRUCTIONS
    • E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
    • E02F—DREDGING; SOIL-SHIFTING
    • E02F5/00—Dredgers or soil-shifting machines for special purposes
    • E02F5/28—Dredgers or soil-shifting machines for special purposes for cleaning watercourses or other ways
    • E02F5/282—Dredgers or soil-shifting machines for special purposes for cleaning watercourses or other ways with rotating cutting or digging tools
    • E—FIXED CONSTRUCTIONS
    • E02—HYDRAULIC ENGINEERING; FOUNDATIONS; SOIL SHIFTING
    • E02F—DREDGING; SOIL-SHIFTING
    • E02F3/00—Dredgers; Soil-shifting machines
    • E02F3/04—Dredgers; Soil-shifting machines mechanically-driven
    • E02F3/88—Dredgers; Soil-shifting machines mechanically-driven with arrangements acting by a sucking or forcing effect, e.g. suction dredgers
    • E02F3/90—Component parts, e.g. arrangement or adaptation of pumps
    • E02F3/92—Digging elements, e.g. suction heads
    • E02F3/9256—Active suction heads; Suction heads with cutting elements, i.e. the cutting elements are mounted within the housing of the suction head
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
    • G01D21/00—Measuring or testing not otherwise provided for
    • G01D21/02—Measuring two or more variables by means not covered by a single other subclass
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
    • G05B19/05—Programmable logic controllers, e.g. simulating logic interconnections of signals according to ladder diagrams or function charts
    • G05B19/054—Input/output
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Mechanical Engineering (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Structural Engineering (AREA)
  • Civil Engineering (AREA)
  • Mining & Mineral Resources (AREA)
  • Theoretical Computer Science (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biophysics (AREA)
  • Automation & Control Theory (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Placing Or Removing Of Piles Or Sheet Piles, Or Accessories Thereof (AREA)

Abstract

A full-intelligent cutter suction dredger is characterized in that based on embodiment 1, a traditional cutter suction dredger is transformed electrically and informationized or a newly-built cutter suction dredger is transformed to form a top-down control system and a bottom-up information acquisition system; meanwhile, acquiring electrical operation state data and yield data in a service process through an acquisition system to form a sample database; constructing a neural network online prediction model, and designing five control variable inputs and one output as a mathematical model of the neural network; the mathematical model is updated after the neural network is trained by using the sample, when the hull control variable at the current moment is input, the output prediction yield value is solved on line through the neural network, the optimal control parameter is output by adopting an optimizer optimization algorithm, the optimal process control parameter in an ideal state is continuously approached after iteration, the intelligent operation is realized, and the optimal yield value is kept.

Description

Full-intelligent cutter suction dredger
Technical Field
The invention belongs to the field of dredging of a cutter suction dredger.
Background
The cutter suction dredger is a typical dredging engineering construction ship and is one of the most important production tools of dredging enterprises. The cutter suction dredger control system consists of a plurality of local subsystem controllers, and professional machines such as a large dredge pump, a hydraulic system, an electrical system, a reamer head and a shaft system, a steel pile trolley, a transverse winch system and the like are integrated on the cutter suction dredger control system, and the machines are various. In addition, the existing cutter suction dredger is generally non-motorized, a dredge pump, a bridge frame, main and auxiliary steel piles, a winch and the like are arranged on the dredger, automation and intellectualization of the dredger are difficult to realize on equipment on the dredger, and constructors need to participate in construction operation in the whole process, so that a large amount of waste of manpower, material resources and financial resources is caused.
The professional machines and tools have various local characteristics, and each subsystem is mutually influenced, mutually restricted and has complex relationship. The cutter suction dredging comprises sub-processes of throwing left and right transverse moving anchors, closing, transverse moving, cutter cutting, pumping, blowing bank and the like, complex interaction occurs between dredging machines and the environment, mud surface and water flow in the processes, the manual operation amount is large, and the requirements on control precision and timeliness are high.
Disclosure of Invention
In the traditional mode, the yield of the cutter suction dredger mainly depends on the operation of a dredger, and the control parameters of the system are required to be continuously adjusted according to different construction working conditions. In this embodiment 2, based on embodiment 1, a fully intelligent dredging control of the cutter suction dredger is further provided, a neural network algorithm is constructed to establish a prediction model and an optimizer on line, a sample is collected by a sensing system to train the prediction model, and an optimal mode of prediction control can assist an operator to find a better construction method, so that high efficiency and high yield are ensured. The dredging automatic optimization target of the embodiment 2 comprises time efficiency and energy efficiency of dredging yield, and dozens of influencing factors are involved, and the factors are mutually involved to form a complex nonlinear system.
General technical scheme
A full-intelligent cutter suction dredger is based on embodiment 1, a traditional cutter suction dredger is transformed electrically and informationized or a cutter suction dredger is newly built to form a top-down control system and a bottom-up information acquisition system; meanwhile, acquiring electrical operation state data and yield data in a service process through an acquisition system to form a sample database; constructing a neural network online prediction model, and designing five control variable inputs and one output as a mathematical model of the neural network; the mathematical model is updated after the neural network is trained by using the sample, when the hull control variable at the current moment is input, the output prediction yield value is solved on line through the neural network, the optimal control parameter is output by adopting an optimizer optimization algorithm, the optimal process control parameter in an ideal state is continuously approached after iteration, the intelligent operation is realized, and the optimal yield value is kept. The prediction control mode can help operators to find a better construction method, and high efficiency and high yield are ensured.
The operation process of the traditional cutter suction dredger for dredging is the prior art, each machine tool on the dredger is an independent control system, after the dredger reaches a target sea area, an operator coordinates and operates each operation machine tool according to experience in sequence, and each set of machine tool is manually cooperated to complete the conventional operation process. The conventional dredging yield is determined by the operator's own experience and experience. The invention aims to disclose a full-intelligent cutter suction dredger for the first time in the field, and therefore, the whole technical scheme of the invention is innovated as follows:
firstly, by transforming the existing or newly-built cutter suction dredger for dredging, the independently-controlled machine tool subsystems are integrated into an organic whole. Firstly, all sets of machines are uniformly driven by a motor (a frequency converter), namely, electric drive is adopted; secondly, real-time working state signals and yield information are collected, distributed sensors are uploaded and collected to an operation platform database of the ship body through the PLC, and meanwhile, a processor of the operation platform of each machine tool subsystem coordinates the operation mode of each machine tool in a unified mode through the PLC.
And secondly, constructing a brain on the operation platform, establishing a yield prediction model by using a neural network, accumulating the working state and the yield value of each machine tool to enable a database to collect precious samples, and designing an optimizer to seek the optimal yield control parameters.
And thirdly, optimizing the brain of the operation platform to obtain optimal yield control parameters on the premise of ensuring safe operation, so that the PLC controls each set of machine to drive the working state of the motor in each mechanism according to the operation step rules and the optimal control parameters, and each operation subsystem is adaptive to the sea area under the optimal operation state to achieve the maximum yield. Furthermore, with the increase of database samples, better parameters can be continuously learned by establishing a yield prediction model through a neural network, and the yield of the intelligent ship is continuously improved. Entering a new sea area, a new sample of the 'brain' of the intelligent ship in the new environment is adapted to the new environment through learning.
Drawings
FIG. 1-1 shows the hardware relationships corresponding to the system levels in example 1 (processor, PLC in platform, underlying sensors/motors in actuators)
FIGS. 1-2 show the hardware relationships corresponding to the system levels in example 2 (processor, PLC in platform, underlying sensors/motors in actuators)
FIG. 2 shows a hull and five mechanical parts of the machine tool subsystem (prior art)
FIG. 3 is a schematic view of the mounting position of the motor (embodiment 1 electrical modification of five machine tool subsystems)
FIG. 4 is a schematic view of a sensor arrangement
FIG. 5 is a schematic diagram of an operation algorithm flow of the intelligent control operation system
FIG. 6 is a schematic view of a traverse process by stepping a trolley distance
FIG. 7 yield-related Key parameters behind the five control input variables in inventive example 2
FIG. 8 is a block diagram of the intelligent control in embodiment 2 of the present invention
FIG. 9 RBF neural network model for construction yield of cutter suction dredger in embodiment 2 of the invention
Numerical labeling: bridge winch motor 1, transverse winch motor 2, steel pile trolley electric push rod motor 3, reamer motor 4 and dredge pump motor 5
Detailed Description
The technical solutions provided in the present application will be further described with reference to the following specific embodiments and accompanying drawings. The advantages and features of the present application will become more apparent in conjunction with the following description.
It should be noted that the embodiments of the present application have a better implementation and are not intended to limit the present application in any way. The technical features or combinations of technical features described in the embodiments of the present application should not be considered as being isolated, and they may be combined with each other to achieve a better technical effect. The scope of the preferred embodiments of this application may also include additional implementations, and this should be understood by those skilled in the art to which the embodiments of this application pertain.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate. In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
The drawings in the present application are in simplified form and are not to scale, but rather are provided for convenience and clarity in describing the embodiments of the present application and are not intended to limit the scope of the application. Any modification of the structure, change of the ratio or adjustment of the size of the structure should fall within the scope of the technical disclosure of the present application without affecting the effect and the purpose of the present application. And the same reference numbers appearing in the various drawings of the present application designate the same features or components, which may be employed in different embodiments.
Example 1
In order to realize the full-automatic intellectualization of the cutter suction dredger, hull hardware (including electrification transformation, sensor arrangement and communication facility arrangement) is constructed, an intelligent dredger system is further built, and automatic control system software and safety guarantee software are developed.
The intelligent cutter-suction ship is used as a carrier and is divided into two layers, wherein one layer is an automatic control operation system (upper control), and the other layer is an acquisition system (bottom layer).
Figure BDA0002389367840000041
As shown in fig. 1. Various sensors collect construction state signals, transfer the construction state signals through the PLC, and then provide the construction state signals to a processor of a ship operation platform.
The processor and the microcomputer analyze and calculate to obtain a control signal according to the control instruction and the data collected by each sensor, the control signal is transmitted to the PLC through a TCP/IP network, and the PLC executes the control signal to five machine tool subsystems (motor driving equipment of each actuating mechanism) according to the feedback control instruction.
First part boat carrier and mechanical part
As shown in fig. 2 and 3.
The five machine tool subsystems serve as a service execution mechanism and comprise a mechanical part and a driving part, wherein the driving part is driven by electricity (or a traditional cutter suction ship is transformed into the machine tool which is driven by electricity), and the related motors comprise a bridge winch motor 1, a transverse moving winch motor 2, a steel pile trolley push rod motor 3, a reamer head motor 4 and a dredge pump motor 5 which belong to a frame winch system, a transverse moving system, a trolley system, a reamer system and a dredge pump system respectively.
Except that the trolley is connected with the positioning steel pile through the electric push rod and the displacement adjustment of the advancing and retreating of the ship body is realized through the expansion of the electric push rod driven by the electric push rod motor 3 of the steel pile trolley. Except for the design, the mechanical parts of all other service execution mechanisms are not the innovative part of the invention, and the components, the installation positions and the connection relations of the mechanical parts and the mechanical parts are the prior art.
The arrangement and the constitution of each mechanical part in the figure are as follows:
the ship hull provides bearing capacity and provides main body buoyancy on the water surface.
The bridge is fixed at the middle front end of the ship body and used for carrying the reamer head, the mud pipe and the anchor mechanism. The raising or lowering is driven by a bridge motor 1.
The reamer head is positioned at the bow of the ship body and is arranged at the foremost end of the bridge, and the reamer head penetrates into the water and rotates under the driving of the reamer motor 4, so that the function of cutting soil and gravel is realized.
And the mud pipe is positioned at the foremost end of the bridge frame, transports the mud absorbed at the reamer head from the bow part to the stern part along the bridge frame, transmits the mud to the shore and is driven by a mud pump motor 5.
The temporary displacement adjusting mechanism consists of a trolley and a positioning steel pile and is positioned at the stern part of the ship body. The trolley is fixed on the ship body, the positioning steel pile is perpendicular to the ship body and fixed with the bottom of the ship body to play a role in fixing the ship body, and the trolley is connected with the positioning steel pile through the electric push rod and achieves displacement adjustment of advancing and retreating of the ship body through stretching of the electric push rod driven by the electric push rod motor 3 of the steel pile trolley.
The temporary displacement adjusting mechanism is also provided with a transverse moving winch which is driven by a transverse moving winch motor 2, takes the positioning steel pile as the center of a circle, is connected to the anchor through a steel wire rope, releases/tightens the steel wire rope to realize the sector movement of the ship body towards the left or the right, and adjusts the angle of the ship head.
The anchor mechanism comprises an anchor, an anchor throwing rod, an anchor rod winch and an anchor winch: the anchor is located at the front ends of the port and the starboard of the ship body, the anchor is connected with the anchor throwing rods through steel wire ropes, the position of the ship body is determined through the anchor throwing rods, and after the anchor is anchored into water, the anchor is in contact with a mud surface to play a role in fixing the ship body. The anchor rod winches are suitable for two anchor rod throwing machines, are also positioned at the front ends of the port and the starboard of the ship body, and play a role in pulling back/releasing the respective anchor rod throwing machines through steel wire ropes; and two anchor lifting winches are also provided, and the two anchor lifting winches retract/release the steel wire rope and play a role in lifting/releasing the anchors on the left side and the right side.
And a steel wire rope is arranged between the bridge winch and the bridge and used for adjusting the lifting of the bridge to control the lowering or lifting of the reamer head and start preparation work or finish departure.
Second part boat carrier and sensor
As shown in fig. 4.
The sensing system comprises a bridge frame sensing system, a transverse moving sensing system, a trolley sensing system, a reamer sensing system and a dredge pump sensing system, wherein:
the bridge frame sensing system comprises a draught sensor 11, a rotary encoder 12, a tide level remote-report instrument 13 and a frequency converter 15; the draft sensors 11 are distributed around the cutter suction dredger and used for measuring the draft of the dredger body, the rotary encoders 12 are located on the left side and the right side of the front portion of the dredger body and used for measuring the landing state of the transverse moving anchor and the angle of the anchor throwing rod, and the tide level remote-reporting instrument 13 is used for measuring the tide level; the draft sensor 11, the tide level remote-reporting instrument 13 and the rotary encoder 12 jointly calculate the bridge frame lowering depth HLowering depth＝aDraught of ship body+sin(bBridge frame angle)*cBridge frame length-dTidal level. The frequency converter 15 is used for obtaining the speed of the bridge winch(control amount).
The transverse moving sensing system comprises a GPS21, a laser radar 22, an acceleration gyroscope 23, a transverse moving tension sensor 24 and a frequency converter 25. The laser radars 22 are installed at the front left, rear left, front right, and rear right of the hull for indoor positioning of the ship. And the acceleration gyroscope 23 is used for acquiring the transverse movement acceleration of the ship body.
The trolley sensing system comprises a frequency converter 31 and a pull rope encoder 32; the frequency converter 31 is used for obtaining the traveling speed of the trolley, and the pull rope encoder 32 is used for acquiring the travel of the trolley.
The reamer sensing system comprises a frequency converter 41 for obtaining the reamer speed and pressure.
The dredge pump sensing system comprises a frequency converter 51 and a pressure sensor 52; the pressure sensors 52 are used for measuring the vacuum degree and the discharge pressure in the mud pipe and are uniformly distributed along the conveying pipeline at the rear part of the mud pump.
Description of the individual sensors:
Figure BDA0002389367840000061
Figure BDA0002389367840000071
and annotating: the frequency converter can convert the pressure of the reamer according to the torque, and is equivalent to a pressure sensor in function.
Third part ship carrier and automatic control operation system
According to a drawing provided by a dredging project owner, a construction drawing specifies a horizontal plane for intelligently controlling the operation of the cutter suction dredger, namely an excavation width W, through a left working line, a middle working line and a right working line; the depth of the intelligent control ship operation, namely the excavation depth D, is specified through a water depth map; the width, the depth and the working line form an excavation three-dimensional area, namely a working area, for intelligently controlling the operation of the cutter suction dredger. The intelligent control cutter suction dredger is moved to an operation area under the dragging of a tugboat (or automatically if the tugboat has a navigation function), the auxiliary pile is lifted to leave the mud surface, and the main positioning pile is placed in the auxiliary pileThe working line between the two sides, the mud discharge pipe mouth of the stern is connected with the pipe above the water, the left and right transverse moving anchor is fixed under the assistance of the tugboat or the anchor boat, the bow is close to the working line on one side (left or right) under the assistance of the tugboat, five machine subsystem devices are inspected, and the inspection is completedPreparatory work before work。
Starting an intelligent control operation system, sequentially completing operation algorithms (as shown in fig. 5 and 6), taking a trolley period as an example, and comprising the steps of ' automatically lowering to a specified depth ', ' automatically starting and adjusting a dredge pump ', ' automatically starting and adjusting a reamer ', ' automatically laterally moving and ' automatically stepping ', and specifically:
starting a bridge winch motor 1, and lowering the bridge to the depth determined by an intelligent control program, namely the depth of the reamer head capable of entering the soil;
in the process of lowering the bridge, once the depth of the bridge calculated by integrating the draft sensor 11, the rotary encoder 12 and the tide level remote-reporting instrument 13 senses that a mud conveying pipeline suction port on the inner side of a reamer head at the front end of the bridge is submerged into water, the mud pump motor 5 is started immediately, the mud pump sucks in clean water, and the mud conveying pipeline is filled with the clean water; in the process of lowering the bridge, once the rotary encoder 12 senses that the reamer head positioned at the front end of the bridge is submerged in water, the reamer motor 4 is started, the reamer head rotates to cut and break soil, the mud pump sucks mud, and the mud pump is filled with a mud conveying pipeline; the bridge frame lowering depth is calculated by a draft sensor, a tide level remote-report instrument and a rotary encoder together; hLowering depth＝aDraught of ship body+sin(bBridge frame angle)*cBridge frame length-dTidal level；
Then, starting the traverse winch motor 3, moving to one side of the traverse direction by tightening the traverse cables on one side connected with the anchor in the same advancing direction until the GPS21 or the laser radar 22 detects a traverse side line, and passively releasing the traverse cables on the other side connected with the anchor in the opposite advancing direction in the moving process;
after the trolley is moved transversely and stopped at the same time, the electric push rod motor 3 of the steel pile trolley is started to push the ship body to move forwards to the advancing distance determined by the intelligent control program, namely the stepping distance L, then the transverse movement winch motor 2 is started to move continuously on one side, and the process is repeated in a circulating mode until the stay cord encoder 32 detects that the trolley reaches the maximum displacement, so that the production process period of the trolley is finished.
The transverse movement is always kept at the excavation depth D to adapt to the change of the bridge depth along with the influence of the tide level, so that the transverse movement can be completed at a certain depth in one trolley periodTransverse (dredging) work。
Repeating the trolley stepping, advancing the process and repeating the cycle.
If the single excavation depth does not meet the depth requirement of the owner, returning the trolley to the initial position of the trolley after the trolley reaches the end position of the trolley, lowering the bridge frame, and repeating the dredging operation described above until the end position of the trolley; therefore, the bridge is lowered and the mud is dug, and the bridge is continuously close to the depth required by the owner.
The fourth part automatic control operation system also comprises a safety guarantee module
The cutter suction ship is interfered by field uncertain factors, and the cutter suction ship is easy to run in an overload state.
In order to ensure the service life of the five machine tool subsystem devices, the automatic control layer is used for controlling the automatic operation of the machine tools on one hand, and controlling the operation of the motor of the machine tools below a rated standard when the machine tools run in an overload mode on the other hand.
According to the lowering depth of the reamer and the bridge tension of a bridge tension sensor 14, which are fed back by a draft sensor 11, a rotary encoder 12 and a tide level remote-report instrument 13, the output of a processor automatically adjusts a bridge winch motor 1 through a frequency converter 15 by a PLC (programmable logic controller);
according to the traversing speed fed back by the GPS21, the laser radar 22 or the acceleration gyroscope 23 and the traversing tension fed back by the traversing tension sensor 24, the processor outputs a signal to automatically adjust the traversing winch motor 2 through the PLC by the frequency converter 25;
according to the step speed fed back by the frequency converter 31 and the step distance fed back by the pull rope encoder 32, the processor outputs and automatically adjusts the electric push rod motor 3 through the frequency converter 32 through a PLC;
according to the reamer rotating speed and the reamer pressure fed back by the frequency converter 41, the output of the processor automatically adjusts the reamer motor 4 through the frequency converter 41 through a PLC;
the processor output automatically adjusts the dredge pump motor 5 via the PLC through the frequency converter 51 according to the vacuum level measured by the pressure sensor 52.
In conclusion, when the bridge frame tension, the transverse movement tension, the reamer pressure and the vacuum degree exceed the allowable range, the rotation speeds of the winch motor 1, the transverse movement winch motor 2, the reamer motor 4 and the dredge pump motor 5 are automatically adjusted to the rated rotation speed by the PLC, so that the safety of the system is ensured.
Example 2
The full-intelligent cutter suction ship in the embodiment 1 is used as a carrier and is divided into three layers, wherein one layer is an intelligent optimization system (top layer), the other layer is an automatic control operation system (upper control), and the third layer is an acquisition system (bottom layer).
Figure BDA0002389367840000101
As shown in fig. 1. Various sensors collect construction state signals, transfer the construction state signals through the PLC, and then transmit and gather the construction state signals to the ship operation platform database. The platform also includes a neural net model and an optimizer. The processor can be a microcomputer, a control signal is obtained according to a control instruction output by the optimizer, the control signal is transmitted to the PLC through a TCP/IP network, and the PLC executes to each execution mechanism (various motor driving devices) according to the feedback control instruction.
First part boat carrier and mechanical part
As shown in fig. 2 and 3.
The five machine tool subsystems serve as a service execution mechanism and comprise a mechanical part and a driving part, wherein the driving part is driven by electricity (or a traditional cutter suction ship is transformed into the machine tool which is driven by electricity), and the related motors comprise a bridge winch motor 1, a transverse moving winch motor 2, a steel pile trolley push rod motor 3, a reamer head motor 4 and a dredge pump motor 5 which belong to a frame winch system, a transverse moving system, a trolley system, a reamer system and a dredge pump system respectively.
Except that the trolley is connected with the positioning steel pile through the electric push rod and the displacement adjustment of the advancing and retreating of the ship body is realized through the expansion of the electric push rod driven by the electric push rod motor 3 of the steel pile trolley. Except for the design, the mechanical parts of all other service execution mechanisms are not the innovative part of the invention, and the components, the installation positions and the connection relations of the mechanical parts and the mechanical parts are the prior art.
The arrangement and the constitution of each mechanical part in the figure are as follows:
the ship hull provides bearing capacity and provides main body buoyancy on the water surface.
The bridge is fixed at the middle front end of the ship body and used for carrying the reamer head, the mud pipe and the anchor mechanism. The raising or lowering is driven by a bridge motor 1.
The reamer head is positioned at the bow of the ship body and is arranged at the foremost end of the bridge, and the reamer head penetrates into the water and rotates under the driving of the reamer motor 4, so that the function of cutting soil and gravel is realized.
And the mud pipe is positioned at the foremost end of the bridge frame, transports the mud absorbed at the reamer head from the bow part to the stern part along the bridge frame, transmits the mud to the shore and is driven by a mud pump motor 5.
The temporary displacement adjusting mechanism consists of a trolley and a positioning steel pile and is positioned at the stern part of the ship body. The trolley is fixed on the ship body, the positioning steel pile is perpendicular to the ship body and fixed with the bottom of the ship body to play a role in fixing the ship body, and the trolley is connected with the positioning steel pile through the electric push rod and achieves displacement adjustment of advancing and retreating of the ship body through stretching of the electric push rod driven by the electric push rod motor 3 of the steel pile trolley.
The temporary displacement adjusting mechanism is also provided with a transverse moving winch which is driven by a transverse moving winch motor 2, takes the positioning steel pile as the center of a circle, is connected to the anchor through a steel wire rope, releases/tightens the steel wire rope to realize the sector movement of the ship body towards the left or the right, and adjusts the angle of the ship head.
The anchor mechanism comprises an anchor, an anchor throwing rod, an anchor rod winch and an anchor winch: the anchor is located at the front ends of the port and the starboard of the ship body, the anchor is connected with the anchor throwing rods through steel wire ropes, the position of the ship body is determined through the anchor throwing rods, and after the anchor is anchored into water, the anchor is in contact with a mud surface to play a role in fixing the ship body. The anchor rod winches are suitable for two anchor rod throwing machines, are also positioned at the front ends of the port and the starboard of the ship body, and play a role in pulling back/releasing the respective anchor rod throwing machines through steel wire ropes; and two anchor lifting winches are also provided, and the two anchor lifting winches retract/release the steel wire rope and play a role in lifting/releasing the anchors on the left side and the right side.
And a steel wire rope is arranged between the bridge winch and the bridge and used for adjusting the lifting of the bridge to control the lowering or lifting of the reamer head and start preparation work or finish departure.
Second part boat carrier and sensor
As shown in fig. 4.
The sensing system comprises a bridge frame sensing system, a transverse moving sensing system, a trolley sensing system, a reamer sensing system, a dredge pump sensing system and a yield measurement sensing system, wherein:
the bridge frame sensing system comprises a draught sensor 11, a rotary encoder 12, a tide level remote-report instrument 13 and a frequency converter 15; the draft sensors 11 are distributed around the cutter suction dredger and used for measuring the draft of the dredger body, the rotary encoders 12 are located on the left side and the right side of the front portion of the dredger body and used for measuring the landing state of the transverse moving anchor and the angle of the anchor throwing rod, and the tide level remote-reporting instrument 13 is used for measuring the tide level; the draft sensor 11, the tide level remote-reporting instrument 13 and the rotary encoder 12 jointly calculate the bridge frame lowering depth HDepth of penetration＝aDraught of ship body+sin(bBridge frame angle)×cBridge frame length-dTidal level. The frequency converter 15 is used to obtain the bridge winch speed (control quantity).
The transverse moving sensing system comprises a GPS21, a laser radar 22, an acceleration gyroscope 23, a transverse moving tension sensor 24 and a frequency converter 25. The laser radars 22 are installed at the front left, rear left, front right, and rear right of the hull for indoor positioning of the ship. And the acceleration gyroscope 23 is used for acquiring the transverse movement acceleration of the ship body.
The trolley sensing system comprises a frequency converter 31 and a pull rope encoder 32; the frequency converter 31 is used for obtaining the traveling speed of the trolley, and the pull rope encoder 32 is used for acquiring the travel of the trolley.
The reamer sensing system comprises a frequency converter 41 for obtaining the reamer speed and pressure.
The dredge pump sensing system comprises a frequency converter 51 and a pressure sensor 52; the pressure sensors 52 are used for measuring the vacuum degree and the discharge pressure in the mud pipe and are uniformly distributed along the conveying pipeline at the rear part of the mud pump.
The production measurement sensing system includes a flow meter 61 and a densitometer 62. The flowmeter 61 is used for measuring the flow rate of the slurry in the sludge discharge pipe and is arranged on a vertical pipeline where a sludge pump discharge port is positioned; and the densimeter 62 is used for measuring the density of the slurry in the sludge discharge pipe and is arranged on a horizontal pipeline at the rear part of the discharge port of the sludge pump.
Description of the individual sensors:
Figure BDA0002389367840000121
Figure BDA0002389367840000131
Figure BDA0002389367840000141
and annotating: the frequency converter can convert the pressure of the reamer according to the torque, and is equivalent to a pressure sensor in function.
Third part ship carrier and automatic control operation system
According to a drawing provided by a dredging project owner, a construction drawing specifies a horizontal plane for intelligently controlling the operation of the cutter suction dredger, namely an excavation width W, through a left working line, a middle working line and a right working line; the depth of the intelligent control ship operation, namely the excavation depth D, is specified through a water depth map; the width, the depth and the working line form an excavation three-dimensional area, namely a working area, for intelligently controlling the operation of the cutter suction dredger. The intelligent control cutter suction ship moves to an operation area under the dragging of a tugboat (if the tugboat has a navigation function, the intelligent control cutter suction ship can also move automatically), a lifting auxiliary pile leaves a mud surface, a main positioning pile is placed in a middle working line, a mud discharging pipe opening of a stern is connected with an overwater pipe, and a left transverse moving anchor and a right transverse moving anchor are assisted by a tugboat or an anchor boatThe ship is fixed by putting into the soil, the ship head is close to a working line at one side (left or right) under the assistance of a tugboat, five machine and tool subsystem equipment are checked, and the operation is finishedPreparatory work before work。
Starting an intelligent control operation system, sequentially completing operation algorithms (as shown in fig. 5 and 6), taking a trolley period as an example, and comprising the steps of ' automatically lowering to a specified depth ', ' automatically starting and adjusting a dredge pump ', ' automatically starting and adjusting a reamer ', ' automatically laterally moving and ' automatically stepping ', and specifically:
starting a bridge winch motor 1, and lowering the bridge to the depth determined by the given parameters of the optimizer, namely the depth of the reamer head capable of entering the soil;
in the process of lowering the bridge, once the depth of the bridge calculated by integrating the draft sensor 11, the rotary encoder 12 and the tide level remote-reporting instrument 13 senses that a mud conveying pipeline suction port on the inner side of a reamer head at the front end of the bridge is submerged into water, the mud pump motor 5 is started immediately, the mud pump sucks in clean water, and the mud conveying pipeline is filled with the clean water; in the process of lowering the bridge, once the rotary encoder 12 senses that the reamer head positioned at the front end of the bridge is submerged in water, the reamer motor 4 is started, the reamer head rotates to cut and break soil, the mud pump sucks mud, and the mud pump is filled with a mud conveying pipeline; the bridge frame lowering depth is calculated by a draft sensor, a tide level remote-report instrument and a rotary encoder together; hDepth of penetration＝aDraught of ship body+sin(bBridge frame angle)×cBridge frame length-dTidal level；
Then, starting the traverse winch motor 3, moving to one side of the traverse direction by tightening one side of the traverse anchor cable which is connected with the anchor and is in the same advancing direction until the GPS21 or the laser radar 22 detects a traverse sideline, and passively releasing the other side of the traverse anchor cable which is connected with the anchor and is opposite to the advancing direction in the moving process;
after the trolley is moved transversely and stopped at the same time, the electric push rod motor 3 of the steel pile trolley is started to push the ship body to move forwards to the advancing distance determined by the intelligent control program, namely the stepping distance L, then the transverse movement winch motor 2 is started to move continuously on one side, and the process is repeated in a circulating mode until the stay cord encoder 32 detects that the trolley reaches the maximum displacement, so that the production process period of the trolley is finished.
The transverse movement is always kept at the excavation depth D to adapt to the change of the bridge depth along with the influence of the tide level, so that the transverse movement can be completed at a certain depth in one trolley periodTransverse (dredging) work。
Repeating the trolley stepping, advancing the process and repeating the cycle.
If the single excavation depth does not meet the depth requirement of the owner, returning the trolley to the initial position of the trolley after the trolley reaches the end position of the trolley, lowering the bridge frame, and repeating the dredging operation described above until the end position of the trolley; therefore, the bridge is lowered and the mud is dug, and the bridge is continuously close to the depth required by the owner.
After the platform intelligent optimization system obtains excellent control parameters, the operation algorithm executed by the automatic control system is as follows:
Figure BDA0002389367840000151
Figure BDA0002389367840000161
the operation algorithm of the automatic control system also comprises a safety guarantee algorithm, and the following is introduced:
the cutter suction ship is interfered by field uncertain factors, and the cutter suction ship is easy to run in an overload state. In order to ensure the service life of the equipment, the automatic control layer controls the automatic operation of the equipment on one hand, and controls the operation of the motor of the equipment below a rated standard when the overload operation of the equipment is processed on the other hand.
According to the bridge frame soil penetration depth fed back by the draft sensor 11, the rotary encoder 12 and the tide level remote-report instrument 13 and the bridge frame tension of the bridge frame tension sensor 14, combining the optimized control parameter output of the platform, and instructing a PLC (programmable logic controller) to automatically adjust a bridge frame winch motor 1 through a frequency converter 15 by a processor;
according to the traversing speed fed back by the GPS21, the laser radar 22 or the acceleration gyroscope 23 and the traversing tension fed back by the traversing tension sensor 24, the optimized control parameter output of the platform is combined, and the processor instructs the PLC to automatically adjust the traversing winch motor 2 through the frequency converter 25;
according to the stepping speed fed back by the frequency converter 31 and the stepping distance fed back by the pull rope encoder 32, the processor instructs the PLC to automatically adjust the electric push rod motor 3 through the frequency converter 32 by combining the optimized control parameter output of the platform;
according to the reamer rotating speed and the reamer pressure fed back by the frequency converter 41, the optimized control parameter output of the platform is combined, and the processor instructs the PLC to automatically adjust the reamer motor 4 through the frequency converter 41;
according to the vacuum degree measured by the pressure sensor 52, the processor instructs the PLC to automatically adjust the dredge pump motor 5 through the frequency converter 51 in combination with the optimized control parameter output of the platform.
If the optimized control parameters of the platform cause the bridge tension, the cross sliding tension, the reamer pressure and the vacuum degree to exceed the above-mentioned valuesAllowable rangeThe PLC automatically adjusts the rotating speeds of the winch motor 1, the transverse winch motor 2, the reamer motor 4 and the dredge pump motor 5 to the rated rotating speed so as to ensure the safety of the system.
Fourth-part ship carrier and operation platform
The analysis process comprises the following steps:
the yield of the cutter suction dredger is influenced by a plurality of factors, even if the influence of other environmental factors such as wind, wave and flow on a construction site is not considered, only more than 17 key parameters and more than 1500 signal points exist behind 5 control input variables such as the rotating speed of a dredge pump, the stroke (stepping distance) of a trolley, the earth penetration depth of a reamer, the transverse moving speed and the rotating speed of the reamer, the interaction mechanism among the factors is complex, and the control system of the cutter suction dredger is a multi-parameter and nonlinear system. As shown in fig. 7.
Instantaneous yield W (m) of cutter suction dredger3H) depends on the flow rate Q (m)3H) and mud mixture concentration C (%), the expression generally being:
W＝QC＝(πr2v)C (1)
wherein: r is the radius of the mud discharging pipe, v is the mud flow rate (the rotating speed pump _ s of the mud pump), and because the pressure sensor 52 is arranged at the mud pump inlet, the densimeter 61 and the flowmeter 62 are arranged on the mud pump pipeline at a long distance, and a certain time interval exists between the collected data, the formula (1) has a large time lag problem in the calculation of the yield in the mud conveying pipeline, and the real-time yield calculation cannot be accurately completed.
In the ground breaking and cutting process of the reamer, the volume of soil cut by the reamer is changed along with the change of the cutting surface and the transverse moving speed of the reamer: vc＝bc×dc×vs(2)
Wherein: vcVolume of the cutting sand per unit time, bcFor the reamer cutting width (step distance step _ dis, reamer depth ladder _ dep), dcReamer cutting depth (step distance step _ dis, reamer depth ladder _ dep), vsAnd (4) traversing speed swing _ s.
After the silt is cut, the silt and water form a mud mixture along with the rotation of the reamer, and the crushing degree of the silt cut by the reamer is related to the silt thickness in unit time and the current soil quality. ddThe expression for the cut thickness is as follows:
Figure BDA0002389367840000181
wherein: zcNumber of arms of reamer, ncIs the reamer speed cutter _ s.
The volume concentration expression of the slurry in the pipeline is as follows:
Figure BDA0002389367840000182
wherein: vmVolume of silt entering the pipe per unit time, DpipeAnd v is the mud flow rate (mud pump speed pump _ s) for the inner diameter of the mud delivery pipe.
Under normal dredging conditions, VmAnd the volume of the silt cut by the reamer in unit time is converted into V according to the formula (5)m＝KVc(5)
K is the digging coefficient of reamer and can be 0.8-0.9.
According to the formulas (2), (3) and (4), the reamer rotating speed cutter _ s, the traversing speed swing _ s, the trolley stepping distance step _ dis, the bridge lowering depth ladder _ dep and the mud pump rotating speed pump _ s have influence on the mud concentration ins _ pro in the process of forming mud in the pipeline. In the actual construction process, as the field operation environment is variable, the underwater environment is complex, a plurality of experience coefficients are not available, and the relation between the control parameters and the output quantity under the actual operation is not clear. The calculation experience and experimental test results of construction sites for many years show that the linear physical model of the cutter suction dredger about the cutter cutting system and the pipeline conveying system cannot meet the requirements of estimating and predicting the yield in actual construction production, and cannot be applied to a multi-input single-output nonlinear model such as a yield control system.
The invention creates ideas, namely: the relation between the output of the cutter suction dredger and key control factors influencing the cutter suction dredger is regarded as a black box problem, a model is established on line by means of a neural network algorithm, and an operator can be assisted to find a better construction method by means of technical means such as an intelligent control algorithm, data mining and the like.
The method adopts a data driving method, takes the five controllable operation variables and the instantaneous yield of the cutter suction dredger as the problem of black boxes, and utilizes a data driving method and an RBF neural network to establish a cutter suction dredger yield model and carry out yield prediction optimization.
In the new generation of cutter suction dredger integrated automatic control operation system in the embodiment 1, the on-site sensor system collects the state data of the excavation process and the slurry conveying process of the cutter suction dredger through the communication system to establish a 'data center' of a cutter suction dredger platform.Transverse (dredging) workThe method can generate the dredging yield and is a core point of an intelligent optimization system; the preparation work before the operation, the pile replacement operation and the anchor moving operation are all without dredging yield, and the database sample of the invention deletes the information of the part.
According to the invention, the relation between the output of the cutter suction dredger and key control factors influencing the cutter suction dredger is regarded as a black box problem, a model is established on line by means of a neural network algorithm, and the yield is predicted and optimized by technical means such as an intelligent control algorithm and data mining, so that an operator can be assisted to find a better construction method.
As shown in fig. 8. The full-intelligent cutter suction ship operation platform comprises a database, a yield prediction model, an intelligent controller (short for optimizer) and a safety control range limiting module, wherein:
the database collects parameters collected by a sensor system in real time in the action process of the cutter suction dredger in the current sea area, wherein cutter _ s is the rotating speed of a reamer, ladder _ dep is the lowering depth of a bridge, pump _ s is the rotating speed of a mud pump, step _ dis is the stepping distance of a trolley push rod, swing _ s is the traversing speed, ins _ pro is the instant yield and the corresponding instant yield, and the parameters are used for accumulating process control training samples of the current operation area for a yield prediction model.
The yield prediction model is built by adopting an RBF neural network algorithm, the input nodes are five control variables, the output nodes are instantaneous yields, and the multi-input single-output RBF neural network structure of the yield prediction model is shown in FIG. 9:
in the RBF network structure, input and output vectors are respectively as follows:
X＝{cutter_s,ladeer_dep,pump_s,step_dis,swing_s}
Y＝{ins_pro}
wherein: cutter _ s is the rotation speed of the reamer; ladder _ dep is the lowering depth of the bridge; pump _ s is the rotational speed of the dredge pump; step _ dis is the trolley push rod stepping distance; swing _ s is the traversing speed; ins _ pro is the instantaneous yield.
RBF network evaluation index, i.e. decision coefficient R, of the yield prediction model2The expression is as follows
Figure BDA0002389367840000191
R2Value between 0 and 1, R2The larger (close to 1) the better the regression equation fitted.
SST (sum of squares):
Figure BDA0002389367840000192
SSR (regression sum of squares)
Figure BDA0002389367840000193
SSR (residual sum of squares)
Figure BDA0002389367840000194
e is a natural constant;
wherein: y is the value to be fitted, the mean value of which is
Figure BDA0002389367840000201
The fitting value is
Figure BDA0002389367840000202
∑iyi＝y1+y2+ … yi。
Obtaining a certain initial X of the trained yield prediction model pair inputkPerforming on-line solution and outputting an analog control variable sequence X within a period of time (K + ns time)K+nsWith corresponding sequences of predicted yield values YK+nsSequence X to be obtainedK+ns、YK+nsIs provided to an optimizer.
The initial X to be input into the yield prediction modelkThe precondition satisfies the monitoring of the safety control range limiting module.
The optimizer is used for setting a target yield value YPeriod of timeThe optimizer comprises an objective function and an optimizing module, wherein the objective function J is YPreparation of-YPeriod of timeFor setting an error range, the optimizing module outputs a sequence [ X ] after the yield prediction model is solved on linek+1sXk+2s… Xk+(n-1)sXK+ns；Yk+1sYk+2s… Yk+(n-1)sYK+ns]Screening out the predicted yield value YPreparation ofAnd the expected yield value YPeriod of timeThe sequence with the minimum error is found out and the control parameter X corresponding to the optimal output value is found outSuperior food. Wherein, the control variable X under each time sequence consists of five control parameters,for example Xk+1sIs (x)1 k+1sx2 k+1sx3 k+1sx4 k+1sx5 k+1s) Namely, the five control variables are respectively corresponded: cutter _ s is the rotation speed of the reamer; ladder _ dep is the lowering depth of the bridge; pump _ s is the rotational speed of the dredge pump; step _ dis is the trolley push rod stepping distance; swing _ s is the traversing speed; ins _ pro is the instantaneous yield.
The full-intelligent cutter-suction ship operation platform outputs the control parameter X to the automatic control system through the optimizerSuperior food。
As shown in fig. 8. The intelligent optimization system of the cutter suction ship operation platform obtains the optimal control variable for providing the automatic control operation system with the optimal operation control method, and the process comprises the following steps:
step 1, building a prediction model of five control factors and one yield by using a neural network algorithm, and providing the prediction model for a step 3 optimization algorithm
In the prediction model neural network structure (for example, using an RBF neural network), input and output vectors are respectively:
X＝{cutter_s,ladder_dep,pump_s,step_dis,swing_s}
Y＝{ins_pro}
wherein: cutter _ s is the rotation speed of the reamer; ladder _ dep is the lowering depth of the bridge; pump _ s is the rotational speed of the dredge pump; step _ dis is the step distance; swing _ s is the traversing speed; ins _ pro is the instantaneous yield.
Step 2, the cutter suction dredger enters a new operation area, a database collects and records the dredging construction process, an updated yield prediction model is obtained through training, and meanwhile, a yield expected value Y is given to the optimizerPeriod of time：
Step 3 safety control range limitation
If and only if the current K moment X of the cutter suction dredgerKIf the corresponding transverse winch pulling force, transverse winch speed, reamer torque, pump power and pump rotating speed under the dredger information are in the safe operation range, the transverse winch pulling force, the transverse winch speed, the reamer torque, the pump power and the pump rotating speed are provided for the optimization algorithm in the step 4 to carry out optimization;
and 4, entering an optimization algorithm process by using the yield prediction model trained in the step 2 and the construction yield expected value set by the optimizer:
step 4.1 obtaining optimized initial values
Obtaining information X of the dredger at the current K moment according to the ship bodyK: the traversing speed, the rotating speed of the reamer, the lowering depth of the bridge, the rotating speed of the mud pump, the stepping distance and the yield value are provided for the yield prediction model after training and updating in the step 2;
step 4.2 yield prediction model is solved on line and output a simulation control variable sequence X in a period of time (K + ns moment)K+nsWith corresponding sequences of predicted yield values YK+nsThe sequence [ X ]k+1sXk+2s… Xk+(n-1)sXK+ns；Yk+1sYk+2s…Yk+(n-1)sYK+ns]Sequence X to be obtainedK+ns、YK+nsI.e. the sequence [ Xk+1sXk+2s… Xk+(n-1)sXK+ns；Yk+1sYk+2s…Yk+(n-1)sYK+ns]Providing to step 4.3;
step 4.3 sequence [ X ] from step 4.2k+1sXk+2s… Xk+(n-1)sXK+ns；Yk+1sYk+2s…Yk+(n-1)sYK+ns]Optimizing; find the predicted yield value YPreparation ofAnd the expected yield value YPeriod of timeThe sequence with the minimum error is found out, and the control parameter sequence X corresponding to the optimal yield value at the moment is found outSuperior foodSupplied to step 5;
step 5 control output
Automated control of various actuator subsystems of an operating system to optimize a sequence of control parameters (X)Superior foodYPreparation of) Controlling a dredging process and executing an optimal dredging action;
step 6, iterative optimization and real-time optimal control
And the optimization steps are used for optimizing the control parameters in an online repeated iteration mode, so that the actual yield of the cutter suction dredger is stably close to the expected yield value, and the optimal yield value is finally obtained.
The above description is only illustrative of the preferred embodiments of the present application and is not intended to limit the scope of the present application in any way. Any changes or modifications made by those skilled in the art based on the above disclosure should be considered as equivalent effective embodiments, and all the changes or modifications should fall within the protection scope of the technical solution of the present application.

Claims (3)

1. A full-intelligent cutter suction dredger is characterized in that based on embodiment 1, a traditional cutter suction dredger is transformed electrically and informationized or a newly-built cutter suction dredger is transformed to form a top-down control system and a bottom-up information acquisition system; meanwhile, acquiring electrical operation state data and yield data in a service process through an acquisition system to form a sample database; constructing a neural network online prediction model, and designing five control variable inputs and one output as a mathematical model of the neural network; the mathematical model is updated after the neural network is trained by using the sample, when the hull control variable at the current moment is input, the output prediction yield value is solved on line through the neural network, the optimal control parameter is output by adopting an optimizer optimization algorithm, the optimal process control parameter in an ideal state is continuously approached after iteration, the intelligent operation is realized, and the optimal yield value is kept.
2. The fully intelligent cutter suction dredger of claim 1, comprising a cutter suction dredger, an automatic control operation system, a data acquisition system and an intelligent optimization system; the intelligent optimization system provides the optimized control quantity to the automatic control operation system to realize the optimal yield of the ship body; the automatic control operation system coordinately controls five machine tool subsystems, wherein the five machine tool subsystems comprise a frame winch system, a transverse moving system, a trolley system, a dredge pump system and a reamer system; the data acquisition system collects a real-time database and samples for the intelligent optimization system and feeds back the real-time database and samples for the automatic control operation system in real time.
The intelligent optimization system comprises a database, a yield prediction model, an optimizer and a safety control range limiting module, wherein:
the database collects parameters collected by a sensor system in real time in the action process of the cutter suction dredger in the current sea area, wherein cutter _ s is the rotating speed of a reamer, ladder _ dep is the lowering depth of a bridge, pump _ s is the rotating speed of a mud pump, step _ dis is the stepping distance of a trolley push rod, swing _ s is the traversing speed, ins _ pro is the instant yield and the corresponding instant yield, and the parameters are used for accumulating process control training samples of the current operation area for a yield prediction model.
The yield prediction model is built by adopting an RBF neural network algorithm, the input nodes are five control variables, the output nodes are instantaneous yields, and the multi-input single-output RBF neural network structure of the yield prediction model is shown in FIG. 9:
in the RBF network structure, input and output vectors are respectively as follows:
X＝{cutter_s,ladder_dep,pump_s,step_dis,swing_s}
Y＝{ins_pro}
wherein: cutter _ s is the rotation speed of the reamer; ladder _ dep is the lowering depth of the bridge; pump _ s is the rotational speed of the dredge pump; step _ dis is the trolley push rod stepping distance; swing _ s is the traversing speed; ins _ pro is the instantaneous yield.
RBF network evaluation index, i.e. decision coefficient R, of the yield prediction model2The expression is as follows
Figure FDA0002389367830000021
R2Value between 0 and 1, R2The larger (close to 1) the better the regression equation fitted.
SST (sum of squares):
Figure FDA0002389367830000022
SSR (regression sum of squares)
Figure FDA0002389367830000023
SSR (residual sum of squares)
Figure FDA0002389367830000024
e is a natural constant;
wherein: y is the value to be fitted, the mean value of which is
Figure FDA0002389367830000025
The fitting value is
Figure FDA0002389367830000026
∑iyi＝y1+y2+…yi。
Obtaining a certain initial X of the trained yield prediction model pair inputkPerforming on-line solution and outputting an analog control variable sequence X within a period of time (K + ns time)K+nsWith corresponding sequences of predicted yield values YK+nsSequence X to be obtainedK+ns、YK+nsIs provided to an optimizer.
The initial X to be input into the yield prediction modelkThe precondition satisfies the monitoring of the safety control range limiting module.
The optimizer is used for setting a target yield value YPeriod of timeThe optimizer comprises an objective function and an optimizing module, wherein the objective function J is YPreparation of-YPeriod of timeFor setting an error range, the optimizing module outputs a sequence [ X ] after the yield prediction model is solved on linek+1sXk+2s… Xk+(n-1)sXK+ns；Yk+1sYk+2s… Yk+(n-1)sYK+ns]Screening out the predicted yield value YPreparation ofAnd the expected yield value YPeriod of timeThe sequence with the minimum error is found out and the control parameter X corresponding to the optimal output value is found outSuperior food。
The full-intelligent cutter-suction ship operation platform outputs the control parameter X to the automatic control system through the optimizerSuperior food。
3. The fully intelligent cutter suction dredger of claim 2, wherein the intelligent optimization system obtains optimal control variables for providing to the automatically controlled operation system an implementation method process for controlling operation in an optimal manner:
step 1, building a prediction model of five control factors and one yield by using a neural network algorithm, and providing the prediction model for a step 3 optimization algorithm
In the prediction model neural network structure (for example, using an RBF neural network), input and output vectors are respectively:
X＝{cutter_s,ladder_dep,pump_s,step_dis,swing_s}
Y＝{ins_pro}
wherein: cutter _ s is the rotation speed of the reamer; ladder _ dep is the lowering depth of the bridge; pump _ s is the rotational speed of the dredge pump; step _ dis is the step distance; swing _ s is the traversing speed; ins _ pro is the instantaneous yield.
Step 2, the cutter suction dredger enters a new operation area, a database collects and records the dredging construction process, an updated yield prediction model is obtained through training, and meanwhile, a yield expected value Y is given to the optimizerPeriod of time：
Step 3 safety control range limitation
If and only if the current K moment X of the cutter suction dredgerKIf the corresponding transverse winch pulling force, transverse winch speed, reamer torque, pump power and pump rotating speed under the dredger information are in the safe operation range, the transverse winch pulling force, the transverse winch speed, the reamer torque, the pump power and the pump rotating speed are provided for the optimization algorithm in the step 4 to carry out optimization;
and 4, entering an optimization algorithm process by using the yield prediction model trained in the step 2 and the construction yield expected value set by the optimizer:
step 4.1 obtaining optimized initial values
Obtaining information X of the dredger at the current K moment according to the ship bodyK: the traversing speed, the rotating speed of the reamer, the lowering depth of the bridge, the rotating speed of the mud pump, the stepping distance and the yield value are provided for the yield prediction model after training and updating in the step 2;
step 4.2 yield prediction model is solved on line and output a simulation control variable sequence X in a period of time (K + ns moment)K+nsWith corresponding sequences of predicted yield values YK+nsSequence X to be obtainedK+ns、YK+nsProviding to step 4.3;
step 4.3 performs optimization from the series of sequences of step 4.2; find the predicted yield value YPreparation ofAnd the expected yield value YPeriod of timeThe sequence with the smallest error and finding the control corresponding to the best yield value at that momentParameter sequence XSuperior foodSupplied to step 5;
step 5 control output
Automated control of various actuator subsystems of an operating system to optimize a sequence of control parameters (X)Superior foodYPreparation of) Controlling a dredging process and executing an optimal dredging action;
step 6, iterative optimization and real-time optimal control
And the optimization steps are used for optimizing the control parameters in an online repeated iteration mode, so that the actual yield of the cutter suction dredger is stably close to the expected yield value, and the optimal yield value is finally obtained.
CN202010109232.6A 2020-02-21 2020-02-21 Full-intelligent cutter suction dredger Pending CN111335388A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010109232.6A CN111335388A (en) 2020-02-21 2020-02-21 Full-intelligent cutter suction dredger

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010109232.6A CN111335388A (en) 2020-02-21 2020-02-21 Full-intelligent cutter suction dredger

Publications (1)

Publication Number Publication Date
CN111335388A true CN111335388A (en) 2020-06-26

Family

ID=71177823

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010109232.6A Pending CN111335388A (en) 2020-02-21 2020-02-21 Full-intelligent cutter suction dredger

Country Status (1)

Country Link
CN (1) CN111335388A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113668450A (en) * 2021-10-25 2021-11-19 交通运输部天津水运工程科学研究所 Centrifugal model test device for simulating channel dredging and simulation method thereof
CN114418248A (en) * 2022-03-31 2022-04-29 武汉理工大学 Cutter suction dredger automatic point selection construction method and system based on global optimal idea

Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101021878A (en) * 2006-02-14 2007-08-22 中国交通建设集团有限公司 Automatic computerized selecting optimized dredging method for cutter suction dredger
CN201932865U (en) * 2011-03-16 2011-08-17 徐州苏煤矿山设备制造有限公司 System for supervising haulage winch tension
CN201952829U (en) * 2011-01-28 2011-08-31 中国交通建设股份有限公司 Positioning and traveling device with double steel piles and double trolleys for suction dredger
CN104573869A (en) * 2015-01-16 2015-04-29 河海大学常州校区 Optimization method and system for achieving dredging operations based on BP neural network and NSGA-II
CN104573819A (en) * 2015-01-26 2015-04-29 河海大学常州校区 Evolution model method and system utilizing EKF algorithm to perform dynamic dredge operation
CN105045091A (en) * 2015-07-14 2015-11-11 河海大学常州校区 Dredging process intelligent decision analysis method based on fuzzy neural control system
CN105512383A (en) * 2015-12-03 2016-04-20 河海大学常州校区 Dredging process regulation and control parameter screening method based on BP neural network
CN106836341A (en) * 2017-02-23 2017-06-13 中交烟台环保疏浚有限公司 The control system and control method of intelligent cutter suction dredger
GB2562122A (en) * 2017-05-05 2018-11-07 Bamford Excavators Ltd Training machine
CN109750702A (en) * 2019-03-12 2019-05-14 中交天津航道局有限公司 A kind of cutter suction dredger economic flow rate is dredged control method automatically
CN109750713A (en) * 2019-03-12 2019-05-14 中交天津航道局有限公司 A kind of cutter suction dredger piling bar trolley automatic controller
CN110045614A (en) * 2019-05-16 2019-07-23 河海大学常州校区 A kind of traversing process automatic learning control system of strand suction ship and method based on deep learning
CN110593332A (en) * 2019-08-16 2019-12-20 中交疏浚技术装备国家工程研究中心有限公司 Full-automatic control system and method for dredging of cutter suction dredger

Patent Citations (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101021878A (en) * 2006-02-14 2007-08-22 中国交通建设集团有限公司 Automatic computerized selecting optimized dredging method for cutter suction dredger
CN201952829U (en) * 2011-01-28 2011-08-31 中国交通建设股份有限公司 Positioning and traveling device with double steel piles and double trolleys for suction dredger
CN201932865U (en) * 2011-03-16 2011-08-17 徐州苏煤矿山设备制造有限公司 System for supervising haulage winch tension
CN104573869A (en) * 2015-01-16 2015-04-29 河海大学常州校区 Optimization method and system for achieving dredging operations based on BP neural network and NSGA-II
CN104573819A (en) * 2015-01-26 2015-04-29 河海大学常州校区 Evolution model method and system utilizing EKF algorithm to perform dynamic dredge operation
CN105045091A (en) * 2015-07-14 2015-11-11 河海大学常州校区 Dredging process intelligent decision analysis method based on fuzzy neural control system
CN105512383A (en) * 2015-12-03 2016-04-20 河海大学常州校区 Dredging process regulation and control parameter screening method based on BP neural network
CN106836341A (en) * 2017-02-23 2017-06-13 中交烟台环保疏浚有限公司 The control system and control method of intelligent cutter suction dredger
GB2562122A (en) * 2017-05-05 2018-11-07 Bamford Excavators Ltd Training machine
CN109750702A (en) * 2019-03-12 2019-05-14 中交天津航道局有限公司 A kind of cutter suction dredger economic flow rate is dredged control method automatically
CN109750713A (en) * 2019-03-12 2019-05-14 中交天津航道局有限公司 A kind of cutter suction dredger piling bar trolley automatic controller
CN110045614A (en) * 2019-05-16 2019-07-23 河海大学常州校区 A kind of traversing process automatic learning control system of strand suction ship and method based on deep learning
CN110593332A (en) * 2019-08-16 2019-12-20 中交疏浚技术装备国家工程研究中心有限公司 Full-automatic control system and method for dredging of cutter suction dredger

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王柳艳，陈新华，王伟: "基于RBF神经网络的绞吸挖泥船施工产量预测研究及分析", 《中国港湾建设》 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113668450A (en) * 2021-10-25 2021-11-19 交通运输部天津水运工程科学研究所 Centrifugal model test device for simulating channel dredging and simulation method thereof
CN113668450B (en) * 2021-10-25 2022-02-11 交通运输部天津水运工程科学研究所 Centrifugal model test device for simulating channel dredging and simulation method thereof
CN114418248A (en) * 2022-03-31 2022-04-29 武汉理工大学 Cutter suction dredger automatic point selection construction method and system based on global optimal idea

Similar Documents

Publication Publication Date Title
CN111305301A (en) Full-automatic control dredging cutter suction dredger
US20190204287A1 (en) Intelligent device for integrated sampling of layered water and sediment core of deep reservoir
CN111335388A (en) Full-intelligent cutter suction dredger
CN106836341A (en) The control system and control method of intelligent cutter suction dredger
CN102041824A (en) Automatic control system and control method of working device of excavator
CN110453709A (en) A kind of offshore wind farm large-diameter pile process for sinking
CN110826790A (en) Intelligent prediction method for construction productivity of cutter suction dredger
CN111271071A (en) Shield tunneling machine attitude control method based on fuzzy adaptive neural network
CN109750701A (en) A kind of cutter suction dredger maximum production is dredged control method automatically
CN114661006A (en) Optimized control system and method for cabin pumping and bank blowing process of trailing suction hopper dredger
CN109944287A (en) Dredging operation system below harbour
CN109750707A (en) A kind of cutter suction dredger target output is dredged control method automatically
AU2014321147B2 (en) Method for manoeuvring a vessel
CN110847272B (en) Intelligent dredging control method for cutter suction dredger
CN109208686B (en) Dredging and measuring integrated water depth measuring system for self-propelled trailing suction dredger
CN109750697A (en) A kind of automatically dredge control method of the cutter suction dredger based on yield
CN115434687A (en) Intelligent adjusting system based on pile driving
CN109750703A (en) A kind of more drilling depths of cutter suction dredger multilayer are dredged control method automatically
CN115030258A (en) Automatic loading method for remotely operating electric shovel
CN109750702A (en) A kind of cutter suction dredger economic flow rate is dredged control method automatically
Chernyi The problems of automation technological process of drilling oil and gas wells
Wei et al. A computational model for devising an intelligent densitometer for cutter suction dredgers
CN115653032B (en) Intelligent control method for overcoming hob applied to cutter suction dredger
CN109750700A (en) A kind of cutter suction dredger gantry lifting automatic controller
Lu et al. Research on Intelligent Control Method of Cutter Suction Dredger Based on Reinforcement Learning

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination