CN109548762A - A kind of bionical fishing device and its control method - Google Patents
A kind of bionical fishing device and its control method Download PDFInfo
- Publication number
- CN109548762A CN109548762A CN201910043907.9A CN201910043907A CN109548762A CN 109548762 A CN109548762 A CN 109548762A CN 201910043907 A CN201910043907 A CN 201910043907A CN 109548762 A CN109548762 A CN 109548762A
- Authority
- CN
- China
- Prior art keywords
- fishing device
- fishing
- device ontology
- bionical
- fish
- 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.)
- Granted
Links
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; CARE OF BIRDS, FISHES, INSECTS; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K79/00—Methods or means of catching fish in bulk not provided for in groups A01K69/00 - A01K77/00, e.g. fish pumps; Detection of fish; Whale fishery
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B63—SHIPS OR OTHER WATERBORNE VESSELS; RELATED EQUIPMENT
- B63C—LAUNCHING, HAULING-OUT, OR DRY-DOCKING OF VESSELS; LIFE-SAVING IN WATER; EQUIPMENT FOR DWELLING OR WORKING UNDER WATER; MEANS FOR SALVAGING OR SEARCHING FOR UNDERWATER OBJECTS
- B63C11/00—Equipment for dwelling or working underwater; Means for searching for underwater objects
- B63C11/52—Tools specially adapted for working underwater, not otherwise provided for
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Environmental Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Ocean & Marine Engineering (AREA)
- Mechanical Engineering (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
Abstract
The present invention discloses a kind of bionical fishing device, comprising: fishing device ontology comprising: storage compartment is arranged in the intrinsic lower part of the fishing device；Cabin is gone up and down, is arranged in the fishing device ontology above the storage compartment；Multiple walking limbs based on artificial-muscle are separately positioned on the quadrangle of the fishing device ontology, walking and shoal of fish fishing for fishing device ontology comprising: the walking limb axle center is run through, and one end is connected to the storage compartment in fishing channel；Multiple sector cylindrical cavities separate on the walking limb that the fishing channel circumferential direction is arranged in, and the closed setting in one end far from the fishing device ontology；Multiple highly pressurised liquid pipes are separately positioned in the fan-shaped cylindrical cavity, and are connected to the fan-shaped cylindrical cavity one-to-one correspondence, for controlling the pressure of the fan-shaped cylindrical cavity.The present invention also provides a kind of control methods of bionical fishing device, realize the efficient fishing of the shoal of fish.
Description
Technical field
The present invention relates to bio-robot technical fields, more particularly, the present invention relates to a kind of bionical fishing device and its
Control method.
Background technique
Abyssopelagic organism fishing, i.e., abyssopelagic organism is caught, biology from deep-sea capture water outlet progress scientific research or
Other commercial uses of person.A kind of trawlnet capture technique is generallyd use at present, it is a kind of towed fishing using ship's navigation
Mode.Otter-trawl is a kind of for carrying out capture technique to small-sized biologicals such as abyssal benthos.This otter-trawl technology is to life
State system causes catastrophic injury, therefore coral, sponge, fish and other animals will all be catched and killed.Numerous oceans simultaneously
The underwater ecosystem such as habitat-seamount of biology is also by serious destruction.This fishing style is to marine ecosystems
Cause irreparable damage.Since trawlnet technology is difficult targetedly to capture biology, often result in regardless of blueness
Red black and white " slaughtering the innocent ", success rate is low and waste of resource.
Underwater robot applies to exploration of the mankind to deep-sea resources more and more in recent years.Wherein, to abyssopelagic organism
The exploration of resource is also a particularly important ring.The most intuitive advantage of bathyscaph be scientist can remotely manipulate and
Specific aim is high, will not damage to deep-marine-environment.But underwater robot is sufficiently expensive at present, applied to commercial use
Benthic organism hauls remain many problems.
Underwater robot is also known as unmanned remotely controlled submersible vehicle, and working method is to pass through company by the staff on surface mother ship
The umbilical cord for connecing submersible provides power, manipulation or control submersible, is observed using special equipments such as underwater television, sonars,
And underwater operation is carried out by manipulator.In abyssopelagic organism capture, underwater robot is put into the biology of capture using manipulator
The water surface is taken in collecting chamber.Wherein underwater television system is a kind of observation device of most development potentiality.As the U.S. 5 hereby
The institute of oceanography Hall (Woods Hole) develops the deep diving underwater robot of one entitled " castaway of global most stick ", it
Equipped with high-definition camera, can in the underwater operation as deep as 3000 meters, scientist can remote-controlled operation, by what is arrested in water
Biology is stored in the collecting chamber of robot.But it is currently used in acquired in the underwater television system in underwater robot
Image is still plane visual information, can not obtain the depth information of captured object；And visual range is extremely limited.It is this
The manufacturing cost of underwater robot is extremely expensive.
It being caught for some small-sized abyssopelagic organisms, researcher has developed a kind of " ocean grab bucket " as bivalve shell,
Energy quick-make when striking seabed, will be in sample all " grabbing " to bucket.In addition, researcher have also been devised box corer,
They are vertically transferred to seabed by gravity corer and piston sampler etc., are rapidly fully taken sample using special device
Come up, thus deposit can successively be studied.This fishing style operating efficiency is low, and manufacturing cost is high.
The mode that many animals of nature obtain food is designed to us brings some enlightenments, i.e., bionical benthic organism hauls
Mechanical hand design, if the nose of elephant can easily take the fruit on tree, can uproop the grass on ground, energy
Draw the water in pond has one piece of special cartilage, plays " valve " equally behind the nasal cavity of elephant above esophagus.As inhaling
When water, the contraction of muscle at throat position, " valve " is closed, and water can smoothly enter into esophagus, and the nose of elephant is clever as manpower
It is living.Studies have shown that big trunk is nearly 40,000 pieces flexible small muscle compositions, it can pole it is neatly capable of expansion and contraction, make spirit
Ingeniously act.In the design of bionical benthic organism hauls mechanical hand, the pipe design on mechanical hand will be caught into the nose of such as elephant
Son will catch the process for the nasal cavity sucking fished species that process simulation is elephant.Some benthons use mouth when capturing food
The suction in portion takes captured object to gulp down, and has the function similar with the nose of elephant.
Summary of the invention
It is an object of the invention to design and develop a kind of bionical fishing device, it is provided with the walking based on artificial-muscle
Limb, the pressure by controlling fan-shaped cylindrical cavity realize the bending of walking limb, and by injection principle that the shoal of fish is logical along fishing
Road sucks in holding bay, realizes efficiently fishing.
Another object of the present invention is to have designed and developed a kind of control method of bionical fishing device, by acquiring fishing device
Seawater pressure suffered by the direction of travel and fishing device ontology of panoramic picture, fishing device ontology around ontology, and be based on
BP neural network determines the walking states of the walking limb based on artificial-muscle and the adjustable height of fishing device ontology, determines wait fish
Group.
The present invention can also accurately control the displacement in lifting cabin, realize the precision lift of bionical fishing device.
The present invention passes through injection principle and controls the negative suction of the shoal of fish in fishing pipeline, and the shoal of fish is inhaled along fishing channel
Enter in holding bay, realizes efficiently fishing.
Technical solution provided by the invention are as follows:
A kind of bionical fishing device, comprising:
Fishing device ontology comprising:
Storage compartment, setting is in the intrinsic lower part of the fishing device, for storing the shoal of fish of fishing；
Cabin is gone up and down, is arranged in the fishing device ontology above the storage compartment, the lifting for fishing device ontology；
Multiple walking limbs based on artificial-muscle are separately positioned on the quadrangle of the fishing device ontology, are used for fishing device
The walking of ontology and shoal of fish fishing comprising:
Channel is fished, runs through the walking limb axle center, and one end is connected to the storage compartment；
Multiple sector cylindrical cavities separate on the walking limb that the fishing channel circumferential direction is arranged in, and both ends are close
Close setting；
Multiple highly pressurised liquid pipes, be separately positioned in the fan-shaped cylindrical cavity and with the fan-shaped cylindrical cavity one by one
Corresponding connection, and one end is pierced by the fan-shaped cylindrical cavity, for controlling the pressure of the fan-shaped cylindrical cavity；
Control cabinet is arranged in the fishing device ontology above the lifting cabin, and with the lifting cabin and based on artificial
The walking limb of muscle connects, for controlling the lifting of fishing device ontology and the walking and shoal of fish fishing of fishing device ontology.
Preferably, the lifting cabin includes:
Water pump is arranged in the fishing device ontology；
The first opening and the second opening are separately positioned on the lifting cabin, and first opening communicates with the outside world, the
Two openings are connected to pump entrance；
First solenoid valve, setting is in first opening；
Wherein, when first solenoid valve is opened, first opening is in communication with the outside；When first solenoid valve closes
When closing, first opening is isolated from the outside；When the pump working, it can will go up and down the seawater in cabin and extract out.
Preferably, the walking limb based on artificial-muscle further include:
High-pressure water is connected to by proportional pressure valve with highly pressurised liquid pipe one end, for controlling the fan-shaped column
Hydraulic pressure in shape cavity；
Nozzle is positioned close to be arranged in the storage compartment in fishing channel and towards storage compartment, the nozzle and the height
Press water source connection；
Pulsed negative pressure generator is connect with the high-pressure water and nozzle, for controlling the row based on artificial-muscle
It walks limb and carries out shoal of fish fishing.
Preferably, further includes:
Pressure sensor is arranged on the fishing device body top surface, for detecting sea suffered by fishing device ontology
Water pressure；
Digital compass is arranged in the control cabinet, for detecting the direction of travel of fishing device ontology；
Binocular solid panoramic vision sensor is arranged at fishing device body top surface center, for obtaining fishing device
Panoramic picture around ontology.
Preferably, the connectivity part of the fishing channel and the storage compartment is provided with second solenoid valve；The sector column
Shape cavity is 4, and mutually at an angle of 90.
A kind of control method of bionical fishing device, acquire fishing device ontology around panoramic picture, fishing device ontology row
Seawater pressure suffered by direction and fishing device ontology is walked, and the walking limb based on artificial-muscle is determined based on BP neural network
Walking states and fishing device ontology adjustable height, specifically comprise the following steps:
Step 1: acquiring shoal of fish volume, quantity around fishing device ontology, fishing device by sensor according to the sampling period
Seawater pressure suffered by the real-time direction of travel and fishing device ontology of ontology；
Step 2: determining input layer vector x={ x of three layers of BP neural network1,x2,x3,x4}；Wherein, x1To catch
Shoal of fish volume around fish device ontology, x2For the number of fish school around fishing device ontology, x3For the real-time direction of travel of fishing device ontology,
x4For seawater pressure suffered by fishing device ontology；
Wherein, the input neuron value x1={ V1,V2,...,Vi,...,Vq, x2={ N1,N2,...,Ni,...,
Nq, wherein ViFor the shoal of fish volume on i-th of direction, NiFor the number of fish school on i-th of direction, q is that fishing device ontology is circumferential
360 ° points of direction number；
Step 3: the input layer DUAL PROBLEMS OF VECTOR MAPPING is to hidden layer, the neuron of hidden layer is m；
Step 4: obtaining output layer neuron vector o={ o1,o2,o3,o4,o5,o6,o7}；Wherein, o1,o2,o3,o4Respectively
For the state of four walking limbs based on artificial-muscle, o5For the adjustable height of bionical fishing device, o6It should go for fishing device ontology
The direction walked, o7The distance walked on the direction that should be walked for fishing device ontology；
Wherein, the output layer neuron value is ok={ p1,k,p2,k,p3,k,p4,k, k is output layer neuron sequence number,
K={ 1,2,3,4 }, p1,k,p2,k,p3,k,p4,kRespectively kth basipodium is empty in four fan-shaped columns on the walking limb of artificial-muscle
The pressure of chamber.
Preferably, when fishing device ontology is gone up and down, the displacement in control lifting cabin meets:
Wherein, V is the displacement for going up and down cabin, and V > 0 is the draining of lifting cabin, and V < 0 is the water suction of lifting cabin, and m is bionical fishing
The weight of device, h are the adjustable height of bionical fishing device, and h > 0 is the rising of bionical fishing device, and h < 0 is the sinking of bionical fishing device, H
For the working frequency of walking limb, L is the axial length of walking limb, αmaxFor the maximum bend angle of walking limb, ρ is density of sea water,
G is acceleration of gravity, and d is the distance that bionical fishing device is walked on the direction that should be walked, V0For go up and down cabin original water,
VNFor the displacement of fishing device ontology.
Preferably, when fishing device ontology runs to the walking limb alignment shoal of fish, the control of pulsed negative pressure generator
Walking limb is by the shoal of fish in fishing pipeline sucking storage compartment, and the negative suction of the shoal of fish meets in control fishing pipeline:
Wherein, P is the negative suction for fishing the shoal of fish in pipeline, and N is the quantity of the shoal of fish, and V is the volume of the shoal of fish, and R is fishing
The diameter of pipeline.
Preferably, the hidden node number m meets:
Preferably, the excitation function of the hidden layer and the output layer is all made of S type function fj(x)=1/ (1+e-x)。
It is of the present invention the utility model has the advantages that
(1) the bionical fishing device that the present invention designs and develops, is provided with the walking limb based on artificial-muscle, fan-shaped by control
The pressure of cylindrical cavity realizes the bending of walking limb, and is sucked the shoal of fish in holding bay along fishing channel by injection principle,
Realize efficiently fishing.
(2) control method for the bionical fishing device that the present invention designs and develops passes through the panorama around acquisition fishing device ontology
Seawater pressure suffered by image, the direction of travel of fishing device ontology and fishing device ontology, and determined based on BP neural network
The walking states of walking limb based on artificial-muscle and the adjustable height of fishing device ontology determine group to be fished.The present invention can also
The displacement in accurate control lifting cabin, realizes the precision lift of bionical fishing device.The present invention passes through injection principle and controls fishing
The negative suction of the shoal of fish in pipeline realizes efficiently fishing by the shoal of fish in fishing channel sucking holding bay.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of bionical fishing device of the present invention.
Fig. 2 is the structural schematic diagram of the walking limb of the present invention based on artificial-muscle.
Fig. 3 is the schematic cross-sectional view of the walking limb of the present invention based on artificial-muscle.
Fig. 4 is the curved schematic of the walking limb of the present invention based on artificial-muscle.
Specific embodiment
Present invention will be described in further detail below with reference to the accompanying drawings, to enable those skilled in the art referring to specification text
Word can be implemented accordingly.
As shown in Figure 1, the present invention provides a kind of bionical fishing device, comprising: fishing device ontology 100 comprising: storage compartment
110, the lower part in fishing device ontology 100 is set, for storing the shoal of fish of fishing；Cabin 120 is gone up and down, is arranged in storage compartment
In the fishing device ontology 100 of 110 tops, the lifting for fishing device ontology 100；Mouth there are two being opened on the lifting cabin 120
That is the first opening and the second opening, and water pump is provided in ontology 100, the first opening with the first solenoid valve control its open with
It closes, when the state opened, lifting cabin 120 is communicated with the outside world, and when the state closed, lifting cabin 120 is isolated from the outside world；Second opening
It is connect with water pump input port, the seawater extraction in cabin 120 will be gone up and down when pump working, forms certain vacuum in lifting cabin 120,
So that bionical fishing device floats；Therefore when wanting the decline of control biomimetics fishing device, control the first solenoid valve unlatching allow seawater into
Enter the lifting cabin 120；When wanting the rising of control biomimetics fishing device, the first solenoid valve of control is closed, and then makes plugman
The seawater in the lifting cabin 120 is allowed to extract out, so that bionical fisher has upward buoyancy.
As shown in Figures 2 and 3, multiple walking limbs 130 based on artificial-muscle, are separately positioned on fishing device ontology 100
Quadrangle, walking and shoal of fish fishing for fishing device ontology 100 comprising: the walking limb 130 is run through in fishing channel 131
Axle center, and one end is connected to storage compartment 110；Multiple sector cylindrical cavities 132, separate and are fishing channel 131 weeks through setting
To walking limb 130 on, and the closed setting in both ends avoids seawater from entering in fan-shaped cylindrical cavity 132, described in the present embodiment
Fan-shaped cylindrical cavity 132 is 4, and mutually at an angle of 90.Multiple highly pressurised liquid pipes 133, are separately positioned on fan-shaped cylindrical cavity
It is connected in 132 and with fan-shaped cylindrical cavity 132 one-to-one correspondence, and the fan-shaped cylindrical cavity 132 and and high pressure water are stretched out in one end
Source connection for filling the water into fan-shaped cylindrical cavity, and then controls the water pressure of fan-shaped cylindrical cavity 132, realizes fan-shaped column
Cavity 132 along flexible and any one direction of its axial direction bending, as shown in Figure 4；Realize the control of four freedom degrees,
And then realize that walking limb 130 supports the walking of fishing device ontology.
The connectivity part in the fishing channel 131 and storage compartment 110 is provided with second solenoid valve, and second solenoid valve is in and opens
State when, the fishing channel 131 is communicated with storage compartment；In the described bionical fishing device walking or lifting
When, second solenoid valve is in close state, and it is marine to can guarantee that fished species will not flow back in this way, while also achieving to fishing
The pressure maintaining of object；Only when the front end of the walking limb 130 alignment fished species, and it is ready for fishing constantly, the second electricity
Magnet valve is in the open state.
The walking limb 130 based on artificial-muscle further include: high-pressure water is arranged in the fishing device ontology 100
It is interior, it is connected to by proportional pressure valve with the highly pressurised liquid pipe 133, for controlling the hydraulic pressure in the fan-shaped cylindrical cavity,
And then realize flexible and any one direction bending of the fan-shaped cylindrical cavity 132 along its axial direction；Nozzle, setting are being leaned on
It is arranged in the storage compartment 110 in nearly fishing channel 131 and towards storage compartment 110, the nozzle is connected to high-pressure water；Pulsed
Negative pressure generator is arranged in control cabinet 140, connect with high-pressure water and nozzle, for controlling based on artificial-muscle
Walking limb 130 carries out shoal of fish fishing.Specifically, pulsed negative pressure generator, for issuing a kind of pulsed vacuum liquid stream realization
Then negative pressure absorbing fishing to fished species sucks fished species by fishing channel 131, and will catch along fishing channel
Object is collected into storage compartment.The high-pressure water is attached by two position three-way valve and nozzle, and nozzle direction is towards storage
Hide cabin, when the two position three-way valve is powered described in high-pressure water provide highly pressurised liquid for the nozzle, according to injection
At this moment principle forms negative pressure of vacuum in fishing channel；By controlling the Push And Release of the two-position three way hydraulic valve and opening
Size is opened, a kind of pulsed vacuum liquid stream is generated in fishing pipeline, and then realizes negative pressure absorbing fishing.
In the walking of bionical fishing device, four walking limbs 130 support the bionical fishing device ontology；Institute
When the bionical fishing device stated is caught, four 130 front ends of walking limb alignment fished species realize alignment fished species
Sucking fishing.
Control cabinet 140 is arranged in the fishing device ontology 100 of 120 top of lifting cabin, wherein being installed with intelligence
Body, other control instrument and meters and backup power source, and connect with the lifting cabin 120 with the walking limb 130 based on artificial-muscle
It connects, for controlling the lifting of fishing device ontology 100 and the walking and shoal of fish fishing of fishing device ontology 100.
Binocular solid panoramic vision sensor 141 carries promising bionical fishing device and provides the annular LED light source of illumination, Gu
It is scheduled on the end face center of the bionical fishing device ontology, the panorama for obtaining the bionical fishing device periphery of bionical benthon is vertical
Body vision video image is linked into control cabinet and is attached with the interface of the intelligent body；Pressure sensor is fixed on institute
On the top surface for the bionical fishing device ontology stated, it is linked into control cabinet and is attached with the intelligent body interface, for detecting
Seawater pressure suffered by the bionical fishing device ontology, to extrapolate the bionical fishing device ontology institute from pressure value
The depth at place；Digital compass is placed in control cabinet 140, is attached with the interface of the intelligent body, described for detecting
Bionical fishing device direction of travel, described bionical catch is obtained according to the bionical fishing device travelling control and direction of travel
The track that fish device walks on the seafloor.
The bionical fishing device that the present invention designs and develops, is provided with the walking limb based on artificial-muscle, by controlling fan-shaped column
The pressure of shape cavity realizes the bending of walking limb, and is sucked the shoal of fish in holding bay along fishing channel by injection principle, real
Now efficiently fishing.
The present invention also provides a kind of control methods of bionical fishing device, acquire the panoramic picture around fishing device ontology, catch
Seawater pressure suffered by the direction of travel and fishing device ontology of fish device ontology, and determined based on BP neural network based on artificial
The walking states of the walking limb of muscle and the adjustable height of fishing device ontology, specifically comprise the following steps:
Step 1: establishing BP neural network model.
Totally interconnected connection is formed on BP model between the neuron of each level, is not connected between the neuron in each level
It connects, the output of input layer is identical as input, i.e. oi=xi.The operating characteristic of the neuron of intermediate hidden layer and output layer
For
opj=fj(netpj)
Wherein p indicates current input sample, ωjiFor from neuron i to the connection weight of neuron j, opiFor neuron
The current input of j, opjIt is exported for it；fjFor it is non-linear can micro- non-decreasing function, be generally taken as S type function, i.e. fj(x)=1/ (1
+e-x)。
For the BP network architecture that the present invention uses by up of three-layer, first layer is input layer, total n node, corresponding
N detection signal of bionical fishing device working condition, these signal parameters are provided by data preprocessing module；The second layer is hidden
Layer, total m node are determined in an adaptive way by the training process of network；Third layer is output layer, total p node, by being
System actual needs output in response to determining that.
The mathematical model of the network are as follows:
Input vector: x=(x1,x2,...,xn)T
Middle layer vector: y=(y1,y2,...,ym)T
Output vector: o=(o1,o2,...,op)T
In the present invention, input layer number is n=4, and output layer number of nodes is p=7, and 360 ° circumferential in fishing device ontology
Dividing has 8 directions, i.e. q=8, hidden layer number of nodes
4 parameters of input layer respectively indicate are as follows: x1For shoal of fish volume around fishing device ontology, x2Around fishing device ontology
The number of fish school, x3For the real-time direction of travel of fishing device ontology, x4For seawater pressure suffered by fishing device ontology；
Wherein, the input neuron value x1={ V1,V2,...,Vi,...,Vq, x2={ N1,N2,...,Ni,...,
Nq, wherein ViFor the shoal of fish volume on i-th of direction, NiFor the number of fish school on i-th of direction, q is that fishing device ontology is circumferential
360 ° points of direction number.
7 parameters of output layer respectively indicate are as follows: o1,o2,o3,o4The shape of respectively four walking limbs based on artificial-muscle
State, o5For the adjustable height of bionical fishing device, o6For the direction that fishing device ontology should walk, o7It is fishing device ontology should
The distance walked on the direction of walking；
Wherein, the output layer neuron value is ok={ p1,k,p2,k,p3,k,p4,k, k is output layer neuron sequence number,
K={ 1,2,3,4 }, p1,k,p2,k,p3,k,p4,kRespectively kth basipodium is empty in four fan-shaped columns on the walking limb of artificial-muscle
The pressure of chamber.
Step 2: carrying out the training of BP neural network.
After establishing BP neural network nodal analysis method, the training of BP neural network can be carried out.It is passed through according to the history of product
Test the sample of data acquisition training, and the connection weight between given input node i and hidden layer node j, hidden node j and defeated
Connection weight between node layer k out.
(1) training method
Each subnet is using individually trained method；When training, first have to provide one group of training sample, each of these sample
This, to forming, when all reality outputs of network and its consistent ideal output, is shown to train by input sample and ideal output
Terminate；Otherwise, by correcting weight, keep the ideal output of network consistent with reality output；Output sample when the training of each subnet
As shown in table 1.
The output sample of 1 network training of table
(2) training algorithm
BP network is trained using error back propagation (Backward Propagation) algorithm, and step can be concluded
It is as follows:
Step 1: a selected structurally reasonable network, is arranged the initial value of all Node B thresholds and connection weight.
Step 2: making following calculate to each input sample:
(a) forward calculation: to l layers of j unit
In formula,L layers of j unit information weighted sum when being calculated for n-th,For l layers of j units with it is previous
Connection weight between the unit i of layer (i.e. l-1 layers),For preceding layer (i.e. l-1 layers, number of nodes nl-1) unit i send
Working signal；When i=0, enableFor the threshold value of l layers of j unit.
If the activation primitive of unit j is sigmoid function,
And
If neuron j belongs to the first hidden layer (l=1), have
If neuron j belongs to output layer (l=L), have
And ej(n)=xj(n)-oj(n)；
(b) retrospectively calculate error:
For output unit
To hidden unit
(c) weight is corrected:
η is learning rate.
Step 3: new sample or a new periodic samples are inputted, and until network convergence, the sample in each period in training
Input sequence is again randomly ordered.
BP algorithm seeks nonlinear function extreme value using gradient descent method, exists and falls into local minimum and convergence rate is slow etc.
Problem.A kind of more efficiently algorithm is Levenberg-Marquardt optimization algorithm, it makes the e-learning time shorter,
Network can be effectively inhibited and sink into local minimum.Its weighed value adjusting rate is selected as
Δ ω=(JTJ+μI)-1JTe
Wherein J is error to Jacobi (Jacobian) matrix of weight differential, and I is input vector, and e is error vector,
Variable μ is the scalar adaptively adjusted, for determining that study is completed according to Newton method or gradient method.
In system design, system model is one merely through the network being initialized, and weight needs basis using
The data sample obtained in journey carries out study adjustment, devises the self-learning function of system thus.Specify learning sample and
In the case where quantity, system can carry out self study, to constantly improve network performance.
In the lifting of fishing device ontology, the displacement in control lifting cabin meets:
Wherein, V is the displacement for going up and down cabin, and V > 0 is the draining of lifting cabin, and V < 0 is the water suction of lifting cabin, and m is bionical fishing
The weight of device, h are the adjustable height of bionical fishing device, and h > 0 is the rising of bionical fishing device, and h < 0 is the sinking of bionical fishing device, H
For the working frequency of walking limb, L is the axial length of walking limb, αmaxFor the maximum bend angle of walking limb, ρ is density of sea water,
G is acceleration of gravity, and d is the distance that bionical fishing device is walked on the direction that should be walked, V0For go up and down cabin original water,
VNFor the displacement of fishing device ontology.
When fishing device ontology runs to the walking limb alignment shoal of fish, pulsed negative pressure generator controls walking limb for fish
Group is in fishing pipeline sucking storage compartment, and the negative suction of the shoal of fish meets in control fishing pipeline:
Wherein, P is the negative suction for fishing the shoal of fish in pipeline, and N is the quantity of the shoal of fish, and V is the volume of the shoal of fish, and R is fishing
The diameter of pipeline.
Further the control method of bionical fishing device provided by the invention is said below with reference to specific embodiment
It is bright.
The diameter in the fishing channel of the present embodiment design is 200mm, and the quality of fishing device ontology is 2.5t, and displacement is
5m3, the volume for going up and down original water in cabin is 3.5m3, the maximum bend angle of walking limb is 60 degree, and the length of walking limb is
500mm, working frequency 0.5/s.Underwater environment is simulated, and the quantity of the shoal of fish in all directions is set, specific data such as 2 institute of table
Show.
2 simulated experiment data of table
Wherein, direction 1 is direct north, and direction 2 is northeastward, direction 3 be positive east to, direction 4 be southeastern direction,
Direction 5 is Due South to direction 6 is southwestward, and direction 7 is positive west to direction 8 is direction northwest.
Using bionical fishing device of the invention control method determine the walking limb based on artificial-muscle walking states and
The adjustable height of fishing device ontology, concrete outcome are as shown in table 3.
Table 3 exports result
And the displacement in lifting cabin is determined according to the following formula:
Further according toThe negative suction of the shoal of fish in control fishing pipeline, can carry out the shoal of fish efficient
Fishing.
The control method for the bionical fishing device that the present invention designs and develops passes through the panorama sketch around acquisition fishing device ontology
Seawater pressure suffered by picture, the direction of travel of fishing device ontology and fishing device ontology, and base is determined based on BP neural network
In the walking states of the walking limb of artificial-muscle and the adjustable height of fishing device ontology, group to be fished is determined.The present invention can also essence
The really displacement in control lifting cabin, realizes the precision lift of bionical fishing device.The present invention passes through injection principle and controls fishing pipe
The negative suction of the shoal of fish in road realizes efficiently fishing by the shoal of fish in fishing channel sucking holding bay.
Although the embodiments of the present invention have been disclosed as above, but its is not only in the description and the implementation listed
With it can be fully applied to various fields suitable for the present invention, for those skilled in the art, can be easily
Realize other modification, therefore without departing from the general concept defined in the claims and the equivalent scope, the present invention is simultaneously unlimited
In specific details and legend shown and described herein.
Claims (10)
1. a kind of bionical fishing device characterized by comprising
Fishing device ontology comprising:
Storage compartment, setting is in the intrinsic lower part of the fishing device, for storing the shoal of fish of fishing；
Cabin is gone up and down, is arranged in the fishing device ontology above the storage compartment, the lifting for fishing device ontology；
Multiple walking limbs based on artificial-muscle are separately positioned on the quadrangle of the fishing device ontology, are used for fishing device ontology
Walking and the shoal of fish fishing comprising:
Channel is fished, runs through the walking limb axle center, and one end is connected to the storage compartment；
Multiple sector cylindrical cavities separate on the walking limb that the fishing channel circumferential direction is arranged in, and both ends are closed sets
It sets；
Multiple highly pressurised liquid pipes are separately positioned in the fan-shaped cylindrical cavity and correspond with the fan-shaped cylindrical cavity
Connection, and one end is pierced by the fan-shaped cylindrical cavity, for controlling the pressure of the fan-shaped cylindrical cavity；
Control cabinet is arranged in the fishing device ontology above the lifting cabin, and with the lifting cabin and based on artificial-muscle
Walking limb connection, for control fishing device ontology lifting and fishing device ontology walking and the shoal of fish fishing.
2. bionical fishing device as described in claim 1, which is characterized in that the lifting cabin includes:
Water pump is arranged in the fishing device ontology；
The first opening and the second opening are separately positioned on the lifting cabin, and first opening communicates with the outside world, and second opens
Mouth is connected to pump entrance；
First solenoid valve, setting is in first opening；
Wherein, when first solenoid valve is opened, first opening is in communication with the outside；When first solenoid valve is closed
When, first opening is isolated from the outside；When the pump working, it can will go up and down the seawater in cabin and extract out.
3. bionical fishing device as described in claim 1, which is characterized in that the walking limb based on artificial-muscle further include:
High-pressure water is connected to by proportional pressure valve with highly pressurised liquid pipe one end, empty for controlling the fan-shaped column
Intracavitary hydraulic pressure；
Nozzle is positioned close to be arranged in the storage compartment in fishing channel and towards storage compartment, the nozzle and the high pressure water
Source connection；
Pulsed negative pressure generator is connect with the high-pressure water and nozzle, for controlling the walking limb based on artificial-muscle
Carry out shoal of fish fishing.
4. bionical fishing device as described in claim 1, which is characterized in that further include:
Pressure sensor is arranged on the fishing device body top surface, for detecting seawater pressure suffered by fishing device ontology
Power；
Digital compass is arranged in the control cabinet, for detecting the direction of travel of fishing device ontology；
Binocular solid panoramic vision sensor is arranged at fishing device body top surface center, for obtaining fishing device ontology
The panoramic picture of surrounding.
5. bionical fishing device as described in claim 1, which is characterized in that the connectivity part in the fishing channel and the storage compartment
It is provided with second solenoid valve；The sector cylindrical cavity is 4, and is mutually the angle 90o.
6. a kind of control method of bionical fishing device, which is characterized in that panoramic picture, fishing device around acquisition fishing device ontology
Seawater pressure suffered by the direction of travel and fishing device ontology of ontology, and determined based on BP neural network and be based on artificial-muscle
Walking limb walking states and fishing device ontology adjustable height, specifically comprise the following steps:
Step 1: acquiring shoal of fish volume, quantity around fishing device ontology, fishing device ontology by sensor according to the sampling period
Real-time direction of travel and fishing device ontology suffered by seawater pressure；
Step 2: determining input layer vector x={ x of three layers of BP neural network1,x2,x3,x4}；Wherein, x1For fishing device
Shoal of fish volume around ontology, x2For the number of fish school around fishing device ontology, x3For the real-time direction of travel of fishing device ontology, x4For
Seawater pressure suffered by fishing device ontology；
Wherein, the input neuron value x1={ V1,V2,...,Vi,...,Vq, x2={ N1,N2,...,Ni,...,Nq,
In, ViFor the shoal of fish volume on i-th of direction, NiFor the number of fish school on i-th of direction, q is the circumferential 360 ° of institutes of fishing device ontology
The direction number divided；
Step 3: the input layer DUAL PROBLEMS OF VECTOR MAPPING is to hidden layer, the neuron of hidden layer is m；
Step 4: obtaining output layer neuron vector o={ o1,o2,o3,o4,o5,o6,o7}；Wherein, o1,o2,o3,o4Respectively four
The state of a walking limb based on artificial-muscle, o5For the adjustable height of bionical fishing device, o6It should walk for fishing device ontology
Direction, o7The distance walked on the direction that should be walked for fishing device ontology；
Wherein, the output layer neuron value is ok={ p1,k,p2,k,p3,k,p4,k, k is output layer neuron sequence number, k=
{ 1,2,3,4 }, p1,k,p2,k,p3,k,p4,kRespectively kth basipodium is in four fan-shaped cylindrical cavities on the walking limb of artificial-muscle
Pressure.
7. the control method of bionical fishing device as claimed in claim 6, which is characterized in that in the lifting of fishing device ontology, control
The displacement in system lifting cabin meets:
Wherein, V is the displacement for going up and down cabin, and V > 0 is the draining of lifting cabin, and V < 0 is the water suction of lifting cabin, and m is bionical fishing device
Weight, h are the adjustable height of bionical fishing device, and h > 0 is the rising of bionical fishing device, and h < 0 is the sinking of bionical fishing device, and H is row
The working frequency of limb is walked, L is the axial length of walking limb, αmaxFor the maximum bend angle of walking limb, ρ is density of sea water, and g is
Acceleration of gravity, d are the distance that bionical fishing device is walked on the direction that should be walked, V0For the original water for going up and down cabin, VNFor
The displacement of fishing device ontology.
8. the control method of bionical fishing device as claimed in claim 7, which is characterized in that described in being run to when fishing device ontology
When walking limb is directed at the shoal of fish, pulsed negative pressure generator controls walking limb by the shoal of fish in fishing pipeline sucking storage compartment, control
The negative suction of the shoal of fish meets in system fishing pipeline:
Wherein, P is the negative suction for fishing the shoal of fish in pipeline, and N is the quantity of the shoal of fish, and V is the volume of the shoal of fish, and R is fishing pipeline
Diameter.
9. the control method of the bionical fishing device as described in claim 6,7 or 8, which is characterized in that the hidden node number m
Meet:
10. the control method of bionical fishing device as claimed in claim 9, which is characterized in that the hidden layer and the output layer
Excitation function be all made of S type function fj(x)=1/ (1+e-x)。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910043907.9A CN109548762B (en) | 2019-01-17 | 2019-01-17 | Bionic fishing device and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910043907.9A CN109548762B (en) | 2019-01-17 | 2019-01-17 | Bionic fishing device and control method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109548762A true CN109548762A (en) | 2019-04-02 |
| CN109548762B CN109548762B (en) | 2021-11-05 |
Family
ID=65873161
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910043907.9A Active CN109548762B (en) | 2019-01-17 | 2019-01-17 | Bionic fishing device and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109548762B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222832A (en) * | 2019-06-19 | 2019-09-10 | 中国水产科学研究院东海水产研究所 | Entrance of Changjiang River salt marshes macrobenthos habitat simulation prediction technique |
| CN111994235A (en) * | 2019-06-20 | 2020-11-27 | 青岛海利创电子科技有限公司 | Electric controllable shrinkage ring structure and annular intelligent underwater robot |
| CN115316351A (en) * | 2022-05-25 | 2022-11-11 | 吉林大学威海仿生研究院 | Underwater bionic non-contact fishing equipment and fishing method thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102873675A (en) * | 2012-09-19 | 2013-01-16 | 浙江工业大学 | Biomimetic crop picking robot |
| CN103029818A (en) * | 2012-12-18 | 2013-04-10 | 浙江工业大学 | Biomimetic benthon fishing robot |
| CN108335457A (en) * | 2018-02-08 | 2018-07-27 | 吉林大学 | A kind of driving safety monitoring method based on driver's bracelet |
| CN108859477A (en) * | 2018-07-05 | 2018-11-23 | 吉林工程技术师范学院 | A kind of children's literature book binder and its control method |
| CN108869056A (en) * | 2018-07-31 | 2018-11-23 | 辽宁工业大学 | A kind of cylinder-variable cylinder deactivation of engine device and its control method |
-
2019
- 2019-01-17 CN CN201910043907.9A patent/CN109548762B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102873675A (en) * | 2012-09-19 | 2013-01-16 | 浙江工业大学 | Biomimetic crop picking robot |
| CN103029818A (en) * | 2012-12-18 | 2013-04-10 | 浙江工业大学 | Biomimetic benthon fishing robot |
| CN108335457A (en) * | 2018-02-08 | 2018-07-27 | 吉林大学 | A kind of driving safety monitoring method based on driver's bracelet |
| CN108859477A (en) * | 2018-07-05 | 2018-11-23 | 吉林工程技术师范学院 | A kind of children's literature book binder and its control method |
| CN108869056A (en) * | 2018-07-31 | 2018-11-23 | 辽宁工业大学 | A kind of cylinder-variable cylinder deactivation of engine device and its control method |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222832A (en) * | 2019-06-19 | 2019-09-10 | 中国水产科学研究院东海水产研究所 | Entrance of Changjiang River salt marshes macrobenthos habitat simulation prediction technique |
| CN111994235A (en) * | 2019-06-20 | 2020-11-27 | 青岛海利创电子科技有限公司 | Electric controllable shrinkage ring structure and annular intelligent underwater robot |
| CN111994235B (en) * | 2019-06-20 | 2022-08-19 | 青岛海利创电子科技有限公司 | Electric controllable shrinkage ring structure and annular intelligent underwater robot |
| CN115316351A (en) * | 2022-05-25 | 2022-11-11 | 吉林大学威海仿生研究院 | Underwater bionic non-contact fishing equipment and fishing method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109548762B (en) | 2021-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103029818B (en) | A kind of bionical benthic organism hauls robot | |
| CN109548762A (en) | A kind of bionical fishing device and its control method | |
| CN206615369U (en) | A kind of special complicated underwater environment of criminal investigation searches fishing device | |
| CN106741763B (en) | A kind of mini underwater observation humanoid robot | |
| Bush et al. | Brooding and sperm storage by the deep-sea squid Bathyteuthis berryi (Cephalopoda: Decapodiformes) | |
| CN103057678A (en) | Autonomous navigation and man-machine coordination catching operating system of benthic organism catching robot | |
| CN106094829A (en) | A kind of autonomous type Stichopus japonicus fishes for robot system and method | |
| CN102132676B (en) | Automatic control platform for fish and using method thereof | |
| Jamieson et al. | Deep‐Sea Benthic Sampling | |
| CN205652313U (en) | Marine environment ecological remediation underwater observation robot | |
| Szymak et al. | Using pretrained alexnet deep learning neural network for recognition of underwater objects | |
| Robison | Light in the ocean’s midwaters | |
| CN205449549U (en) | Water sample collection system and collector under water based on autonomic underwater vehicle | |
| CN107637581B (en) | Using Sepiella maindroni get into the cave cave habit bottom sink formula concentrate collecting device | |
| Wang et al. | Capturing amphipods in the Mariana Trench with a novel pressure retaining sampler | |
| CN114560059B (en) | Underwater lifesaving robot and rescuing method | |
| CN207923720U (en) | A kind of deep-sea detection equipment using real-time VR technologies | |
| CN114735165B (en) | Intelligent underwater lifesaving system and drowning detection and rescue method | |
| Shobana et al. | Ai-underwater drone in protection of waterways by relating design thinking framework | |
| CN107018963B (en) | A kind of quick catching method and quick catching system of deep water mesh cage aquatic livestock | |
| JP2013141426A (en) | Ship-towed net | |
| Gibbons | Exploring the deep, dark sea | |
| Ahn | Development of Moon Jellyfish Removal ROV System and Its Sea Trial | |
| Szymak | Recognition of underwater objects using deep learning in Matlab | |
| CN215684317U (en) | Fishing tool containing piston type fishing basket |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |