CN110476839B - Optimal regulation and control method and system based on fish growth - Google Patents

Optimal regulation and control method and system based on fish growth Download PDF

Info

Publication number
CN110476839B
CN110476839B CN201910670857.7A CN201910670857A CN110476839B CN 110476839 B CN110476839 B CN 110476839B CN 201910670857 A CN201910670857 A CN 201910670857A CN 110476839 B CN110476839 B CN 110476839B
Authority
CN
China
Prior art keywords
fish
water quality
environment data
quality environment
growth
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.)
Active
Application number
CN201910670857.7A
Other languages
Chinese (zh)
Other versions
CN110476839A (en
Inventor
位耀光
李文姝
安冬
李道亮
焦怡莎
魏琼
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.)
China Agricultural University
Original Assignee
China Agricultural University
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 China Agricultural University filed Critical China Agricultural University
Priority to CN201910670857.7A priority Critical patent/CN110476839B/en
Publication of CN110476839A publication Critical patent/CN110476839A/en
Application granted granted Critical
Publication of CN110476839B publication Critical patent/CN110476839B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • A01K61/00—Culture of aquatic animals
    • A01K61/10—Culture of aquatic animals of fish
    • 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
    • A01K63/00—Receptacles for live fish, e.g. aquaria; Terraria
    • A01K63/04—Arrangements for treating water specially adapted to receptacles for live fish
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/02—Agriculture; Fishing; Mining
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
    • Y02A40/80—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in fisheries management
    • Y02A40/81—Aquaculture, e.g. of fish

Abstract

The invention provides an optimal regulation and control method and system based on fish growth, wherein the method comprises the following steps: acquiring a plurality of water quality environment data variables and fish images in an aquaculture system; analyzing and processing the fish image to obtain a healthy growth index of the fish; determining a plurality of key water quality environment data variables influencing the growth of fishes in the plurality of water quality environment data variables according to the healthy growth indexes of the fishes; and inputting the determined multiple key water quality environment data variables and fish health growth indexes into the trained prediction regulation and control model, and outputting corresponding regulation and control quantity. The invention seeks the interaction mechanism between the water quality environment variable and the fish growth state, dynamically regulates and controls the water quality environment parameters for healthy growth of the fish by constructing a prediction regulation and control model between the water quality and the fish growth, ensures the stability of the water environment, reduces the resource consumption, and improves the economic benefit of cultivation.

Description

Optimal regulation and control method and system based on fish growth
Technical Field
The embodiment of the invention relates to the technical field of aquaculture, in particular to an optimal regulation and control method and system based on a fish growth model.
Background
With the continuous growth of population and the increasing strengthening of resource and environment constraints, the promotion of green development and the efficient and intensive utilization of natural resources become the main targets of the current agricultural development. Industrial aquaculture is taken as a novel culture mode, and the defects of the traditional culture mode are overcome. The system can be used for comprehensively and automatically monitoring and treating the water quality parameters, sewage treatment, disease prevention and other processes in the whole culture production process, so that the culture risk is reduced, and the economic benefit is improved.
The water quality is an important part of aquaculture, and along with the aggravation of environmental pollution, the aquaculture needs to improve the aquaculture efficiency by means of a regulation and control technology to meet the aquaculture requirement. Meanwhile, as the most basic and important condition for the survival of the fishes, the quality of the water quality directly influences the healthy growth of the fishes. In the traditional intensive circulating water fish culture of aquaculture, the regulation and control of water quality mostly depend on artificial culture experience, and the water quality control is realized by methods of changing a large amount of water, continuously increasing oxygen and the like. On one hand, a large amount of water resources and energy are wasted; on the other hand, the large floating fluctuation and the continuous change of the water quality can cause the fish to be easy to generate stress response, thereby influencing the healthy growth of the fish.
The fish is extremely sensitive to the change of the environment, and the yield of a unit water body is increased along with the increase of the culture density. Meanwhile, the water quality is continuously deteriorated due to the changes of water environment parameters such as the consumption of dissolved oxygen in the water body, the increase of the emission of ammonia nitrogen and carbon dioxide and the like. Unhealthy water environment has negative influence on behaviors such as ingestion, growth and the like of the fish, and further the fish can not grow healthily.
Disclosure of Invention
The embodiment of the invention provides an optimal regulation and control method and system based on fish growth.
According to one aspect of the invention, an optimal regulation and control method based on fish growth is provided, which comprises the following steps:
s1, collecting a plurality of water quality environment data variables and fish images in the aquaculture system;
s2, analyzing and processing the fish image to obtain a healthy growth index of the fish;
s3, determining multiple key water quality environment data variables influencing fish growth in the multiple water quality environment data variables according to the healthy growth indexes of the fishes;
and S4, inputting the determined multiple key water quality environment data variables and fish health growth indexes into the trained prediction regulation and control model, outputting corresponding regulation and control quantity, and regulating and controlling the water quality in the aquaculture system according to the regulation and control quantity.
On the basis of the technical scheme, the invention can be further improved.
Further, the step S2 specifically includes:
s21, extracting the boundary contour of each fish in the fish image by using an edge detection method based on a Canny operator;
s22, obtaining the growth state information of each fish based on the extracted boundary contour of each fish, obtaining the healthy growth index of each fish according to the growth state information of each fish, and further obtaining the healthy growth index of the fishes in the aquaculture system.
Further, the step S1 further includes:
obtaining fish culture density and fish growth day age in the aquaculture system;
the growth state information of each fish in the step S22 includes a fish body length, a fish body height, and a fish body area; correspondingly, the step S22 of obtaining the healthy growth index of each fish according to the growth state information of each fish, and further obtaining the healthy growth index of the fish in the aquaculture system specifically includes:
a. calculating the fish body mass according to the fish body length and the fish body height of each fish;
b. calculating to obtain a healthy growth index X of each fish according to the fish body mass, the fish body length, the fish culture density of an aquaculture system and the fish growth day age of each fish0F (W, L, ρ, T), where X0The healthy growth index of each fish is W, the fish body mass is L, the fish body length is L, rho is the breeding density, and T is the growth day age of the fish;
c. taking the average value of the healthy growth indexes of each fish as the healthy growth indexes of the fishes in the aquaculture system.
Further, the step S3 specifically includes:
and calculating the correlation degree between each water quality environment data variable and the fish health growth index, and selecting multiple water quality environment data variables with the highest correlation degree as multiple key water quality environment data variables influencing fish growth.
Further, each of the water quality environment data variables comprises a water quality environment data variable sequence of a plurality of time points in a preset time period.
Further, the calculating the correlation between each water quality environment data variable and the fish health growth index specifically includes:
averaging the water quality environment data variables at each time point in each water quality environment data variable sequence:
Figure BDA0002141633680000031
wherein x isi(k) Representing the water quality environment data variable of the kth time point in the ith water quality environment data variable sequence,
Figure BDA0002141633680000032
is the average value, x, of the ith water quality environment data variable sequencei(k) d represents the water quality environment data variable of the kth time point in the ith water quality environment data variable sequence after the mean value is obtained;
calculating a mean value of gray correlation coefficient gamma between the water quality environment data variable at each time point in each water quality environment data variable sequence and the fish growth index0i(k)：
Figure BDA0002141633680000033
Wherein, ξ∈ [0,1]Is a resolution factor, x0Representing the healthy growth index of the fish;
calculating the correlation degree between each water quality environment data variable sequence and the fish growth index;
Figure BDA0002141633680000041
wherein, γ0iAnd the correlation degree between the ith water quality environment data variable sequence and the fish growth index is represented, and n represents the number of water quality environment data variables in the ith water quality environment data variable sequence.
Further, the step S1 further includes:
collecting oxygen flow and water pump flow in the same time period in an aquaculture system;
correspondingly, the step S4 specifically includes:
inputting the determined multiple key water quality environment data variables, the oxygen flow, the water pump flow and the fish health growth index in the same time period in the aquaculture system into a trained prediction regulation and control model, and outputting the regulation and control quantity of each key water quality environment data variable, the oxygen flow and the water pump flow.
Further, the predictive control model is a deep convolutional neural network model, and before the step S4, the method further includes training the deep convolutional neural network model as follows:
inputting a plurality of key water quality environment data variables, fish health growth indexes, oxygen flow and water pump flow of different time periods in a training set into a constructed deep convolutional neural network model, and outputting corresponding regulating and controlling amounts of the oxygen flow and the water pump flow of each time period, wherein the regulating and controlling amounts of the oxygen flow and the water pump flow corresponding to the fish health growth indexes are known in the training set;
respectively calculating a first loss function between the regulating quantity of the oxygen flow corresponding to each time period and the known regulating quantity of the oxygen flow output by the deep convolutional neural network model, and calculating a second loss function between the regulating quantity of the water pump flow output by the deep convolutional neural network model and the known regulating quantity of the water pump flow;
adjusting parameters of the deep convolutional neural network model such that the first loss function and the second loss function both satisfy a convergence condition.
According to a second aspect of the present invention, there is provided a fish growth-based optimal regulation system, comprising:
the acquisition module is used for acquiring a plurality of water quality environment data variables and fish images in the aquaculture system;
the analysis processing module is used for analyzing and processing the fish image to obtain a healthy growth index of the fish;
the determining module is used for determining multiple key water quality environment data variables influencing the growth of the fishes in the multiple water quality environment data variables according to the healthy growth indexes of the fishes;
and the regulation and control module is used for inputting the determined multiple key water quality environment data variables and the fish health growth indexes into the trained prediction and control model, outputting corresponding regulation and control quantity, and regulating and controlling the water quality in the aquaculture system according to the regulation and control quantity.
According to a third aspect of the invention, a non-transitory computer readable storage medium is provided, having stored thereon a computer program which, when being executed by a processor, carries out the steps of a method for optimal regulation based on fish growth.
The invention has the beneficial effects that: the interaction mechanism between the water environment variable and the fish growth state is searched, and the accurate dynamic regulation and control of the healthy growth of the fish are realized by constructing a prediction regulation and control model between the water quality and the fish growth, so that the stability of the water environment is ensured, the resource consumption is reduced, and the economic benefit of the culture is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flow chart of an optimal regulation and control method based on fish growth according to an embodiment of the invention;
FIG. 2 is a flow chart of a method for calculating a healthy growth indicator of fish according to an embodiment of the present invention;
FIG. 3 is a flow chart of a method for calculating a healthy growth indicator for fish according to another embodiment of the present invention;
FIG. 4 is a connection block diagram of an optimal regulation and control system based on fish growth according to an embodiment of the invention.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the invention but are not intended to limit the scope of the invention.
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
With the rapid development of industrial aquaculture and the continuous increase of aquaculture density, the change of water quality parameters in the water environment is closely related to the healthy growth of fishes, and the influence degrees of different water quality environment data variables on the healthy growth of fishes are different. At present, interaction and interaction among various water quality environment data variables are influenced, a very complex nonlinear relation exists among various environment data variables in water, and researches on the relation between the water body environment data variables and a fish growth coupling mechanism are few. Therefore, the healthy growth of the fish needs to be dynamically regulated, so that the stable environment of water quality is ensured, the consumption of energy and resources is reduced, and the maximum economic benefit of cultivation is obtained. The invention researches the interaction mechanism between the water body environment data variable and the fish growth, and realizes the dynamic regulation and control of the healthy growth of the fish based on a prediction regulation and control model.
Referring to fig. 1, a method for optimal regulation and control based on fish growth according to an embodiment of the present invention is provided, the method comprising: s1, collecting a plurality of water quality environment data variables and fish images in the aquaculture system; s2, analyzing and processing the fish image to obtain a healthy growth index of the fish; s3, determining multiple key water quality environment data variables influencing fish growth in the multiple water quality environment data variables according to the healthy growth indexes of the fishes; and S4, inputting the determined multiple key water quality environment data variables and fish health growth indexes into the trained prediction regulation and control model, outputting corresponding regulation and control quantity, and regulating and controlling the water quality in the aquaculture system according to the regulation and control quantity.
Specifically, the embodiment of the invention mainly collects data of two aspects, namely, a plurality of water quality environment data variables in a certain time period of an aquaculture system, and fish images in the same time period, and obtains the healthy growth indexes of the fishes through analysis and processing of the collected fish images.
Wherein, water quality environment data variable is gathered with the help of multi-parameter water quality monitoring appearance, and the fish image is acquireed with the help of the computer monitoring device based on the visualization, for example, adopts the camera to shoot the fish image in the aquaculture system, places the camera respectively in the left side, the right side and the upside in breed pond, shoots and acquires the fish image from different angles.
According to the healthy growth indexes of the fishes in the aquaculture system, multiple key water quality environment data variables influencing the growth of the fishes in the multiple water quality environment data variables are determined. According to the determined multiple key water quality environment data variables and the healthy growth indexes of the fishes in the aquaculture system, the regulation and control quantity for correspondingly regulating the water quality of the water body can be obtained by combining the prediction regulation and control model, and the water body in the aquaculture system is regulated and controlled according to the regulation and control quantity, so that the water quality environment parameters in the aquaculture system can ensure the healthy growth of the fishes.
The invention finds the interaction mechanism between the water environment variable and the fish growth state, realizes the dynamic regulation and control of the healthy growth of the fish by constructing a prediction regulation and control model between the water quality and the fish growth, ensures the stability of the water environment, reduces the resource consumption and improves the economic benefit of the culture.
Referring to fig. 2, in an embodiment of the present invention, the step S2 specifically includes: s21, extracting the boundary contour of each fish in the fish image by using an edge detection method based on a Canny operator; s22, obtaining the growth state information of each fish based on the extracted boundary contour of each fish, obtaining the healthy growth index of each fish according to the growth state information of each fish, and further obtaining the healthy growth index of the fishes in the aquaculture system.
After the fish image in the aquaculture system is acquired, because a plurality of fishes exist in the fish image, the boundary contour of each fish in the fish image is extracted, namely the image area of each fish in the fish image is extracted, and the growth state information of each fish is obtained. And obtaining the healthy growth index of each fish according to the growth state information of each fish, and then obtaining the healthy growth index of the fishes in the aquaculture system according to the healthy growth index of each fish.
Specifically, when the boundary contour of each fish is extracted from the fish image, the boundary contour of each fish in the image is extracted by using an edge detection method based on a Canny operator. Before extracting the boundary contour of each fish by using a Canny operator edge detection method, preprocessing an acquired original fish image, specifically, smoothing an original input image by using a Gaussian filter, and reducing the influence of noise on an edge detection result, wherein the Gaussian function is as follows:
Figure BDA0002141633680000081
where σ is the standard deviation of the gaussian function used to control the degree of smoothing of the gaussian filter, and x and y represent the coordinates of each point in the filter kernel of the gaussian filter relative to the center point.
Extracting each fish image from the preprocessed fish images by utilizing an edge detection method of Canny operatorThe process of the boundary contour of the fish is that firstly, the gradient strength and the gradient direction of each pixel point in the graph are calculated, in the embodiment of the invention, the gradient value G of each pixel point in the image in the horizontal direction is calculated by means of a Sobel operatorxAnd a gradient value G in the vertical directionyAnd further obtaining the gradient strength and the gradient direction of each pixel point, wherein the specific calculation formula is as follows:
Figure BDA0002141633680000082
where G denotes the gradient strength and θ denotes the gradient direction.
Then, each pixel point in the gradient image is subjected to non-maximum suppression, the local maximum of the pixel point is searched, specifically, gradient values of two pixel points in front and back are compared along the gradient direction, the pixel point with the local maximum gradient value is reserved, other pixel points are suppressed, the edge of the fish image is rough, and the reserved pixel points are edge pixel points which are preliminarily screened out.
For the preliminarily screened edge pixel points, part of the edge pixel points may be caused by noise or color change, so that double-threshold detection needs to be performed on the gradient values Gp of the edge pixel points which are roughly extracted, the edge pixel points with high gradient values are reserved by selecting high and low thresholds, and low thresholds which do not belong to the edge pixels are discarded, and the specific operation is as follows:
Figure BDA0002141633680000083
for the screened edge pixel points, two conditions exist: firstly, the pixels belong to real edge pixels, and secondly, the pixels are caused by other factors, so that the pixels with weak edges need to be judged again. The specific judgment mode is that if strong edge pixel points exist in 8 neighborhood pixel points of the current weak edge pixel points, the weak edge pixel points are reserved and used as edge pixel points; otherwise, the weak edge pixel points are inhibited from being discarded, and the extraction of the boundary contour of each fish in the fish image is completed.
After the boundary contour of each fish is extracted from the fish image, the whole area of each fish can be obtained, the growth state information of each fish is obtained according to the area image of each fish, and the healthy growth index of each fish is calculated according to the growth state information of each fish. And taking the average value of the healthy growth indexes of each fish in the image as the healthy growth indexes of the fishes in the aquaculture system.
Referring to fig. 3, in an embodiment of the present invention, the growth state information of each fish in the step S22 includes a fish body length, a fish body height, and a fish body area; correspondingly, the step S22 of obtaining the healthy growth index of each fish according to the growth state information of each fish, and further obtaining the healthy growth index of the fish in the aquaculture system specifically includes: calculating the fish body mass according to the fish body length and the fish body height of each fish; calculating the healthy growth index of each fish according to the fish body mass, the fish body length, the fish culture density of the aquaculture system and the fish growth day age of each fish; taking the average value of the healthy growth indexes of each fish as the healthy growth indexes of the fishes in the aquaculture system.
Specifically, the healthy growth indexes of each fish in the embodiment of the invention mainly comprise fish body length, fish body height and fish body area. After the boundary contour of each fish in the fish image is extracted by adopting an edge detection method based on a Canny operator, the size of the fish body in the image is firstly converted into the size of the actual fish body.
Selecting two target points in the collected image, calculating the distance L1 between the two target points on the image and the actual distance L2 between the two target points to obtain a distance proportionality coefficient delta l, wherein the calculation formula is as follows:
Figure BDA0002141633680000091
and selecting a target region in the acquired image, and calculating the area S1 of the target region on the image and the area S2 of the corresponding region in practice to obtain an area proportion coefficient delta S, wherein the calculation formula is as follows:
Figure BDA0002141633680000101
according to the boundary contour of each fish extracted from the fish image, obtaining the growth state information of each fish in the fish image, wherein the growth state information specifically comprises a fish body length L0, a fish body height H0 and a fish body area S0, and then according to a distance proportion coefficient delta l and an area proportion coefficient delta S, obtaining the actual fish growth state information, and specifically calculating as follows:
L＝Δl*L0，H＝Δl*H0，S＝Δs*S0；
wherein L and H, S are the actual fish body length, fish body height and fish body area, respectively.
And finally, on the basis, establishing a multiple linear regression model to obtain the relation equation between the actual fish body mass and the fish body length, the fish body height and the fish body area, wherein W is a L + bH + cS + d, and further obtain the actual fish body mass, wherein W is the fish body mass, L is the fish body length, H is the fish body height, S is the fish body area, and a, b, c and d are constants.
Before calculating the healthy growth index of each fish, obtaining the fish culture density rho of an aquaculture system, wherein different culture density values have certain influence on the healthy growth of the fish because a certain relation exists between the weight and the body length of the fish and the growth of the fish at different growth moments of the fish; and acquiring the culture density rho, acquiring the growth day age T of the fish when acquiring water quality environment data variables in the aquaculture system and shooting fish images. Therefore, according to different fish species, a functional relation between the healthy growth indexes of the fish and the weight, the body length, the breeding density rho and the growth age of day T is constructed through correlation analysis, and a functional relation formula is established: x0F (W, L, ρ, T), where X0W is the healthy growth index of each fish, W is the fish body mass, L is the fish body length, rho is the breeding density, and T is the growth day age of the fish.
And calculating to obtain the healthy growth index of each fish, and calculating the average value of the healthy growth indexes of each fish, wherein the calculated average value is the healthy growth index of the fish in the aquaculture system.
In an embodiment of the present invention, the step S3 specifically includes: and calculating the correlation degree between each water quality environment data variable and the fish health growth index, and selecting multiple water quality environment data variables with the highest correlation degree as multiple key water quality environment data variables influencing fish growth.
After the healthy growth indexes of the fishes in the aquaculture system are calculated, the correlation degree between each water quality environment data variable and the healthy growth indexes of the fishes is calculated, the larger the correlation degree between the water quality environment data variable and the healthy growth indexes of the fishes is, the larger the influence of the water quality environment data variable on the healthy growth of the fishes is, and therefore the water quality environment data variable with the larger correlation degree with the healthy growth indexes of the fishes is selected as the key water quality environment data variable influencing the growth of the fishes.
In one example of the invention, each water quality environment data variable comprises a sequence of water quality environment data variables at a plurality of points in time within a predetermined period of time of collection. Correspondingly, the step of calculating the correlation degree between each water quality environment data variable and the fish health growth index specifically comprises the following steps:
calculating the water quality environment data variable of each time point after the mean value in each water quality environment data variable sequence:
Figure BDA0002141633680000111
wherein x isi(k) Representing the water quality environment data variable of the kth time point in the ith water quality environment data variable sequence,
Figure BDA0002141633680000112
is the average value, x, of the ith water quality environment data variable sequencei(k) d represents the water quality environment data variable of the kth time point in the ith water quality environment data variable sequence after the mean value is obtained.
Calculating the gray correlation coefficient between the water quality environment data variable and the fish growth index of each time point in each water quality environment data variable sequence after the mean value is calculatedγ0i(k)：
Figure BDA0002141633680000113
Wherein, ζ ∈ [0,1 ]]Is a resolution factor, x0Indicates the healthy growth index of the fish.
Calculating the correlation degree between each water quality environment data variable sequence and the fish growth index;
Figure BDA0002141633680000114
wherein, γ0iAnd the correlation degree between the ith water quality environment data variable sequence and the fish growth index is represented, and n represents the number of water quality environment data variables in the ith water quality environment data variable sequence.
The correlation degree between each water quality environment data variable and the fish health growth index can be obtained through the calculation process, and a plurality of water quality environment data variables with the correlation degree before the fish health growth index are used as key water quality environment data variables influencing the fish health growth.
It should be noted that, in the embodiment of the present invention, 12 water quality environmental data variables in the aquaculture system are mainly collected, which mainly include water temperature, dissolved oxygen, carbon dioxide, pH, ammonia nitrogen, nitrite, sulfide, BOD, COD, total phosphorus, turbidity, liquid level, and the like. And 5 water quality environment data variables with the front relevance degree are selected as key water quality environment data variables influencing the healthy growth of the fishes by calculating the relevance degree between each water quality environment data variable and the healthy growth index of the fishes.
In an embodiment of the present invention, the step S1 further includes: collecting the current oxygen flow and water pump flow in an aquaculture system; correspondingly, the step S4 specifically includes: inputting the determined multiple key water quality environment data variables, the oxygen flow of the current time period in the aquaculture system, the water pump flow and the fish health growth index into the trained prediction regulation model, and outputting the regulation quantity of the oxygen flow and the water pump flow through the prediction regulation model.
The method is characterized in that the oxygen flow and the water pump flow in the aquaculture system in the same time period are collected while the water quality environment data variable in the aquaculture system is collected and the fish image is shot. In order to ensure the healthy growth of fishes in an aquaculture system, a prediction regulation model is constructed in the embodiment of the invention, firstly, the prediction regulation model is trained through a training set, a plurality of determined key water quality environment data variables, the oxygen flow, the water pump amount and the corresponding calculated healthy growth indexes of fishes in the aquaculture system in the same time period are input into the trained prediction regulation model, and the prediction regulation model outputs the regulation amount of the oxygen flow and the water pump flow corresponding to the time period.
The prediction regulation and control model generates a regulation and control instruction according to the regulation and control quantity, and controls the water quality regulation equipment to regulate the oxygen flow and the water flow in the aquaculture system. In the embodiment of the invention, the water quality regulating equipment mainly comprises an oxygen increasing regulator and a water pump regulator, wherein the oxygen increasing regulator is used for regulating and controlling an oxygen flow regulating valve according to a regulating and controlling instruction so as to control the flow of dissolved oxygen in a water body and regulate and control the content of the dissolved oxygen in the water body of an aquaculture system; the water pump regulator is used for regulating and controlling a frequency converter connected with the water pump according to a regulating and controlling instruction, and regulating and controlling the water circulation flow and the flow velocity of the water body in the aquaculture system. Oxygen flow and water pump flow in the aquaculture system are regulated and controlled through the oxygenation regulator and the water pump regulator, and because a plurality of water quality environment data variables are in certain correlation with the oxygen flow and the water pump flow, when the oxygen flow and the water pump flow in the water body meet the condition of healthy growth of fishes, the plurality of water quality environment data variables also meet the condition of healthy growth of the fishes. The fish in the aquaculture system is ensured to be in a healthy growth environment by continuously regulating and controlling the water body environment parameters of the aquaculture system.
In an embodiment of the present invention, the predictive control model is a deep convolutional neural network model, and the step S4 is preceded by training the deep convolutional neural network model as follows: inputting a plurality of key water quality environment data variables, fish health growth indexes, oxygen flow and water pump flow of different time periods in a training set into a constructed deep convolutional neural network model, and outputting corresponding regulating and controlling amounts of the oxygen flow and the water pump flow of each time period, wherein the regulating and controlling amounts of the oxygen flow and the water pump flow corresponding to the fish health growth indexes are known in the training set; respectively calculating a first loss function between the regulating quantity of the oxygen flow corresponding to each time period and the known regulating quantity of the oxygen flow output by the deep convolutional neural network model, and calculating a second loss function between the regulating quantity of the water pump flow output by the deep convolutional neural network model and the known regulating quantity of the water pump flow; adjusting parameters of the deep convolutional neural network model such that the first loss function and the second loss function both satisfy a convergence condition.
Specifically, the prediction regulation and control model in the embodiment of the present invention employs a deep convolutional neural network model, and the deep convolutional neural network model includes six-layer network structures, specifically, includes 3 convolutional layers, 2 downsampling layers, and 1 full-link layer. The training process of the deep convolutional neural network comprises the steps of dividing the healthy growth indexes of the fishes into 3 grades according to the healthy growth indexes of the fishes and combining with actual culture experience, wherein the three grades are respectively slow in growth, normal growth and excessive growth, and the three grades respectively correspond to the regulation and control quantity of the oxygen flow and the water pump flow in a water body according to the healthy growth indexes of the fishes.
Data in the aquaculture system collected at different time periods is divided into training sets and test sets, for example, sample data is divided into training sets and test sets according to a ratio of 4: 1. The training set and the test set comprise a plurality of key environmental data variables, fish health growth indexes, oxygen flow and water pump flow of the aquaculture system in different time periods, and the corresponding regulation and control quantity of the oxygen flow and the water pump flow is given according to the fish health growth indexes obtained by calculation in each time period, namely the corresponding regulation and control quantity of the oxygen flow and the water pump flow is known for the fish health growth indexes in each time period in the training set and the test set.
Inputting a plurality of key water quality environment data variables, fish health growth indexes, oxygen flow and water pump flow in different time periods in a training set into a constructed deep convolutional neural network model, and outputting the regulating and controlling quantity of the oxygen flow and the water pump flow. Respectively calculating a first loss function between the regulating quantity of the oxygen flow output by the deep convolutional neural network model and the known regulating quantity of the oxygen flow, and calculating a second loss function between the regulating quantity of the water pump flow output by the deep convolutional neural network model and the known regulating quantity of the water pump flow; and adjusting parameters of the deep convolutional neural network model so that the first loss function and the second loss function both meet the convergence condition.
After the deep convolutional neural network model is trained, in order to verify the effect of the deep convolutional neural network model, data in a test set is used for verifying the deep convolutional neural network model, a plurality of key water quality environment data variables, fish health growth indexes, oxygen flow and water pump flow in different time periods in the test set are input into the built deep convolutional neural network model, and the regulation and control quantity of the oxygen flow and the water pump flow is output. And comparing the regulation quantity of the oxygen flow and the water pump flow in each time period output by the deep convolutional neural network model with the known regulation quantity of the oxygen flow and the water pump flow, and calculating the accuracy of perusal of the convolutional neural network model.
For example, the test set has 100 data of different time periods, and a plurality of key water quality environment data variables, fish health growth indexes, oxygen flow and water pump flow of 100 different time periods are input into a deep convolution neural network model constructed, and 100 regulation and control quantities of oxygen flow and water pump flow are output and respectively correspond to 100 different time periods. And comparing the regulating quantity of the oxygen flow and the water pump flow in each time period output by the deep convolutional neural network model with the known regulating quantity of the oxygen flow and the water pump flow, if the regulating quantity is consistent, indicating that the regulating quantity of the oxygen flow and the water pump flow output by the deep convolutional neural network model is correct, and otherwise, indicating that the regulating quantity is wrong.
And calculating the correct number of oxygen flow and water pump flow output by the deep convolutional neural network model in 100 different time periods in the test set, further calculating the accuracy, if the accuracy reaches the condition, indicating that the trained deep convolutional neural network model reaches the standard, otherwise, not reaching the standard and needing to be trained.
Referring to fig. 4, an optimized regulation system based on a fish growth model is provided, which comprises an acquisition module 21, a processing module 22, a determination module 23 and a regulation module 24.
And the acquisition module 21 is used for acquiring a plurality of water quality environment data variables and fish images in the aquaculture system.
And the analysis processing module 22 is used for analyzing and processing the fish image to obtain a healthy growth index of the fish.
And the determining module 23 is configured to determine multiple key water quality environment data variables affecting fish growth in the multiple water quality environment data variables according to the healthy fish growth index.
And the regulation and control module 24 is used for inputting the determined multiple key water quality environment data variables and the fish health growth indexes into the trained prediction and control model, outputting corresponding regulation and control quantity, and regulating and controlling the water quality in the aquaculture system according to the regulation and control quantity.
The acquisition module 21 in the embodiment of the invention mainly acquires a plurality of water quality environment data variables in a certain time period of the aquaculture system and fish images in the same time period, and the analysis processing module 22 obtains the healthy growth indexes of the fishes by analyzing and processing the acquired fish images.
The determining module 23 determines a plurality of key water quality environment data variables affecting fish growth in the plurality of water quality environment data variables according to the healthy fish growth indexes in the aquaculture system calculated by the analyzing and processing module 22.
The regulation and control module 24 combines the prediction regulation and control model according to the determined multiple key water quality environment data variables and the healthy growth indexes of the fishes in the aquaculture system to obtain corresponding regulation and control quantity, and regulates and controls the water quality of the water body in the aquaculture system according to the regulation and control quantity, so that the water quality environment parameters in the aquaculture system can ensure the healthy growth of the fishes.
The optimal regulation and control system based on the fish growth model provided by the embodiment of the invention corresponds to the optimal regulation and control method based on the fish growth model provided by each embodiment, and the relevant technical characteristics of the optimal regulation and control system based on the fish growth model can refer to the relevant technical characteristics of the optimal regulation and control method based on the fish growth model, and are not described herein again.
An embodiment of the present invention also provides a non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, implements the steps of a fish growth model-based optimal regulation method as above.
According to the optimal regulation and control method and system based on the fish growth model, the edge contour of each fish is extracted from the image by means of an edge detection method based on a Canny operator, so that the growth state information of the fish is extracted, and the healthy growth index of the fish in an aquaculture system is obtained through calculation; the interaction mechanism between the water quality environment data variable and the fish healthy growth index is searched by a grey correlation degree analysis method, the regulation and control quantity of oxygen flow and water pump flow in different time periods can be accurately output by taking a deep convolutional neural network as a prediction regulation and control model, accurate dynamic regulation and control of fish healthy growth are realized, and current water quality environment parameters are optimized and regulated, so that the regulated water quality environment parameters are most beneficial to healthy growth of fish, and compared with the traditional artificial regulation and control, the method is more accurate, the stability of the water environment is ensured, the resource consumption is reduced, and the economic benefit of culture is improved.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (8)

1. An optimal regulation and control method based on fish growth is characterized by comprising the following steps:
s1, collecting a plurality of water quality environment data variables and fish images in the aquaculture system;
s2, analyzing and processing the fish image to obtain a healthy growth index of the fish;
s3, determining multiple key water quality environment data variables influencing fish growth in the multiple water quality environment data variables according to the healthy growth indexes of the fishes;
s4, inputting the determined multiple key water quality environment data variables and fish health growth indexes into a trained prediction regulation and control model, outputting corresponding regulation and control quantity, and regulating and controlling the water quality in the aquaculture system according to the regulation and control quantity;
wherein the S1 further includes:
collecting oxygen flow and water pump flow in the same time period in an aquaculture system;
correspondingly, the S4 specifically includes:
inputting the determined multiple key water quality environment data variables, the oxygen flow, the water pump flow and the fish health growth index in the same time period in the aquaculture system into a trained prediction regulation model, and outputting regulation quantities of the oxygen flow and the water pump flow;
the predicting and controlling model is a deep convolutional neural network model, and the training of the deep convolutional neural network model by the following method is further included before S4:
inputting a plurality of key water quality environment data variables, fish health growth indexes, oxygen flow and water pump flow of different time periods in a training set into a constructed deep convolutional neural network model, and outputting corresponding regulating and controlling amounts of the oxygen flow and the water pump flow of each time period, wherein the regulating and controlling amounts of the oxygen flow and the water pump flow corresponding to the fish health growth indexes are known in the training set;
respectively calculating a first loss function between the regulating quantity of the oxygen flow corresponding to each time period and the known regulating quantity of the oxygen flow output by the deep convolutional neural network model, and calculating a second loss function between the regulating quantity of the water pump flow output by the deep convolutional neural network model and the known regulating quantity of the water pump flow;
adjusting parameters of the deep convolutional neural network model such that the first loss function and the second loss function both satisfy a convergence condition.
2. The optimal regulation and control method according to claim 1, wherein the S2 specifically comprises:
s21, extracting the boundary contour of each fish in the fish image by using an edge detection method based on a Canny operator;
s22, obtaining the growth state information of each fish based on the extracted boundary contour of each fish, obtaining the healthy growth index of each fish according to the growth state information of each fish, and further obtaining the healthy growth index of the fishes in the aquaculture system.
3. The optimal regulation method of claim 2, wherein the S1 further comprises:
obtaining fish culture density and fish growth day age in the aquaculture system;
the growth state information of each fish in the S22 comprises fish body length, fish body height and fish body area; correspondingly, the obtaining of the healthy growth index of each fish in S22 according to the growth state information of each fish, and further obtaining the healthy growth index of the fishes in the aquaculture system specifically includes:
a. calculating the fish body mass according to the fish body length and the fish body height of each fish;
b. calculating to obtain a healthy growth index X of each fish according to the fish body mass, the fish body length, the fish culture density of an aquaculture system and the fish growth day age of each fish0F (W, L, ρ, T), where X0The healthy growth index of each fish is W, the fish body mass is L, the fish body length is L, rho is the breeding density, and T is the growth day age of the fish;
c. taking the average value of the healthy growth indexes of each fish as the healthy growth indexes of the fishes in the aquaculture system.
4. The optimal regulation and control method according to claim 1, wherein the S3 specifically comprises:
and calculating the correlation degree between each water quality environment data variable and the fish health growth index, and selecting multiple water quality environment data variables with the highest correlation degree as multiple key water quality environment data variables influencing fish growth.
5. The optimal regulation method of claim 4, wherein each of the water quality environment data variables comprises a sequence of water quality environment data variables at a plurality of time points within a predetermined period of time of collection.
6. The optimal regulation and control method of claim 5, wherein the calculating of the correlation between each water quality environment data variable and the fish health growth index specifically comprises:
averaging the water quality environment data variables at each time point in each water quality environment data variable sequence:
Figure FDA0002457469630000031
wherein x isi(k) Representing the water quality environment data variable of the kth time point in the ith water quality environment data variable sequence,
Figure FDA0002457469630000032
is the average value, x, of the ith water quality environment data variable sequencei(k) d represents the water quality environment data variable of the kth time point in the ith water quality environment data variable sequence after the mean value is obtained;
calculating a gray correlation coefficient gamma between the water quality environment data variable at each time point in each water quality environment data variable sequence after the mean value is calculated and the fish health growth index0i(k)：
Figure FDA0002457469630000033
Wherein, ξ∈ [0,1]Is a resolution factor, x0Representing the healthy growth index of the fish;
calculating the correlation degree between each water quality environment data variable sequence and the fish health growth index;
Figure FDA0002457469630000034
wherein, γ0iAnd the correlation degree between the ith water quality environment data variable sequence and the fish health growth index is represented, and n represents the number of water quality environment data variables in the ith water quality environment data variable sequence.
7. An optimal regulation and control method based on fish growth is characterized by comprising the following steps:
the acquisition module is used for acquiring a plurality of water quality environment data variables and fish images in the aquaculture system;
the analysis processing module is used for analyzing and processing the fish image to obtain a healthy growth index of the fish;
the determining module is used for determining multiple key water quality environment data variables influencing the growth of the fishes in the multiple water quality environment data variables according to the healthy growth indexes of the fishes;
the regulation and control module is used for inputting the determined multiple key water quality environment data variables and the fish health growth indexes into a trained prediction and control model, outputting corresponding regulation and control quantity, and regulating and controlling the water quality in the aquaculture system according to the regulation and control quantity;
wherein the acquisition module is further configured to:
collecting oxygen flow and water pump flow in the same time period in an aquaculture system;
correspondingly, the regulatory module is specifically configured to:
inputting the determined multiple key water quality environment data variables, the oxygen flow, the water pump flow and the fish health growth index in the same time period in the aquaculture system into a trained prediction regulation model, and outputting regulation quantities of the oxygen flow and the water pump flow;
the prediction regulation and control model is a deep convolution neural network model, and the deep convolution neural network model is trained in the following mode:
inputting a plurality of key water quality environment data variables, fish health growth indexes, oxygen flow and water pump flow of different time periods in a training set into a constructed deep convolutional neural network model, and outputting corresponding regulating and controlling amounts of the oxygen flow and the water pump flow of each time period, wherein the regulating and controlling amounts of the oxygen flow and the water pump flow corresponding to the fish health growth indexes are known in the training set;
respectively calculating a first loss function between the regulating quantity of the oxygen flow corresponding to each time period and the known regulating quantity of the oxygen flow output by the deep convolutional neural network model, and calculating a second loss function between the regulating quantity of the water pump flow output by the deep convolutional neural network model and the known regulating quantity of the water pump flow;
adjusting parameters of the deep convolutional neural network model such that the first loss function and the second loss function both satisfy a convergence condition.
8. A non-transitory computer-readable storage medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the steps of a method for optimal regulation and control based on fish growth according to any one of claims 1 to 6.
CN201910670857.7A 2019-07-24 2019-07-24 Optimal regulation and control method and system based on fish growth Active CN110476839B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910670857.7A CN110476839B (en) 2019-07-24 2019-07-24 Optimal regulation and control method and system based on fish growth

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910670857.7A CN110476839B (en) 2019-07-24 2019-07-24 Optimal regulation and control method and system based on fish growth

Publications (2)

Publication Number Publication Date
CN110476839A CN110476839A (en) 2019-11-22
CN110476839B true CN110476839B (en) 2020-07-31

Family

ID=68548092

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910670857.7A Active CN110476839B (en) 2019-07-24 2019-07-24 Optimal regulation and control method and system based on fish growth

Country Status (1)

Country Link
CN (1) CN110476839B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024010461A1 (en) * 2022-07-05 2024-01-11 Salfjord As A method and apparatus for fish farming by means of utilizing a computer-implemented fish farm simulation model.

Families Citing this family (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110910067A (en) * 2019-11-25 2020-03-24 南京师范大学 Intelligent regulation and control method and system for live fish transportation water quality by combining deep learning and Q-learning
CN111582642B (en) * 2020-04-03 2021-03-19 中国水产科学研究院东海水产研究所 Fish optimum environment judgment method, electronic device and storage medium
CN112067774A (en) * 2020-09-16 2020-12-11 保定职业技术学院 Intelligent aquaculture system and method based on Internet of things
CN112257277A (en) * 2020-10-27 2021-01-22 天津农学院 Method for selecting multi-dimensional growth factors of aquatic products and application
CN112380486B (en) * 2020-10-29 2023-09-19 中国农业大学 Dynamic monitoring and evaluating method and system for sea water ornamental fish culture state
CN112417378A (en) * 2020-12-10 2021-02-26 常州大学 Eriocheir sinensis quality estimation method based on unmanned aerial vehicle image processing
CN112889712A (en) * 2021-01-28 2021-06-04 海南昌江元道养殖有限公司 Standardized healthy breeding method for high-quality golden pomfret
CN113126490B (en) * 2021-04-02 2022-11-15 中国农业大学 Intelligent frequency conversion oxygenation control method and device
CN113197145B (en) * 2021-05-08 2022-02-08 浙江大学 Fish biomass estimation system based on cyclic neural network and infrared measurement grating
CN113317265B (en) * 2021-05-28 2022-05-20 重庆工商大学 Intelligent control system for recirculating aquaculture
CN113312844B (en) * 2021-05-28 2022-07-29 重庆工商大学 Recirculating aquaculture monitoring system based on machine learning
CN113516563A (en) * 2021-07-21 2021-10-19 中国农业大学 Fish culture environment adjusting method and system based on sensing data and storage medium
CN113598131B (en) * 2021-07-24 2022-12-13 浙江中兴慧农信息科技有限公司 Interior lake farming systems based on big data block chain
CN114009380A (en) * 2021-10-25 2022-02-08 湖北清江鲟鱼谷特种渔业有限公司 Sturgeon hatching method and system based on neural network model
CN114128661B (en) * 2021-11-17 2023-04-07 江苏大学 Pond river crab accurate bait casting method based on river crab growth model
CN114136906A (en) * 2021-12-01 2022-03-04 浙江省海洋水产养殖研究所 Intelligent fishery regulation and control method and system based on hyperspectral fish meat quality detection
CN115100414B (en) * 2022-07-25 2022-12-23 中国水产科学研究院南海水产研究所 Algae cultivation method, system and medium based on data analysis
CN115349473A (en) * 2022-09-29 2022-11-18 嘉祥县农业技术推广服务中心 Three-dimensional ecological culture method for fish, shrimp and vegetable
CN115578678A (en) * 2022-11-08 2023-01-06 中国农业大学 Fish feeding intensity classification method and system

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2002000013A3 (en) * 2000-06-23 2002-08-01 Women And Infants Hospital Of Meiotic spindle imaging in oocytes and uses therefor in in vitro fertilization
CN101908182A (en) * 2010-09-03 2010-12-08 北京师范大学 Association degree analysis technique for fish growth suitability and fish growth environment
CN201830751U (en) * 2009-07-14 2011-05-18 大连水产学院 System for forecasting influence of water quality parameters of aquaculture water body over growth state of aquaculture organisms
CN101796928B (en) * 2009-07-14 2012-07-25 大连水产学院 Method for predicting effect of water quality parameters of aquaculture water on growth conditions of aquaculture living beings
CN205922507U (en) * 2016-05-21 2017-02-08 广东粤三胖农业科技有限责任公司 Intelligence aquaculture pond based on big data analysis
CN108614422A (en) * 2018-05-23 2018-10-02 中国农业大学 Dissolved oxygen optimal control method, apparatus and system in the cultivation of continental rise plant circulation water
CN109591982A (en) * 2018-12-29 2019-04-09 浙江大学 A kind of no worker monitor underwater culture robot
CN109948532A (en) * 2019-03-19 2019-06-28 桂林电子科技大学 ULTRA-WIDEBAND RADAR human motion recognition method based on depth convolutional neural networks

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2002000013A3 (en) * 2000-06-23 2002-08-01 Women And Infants Hospital Of Meiotic spindle imaging in oocytes and uses therefor in in vitro fertilization
CN201830751U (en) * 2009-07-14 2011-05-18 大连水产学院 System for forecasting influence of water quality parameters of aquaculture water body over growth state of aquaculture organisms
CN101796928B (en) * 2009-07-14 2012-07-25 大连水产学院 Method for predicting effect of water quality parameters of aquaculture water on growth conditions of aquaculture living beings
CN101908182A (en) * 2010-09-03 2010-12-08 北京师范大学 Association degree analysis technique for fish growth suitability and fish growth environment
CN205922507U (en) * 2016-05-21 2017-02-08 广东粤三胖农业科技有限责任公司 Intelligence aquaculture pond based on big data analysis
CN108614422A (en) * 2018-05-23 2018-10-02 中国农业大学 Dissolved oxygen optimal control method, apparatus and system in the cultivation of continental rise plant circulation water
CN109591982A (en) * 2018-12-29 2019-04-09 浙江大学 A kind of no worker monitor underwater culture robot
CN109948532A (en) * 2019-03-19 2019-06-28 桂林电子科技大学 ULTRA-WIDEBAND RADAR human motion recognition method based on depth convolutional neural networks

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024010461A1 (en) * 2022-07-05 2024-01-11 Salfjord As A method and apparatus for fish farming by means of utilizing a computer-implemented fish farm simulation model.

Also Published As

Publication number Publication date
CN110476839A (en) 2019-11-22

Similar Documents

Publication Publication Date Title
CN110476839B (en) Optimal regulation and control method and system based on fish growth
Viazzi et al. Automatic mass estimation of Jade perch Scortum barcoo by computer vision
An et al. Application of computer vision in fish intelligent feeding system—A review
CN111243005B (en) Livestock weight estimation method, apparatus, device and computer readable storage medium
CN106529006A (en) Depth image-based broiler growth model fitting method and apparatus
CN115067243B (en) Fishery monitoring and analyzing method, system and storage medium based on Internet of things technology
CN112232978B (en) Aquatic product length and weight detection method, terminal equipment and storage medium
CN113592896B (en) Fish feeding method, system, equipment and storage medium based on image processing
CN110866872B (en) Pavement crack image preprocessing intelligent selection method and device and electronic equipment
CN113126490A (en) Intelligent frequency conversion oxygenation control method and device
CN113349111A (en) Dynamic feeding method, system and storage medium for aquaculture
CN113487143A (en) Fish shoal feeding decision method and device, electronic equipment and storage medium
Li et al. An adaptive method for fish growth prediction with empirical knowledge extraction
CN113344972A (en) Intensive culture-based fish track prediction method
CN116630080B (en) Method and system for determining capacity of aquatic product intensive culture feed based on image recognition
TW202100944A (en) A computer-stereo-vision-based automatic measurement system and its approaches for aquatic creatures
CN114004433A (en) Method and device for regulating and controlling growth environment of cultured fishes
CN111275269A (en) Online water quality dissolved oxygen change prediction method based on abnormal behavior of cultured fish
Chen et al. Establishing an eyeball-weight relationship for Litopenaeus vannamei using machine vision technology
CN109118540B (en) Sturgeon rapid statistical method based on ridge line extraction
CN116206194A (en) Method, device, system and storage medium for shoal feeding
CN110517226A (en) The offal method for extracting region of multiple features texture image fusion based on bilateral filtering
CN114442686B (en) Dissolved oxygen concentration control method, dissolved oxygen concentration control device, electronic equipment and storage medium
CN112907503B (en) Penaeus vannamei Boone quality detection method based on self-adaptive convolutional neural network
CN115512215A (en) Underwater biological monitoring method and device and storage medium

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