CN114467825A - Intelligent classification system for recirculating aquaculture fishes - Google Patents

Intelligent classification system for recirculating aquaculture fishes Download PDF

Info

Publication number
CN114467825A
CN114467825A CN202210114847.7A CN202210114847A CN114467825A CN 114467825 A CN114467825 A CN 114467825A CN 202210114847 A CN202210114847 A CN 202210114847A CN 114467825 A CN114467825 A CN 114467825A
Authority
CN
China
Prior art keywords
fish
community
aquaculture
individuals
level
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
Application number
CN202210114847.7A
Other languages
Chinese (zh)
Other versions
CN114467825B (en
Inventor
赵建
文彦慈
魏丹
朋泽群
叶章颖
刘鹰
朱松明
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.)
Zhejiang University ZJU
Original Assignee
Zhejiang University ZJU
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 Zhejiang University ZJU filed Critical Zhejiang University ZJU
Priority to CN202210114847.7A priority Critical patent/CN114467825B/en
Publication of CN114467825A publication Critical patent/CN114467825A/en
Application granted granted Critical
Publication of CN114467825B publication Critical patent/CN114467825B/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
    • A01K61/90—Sorting, grading, counting or marking live aquatic animals, e.g. sex determination
    • A01K61/95—Sorting, grading, counting or marking live aquatic animals, e.g. sex determination specially adapted for 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
    • A01K63/003—Aquaria; Terraria
    • 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
    • A01K63/06—Arrangements for heating or lighting in, or attached to, receptacles for live 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
    • 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
    • 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
    • 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 discloses an intelligent grading system for fish cultured in circulating water, which can comprise a culture pond, an underwater camera, a biomass evaluation channel, a fish sucking pump, a server, a light supplementing lamp and the like. The system mainly utilizes machine vision and an artificial intelligence algorithm to quantify and analyze the community hierarchical structure information of the recirculating aquaculture fish, then combines swimming strategy game characteristics among individuals with different community levels of the fish, couples the information of the recirculating aquaculture environment, solves the best community hierarchical structure configuration of the current aquaculture object, and realizes intelligent classification of the aquaculture fish based on the configuration. The system provided by the invention is simple in structure, the method is simple, convenient and effective, the feeding welfare of the cultured fishes is ensured, meanwhile, the stable hierarchical structure of the fish community is promoted, and the differentiation of the individual community levels in the fish community is avoided, so that the production efficiency is improved, and the culture benefit is maximized.

Description

Intelligent classification system for recirculating aquaculture fishes
Technical Field
The invention belongs to the field of industrial circulating water intelligent culture, relates to an intelligent culture mode for coupling the analysis of ingestion welfare and swimming energy consumption of cultured fishes, and particularly relates to an intelligent grading system for the cultured fishes in the circulating water.
Background
China is a large fish culture country, the current domestic fish culture mode is mainly characterized by soil ponds and net cages, and circulating water culture with controllable environment and production tends to be realized along with the increasing shortage of water resources and the pressure brought by environmental pollution. How to relieve the individual size differentiation among the cultured objects is a difficult problem in aquaculture. Generally, the size of the breeding object determines the community level, and the larger the size, the higher the community level. The individual size differentiation results in a large degree of community-level differentiation of the breeding objects, which not only affects the feeding and growth benefits of the breeding objects (especially the individuals with lower community levels), but also is not beneficial to the daily management of the breeding people. For fish (particularly, fishes with obvious community grade), the aquaculture currently advocates to solve the above problems by carrying out uniform size classification on cultured objects, i.e. re-gathering individuals with similar sizes to the same culture water body, so as to weaken the physical stress among fish community individuals caused by community grade differentiation. However, the method is time-consuming, labor-consuming and cost-prohibitive, and the stability of the hierarchical structure of the fish community after classification is not fully considered, so that the size of the individual cultured object is easily differentiated again, and secondary or even multiple subsequent classifications are caused.
Research shows that under the same environment, besides the influence of innate factors in gene and physiology, behavioral interaction among individuals is a main factor influencing the size differentiation of individuals in fish stocks. This type of behavioral interaction is mainly manifested as aggression between individuals with large differences in community levels and fighting between individuals with similar community levels. The aggressive behavior and the fighting behavior not only cause the stress of the two interactive parties, but also easily cause the damage of the body surfaces of the two interactive parties. In order to avoid the behavior interaction, the fish community individuals often form a specific swimming strategy according to the community level and benefit requirements, and the swimming strategy determines the food intake and growth of the fish community individuals to a great extent and then influences the stability of the community level structure of the fish community.
On the basis of the background, the invention provides an intelligent grading system for the recirculating aquaculture fishes, which quantifies and analyzes the community hierarchical structure information of the recirculating aquaculture fishes by using machine vision and an artificial intelligence algorithm, then solves the optimal community hierarchical structure configuration of the current aquaculture object by combining swimming strategy game characteristics among individuals with different community levels of the fish community and the information of the recirculating aquaculture environment, and realizes the intelligent grading of the aquaculture fishes based on the configuration. The system provided by the invention is simple in structure, the method is simple, convenient and effective, the feeding welfare of the cultured fishes is ensured, meanwhile, the stable hierarchical structure of the fish community is promoted, and the differentiation of the individual community levels in the fish community is avoided, so that the production efficiency is improved, and the culture benefit is maximized.
Disclosure of Invention
The invention aims to provide an intelligent grading system for recirculating aquaculture fishes, which can determine the optimal community hierarchy configuration mode of a current aquaculture object according to the community hierarchy structure of fish and game characteristics of an analysis fish swimming strategy, and provides good technical support for intelligent grading of recirculating aquaculture.
The technical scheme adopted by the invention is as follows:
a recirculating aquaculture fish intelligent grading system is characterized in that firstly, quantification and analysis are carried out on recirculating aquaculture fish community hierarchical structure information through a machine vision and artificial intelligence algorithm, then, swimming strategy game characteristics among individuals with different community levels of a fish community and aquaculture environment information are combined, the best community hierarchical structure configuration of a current aquaculture object is solved, and intelligent grading of aquaculture fish is achieved based on the configuration.
The system can comprise a culture pond, an underwater camera, a biomass evaluation channel, a fish sucking pump, a server, a light supplementing lamp and the like; the underwater camera and the biomass evaluation channel are arranged in the culture pond and are connected with the server; and the output end of the server is respectively connected with the light supplementing lamp and the fish sucking pump.
By applying the intelligent grading system, the intelligent grading decision in the circulating water culture can be carried out by analyzing the breeding object community grade structure characteristics, the swimming strategy game characteristics and the breeding environment conditions, and the intelligent grading system specifically comprises the following steps:
(1) the server triggers the underwater camera to read the real-time picture, and calculates the individual length (L) and width (W) information of the fish school in the current culture pond by using an artificial intelligence algorithm; then, carrying out normalization on the individual body length information of the fish school: when Wi≤0.4LiWhen the temperature of the water is higher than the set temperature,
Figure BDA0003495850830000021
when Wi＞0.4LiWhen the utility model is used, the water is discharged,
Figure BDA0003495850830000022
wherein i is more than or equal to 1 and less than or equal to N, N is the number of the objects cultured in the current culture pond, and LiIs the body length of the ith subject, LmaxAnd LminRespectively representing the longest length and the shortest length of the cultured objects in the current culture pond;
(2) based on the normalized fish community individual length information, the fish community level structure characteristics are quantized, and the proportion of different community level individuals in the community is calculated as follows: high community-level individual proportion
Figure BDA0003495850830000023
Wherein N ishThe number of fish school individuals is more than or equal to 0.7 and less than or equal to 1; percentage of individuals in the second Community level
Figure BDA0003495850830000024
Wherein N ismThe individual number of fish school is more than 0.3 and less than 0.7; low community level individual proportion
Figure BDA0003495850830000031
Wherein N islThe number of fish school individuals is more than or equal to 0 and less than or equal to 0.3;
(3) coupling water body flow velocity information based on quantized fish community hierarchical structure characteristic information and game characteristics of fish swimming strategy analysis, and determining the current best community hierarchical structure configuration of the fish community:
1) when the average flow velocity V of the aquaculture water is more than or equal to 1BLhS, where BLhIf the average length of the individuals with high community level is not normalized, then: ph’＝Ph，Pm’＝Pm，Pl’＝Pl；
2) When the average flow velocity of the aquaculture water is 1BLh/s＞V≥1BLmS, where BLmIf the average length of the individuals at the middle community level is not normalized, then:
when N ishWhen 1, Ph’＝Ph，Pm’＝Pm，Pl’＝Pl；
When N ishWhen the pressure is higher than 1,
Figure BDA0003495850830000032
Pm’＝1-Ph’-Pl’，Pl’＝Plwherein
Figure BDA0003495850830000033
MfeedThe feeding amount for the current day, MallThe total biomass of the current fish school;
3) when the average flow velocity of the aquaculture water is 1BLm/s＞V≥1BLlS, where BLlThe average length of the low community level individuals without normalization processing is as follows:
when N ish＝NmWhen 1, Ph’＝Ph，Pm’＝Pm，Pl’＝Pl；
When N ish＝1，NmWhen > 1, Ph’＝Ph，
Figure BDA0003495850830000034
Pl’＝1-Ph’-Pm’；
(iii) when Nh＞1，NmWhen the pressure is higher than 1,
Figure BDA0003495850830000035
Figure BDA0003495850830000036
Pl’＝1-Ph’-Pm’；
4) when the average flow velocity V of the aquaculture water is less than 1BLl/s：
When N ish＝NmWhen 1, Ph’＝Ph，Pm’＝Pm，Pl’＝Pl；
When N ish＝1，NlWhen the pressure is higher than 1,
Figure BDA0003495850830000041
Pl’＝1-Ph’-Pm’；
(iii) when Nh＞1，NmWhen the pressure is higher than 1,
Figure BDA0003495850830000042
Figure BDA0003495850830000043
Pl’＝1-Ph’-Pm’；
according to the solved optimal community level structure configuration of the fish school, recalculating the optimal individual number of different community levels in the current fish school: (ii) a high community-level population number Nh’＝round(Ph' × N), the number of community-level individuals Nm’＝round(Pm' × N), c number of individuals of low community level Nl’＝N-Nh’-Nm'; wherein N is the total number of fish, i.e. N ═ Nh+Nm+Nl(ii) a Wherein the round function means "round off;
(4) on the basis, the biomass evaluation channel and the fish sucking pump are utilized to accurately adjust the individual quantity of different community grade intervals (high, medium and low) so as to realize stable grade structure of the fish community; in particular, when the individual fish needs to be moved out of the current culture pond, the fish suction pump is triggered to move the individual fish out of the current culture pond if and only if the single object swims into the biomass evaluation channel and is identified as the individual within the community grade interval to be adjusted;
(5) the above operation may be repeated periodically, for example, once every 7 days.
The invention has the advantages that;
the intelligent grading system for the recirculating aquaculture fishes is simple in structure and accurate and effective in method, the decision of the optimal community hierarchical structure configuration of the fish is obtained based on the machine vision technology and the characteristic analysis of the swimming strategy game of the fish, the intelligent grading system for the aquaculture fishes abandons the traditional size homogenization grading mode, the feeding and growth benefits of the aquaculture fishes are guaranteed, meanwhile, the stable community hierarchical structure of the fish is promoted, the differentiation of individual community levels in the fish is avoided, the production efficiency of the recirculating aquaculture fishes is effectively improved, and the aquaculture benefit is maximized.
Drawings
FIG. 1 is a structure diagram of an intelligent grading system for recirculating aquaculture fishes.
In the figure: 1-a culture pond; 2-an underwater camera; 3-a biomass evaluation channel; 4-a fish pump; 5-a server; 6-light supplement lamp.
Detailed Description
The invention is further described with reference to the following figures and specific examples.
Referring to fig. 1, a specific structure example of the intelligent fish grading system applicable to a recirculating aquaculture mode of the invention includes an aquaculture pond 1, an underwater camera 2, a biomass evaluation channel 3, a fish suction pump 4, a server 5, and a light supplement lamp 6; the underwater camera 2 and the biomass evaluation channel 3 are arranged inside the culture pond 1 and are connected with the server 5; meanwhile, the output end of the server 5 is respectively connected with the fish sucking pump 4 and the light supplementing lamp 6.
The device is applied to the intelligent grading of the fish in the recirculating aquaculture, and the decision method comprises the following steps:
(1) the server triggers the underwater camera to read the real-time picture, and calculates the individual length (L) and width (W) information of the fish school in the current culture pond by using an artificial intelligence algorithm; then the individual body length information of the fish school is processedAnd (3) carrying out normalization: when Wi≤0.4LiWhen the temperature of the water is higher than the set temperature,
Figure BDA0003495850830000051
when Wi＞0.4LiWhen the temperature of the water is higher than the set temperature,
Figure BDA0003495850830000052
wherein i is more than or equal to 1 and less than or equal to N, N is the number of the objects cultured in the current culture pond, and LiIs the body length of the ith subject, LmaxAnd LminRespectively representing the longest length and the shortest length of the cultured objects in the current culture pond;
(2) based on the normalized fish community individual length information, the fish community level structure characteristics are quantized, and the proportion of different community level individuals in the community is calculated as follows: high community-level individual proportion
Figure BDA0003495850830000053
Wherein N ishThe number of fish school individuals is more than or equal to 0.7 and less than or equal to 1; percentage of individuals in the second Community level
Figure BDA0003495850830000054
Wherein N ismThe individual number of fish school is more than 0.3 and less than 0.7; low community level individual proportion
Figure BDA0003495850830000055
Wherein N islThe number of fish school individuals is more than or equal to 0 and less than or equal to 0.3;
(3) coupling water body flow velocity information based on quantized fish community hierarchical structure characteristic information and analyzed fish swimming strategy game characteristics to obtain a current optimal community hierarchical structure configuration scheme of the fish community:
1) when the average flow velocity V of the aquaculture water is more than or equal to 1BLh/s(BLh: high community-level individual average body length without normalization): ph’＝Ph，Pm’＝Pm，Pl’＝Pl；
2) When the average flow velocity of the aquaculture water is 1BLh/s＞V≥1BLm/s(BLm: has no returnNormalized middle-community-level individual average body length):
when N ishWhen 1, Ph’＝Ph，Pm’＝Pm，Pl’＝Pl；
When N ishWhen the pressure is higher than 1,
Figure BDA0003495850830000061
Pm’＝1-Ph’-Pl’，Pl’＝Plwherein
Figure BDA0003495850830000062
MfeedThe feeding amount for the current day, MallThe total biomass of the current fish school;
3) when the average flow velocity of the aquaculture water is 1BLm/s＞V≥1BLl/s(BLl: low community-level individual average body length without normalization):
when N ish＝NmWhen 1, Ph’＝Ph，Pm’＝Pm，Pl’＝Pl；
When N ish＝1，NmWhen > 1, Ph’＝Ph，
Figure BDA0003495850830000063
Pl’＝1-Ph’-Pm’；
(iii) when Nh＞1，NmWhen the pressure is higher than 1,
Figure BDA0003495850830000064
Figure BDA0003495850830000065
Pl’＝1-Ph’-Pm’；
4) when the average flow velocity V of the aquaculture water is less than 1BLl/s：
When N ish＝NmWhen 1, Ph’＝Ph，Pm’＝Pm，Pl’＝Pl；
When N ish＝1，NlWhen the pressure is higher than 1,
Figure BDA0003495850830000066
Pl’＝1-Ph’-Pm’；
(iii) when Nh＞1，NmWhen the ratio is more than 1, the reaction solution is mixed,
Figure BDA0003495850830000067
Figure BDA0003495850830000068
Pl’＝1-Ph’-Pm’；
(4) according to the solved optimal community level structure configuration of the fish school, recalculating the optimal individual number of different community levels in the current fish school: (ii) a high community-level population number Nh’＝round(Ph' × N), the number of community-level individuals Nm’＝round(Pm' × N), c number of individuals of low community level Nl’＝N-Nh’-Nm'; wherein N is the total number of fish, i.e. N ═ Nh+Nm+Nl；
(5) On the basis, the biomass evaluation channel and the fish sucking pump are utilized to accurately adjust the individual quantity of different community grade intervals (high, medium and low) so as to realize stable grade structure of the fish community; in particular, when the individual fish needs to be moved out of the culture pond, the fish suction pump is triggered to move the individual fish out of the current culture pond if and only if the individual fish swims into the biomass evaluation channel and is identified as an individual within the community level interval to be adjusted;
(6) the above operation is repeated once every 7 days.
The above disclosure is only for the specific embodiment of the present invention, but the present invention is not limited thereto, and it should be understood by those skilled in the art that the modifications made without departing from the present invention shall fall within the protection scope of the present invention.

Claims (7)

1. The system is characterized in that the system quantifies and analyzes the community hierarchical structure information of the recirculating aquaculture fish by using a machine vision and artificial intelligence algorithm, then obtains the best community hierarchical structure configuration of the current aquaculture object by combining swimming strategy game characteristics among individuals of different community levels of the fish and aquaculture environment information, and realizes the intelligent grading of the aquaculture fish based on the configuration.
2. The intelligent grading system for recirculating aquaculture fishes as claimed in claim 1, wherein the system comprises an aquaculture pond, an underwater camera, a biomass evaluation channel, a fish sucking pump, a server and a supplementary lighting lamp; the underwater camera and the biomass evaluation channel are arranged in the culture pond and are connected with the server; and the output end of the server is respectively connected with the light supplementing lamp and the fish sucking pump.
3. The intelligent grading system for recirculating aquaculture fish of claim 1, wherein the quantification and analysis of the information of the community hierarchy structure of recirculating aquaculture fish is performed by using machine vision and artificial intelligence algorithms, which are as follows:
(1) calculating the individual body length (L) and body width (W) information of the fish school in the current culture pond by using a machine vision technology and an artificial intelligence algorithm; then, carrying out normalization on the individual body length information of the fish school: when Wi≤0.4LiWhen the temperature of the water is higher than the set temperature,
Figure FDA0003495850820000011
when Wi＞0.4LiWhen the temperature of the water is higher than the set temperature,
Figure FDA0003495850820000012
wherein i is more than or equal to 1 and less than or equal to N, N is the number of the objects cultured in the current culture pond, and LiIs the body length of the ith subject, LmaxAnd LminRespectively representing the longest length and the shortest length of the cultured objects in the current culture pond;
(2) fish shoal based on normalizationThe individual length information, the fish community level structure characteristics are quantized, and the proportion of individuals with different community levels in the group is calculated as follows: high community-level individual proportion
Figure FDA0003495850820000013
Wherein N ishThe number of fish school individuals is more than or equal to 0.7 and less than or equal to 1; percentage of individuals in the second Community level
Figure FDA0003495850820000014
Wherein N ismThe number of fish groups is more than 0.3 and less than 0.7; low community level individual proportion
Figure FDA0003495850820000015
Wherein N islThe number of fish groups is more than or equal to 0 and less than or equal to 0.3.
4. The system for intelligently grading recirculating aquaculture fishes as claimed in claim 3, wherein the optimal community level structure configuration of the current aquaculture object is solved by combining swimming strategy game characteristics among individuals of different community levels of the fish community and aquaculture environment information, specifically:
determining the best community hierarchical structure configuration P of the current fish community according to the quantized fish community hierarchical structure characteristic information and the game characteristic analysis of the fish swimming strategy, coupling the water flow rate informationh’、Pm’、Pl’：
1) When the average flow velocity V of the aquaculture water is more than or equal to 1BLhS, where BLhIf the average length of the individuals with high community level is not normalized, then: ph’＝Ph，Pm’＝Pm，Pl’＝Pl；
2) When the average flow velocity of the aquaculture water is 1BLh/s＞V≥1BLmS, where BLmIf the average length of the individuals at the middle community level is not normalized, then:
when N ishWhen 1, Ph’＝Ph，Pm’＝Pm，Pl’＝Pl；
When N ishWhen the pressure is higher than 1,
Figure FDA0003495850820000021
Pm’＝1-Ph’-Pl’，Pl’＝Plwherein
Figure FDA0003495850820000022
MfeedThe feeding amount for the current day, MallThe sum of the biomass of the current fish school;
3) when the average flow velocity of the aquaculture water is 1BLm/s＞V≥1BLlS, where BLlThe average length of the low community level individuals without normalization processing is as follows:
when N ish＝NmWhen 1, Ph’＝Ph，Pm’＝Pm，Pl’＝Pl；
When Nh＝1，NmWhen > 1, Ph’＝Ph，
Figure FDA0003495850820000023
Pl’＝1-Ph’-Pm’；
(iii) when Nh＞1，NmWhen the pressure is higher than 1,
Figure FDA0003495850820000024
Figure FDA0003495850820000025
Pl’＝1-Ph’-Pm’；
4) when the average flow velocity V of the aquaculture water is less than 1BLl/s：
When N ish＝NmWhen 1, Ph’＝Ph，Pm’＝Pm，Pl’＝Pl；
When N ish＝1，NlWhen > 1, Ph’＝Ph，
Figure FDA0003495850820000026
Pl’＝1-Ph’-Pm’；
(iii) when Nh＞1，NmWhen the pressure is higher than 1,
Figure FDA0003495850820000031
Figure FDA0003495850820000032
Pl’＝1-Ph’-Pm’。
5. the intelligent grading system for recirculating aquaculture fish of claim 4, wherein the optimal number of individuals in different community levels in the current fish is recalculated according to the optimal community level structure configuration of the current aquaculture object: (ii) a high community-level population number Nh’＝round(Ph' × N), the number of community-level individuals Nm’＝round(Pm' × N), c number of individuals of low community level Nl’＝N-Nh’-Nm'; wherein N is the total number of fish, i.e. N ═ Nh+Nm+Nl。
6. The intelligent grading system for recirculating aquaculture fishes as claimed in claim 1, wherein the biomass evaluation channel and the fish sucking pump are used for accurately adjusting the number of individuals in different community grade intervals (high, medium and low) so as to realize stable community grade structure of the fishes; when the individual fish needs to be moved out of the current culture pond, the fish suction pump is triggered to move the individual fish out of the current culture pond if and only if the individual fish swims into the biomass evaluation channel and is identified as an individual within the community level interval to be adjusted.
7. The system for intelligently grading recirculating aquaculture fish of claim 1, wherein said system periodically performs intelligent grading of aquaculture fish.
CN202210114847.7A 2022-01-30 2022-01-30 Intelligent classification system for recirculating aquaculture fishes Active CN114467825B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210114847.7A CN114467825B (en) 2022-01-30 2022-01-30 Intelligent classification system for recirculating aquaculture fishes

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210114847.7A CN114467825B (en) 2022-01-30 2022-01-30 Intelligent classification system for recirculating aquaculture fishes

Publications (2)

Publication Number Publication Date
CN114467825A true CN114467825A (en) 2022-05-13
CN114467825B CN114467825B (en) 2022-10-28

Family

ID=81478139

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210114847.7A Active CN114467825B (en) 2022-01-30 2022-01-30 Intelligent classification system for recirculating aquaculture fishes

Country Status (1)

Country Link
CN (1) CN114467825B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104542399A (en) * 2015-01-07 2015-04-29 浙江大学 Fish welfare grading device
CN110089477A (en) * 2019-05-23 2019-08-06 浙江大学 A kind of fish welfare intelligent cultivation system and method for circulating water cultivation mode
CN111436386A (en) * 2020-04-07 2020-07-24 玉林师范学院 Swimming type cultured fish culture method and system based on ingestion intensity measurement
CN112790134A (en) * 2021-02-02 2021-05-14 山东鲁威海洋科技有限公司 Swimming type fish self-adaptive feeding device and method based on water surface fluctuation information
CN113040081A (en) * 2021-03-24 2021-06-29 浙江大学 Intelligent feeding decision making system for recirculating aquaculture fishes based on fish shoal swimming energy consumption analysis
CN113749030A (en) * 2021-09-09 2021-12-07 浙江大学 Fish welfare self-adaptive feeding system suitable for recirculating aquaculture mode

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104542399A (en) * 2015-01-07 2015-04-29 浙江大学 Fish welfare grading device
CN110089477A (en) * 2019-05-23 2019-08-06 浙江大学 A kind of fish welfare intelligent cultivation system and method for circulating water cultivation mode
CN111436386A (en) * 2020-04-07 2020-07-24 玉林师范学院 Swimming type cultured fish culture method and system based on ingestion intensity measurement
CN112790134A (en) * 2021-02-02 2021-05-14 山东鲁威海洋科技有限公司 Swimming type fish self-adaptive feeding device and method based on water surface fluctuation information
CN113040081A (en) * 2021-03-24 2021-06-29 浙江大学 Intelligent feeding decision making system for recirculating aquaculture fishes based on fish shoal swimming energy consumption analysis
CN113749030A (en) * 2021-09-09 2021-12-07 浙江大学 Fish welfare self-adaptive feeding system suitable for recirculating aquaculture mode

Also Published As

Publication number Publication date
CN114467825B (en) 2022-10-28

Similar Documents

Publication Publication Date Title
CN113040081B (en) Recirculating aquaculture fish feeding decision-making system based on fish shoal swimming energy consumption analysis
CN113749030B (en) Fish welfare self-adaptive feeding system suitable for circulating water aquaculture mode
Petipa et al. The food web structure, utilization and transport of energy by trophic levels in the planktonic communities
Berg et al. Managing aquaculture for sustainability in tropical Lake Kariba, Zimbabwe
Van Der Veer et al. Abundance, growth and food demand of the scyphomedusa Aurelia aurita in the western Wadden Sea
Barros et al. Ingestion rates of Artemia nauplii for different larval stages of Macrobrachium rosenbergii
TWI736415B (en) A smart shrimp and/or crab feeding management system and the method thereof
CN106614243B (en) A kind of efficient dirt collection and intelligent feeding system for pond circulation flowing water culture
CN109673543A (en) A kind of sea pond facility cultivating system and its comprehensive breeding method
CN114467825B (en) Intelligent classification system for recirculating aquaculture fishes
CN116228455B (en) Method for processing test data of flow culture of Notopterygium longituba in leaf
CN113951196A (en) Intelligent feeding method and device based on machine vision and environment dynamic coupling
CN105532561A (en) Industrial culture system of pond
CN114946711B (en) Deep-water cage culture method for tuna with yellow fins
Jaspe et al. Increasing salinity tolerance in tilapias: selective breeding using locally available strains
CN111275269A (en) Online water quality dissolved oxygen change prediction method based on abnormal behavior of cultured fish
CN114532273B (en) Non-invasive active feeding method and system for recirculating aquaculture fish
Fan et al. Age, growth, and population characteristics of Sthenoteuthis oualaniensis in the South China Sea
Burhaz et al. Evaluation of the state of industrial water bioresources in fish areas of Ukraine
Biswas et al. Climate change impacts on fish catch in the world fishing grounds
CN112070108A (en) Fish image identification method for improving ResNet network structure
Yang et al. (Retracted) Dynamic scene images-assisted intelligent control method for industrialized feeding through deep vision learning
Bosmans et al. Early weaning of barramundi, Lates calcarifer (BLOCH), in a commercial, intensive, semi-automated, recirculated larval rearing system
Vasechkina Coupled physical biological model of shellfish mariculture
Fuentes-Andraca et al. Modeling Nile tilapia heterogeneous growth under different stocking densities during pre-grow-out Stage

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