CN112213962A - Intelligent feeding system and method based on growth model and sonar feedback - Google Patents
Intelligent feeding system and method based on growth model and sonar feedback Download PDFInfo
- Publication number
- CN112213962A CN112213962A CN202010850121.0A CN202010850121A CN112213962A CN 112213962 A CN112213962 A CN 112213962A CN 202010850121 A CN202010850121 A CN 202010850121A CN 112213962 A CN112213962 A CN 112213962A
- Authority
- CN
- China
- Prior art keywords
- feeding
- fed
- sonar
- fish
- growth model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 241000251468 Actinopterygii Species 0.000 claims abstract description 71
- 235000012054 meals Nutrition 0.000 claims abstract description 31
- 238000002592 echocardiography Methods 0.000 claims abstract description 23
- 210000004712 air sac Anatomy 0.000 claims abstract description 10
- 230000008569 process Effects 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 9
- 230000002776 aggregation Effects 0.000 claims abstract description 4
- 238000004220 aggregation Methods 0.000 claims abstract description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 57
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 20
- 239000001301 oxygen Substances 0.000 claims description 20
- 229910052760 oxygen Inorganic materials 0.000 claims description 20
- 238000005286 illumination Methods 0.000 claims description 12
- 230000037406 food intake Effects 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 230000007613 environmental effect Effects 0.000 claims description 9
- 238000005303 weighing Methods 0.000 claims description 8
- 238000009395 breeding Methods 0.000 claims description 7
- 230000001488 breeding effect Effects 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 6
- 235000012631 food intake Nutrition 0.000 claims description 5
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 claims description 3
- 238000001514 detection method Methods 0.000 claims description 3
- 238000013178 mathematical model Methods 0.000 claims description 3
- 238000009360 aquaculture Methods 0.000 description 7
- 244000144974 aquaculture Species 0.000 description 7
- 238000005266 casting Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000035699 permeability Effects 0.000 description 3
- 230000007423 decrease Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- 238000003911 water pollution Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01K—ANIMAL HUSBANDRY; AVICULTURE; APICULTURE; PISCICULTURE; FISHING; REARING OR BREEDING ANIMALS, NOT OTHERWISE PROVIDED FOR; NEW BREEDS OF ANIMALS
- A01K61/00—Culture of aquatic animals
- A01K61/80—Feeding devices
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S15/00—Systems using the reflection or reradiation of acoustic waves, e.g. sonar systems
- G01S15/88—Sonar systems specially adapted for specific applications
- G01S15/96—Sonar systems specially adapted for specific applications for locating fish
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Environmental Sciences (AREA)
- Automation & Control Theory (AREA)
- Biodiversity & Conservation Biology (AREA)
- Animal Husbandry (AREA)
- Acoustics & Sound (AREA)
- Zoology (AREA)
- Marine Sciences & Fisheries (AREA)
- Computer Networks & Wireless Communication (AREA)
- Farming Of Fish And Shellfish (AREA)
Abstract
The invention discloses an intelligent feeding method based on a growth model and sonar feedback, which comprises the following steps: s1: establishing a growth model and a feeding prediction model of a fed group; s2: before the feed is fed, average specification data of fed groups are obtained through a sonar system; s3: according to the growth model, the feeding prediction model and the average specification data of fed groups, the feeding amount of the current day is made, and the basic feeding amount of each meal is determined by combining the feeding times; s4: feeding the fed group according to the basic feeding amount of each meal, and detecting the number of swim bladder echoes in the feeding process of the fed group by using a sonar system; s5: analyzing and processing the number of the echoes of the fish based on a given algorithm, and grading the number of feeding objects; s6: making feeding decisions according to the aggregation number of fed groups; s7: and controlling the feeding rate and the feeding amount of the fed group according to the feeding decision.
Description
Technical Field
The invention relates to an intelligent feeding system and method, in particular to an intelligent feeding system and method based on a growth model and sonar feedback.
Background
In large-water aquaculture in China, the feed cost accounts for more than 60% of the total aquaculture cost. The guarantee of accurate feeding of fodder has a key effect to control cost. At present, the feed for the large aquatic body cultured fish is basically fed by a traditional bait casting machine. The traditional bait casting machine only has the functions of timing and quantifying, and the food intake of the fish is influenced by the traditional bait casting machine and external factors, so the food intake is changed. Quantitative feeding can result in insufficient feeding or excessive feeding, and can affect the welfare of the fish. Moreover, the determination of the feeding amount highly depends on the breeding experience and quality of workers, and the problems of inaccurate feeding amount determination and high labor cost exist. The problems of irregular fish output specification, large feed waste and water pollution are easily caused by inaccurate feeding of large-water aquaculture.
With the development of intensive aquaculture, a number of advanced technologies are increasingly being applied to aquaculture. Machine vision to detect the feeding status of fish has become a hotspot of research. The information obtained by only depending on machine vision has defects on one side, and the multi-information fusion technology has high requirements on network transmission speed and processing speed, so that the problem of analysis and decision delay occurs, and feedback and decision cannot be carried out in real time. In addition, for the cultured fish, the maximum feeding rate often exceeds the optimal feeding rate, and feeding by feeding only through feeding state feedback easily causes overfeeding, which is not economical. When the machine vision method is used for feeding feedback of aquaculture at the present stage, the influence of factors such as illumination conditions, water permeability and the like is easy to occur, and excessive feeding of fish is easy to occur only by feeding feedback.
Disclosure of Invention
The invention aims to solve the technical problems that factors such as easy illumination conditions, water permeability and the like influence when aquaculture feeding feedback is carried out by using a machine vision method at the present stage, and fish is easily overfed only by feeding feedback, and provides an intelligent feeding system and method based on a growth model and sonar feedback, so that the problems in the background technology are solved.
The invention is realized by the following technical scheme:
an intelligent feeding system based on a growth model and sonar feedback comprises a data acquisition module, a storage module, a fish finder, a feeding control processor and a pneumatic feeding machine;
the data acquisition module is used for acquiring water quality parameters, meteorological parameters and sonar echo intensity data of a water body in which a fed group is located;
the fish finder detects the number of the swim bladder echoes by adopting a simple sonar lower than four wave beams, can reflect the relative result of more fish or less fish, and carries out grading according to the number of the echoes, wherein the lower the grade is, the slower the feeding speed is, and the higher the grade is, the faster the feeding speed is; the fish finder adopts a high-frequency sonar to collect real-time images of fish, and estimates the quantity and the specification of the fish based on a MaskRcnn neural network algorithm to obtain average specification data of a fed group;
the storage module is used for storing a growth model, a feeding prediction model, a water quality parameter, an environment parameter and a feed feeding weight parameter;
the growth model is a growth model which is suitable for different growth rules and is suitable for different cultivation varieties and is established according to growth data of specific cultivation varieties; the feeding prediction model is a mathematical model relation between the feed feeding amount and the water temperature, between the feeding amount and the dissolved oxygen and between the feeding amount and the weather factors, which is established according to the feeding experience data of the specific breeding variety; the weather factors comprise rainfall, atmospheric pressure and illumination intensity;
the feeding control processor is used for: before feeding a culture object, actively acquiring water quality parameters, meteorological parameters and fish body specification parameters, and determining the basic feeding amount of each meal according to a growth model and a feeding prediction model by combining feeding times; feeding the fed group according to the basic feeding amount of each meal, wherein in the feeding process, the fish detector obtains the quantity grade of fishes in a feeding area by utilizing the quantity of echoes to represent the ingestion intensity of the fishes, and the quantity grade of the echoes is determined every 5s, so that the feeding speed and the feeding amount of the bait feeder are determined;
the pneumatic feeding machine is used for feeding the fed group according to the control of the feeding control processor.
The working principle of the invention is as follows: according to the method, the basic feeding amount of each meal is determined according to the growth model, the feeding prediction model and the average specification data of the fed group, and then the feeding rate and the feeding amount are adjusted in real time according to the feeding rule characteristics of the fed group on the basis of the basic feeding amount of each meal by combining the feeding image fed back by the sonar system and according to the control and processing of the feeding control processor, so that reasonable and accurate feeding management is realized.
Further, an intelligence based on growth model and sonar feedback is thrown and is raised system, data acquisition module includes: a weighing sensor, a water temperature sensor, a dissolved oxygen sensor and a meteorological sensor;
the weighing sensor is arranged in the pneumatic feeding machine and used for monitoring the weight of the bin in real time; the water temperature sensor and the dissolved oxygen sensor are arranged 20-50cm below the water surface of the feeding area;
the weighing sensor is used for obtaining the feeding amount and feeding time of each meal and transmitting the feeding amount and feeding time to the feeding control processor;
the water temperature sensor is used for acquiring the water temperature of an area below the water surface of the feeding area and transmitting the water temperature to the feeding control processor;
the dissolved oxygen sensor is used for obtaining dissolved oxygen in an area below the water surface of the feeding area and transmitting the dissolved oxygen to the feeding control processor;
the meteorological sensor is used for obtaining rainfall, atmospheric pressure, illumination intensity, wind direction and humidity and transmitting the rainfall, the atmospheric pressure, the illumination intensity, the wind direction and the humidity to the feeding control processor.
Furthermore, the average specification data of the fed group is the average specification data of the fish obtained by the sonar system by adopting a high-frequency sonar to collect the real-time image of the fish and based on a MaskRcnn neural network algorithm.
Furthermore, the intelligent feeding system based on the growth model and sonar feedback further comprises a fish finder for obtaining the feeding rule characteristics of fed groups; the feeding rule characteristics of the fed groups comprise the number of the fed groups and the feeding intensity of the fed groups.
An intelligent feeding method based on a growth model and sonar feedback comprises the following steps:
s1: establishing a growth model and a feeding prediction model of a fed group;
s2: before the feed is fed, average specification data of fed groups are obtained through a sonar system;
s3: according to the growth model, the feeding prediction model and the average specification data of fed groups, the feeding amount of the current day is made, and the basic feeding amount of each meal is determined by combining the feeding times;
s4: feeding the fed group according to the basic feeding amount of each meal, and detecting the number of swim bladder echoes in the feeding process of the fed group by using a sonar system;
s5: analyzing and processing the number of the echoes of the fish based on a given algorithm, and grading the number of feeding objects;
s6: making feeding decisions according to the aggregation number of fed groups;
s7: and controlling the feeding rate and the feeding amount of the fed group according to the feeding decision.
Further, in S4, the sonar system detects the number of swim bladder echoes during the feeding process of the fed colony, and the detection frequency is once every 5 seconds.
Further, an intelligent feeding method based on a growth model and sonar feedback, wherein the S1 specifically comprises:
collecting water quality parameters and environmental parameters of a fed group, analyzing the water quality parameters, the environmental parameters and the food intake of fishes to obtain main factors influencing feeding amount, and obtaining a growth model and a feeding prediction model according to the main factors influencing feeding amount;
the environmental parameters comprise meteorological parameters, and the water quality parameters comprise the water temperature, ammonia nitrogen and dissolved oxygen in the water of the breeding and feeding object.
Further, an intelligent feeding method based on a growth model and sonar feedback is characterized in that average population specification data fed in S2 are real-time images of the fish acquired by the fish finder through high-frequency sonar, and the number and specification of the fish are evaluated based on a MaskRcnn neural network algorithm.
Further, an intelligent feeding method based on a growth model and sonar feedback specifically divides the number of groups to be fed in S5 into five grades, which are: less, general, more, very many; the corresponding feeding intensity was: weak, relatively weak, general, strong, very strong; the weak is one-level, the weaker is two-level, generally three-level, the strong is four-level, and the very strong is five-level.
Further, an intelligent feeding method based on a growth model and sonar feedback is characterized in that S6 specifically comprises the following steps:
drawing a curve changing along with time according to the number parameters of the fed groups, and judging the feeding speed according to the curve: if the number of fed groups increases with the time, the feeding speed is increased; if the number of fed groups is reduced along with the time, the feeding speed is reduced;
when the basic feeding amount of each meal is already fed and the number of fed groups is three or more, increasing the feeding amount until the number of fed groups is one level or less, and stopping feeding;
and stopping feeding when the basic feeding amount of each meal is not finished and the number of fed groups is reduced to one level or below.
The feeding intensity of the fed colony is evaluated by sending a signal every 5s through a sonar system, converting the signal into a feeding image, analyzing and processing the feeding image through an algorithm, and extracting the number of the fed colony and the feeding intensity of the fed colony as characteristic parameters of the feeding law of the fed colony. The feeding intensity of the fed colony is divided into 5 grades (weak, relatively weak, general, strong and very strong), and a curve changing along with time is drawn according to the characteristic parameters. If the feeding intensity is increased along with the time, the feeding speed is increased; over time, the feeding intensity decreases, reducing the feeding rate. When the basic feeding amount of the meals is already fed and the ingestion intensity of the fed group is more than or equal to grade 3, the feeding amount is increased until the feeding intensity is less than or equal to 1, and feeding is stopped. When the basic feeding amount of the meals is not finished and the feeding intensity of the fed group is reduced to be less than or equal to 1, the feeding is stopped.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. the method is not influenced by factors such as illumination conditions, permeability of water and the like, and can realize accurate feeding of the specific cultured object only by establishing a growth model of the specific cultured object and according to basic feeding amount of the fish and a sonar imaging technology, so that excessive feeding of the fish is not easy to cause.
2. According to the invention, a growth model is established on the basis of a large amount of culture data and is stored in a cloud server, and the specifications of the fish are obtained through a sonar system, so that the basic feeding data of the specific fish are obtained. In the feeding process, the imaging quantity of the fish obtained by the sonar device controls the feeding amount and the feeding speed of the bait casting machine through fuzzy control.
Drawings
The accompanying drawings, which are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
FIG. 1 is a flow chart of an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to examples and accompanying drawings, and the exemplary embodiments and descriptions thereof are only used for explaining the present invention and are not meant to limit the present invention.
Examples
The fed population in this example is fish.
As shown in fig. 1, an intelligent feeding system based on a growth model and sonar feedback comprises a data acquisition module, a storage module, a fish finder, a feeding control processor and a wind-powered feeding machine;
the data acquisition module is used for acquiring water quality parameters, meteorological parameters and sonar echo intensity data of a water body in which a fed group is located;
the fish finder detects the number of the swim bladder echoes by adopting a simple sonar lower than four wave beams, can reflect the relative result of more fish or less fish, and carries out grading according to the number of the echoes, wherein the lower the grade is, the slower the feeding speed is, and the higher the grade is, the faster the feeding speed is; the fish finder adopts a high-frequency sonar to collect real-time images of fish, and estimates the quantity and the specification of the fish based on a MaskRcnn neural network algorithm to obtain average specification data of a fed group;
the storage module is used for storing a growth model, a feeding prediction model, a water quality parameter, an environment parameter and a feed feeding weight parameter;
the growth model is a growth model which is suitable for different growth rules and is suitable for different cultivation varieties and is established according to growth data of specific cultivation varieties; the feeding prediction model is a mathematical model relation between the feed feeding amount and the water temperature, between the feeding amount and the dissolved oxygen and between the feeding amount and the weather factors, which is established according to the feeding experience data of the specific breeding variety; the weather factors comprise rainfall, atmospheric pressure and illumination intensity;
the feeding control processor is used for: before feeding a culture object, actively acquiring water quality parameters, meteorological parameters and fish body specification parameters, and determining the basic feeding amount of each meal according to a growth model and a feeding prediction model by combining feeding times; feeding the fed group according to the basic feeding amount of each meal, wherein in the feeding process, the fish detector obtains the quantity grade of fishes in a feeding area by utilizing the quantity of echoes to represent the ingestion intensity of the fishes, and the quantity grade of the echoes is determined every 5s, so that the feeding speed and the feeding amount of the bait feeder are determined;
the pneumatic feeding machine is used for feeding the fed group according to the control of the feeding control processor.
According to the method, the basic feeding amount of each meal is determined according to the growth model, the feeding prediction model and the average specification data of the fed group, and then the feeding rate and the feeding amount are adjusted in real time according to the feeding rule characteristics of the fed group on the basis of the basic feeding amount of each meal by combining the feeding image fed back by the sonar system and according to the control and processing of the feeding control processor, so that reasonable and accurate feeding management is realized.
Further, an intelligence based on growth model and sonar feedback is thrown and is raised system, data acquisition module includes: a weighing sensor, a water temperature sensor, a dissolved oxygen sensor and a meteorological sensor;
the weighing sensor is arranged in the pneumatic feeding machine and used for monitoring the weight of the bin in real time; the water temperature sensor and the dissolved oxygen sensor are arranged 20-50cm below the water surface of the feeding area;
the weighing sensor is used for obtaining the feeding amount and feeding time of each meal and transmitting the feeding amount and feeding time to the feeding control processor;
the water temperature sensor is used for acquiring the water temperature of an area below the water surface of the feeding area and transmitting the water temperature to the feeding control processor;
the dissolved oxygen sensor is used for obtaining dissolved oxygen in an area below the water surface of the feeding area and transmitting the dissolved oxygen to the feeding control processor;
the meteorological sensor is used for obtaining rainfall, atmospheric pressure, illumination intensity, wind direction and humidity and transmitting the rainfall, the atmospheric pressure, the illumination intensity, the wind direction and the humidity to the feeding control processor.
Furthermore, the average specification data of the fed group is the average specification data of the fish obtained by the sonar system by adopting a high-frequency sonar to collect the real-time image of the fish and based on a MaskRcnn neural network algorithm.
Furthermore, the intelligent feeding system based on the growth model and sonar feedback further comprises a fish finder for obtaining the feeding rule characteristics of fed groups; the feeding rule characteristics of the fed groups comprise the number of the fed groups and the feeding intensity of the fed groups.
An intelligent feeding method based on a growth model and sonar feedback comprises the following steps:
s1: establishing a growth model and a feeding prediction model of a fed group;
s2: before the feed is fed, average specification data of fed groups are obtained through a sonar system;
s3: according to the growth model, the feeding prediction model and the average specification data of fed groups, the feeding amount of the current day is made, and the basic feeding amount of each meal is determined by combining the feeding times;
s4: feeding the fed group according to the basic feeding amount of each meal, and detecting the number of swim bladder echoes in the feeding process of the fed group by using a sonar system;
s5: analyzing and processing the number of the echoes of the fish based on a given algorithm, and grading the number of feeding objects;
s6: making feeding decisions according to the aggregation number of fed groups;
s7: and controlling the feeding rate and the feeding amount of the fed group according to the feeding decision.
Further, in S4, the sonar system detects the number of swim bladder echoes during the feeding process of the fed colony, and the detection frequency is once every 5 seconds.
Further, an intelligent feeding method based on a growth model and sonar feedback, wherein the S1 specifically comprises:
collecting water quality parameters and environmental parameters of a fed group, analyzing the water quality parameters, the environmental parameters and the food intake of fishes to obtain main factors influencing feeding amount, and obtaining a growth model and a feeding prediction model according to the main factors influencing feeding amount;
the environmental parameters comprise meteorological parameters, and the water quality parameters comprise the water temperature, ammonia nitrogen and dissolved oxygen in the water of the breeding and feeding object.
Further, an intelligent feeding method based on a growth model and sonar feedback is characterized in that average population specification data fed in S2 are real-time images of the fish acquired by the fish finder through high-frequency sonar, and the number and specification of the fish are evaluated based on a MaskRcnn neural network algorithm.
Further, an intelligent feeding method based on a growth model and sonar feedback specifically divides the number of groups to be fed in S5 into five grades, which are: less, general, more, very many; the corresponding feeding intensity was: weak, relatively weak, general, strong, very strong; the weak is one-level, the weaker is two-level, generally three-level, the strong is four-level, and the very strong is five-level.
Further, an intelligent feeding method based on a growth model and sonar feedback is characterized in that S6 specifically comprises the following steps:
drawing a curve changing along with time according to the number parameters of the fed groups, and judging the feeding speed according to the curve: if the number of fed groups increases with the time, the feeding speed is increased; if the number of fed groups is reduced along with the time, the feeding speed is reduced;
when the basic feeding amount of each meal is already fed and the number of fed groups is three or more, increasing the feeding amount until the number of fed groups is one level or less, and stopping feeding;
and stopping feeding when the basic feeding amount of each meal is not finished and the number of fed groups is reduced to one level or below.
The feeding intensity of the fed colony is evaluated by sending a signal every 5s through a sonar system, converting the signal into a feeding image, analyzing and processing the feeding image through an algorithm, and extracting the number of the fed colony and the feeding intensity of the fed colony as characteristic parameters of the feeding law of the fed colony. The feeding intensity of the fed colony is divided into 5 grades (weak, relatively weak, general, strong and very strong), and a curve changing along with time is drawn according to the characteristic parameters. If the feeding intensity is increased along with the time, the feeding speed is increased; over time, the feeding intensity decreases, reducing the feeding rate. When the basic feeding amount of the meals is already fed and the ingestion intensity of the fed group is more than or equal to grade 3, the feeding amount is increased until the feeding intensity is less than or equal to 1, and feeding is stopped. When the basic feeding amount of the meals is not finished and the feeding intensity of the fed group is reduced to be less than or equal to 1, the feeding is stopped.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. An intelligent feeding system based on a growth model and sonar feedback is characterized by comprising a data acquisition module, a storage module, a fish finder, a feeding control processor and a wind-driven feeder;
the data acquisition module is used for acquiring water quality parameters, meteorological parameters and sonar echo intensity data of a water body in which a fed group is located;
the fish finder detects the number of the swim bladder echoes by adopting a simple sonar lower than four wave beams, can reflect the relative result of more fish or less fish, and carries out grading according to the number of the echoes, wherein the lower the grade is, the slower the feeding speed is, and the higher the grade is, the faster the feeding speed is; the fish finder adopts a high-frequency sonar to collect real-time images of fish, and estimates the quantity and the specification of the fish based on a MaskRcnn neural network algorithm to obtain average specification data of a fed group;
the storage module is used for storing a growth model, a feeding prediction model, a water quality parameter, an environment parameter and a feed feeding weight parameter;
the growth model is a growth model which is suitable for different growth rules and is suitable for different cultivation varieties and is established according to growth data of specific cultivation varieties; the feeding prediction model is a mathematical model relation between the feed feeding amount and the water temperature, between the feeding amount and the dissolved oxygen and between the feeding amount and the weather factors, which is established according to the feeding experience data of the specific breeding variety; the weather factors comprise rainfall, atmospheric pressure and illumination intensity;
the feeding control processor is used for: before feeding a culture object, actively acquiring water quality parameters, meteorological parameters and fish body specification parameters, and determining the basic feeding amount of each meal according to a growth model and a feeding prediction model by combining feeding times; feeding the fed group according to the basic feeding amount of each meal, wherein in the feeding process, the fish detector obtains the quantity grade of fishes in a feeding area by utilizing the quantity of echoes to represent the ingestion intensity of the fishes, and the quantity grade of the echoes is determined every 5s, so that the feeding speed and the feeding amount of the bait feeder are determined;
the pneumatic feeding machine is used for feeding the fed group according to the control of the feeding control processor.
2. The intelligent feeding system based on growth model and sonar feedback according to claim 1, wherein the data acquisition module comprises: a weighing sensor, a water temperature sensor, a dissolved oxygen sensor and a meteorological sensor;
the weighing sensor is used for obtaining the feeding amount and feeding time of each meal and transmitting the feeding amount and feeding time to the feeding control processor;
the water temperature sensor is used for acquiring the water temperature of an area below the water surface of the feeding area and transmitting the water temperature to the feeding control processor;
the dissolved oxygen sensor is used for obtaining dissolved oxygen in an area below the water surface of the feeding area and transmitting the dissolved oxygen to the feeding control processor;
the meteorological sensor is used for obtaining rainfall, atmospheric pressure, illumination intensity, wind direction and humidity and transmitting the rainfall, the atmospheric pressure, the illumination intensity, the wind direction and the humidity to the feeding control processor.
3. The intelligent feeding system based on the growth model and sonar feedback according to claim 1, wherein the average specification data of the fed population is obtained by the sonar system through high-frequency sonar fish collection and MaskRcnn neural network algorithm.
4. The intelligent feeding system based on the growth model and sonar feedback according to claim 1, characterized by further comprising a fish finder for obtaining feeding law characteristics of fed groups; the feeding rule characteristics of the fed groups comprise the number of the fed groups and the feeding intensity of the fed groups.
5. An intelligent feeding method based on a growth model and sonar feedback is characterized by comprising the following steps:
s1: establishing a growth model and a feeding prediction model of a fed group;
s2: before the feed is fed, average specification data of fed groups are obtained through a sonar system;
s3: according to the growth model, the feeding prediction model and the average specification data of fed groups, the feeding amount of the current day is made, and the basic feeding amount of each meal is determined by combining the feeding times;
s4: feeding the fed group according to the basic feeding amount of each meal, and detecting the number of swim bladder echoes in the feeding process of the fed group by using a sonar system;
s5: analyzing and processing the number of the echoes of the fish based on a given algorithm, and grading the number of feeding objects;
s6: making feeding decisions according to the aggregation number of fed groups;
s7: and controlling the feeding rate and the feeding amount of the fed group according to the feeding decision.
6. The intelligent feeding method based on the growth model and sonar feedback according to claim 5, wherein in S4, the sonar system detects the number of swim bladder echoes during feeding of the fed colony, and the detection frequency is once every 5 seconds.
7. The intelligent feeding method based on the growth model and sonar feedback according to claim 5, wherein S1 specifically comprises:
collecting water quality parameters and environmental parameters of a fed group, analyzing the water quality parameters, the environmental parameters and the food intake of fishes to obtain main factors influencing feeding amount, and obtaining a growth model and a feeding prediction model according to the main factors influencing feeding amount;
the environmental parameters comprise meteorological parameters, and the water quality parameters comprise the water temperature, ammonia nitrogen and dissolved oxygen in the water of the breeding and feeding object.
8. The intelligent feeding method based on the growth model and sonar feedback according to claim 5, wherein the average population specification data fed in S2 is real-time images of the fish collected by the fish finder through high frequency sonar, and the number and specification of the fish are evaluated based on MaskRcnn neural network algorithm.
9. The intelligent feeding method based on the growth model and sonar feedback according to claim 5, wherein the number of groups to be fed in S5 is divided into five levels: less, general, more, very many; the corresponding feeding intensity was: weak, relatively weak, general, strong, very strong; the weak is one-level, the weaker is two-level, generally three-level, the strong is four-level, and the very strong is five-level.
10. The intelligent feeding method based on the growth model and sonar feedback according to claim 9, wherein S6 specifically comprises:
drawing a curve changing along with time according to the number parameters of the fed groups, and judging the feeding speed according to the curve: if the number of fed groups increases with the time, the feeding speed is increased; if the number of fed groups is reduced along with the time, the feeding speed is reduced;
when the basic feeding amount of each meal is already fed and the number of fed groups is three or more, increasing the feeding amount until the number of fed groups is one level or less, and stopping feeding;
and stopping feeding when the basic feeding amount of each meal is not finished and the number of fed groups is reduced to one level or below.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010850121.0A CN112213962A (en) | 2020-08-21 | 2020-08-21 | Intelligent feeding system and method based on growth model and sonar feedback |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010850121.0A CN112213962A (en) | 2020-08-21 | 2020-08-21 | Intelligent feeding system and method based on growth model and sonar feedback |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112213962A true CN112213962A (en) | 2021-01-12 |
Family
ID=74058909
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010850121.0A Pending CN112213962A (en) | 2020-08-21 | 2020-08-21 | Intelligent feeding system and method based on growth model and sonar feedback |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112213962A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112862365A (en) * | 2021-03-16 | 2021-05-28 | 南开大学 | Improved DEB model-based full-life-cycle simulation method for hexagrammos otakii and application of improved DEB model-based full-life-cycle simulation method |
| CN112956440A (en) * | 2021-02-04 | 2021-06-15 | 成都通威水产科技有限公司 | Method for accurately feeding fish pond and control system thereof |
| CN113475430A (en) * | 2021-07-01 | 2021-10-08 | 合肥万康渔业科技有限公司 | Closed-loop control breeding method based on water body detection under 5G and self-adaptive feeding |
| CN113598131A (en) * | 2021-07-24 | 2021-11-05 | 南京添益越科技有限公司 | Interior lake farming systems based on big data block chain |
| CN113875670A (en) * | 2021-10-08 | 2022-01-04 | 武汉理工大学 | Intelligent aquatic product accurate feeding platform and feeding method based on sonar array and visual identification |
| CN113951196A (en) * | 2021-10-21 | 2022-01-21 | 浙江大学 | Intelligent feeding method and device based on machine vision and environment dynamic coupling |
| CN113966723A (en) * | 2021-10-29 | 2022-01-25 | 重庆市水产科学研究所 | Intelligent accurate bait feeding system |
| CN114019518A (en) * | 2021-10-25 | 2022-02-08 | 武汉大学 | Feed feeding accurate control system and method based on fish school density detection |
| CN114323117A (en) * | 2021-11-17 | 2022-04-12 | 玉林师范学院 | Fish feeding intensity assessment method |
| CN114451338A (en) * | 2021-12-29 | 2022-05-10 | 北京市农林科学院信息技术研究中心 | Fish swarm feeding intensity grading method and device and intelligent speed-regulating feeder |
| CN114847209A (en) * | 2022-04-14 | 2022-08-05 | 华中农业大学 | Intelligent fish feeding method and system based on multi-factor comprehensive control |
| TWI778762B (en) * | 2021-08-24 | 2022-09-21 | 國立臺灣海洋大學 | Systems and methods for intelligent aquaculture estimation of the number of fish |
| EP4305958A4 (en) * | 2021-03-12 | 2024-04-10 | Softbank Corp | Information processing program, information processing method, and information processing device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6510815B1 (en) * | 1998-07-30 | 2003-01-28 | Centre National De La Recherche Scientifique (Cnrs) | Method for feeding aquatic animals |
| CN103444613A (en) * | 2013-08-29 | 2013-12-18 | 北京农业信息技术研究中心 | Feeding control system and method for fish culture |
| CN203587800U (en) * | 2013-09-23 | 2014-05-07 | 北京农业信息技术研究中心 | Fish farming feeding control system |
| CN106707806A (en) * | 2016-11-14 | 2017-05-24 | 中国水产科学研究院渔业机械仪器研究所 | Intelligent precise fishman feeding system |
| EP3644717A1 (en) * | 2017-06-28 | 2020-05-06 | Observe Technologies Limited | Data collection system and method for feeding aquatic animals |
| CN111325522A (en) * | 2020-02-24 | 2020-06-23 | 浪潮天元通信信息系统有限公司 | Intelligent fishery breeding management method and system based on Internet of things |
-
2020
- 2020-08-21 CN CN202010850121.0A patent/CN112213962A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6510815B1 (en) * | 1998-07-30 | 2003-01-28 | Centre National De La Recherche Scientifique (Cnrs) | Method for feeding aquatic animals |
| CN103444613A (en) * | 2013-08-29 | 2013-12-18 | 北京农业信息技术研究中心 | Feeding control system and method for fish culture |
| CN203587800U (en) * | 2013-09-23 | 2014-05-07 | 北京农业信息技术研究中心 | Fish farming feeding control system |
| CN106707806A (en) * | 2016-11-14 | 2017-05-24 | 中国水产科学研究院渔业机械仪器研究所 | Intelligent precise fishman feeding system |
| EP3644717A1 (en) * | 2017-06-28 | 2020-05-06 | Observe Technologies Limited | Data collection system and method for feeding aquatic animals |
| CN111325522A (en) * | 2020-02-24 | 2020-06-23 | 浪潮天元通信信息系统有限公司 | Intelligent fishery breeding management method and system based on Internet of things |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112956440A (en) * | 2021-02-04 | 2021-06-15 | 成都通威水产科技有限公司 | Method for accurately feeding fish pond and control system thereof |
| EP4305958A4 (en) * | 2021-03-12 | 2024-04-10 | Softbank Corp | Information processing program, information processing method, and information processing device |
| CN112862365A (en) * | 2021-03-16 | 2021-05-28 | 南开大学 | Improved DEB model-based full-life-cycle simulation method for hexagrammos otakii and application of improved DEB model-based full-life-cycle simulation method |
| CN113475430A (en) * | 2021-07-01 | 2021-10-08 | 合肥万康渔业科技有限公司 | Closed-loop control breeding method based on water body detection under 5G and self-adaptive feeding |
| CN113598131A (en) * | 2021-07-24 | 2021-11-05 | 南京添益越科技有限公司 | Interior lake farming systems based on big data block chain |
| TWI778762B (en) * | 2021-08-24 | 2022-09-21 | 國立臺灣海洋大學 | Systems and methods for intelligent aquaculture estimation of the number of fish |
| CN113875670B (en) * | 2021-10-08 | 2022-10-18 | 武汉理工大学 | Intelligent aquatic product accurate feeding platform and feeding method based on sonar array and visual identification |
| CN113875670A (en) * | 2021-10-08 | 2022-01-04 | 武汉理工大学 | Intelligent aquatic product accurate feeding platform and feeding method based on sonar array and visual identification |
| CN113951196A (en) * | 2021-10-21 | 2022-01-21 | 浙江大学 | Intelligent feeding method and device based on machine vision and environment dynamic coupling |
| CN114019518A (en) * | 2021-10-25 | 2022-02-08 | 武汉大学 | Feed feeding accurate control system and method based on fish school density detection |
| CN114019518B (en) * | 2021-10-25 | 2024-05-28 | 武汉大学 | Precise feed feeding control system and method based on fish swarm density detection |
| CN113966723A (en) * | 2021-10-29 | 2022-01-25 | 重庆市水产科学研究所 | Intelligent accurate bait feeding system |
| CN114323117A (en) * | 2021-11-17 | 2022-04-12 | 玉林师范学院 | Fish feeding intensity assessment method |
| CN114323117B (en) * | 2021-11-17 | 2024-02-09 | 玉林师范学院 | Fish ingestion intensity assessment method |
| CN114451338A (en) * | 2021-12-29 | 2022-05-10 | 北京市农林科学院信息技术研究中心 | Fish swarm feeding intensity grading method and device and intelligent speed-regulating feeder |
| CN114847209A (en) * | 2022-04-14 | 2022-08-05 | 华中农业大学 | Intelligent fish feeding method and system based on multi-factor comprehensive control |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112213962A (en) | Intelligent feeding system and method based on growth model and sonar feedback | |
| CN107094683A (en) | The Autoamtic bait putting and water quality monitoring control system and method for a kind of aquaculture | |
| CN111047583B (en) | Underwater netting system damage detection method based on machine vision | |
| CN111657189A (en) | Fishery aquaculture daily monitoring management system based on big data | |
| CN114467824B (en) | Intelligent bait casting boat | |
| CN108733107A (en) | A kind of livestock rearing condition test-control system based on wireless sensor network | |
| CN113841650A (en) | Intelligent bait feeding system for outdoor aquaculture pond and control method thereof | |
| CN113951196B (en) | Intelligent feeding method and device based on machine vision and environment dynamic coupling | |
| TWM578511U (en) | Feed supplying system of marine cultivation | |
| CN112273310A (en) | Intelligent feeding system for purse net breeding | |
| Sung et al. | Automatic grader for flatfishes using machine vision | |
| CN115202269A (en) | Aquaculture feeding intelligent control system and method thereof | |
| CN114120218A (en) | River course floater monitoring method based on edge calculation | |
| JP2022150284A (en) | Feeding system and feeding method, and sound determination model | |
| CN115843733A (en) | Machine vision-based electronic feeding table device for river crab cultivation and working method | |
| CN116686738A (en) | Automatic weighing and identifying system for dairy cows | |
| CN111275269A (en) | Online water quality dissolved oxygen change prediction method based on abnormal behavior of cultured fish | |
| CN114051983B (en) | Intelligent stichopus japonicus breeding monitoring and collecting system and implementation method | |
| CN206005577U (en) | A kind of automatic feeding simultaneously can gather the ship of information | |
| CN115914560A (en) | Intelligent accurate feeding method and device for sows, electronic equipment and storage medium | |
| CN114998892A (en) | Method and device for improving animal feeding efficiency | |
| Pitakphongmetha et al. | Internet of things for aquaculture in smart crab farming | |
| CN113946715A (en) | Low-cost super box with a net monitoring system | |
| CN114020074A (en) | Intelligent unmanned culture system and method for culture pond | |
| CN113837039A (en) | Fruit growth form visual identification method based on convolutional neural network |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210112 |