CN114009380A - Sturgeon hatching method and system based on neural network model - Google Patents
Sturgeon hatching method and system based on neural network model Download PDFInfo
- Publication number
- CN114009380A CN114009380A CN202111238105.7A CN202111238105A CN114009380A CN 114009380 A CN114009380 A CN 114009380A CN 202111238105 A CN202111238105 A CN 202111238105A CN 114009380 A CN114009380 A CN 114009380A
- Authority
- CN
- China
- Prior art keywords
- hatching
- sturgeon
- neural network
- roes
- incubation
- 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
- 230000012447 hatching Effects 0.000 title claims abstract description 170
- 241000881711 Acipenser sturio Species 0.000 title claims abstract description 108
- 238000003062 neural network model Methods 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 17
- 241000252335 Acipenser Species 0.000 claims abstract description 11
- 238000011534 incubation Methods 0.000 claims description 82
- 238000005286 illumination Methods 0.000 claims description 30
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 30
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 29
- 229910052760 oxygen Inorganic materials 0.000 claims description 29
- 239000001301 oxygen Substances 0.000 claims description 29
- 238000013528 artificial neural network Methods 0.000 claims description 24
- 235000013601 eggs Nutrition 0.000 claims description 23
- 241000251468 Actinopterygii Species 0.000 claims description 19
- 230000005540 biological transmission Effects 0.000 claims description 17
- 241000894007 species Species 0.000 claims description 15
- 238000012544 monitoring process Methods 0.000 claims description 6
- 238000011533 pre-incubation Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims description 2
- 235000013372 meat Nutrition 0.000 description 2
- 210000004712 air sac Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 238000012258 culturing Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000004833 fish glue Substances 0.000 description 1
- 239000010985 leather Substances 0.000 description 1
- 210000003458 notochord Anatomy 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
Images
Classifications
-
- 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
- A01K61/10—Culture of aquatic animals of fish
- A01K61/17—Hatching, e.g. incubators
-
- 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
-
- 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
-
- 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)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Environmental Sciences (AREA)
- Zoology (AREA)
- Animal Husbandry (AREA)
- Biodiversity & Conservation Biology (AREA)
- Marine Sciences & Fisheries (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention discloses a sturgeon hatching method and system based on a neural network model, relates to the field of sturgeon culture, and aims to solve the problem that the control of the hatching conditions of sturgeons at the present stage is not fine.
Description
Technical Field
The invention relates to a sturgeon hatching method and system based on a neural network model, and belongs to the field of sturgeon culture.
Background
Sturgeon is a typical omnivorous fish, has the advantages of high growth speed, strong adaptability, less diseases, high economic value and the like, has thick meat and soft bones, delicious taste and rich nutrition, has high protein content of meat and eggs, is a high-grade nutriment, can be made into high-quality special leather, can be made into fish glue by using swim bladders and notochord cables, can be said that the whole body of sturgeon is treasure, and has high economic value. The sturgeon culturing process has the following problems:
the incubation of sturgeons at the present stage adopts the incubation pool to incubate collectively, the incubation condition is controlled within a suitable incubation range approximately, the control of the incubation condition is not fine, and the incubation is not necessarily the best incubation condition for the incubation of the eggs of sturgeons of different types, so that a method and a system are needed, the best incubation rate and the incubation condition of the eggs of sturgeons of different types can be obtained at any time according to the actual situation, the eggs can be incubated under the best condition, and the incubation efficiency is ensured.
Disclosure of Invention
The invention aims to provide a method and a system for incubating sturgeons based on a neural network model, which aim to solve the problems that the incubation conditions of the sturgeons at the present stage are generally controlled within a proper incubation range, the incubation conditions are not finely controlled, and the incubation conditions are not necessarily optimal for the incubation of sturgeon eggs of different types.
In order to achieve the above purpose, the invention provides the following scheme:
a sturgeon hatching method based on a neural network model comprises the following steps:
acquiring data before hatching, wherein the data comprises the species of sturgeon roes, the total number of the roes, the temperature of a hatching pond in which the sturgeon roes are positioned, the water flow speed, the dissolved oxygen concentration and the illumination intensity;
secondly, collecting data after hatching, wherein the data comprises the time for hatching a single sturgeon, the average hatching duration and the hatching rate;
thirdly, constructing a plurality of experience samples through data acquired and counted in the first step and the second step, wherein a single experience sample corresponds to data of a single hatching pool, the experience samples comprise sturgeon roe types, total number of sturgeon roes, culture temperature, water flow speed, dissolved oxygen concentration, illumination intensity, total hatching rate and average incubation time used for incubation of single sturgeon in the corresponding hatching pool, randomly selecting part of experience samples, taking the sturgeon roe types, the total number of roes and the incubation rate as input layers, and taking the temperature, the water flow speed, the dissolved oxygen concentration, the illumination intensity and the average incubation time as output layers, and constructing a neural network initial model;
selecting the rest experience samples as training samples, and training the neural network initial model until convergence to obtain a neural network model for hatching the sturgeon roes of the corresponding variety;
step five, selecting the maximum hatchability of various sturgeon roes from all experience samples, and respectively taking the maximum hatchability as the ideal hatchability of the next sturgeon roe of the same variety;
step six, selecting sturgeon roes with the same variety as the sturgeon roes in the step one for hatching when hatching the next batch of sturgeon roes;
during incubation, recording the species and the total number of roes of the sturgeon in the incubation pool of the corresponding species, inputting the species, the total number and the ideal incubation rate of the roes of the sturgeon into the neural network model, and outputting the temperature, the water flow speed, the dissolved oxygen concentration, the illumination intensity and the average incubation duration which correspond to the incubation of the roes of the sturgeon of the species;
and seventhly, performing condition control and monitoring on the hatching pond where the variety of roes are located according to the temperature, water flow speed, dissolved oxygen concentration, illumination intensity and average hatching duration corresponding to the hatching of the variety of roes of the sturgeon obtained in the sixth step, and ensuring the hatching rate.
Preferably, the first step further comprises: marking the hatching ponds, recording the types and the quantity of the fish eggs in the hatching ponds, ensuring that the types of the fish eggs in the same hatching pond are the same, setting different temperatures, water flow speeds, dissolved oxygen concentrations and illumination intensities for a plurality of hatching ponds for hatching the fish eggs of the same type so as to form a plurality of sample data, recording the condition data of each hatching pond, and ensuring that the hatching is carried out under a constant condition.
Preferably, the second step further comprises: the time data are recorded from the beginning of the hatching of the roes until the hatching of the roes, the time for hatching the single sturgeon in the single hatching pond is recorded, the average hatching time is calculated, the first sturgeon hatching in the hatching pond is started successfully, the sturgeon roes remaining in the hatching pond cannot be hatched successfully through observation and monitoring judgment, the hatching rate of the sturgeon roes in the single hatching pond is recorded by taking the hatching pond as a unit, and the hatching rate is the ratio of the total hatching number to the total roe number.
A sturgeon hatching system based on a neural network model comprises a pre-hatching data acquisition module, a post-hatching data acquisition module, a neural network controller, a hatching sample data acquisition module, a data transmission module and a user terminal;
the pre-hatching data acquisition module is used for acquiring the serial number of a hatching pond, the type of fish eggs in the hatching pond, the total number of the fish eggs, the temperature, the water flow speed, the dissolved oxygen concentration and the illumination intensity, and acquiring and recording the serial number corresponding to the serial number of the hatching pond;
the post-incubation data acquisition module is used for acquiring the average incubation duration and the total incubation rate of the fish eggs, acquiring and recording and corresponding to the serial number of the incubation pool;
the neural network module is used for constructing a neural network for the pre-incubation data acquisition module and taking the sturgeon roe type, the roe total amount and the incubation rate as input layers and taking the temperature, the water flow speed, the dissolved oxygen concentration, the illumination intensity and the average incubation duration as output layers, and training the neural network until convergence to obtain a neural network model for incubation of corresponding varieties of sturgeon roes;
the hatching sample data acquisition module is used for acquiring parameter data of sturgeon roes to be hatched, wherein the parameter data comprises roe types, roe total number and ideal hatching rate, and the data is input into the neural network model as an input layer;
the user terminal is used for receiving parameter data obtained through the output of the neural network model, and the parameter data comprises temperature, water flow speed, dissolved oxygen concentration, illumination intensity and average incubation duration;
the parameter transmission module is used for transmitting parameter data.
Preferably, the neural network module sends the parameter data output by the neural network model to the user terminal through the parameter delivery module.
More preferably, the parameter transmission module is a wireless transmission module, and the user terminal sends the parameter data of the sturgeon roe to be incubated to the incubation sample data collection module through the wireless transmission module at any time.
Preferably, the sturgeon hatching system based on the neural network model further comprises a control module, the user terminal comprises hatching equipment, the neural network module sends the obtained parameter data to the control module through the parameter conveying module, and the control module controls the operation of the hatching equipment according to the received parameter data.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a sturgeon hatching method and system based on a neural network model, wherein the neural network model is constructed through a plurality of experience samples, the ideal hatching rate of different types of sturgeon roes can be obtained through constructing the neural network model, the types, the total amount and the ideal hatching rate of the sturgeon roes to be hatched are input into the neural network model, the most suitable hatching condition can be obtained, the success rate of hatching of the sturgeons is improved, and the automatic control and the comprehensiveness of the hatching method are ensured.
Drawings
Fig. 1 is a schematic flow chart of a sturgeon hatching method based on big data analysis according to the present invention.
Fig. 2 is a schematic structural diagram of a sturgeon hatching system based on a neural network model.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. 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.
Referring to fig. 1, in this embodiment, a sturgeon hatching method based on a neural network model includes the following steps:
acquiring data before hatching, wherein the data comprises the species of sturgeon roes, the total number of the roes, the temperature of a hatching pond in which the sturgeon roes are positioned, the water flow speed, the dissolved oxygen concentration and the illumination intensity;
secondly, collecting data after hatching, wherein the data comprises the time for hatching a single sturgeon, the average hatching duration and the hatching rate;
thirdly, constructing a plurality of experience samples through data acquired and counted in the first step and the second step, wherein a single experience sample corresponds to data of a single hatching pool, the experience samples comprise sturgeon roe types, total number of sturgeon roes, culture temperature, water flow speed, dissolved oxygen concentration, illumination intensity, total hatching rate and average incubation time used for incubation of single sturgeon in the corresponding hatching pool, randomly selecting part of experience samples, taking the sturgeon roe types, the total number of roes and the incubation rate as input layers, and taking the temperature, the water flow speed, the dissolved oxygen concentration, the illumination intensity and the average incubation time as output layers, and constructing a neural network initial model;
selecting the rest experience samples as training samples, and training the neural network initial model until convergence to obtain a neural network model for hatching the sturgeon roes of the corresponding variety;
step five, selecting the maximum hatchability of various sturgeon roes from all experience samples, and respectively taking the maximum hatchability as the ideal hatchability of the next sturgeon roe of the same variety;
step six, selecting sturgeon roes with the same variety as the sturgeon roes in the step one for hatching when hatching the next batch of sturgeon roes;
during incubation, recording the species and the total number of roes of the sturgeon in the incubation pool of the corresponding species, inputting the species, the total number and the ideal incubation rate of the roes of the sturgeon into the neural network model, and outputting the temperature, the water flow speed, the dissolved oxygen concentration, the illumination intensity and the average incubation duration which correspond to the incubation of the roes of the sturgeon of the species;
and seventhly, performing condition control and monitoring on the hatching pond where the variety of roes are located according to the temperature, water flow speed, dissolved oxygen concentration, illumination intensity and average hatching duration corresponding to the hatching of the variety of roes of the sturgeon obtained in the sixth step, and ensuring the hatching rate.
The first step further comprises: marking the hatching ponds, recording the types and the quantity of the fish eggs in the hatching ponds, ensuring that the types of the fish eggs in the same hatching pond are the same, setting different temperatures, water flow speeds, dissolved oxygen concentrations and illumination intensities for a plurality of hatching ponds for hatching the fish eggs of the same type so as to form a plurality of sample data, recording the condition data of each hatching pond, and ensuring that the hatching is carried out under a constant condition.
The second step further comprises: the time data are recorded from the beginning of the hatching of the roes until the hatching of the roes, the time for hatching the single sturgeon in the single hatching pond is recorded, the average hatching time is calculated, the first sturgeon hatching in the hatching pond is started successfully, the sturgeon roes remaining in the hatching pond cannot be hatched successfully through observation and monitoring judgment, the hatching rate of the sturgeon roes in the single hatching pond is recorded by taking the hatching pond as a unit, and the hatching rate is the ratio of the total hatching number to the total roe number.
The second step is followed by the following steps: time data are recorded from the beginning of the incubation of the roes until the roes are incubated, the time for the incubation of the single sturgeon in a single incubation pool is recorded, the time for the incubation is used as an x axis, the total number of the corresponding incubated sturgeons in the time is used as a y axis, a dot-shaped graph model is constructed, and through the dot-shaped graph model, the incubation time distribution of the sturgeon roes under the temperature, the water flow speed and the illumination intensity corresponding to the incubation pool can be obtained, all the incubation time distribution is added into a database, the incubation is more refined, the deployment personnel are facilitated, and the working efficiency is improved.
And sixthly, outputting the obtained temperature, water flow speed, dissolved oxygen concentration, illumination intensity and average incubation duration according to the variety of the sturgeon roes, the total number of the roes and the ideal incubation rate, and then inquiring the database of the incubation time distribution obtained in the step two to obtain the incubation time distribution corresponding to the variety of the roes under the temperature, the water flow speed, the dissolved oxygen concentration and the illumination intensity, so that the incubation peak period can be conveniently predicted.
Referring to fig. 2, in this embodiment, a sturgeon hatching system based on a neural network model includes a pre-hatching data acquisition module, a post-hatching data acquisition module, a neural network controller, a hatching sample data acquisition module, a data transmission module, and a user terminal;
the pre-hatching data acquisition module is used for acquiring the serial number of a hatching pond, the type of fish eggs in the hatching pond, the total number of the fish eggs, the temperature, the water flow speed, the dissolved oxygen concentration and the illumination intensity, and acquiring and recording the serial number corresponding to the serial number of the hatching pond;
the post-incubation data acquisition module is used for acquiring the average incubation duration and the total incubation rate of the fish eggs, acquiring and recording and corresponding to the serial number of the incubation pool;
the neural network module is used for constructing a neural network for the pre-incubation data acquisition module and taking the sturgeon roe type, the roe total amount and the incubation rate as input layers and taking the temperature, the water flow speed, the dissolved oxygen concentration, the illumination intensity and the average incubation duration as output layers, and training the neural network until convergence to obtain a neural network model for incubation of corresponding varieties of sturgeon roes;
the hatching sample data acquisition module is used for acquiring parameter data of sturgeon roes to be hatched, wherein the parameter data comprises roe types, roe total number and ideal hatching rate, and the data is input into the neural network model as an input layer;
the user terminal is used for receiving parameter data obtained through the output of the neural network model, and the parameter data comprises temperature, water flow speed, dissolved oxygen concentration, illumination intensity and average incubation duration;
the parameter transmission module is used for transmitting parameter data.
And the neural network module sends the parameter data output by the neural network model to the user terminal through the parameter transmission module.
The parameter conveying module is a wireless transmission module, and the user terminal sends the parameter data of the sturgeon roe to be incubated to the incubation sample data acquisition module at any time through the wireless transmission module.
The sturgeon hatching system based on the neural network model further comprises a control module, the user terminal comprises hatching equipment, the neural network module sends obtained parameter data to the control module through the parameter conveying module, and the control module controls the operation of the hatching equipment according to the received parameter data.
The working principle of the invention is as follows: the invention provides a sturgeon hatching method and system based on a neural network model, wherein the neural network model is constructed through a plurality of experience samples, the ideal hatching rate of different types of sturgeon roes can be obtained through constructing the neural network model, the types, the total amount and the ideal hatching rate of the sturgeon roes to be hatched are input into the neural network model, the most suitable hatching condition can be obtained, the success rate of hatching of the sturgeons is improved, and the automatic control and the comprehensiveness of the hatching method are ensured.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Claims (7)
1. A sturgeon hatching method based on a neural network model is characterized by comprising the following steps:
acquiring data before hatching, wherein the data comprises the species of sturgeon roes, the total number of the roes, the temperature of a hatching pond in which the sturgeon roes are positioned, the water flow speed, the dissolved oxygen concentration and the illumination intensity;
secondly, collecting data after hatching, wherein the data comprises the time for hatching a single sturgeon, the average hatching duration and the hatching rate;
thirdly, constructing a plurality of experience samples through data acquired and counted in the first step and the second step, wherein a single experience sample corresponds to data of a single hatching pool, the experience samples comprise sturgeon roe types, total number of sturgeon roes, culture temperature, water flow speed, dissolved oxygen concentration, illumination intensity, total hatching rate and average incubation time used for incubation of single sturgeon in the corresponding hatching pool, randomly selecting part of experience samples, taking the sturgeon roe types, the total number of roes and the incubation rate as input layers, and taking the temperature, the water flow speed, the dissolved oxygen concentration, the illumination intensity and the average incubation time as output layers, and constructing a neural network initial model;
selecting the rest experience samples as training samples, and training the neural network initial model until convergence to obtain a neural network model for hatching the sturgeon roes of the corresponding variety;
step five, selecting the maximum hatchability of various sturgeon roes from all experience samples, and respectively taking the maximum hatchability as the ideal hatchability of the next sturgeon roe of the same variety;
step six, selecting sturgeon roes with the same variety as the sturgeon roes in the step one for hatching when hatching the next batch of sturgeon roes;
during incubation, recording the species and the total number of roes of the sturgeon in the incubation pool of the corresponding species, inputting the species, the total number and the ideal incubation rate of the roes of the sturgeon into the neural network model, and outputting the temperature, the water flow speed, the dissolved oxygen concentration, the illumination intensity and the average incubation duration which correspond to the incubation of the roes of the sturgeon of the species;
and seventhly, performing condition control and monitoring on the hatching pond where the variety of roes are located according to the temperature, water flow speed, dissolved oxygen concentration, illumination intensity and average hatching duration corresponding to the hatching of the variety of roes of the sturgeon obtained in the sixth step, and ensuring the hatching rate.
2. The method for incubating sturgeons based on neural network model according to claim 1, wherein the first step further comprises: marking the hatching ponds, recording the types and the quantity of the fish eggs in the hatching ponds, ensuring that the types of the fish eggs in the same hatching pond are the same, setting different temperatures, water flow speeds, dissolved oxygen concentrations and illumination intensities for a plurality of hatching ponds for hatching the fish eggs of the same type so as to form a plurality of sample data, recording the condition data of each hatching pond, and ensuring that the hatching is carried out under a constant condition.
3. The method for incubating sturgeons based on neural network model according to claim 1, wherein the second step further comprises: the time data are recorded from the beginning of the hatching of the roes until the hatching of the roes, the time for hatching the single sturgeon in the single hatching pond is recorded, the average hatching time is calculated, the first sturgeon hatching in the hatching pond is started successfully, the sturgeon roes remaining in the hatching pond cannot be hatched successfully through observation and monitoring judgment, the hatching rate of the sturgeon roes in the single hatching pond is recorded by taking the hatching pond as a unit, and the hatching rate is the ratio of the total hatching number to the total roe number.
4. A sturgeon hatching system based on a neural network model is characterized by comprising a pre-hatching data acquisition module, a post-hatching data acquisition module, a neural network controller, a hatching sample data acquisition module, a data transmission module and a user terminal;
the pre-hatching data acquisition module is used for acquiring the serial number of a hatching pond, the type of fish eggs in the hatching pond, the total number of the fish eggs, the temperature, the water flow speed, the dissolved oxygen concentration and the illumination intensity, and acquiring and recording the serial number corresponding to the serial number of the hatching pond;
the post-incubation data acquisition module is used for acquiring the average incubation duration and the total incubation rate of the fish eggs, acquiring and recording and corresponding to the serial number of the incubation pool;
the neural network module is used for constructing a neural network for the pre-incubation data acquisition module and taking the sturgeon roe type, the roe total amount and the incubation rate as input layers and taking the temperature, the water flow speed, the dissolved oxygen concentration, the illumination intensity and the average incubation duration as output layers, and training the neural network until convergence to obtain a neural network model for incubation of corresponding varieties of sturgeon roes;
the hatching sample data acquisition module is used for acquiring parameter data of sturgeon roes to be hatched, wherein the parameter data comprises roe types, roe total number and ideal hatching rate, and the data is input into the neural network model as an input layer;
the user terminal is used for receiving parameter data obtained through the output of the neural network model, and the parameter data comprises temperature, water flow speed, dissolved oxygen concentration, illumination intensity and average incubation duration;
the parameter transmission module is used for transmitting parameter data.
5. The sturgeon hatching system based on the neural network model according to claim 4, wherein the neural network module sends parameter data output by the neural network model to the user terminal through the parameter transmission module.
6. The sturgeon hatching system based on the neural network model according to claim 5, wherein the parameter transmission module is a wireless transmission module, and the user terminal sends the parameter data of the sturgeon roe to be hatched to the hatching sample data collection module at any time through the wireless transmission module.
7. The neural network model-based sturgeon hatching system according to claim 4, wherein the neural network model-based sturgeon hatching system further comprises a control module, the user terminal comprises hatching equipment, the neural network module sends the obtained parameter data to the control module through the parameter transmission module, and the control module controls the operation of the hatching equipment according to the received parameter data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111238105.7A CN114009380A (en) | 2021-10-25 | 2021-10-25 | Sturgeon hatching method and system based on neural network model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111238105.7A CN114009380A (en) | 2021-10-25 | 2021-10-25 | Sturgeon hatching method and system based on neural network model |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114009380A true CN114009380A (en) | 2022-02-08 |
Family
ID=80057308
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111238105.7A Pending CN114009380A (en) | 2021-10-25 | 2021-10-25 | Sturgeon hatching method and system based on neural network model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114009380A (en) |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US3406662A (en) * | 1965-08-20 | 1968-10-22 | Nor Laks O C Vik & K O Vik | Method for breeding fish, such as salmon or sea trout |
US20060048714A1 (en) * | 2002-05-17 | 2006-03-09 | Shigeki Kamigauchi | Method and system for breeding fry |
CN101796928A (en) * | 2009-07-14 | 2010-08-11 | 大连水产学院 | Method for predicting effect of water quality parameters of aquaculture water on growth conditions of aquaculture living beings |
CN103065033A (en) * | 2012-01-11 | 2013-04-24 | 戴会超 | Reservoir ecological scheduling method giving consideration to Chinese sturgeon reproductive demands |
CN105637540A (en) * | 2013-10-08 | 2016-06-01 | 谷歌公司 | Methods and apparatus for reinforcement learning |
CN106295843A (en) * | 2015-06-10 | 2017-01-04 | 上海海洋大学 | A kind of northwest Pacific saury resource magnitude of recruitment Forecasting Methodology and application |
CN106719170A (en) * | 2016-12-30 | 2017-05-31 | 贵州锦润水产品有限责任公司 | A kind of sturgeon hatching method |
CN207252566U (en) * | 2017-09-15 | 2018-04-20 | 天津蕴华农业科技发展有限公司 | A kind of new artemia hatching apparatus |
US20180213753A1 (en) * | 2017-01-31 | 2018-08-02 | Florida Atlantic University Board Of Trustees | Systems and methods for larval fish enumeration and growth monitoring |
CN110226561A (en) * | 2019-06-14 | 2019-09-13 | 江苏财经职业技术学院 | The method of low cost cultivation laying hen based on big data |
CN110476839A (en) * | 2019-07-24 | 2019-11-22 | 中国农业大学 | A kind of optimization regulating method and system based on fish growth |
CN110771542A (en) * | 2019-12-05 | 2020-02-11 | 南京坤泰农业发展有限公司 | Breeding method for improving fry hatchability |
CN111406693A (en) * | 2020-04-23 | 2020-07-14 | 上海海洋大学 | Marine ranch fishery resource maintenance effect evaluation method based on bionic sea eels |
CN112734014A (en) * | 2021-01-12 | 2021-04-30 | 山东大学 | Experience playback sampling reinforcement learning method and system based on confidence upper bound thought |
KR20210001032U (en) * | 2019-11-04 | 2021-05-12 | 허수정 | Fishbowl that judge the type and number of fish and automatically adjusts the temperature of the water and supplies feed |
CN113179981A (en) * | 2021-04-26 | 2021-07-30 | 新疆爱华盈通信息技术有限公司 | Apartment crab auxiliary breeding method, system and device based on deep learning |
-
2021
- 2021-10-25 CN CN202111238105.7A patent/CN114009380A/en active Pending
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US3406662A (en) * | 1965-08-20 | 1968-10-22 | Nor Laks O C Vik & K O Vik | Method for breeding fish, such as salmon or sea trout |
US20060048714A1 (en) * | 2002-05-17 | 2006-03-09 | Shigeki Kamigauchi | Method and system for breeding fry |
CN101796928A (en) * | 2009-07-14 | 2010-08-11 | 大连水产学院 | Method for predicting effect of water quality parameters of aquaculture water on growth conditions of aquaculture living beings |
CN103065033A (en) * | 2012-01-11 | 2013-04-24 | 戴会超 | Reservoir ecological scheduling method giving consideration to Chinese sturgeon reproductive demands |
CN105637540A (en) * | 2013-10-08 | 2016-06-01 | 谷歌公司 | Methods and apparatus for reinforcement learning |
CN106295843A (en) * | 2015-06-10 | 2017-01-04 | 上海海洋大学 | A kind of northwest Pacific saury resource magnitude of recruitment Forecasting Methodology and application |
CN106719170A (en) * | 2016-12-30 | 2017-05-31 | 贵州锦润水产品有限责任公司 | A kind of sturgeon hatching method |
US20180213753A1 (en) * | 2017-01-31 | 2018-08-02 | Florida Atlantic University Board Of Trustees | Systems and methods for larval fish enumeration and growth monitoring |
CN207252566U (en) * | 2017-09-15 | 2018-04-20 | 天津蕴华农业科技发展有限公司 | A kind of new artemia hatching apparatus |
CN110226561A (en) * | 2019-06-14 | 2019-09-13 | 江苏财经职业技术学院 | The method of low cost cultivation laying hen based on big data |
CN110476839A (en) * | 2019-07-24 | 2019-11-22 | 中国农业大学 | A kind of optimization regulating method and system based on fish growth |
KR20210001032U (en) * | 2019-11-04 | 2021-05-12 | 허수정 | Fishbowl that judge the type and number of fish and automatically adjusts the temperature of the water and supplies feed |
CN110771542A (en) * | 2019-12-05 | 2020-02-11 | 南京坤泰农业发展有限公司 | Breeding method for improving fry hatchability |
CN111406693A (en) * | 2020-04-23 | 2020-07-14 | 上海海洋大学 | Marine ranch fishery resource maintenance effect evaluation method based on bionic sea eels |
CN112734014A (en) * | 2021-01-12 | 2021-04-30 | 山东大学 | Experience playback sampling reinforcement learning method and system based on confidence upper bound thought |
CN113179981A (en) * | 2021-04-26 | 2021-07-30 | 新疆爱华盈通信息技术有限公司 | Apartment crab auxiliary breeding method, system and device based on deep learning |
Non-Patent Citations (1)
Title |
---|
农业部人事劳动司: "农村社会调查研究方法", 中国农业出版社 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109090004B (en) | Block type bionic pond propagation seedling raising equipment and method | |
CN100496232C (en) | Novel selecting and breeding method for gift tilapia | |
CN101669452A (en) | Mimic ecological propagation method for breeding parent fish of American hilsa herring | |
CN104686430A (en) | Prawn low dissolved oxygen resistance family selection method | |
CN102487866B (en) | Large-scale natural propagation method for artificially culturing siganus guttatus parents | |
CN108235965A (en) | It controllably accelerates the ripening in a kind of egg-shaped pompano parent population room oviposition method | |
CN106489801A (en) | A kind of half pierces thick lip fish artificial seedling rearing's method | |
CN101664006A (en) | Artificial breeding technique of Sarotherodon sp | |
CN102960280A (en) | Method for cultivating super-male fish and fully-male fish of yellow catfish by genetic method | |
CN101664005A (en) | Industrial and artificial breeding method of Sarotherodon sp | |
CN108029903B (en) | Mixed feed of fungus grass and ganoderma lucidum fungus chaff for feeding yellow mealworm adults and preparation method | |
CN114009380A (en) | Sturgeon hatching method and system based on neural network model | |
CN111165401B (en) | Quick and efficient breeding method for tilapia mossambica | |
CN106305522B (en) | A kind of artificial raise seedling method of more precious fishes | |
CN116649263A (en) | Three-stage hanging water culture system and method for slimming fish | |
CN109287533B (en) | Large-scale breeding method and equipment for hybrid scallop offspring seeds | |
CN114885870B (en) | Spawning induction method for sipunculus australis | |
CN103814853B (en) | A kind of selection of import prawn natural selection | |
CN107926770A (en) | Epinephelus akaara and epinephelus lanceolatus fish distant hybrid breeding method | |
Attramadal et al. | A rotifer cultivating method resulting in high production and stability | |
RU2203541C1 (en) | Method for raising sturgeon fishes at multiple yield of roe under captivity conditions | |
CN113881569A (en) | Method for cultivating seawater chlorella in cement pond and method for cultivating grouper fries | |
CN109349170B (en) | Artificial breeding method for cupfish with round mouth | |
CN208987556U (en) | A kind of block type Ecology pond breeding and seedling equipment | |
CN105145329A (en) | Method for promoting concentrated maturity of conchospores of porphyra haitanensis |
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 |
Application publication date: 20220208 |
|
RJ01 | Rejection of invention patent application after publication |