CN117994064A - Carassius auratus breeding whole-process monitoring method and system based on intelligent water quality perception - Google Patents
Carassius auratus breeding whole-process monitoring method and system based on intelligent water quality perception Download PDFInfo
- Publication number
- CN117994064A CN117994064A CN202410404533.XA CN202410404533A CN117994064A CN 117994064 A CN117994064 A CN 117994064A CN 202410404533 A CN202410404533 A CN 202410404533A CN 117994064 A CN117994064 A CN 117994064A
- Authority
- CN
- China
- Prior art keywords
- water quality
- breeding
- crucian
- parameters
- different
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 323
- 238000009395 breeding Methods 0.000 title claims abstract description 307
- 230000001488 breeding effect Effects 0.000 title claims abstract description 307
- 238000012544 monitoring process Methods 0.000 title claims abstract description 159
- 238000000034 method Methods 0.000 title claims abstract description 92
- 230000008447 perception Effects 0.000 title claims abstract description 34
- 241000252229 Carassius auratus Species 0.000 title description 2
- 230000003044 adaptive effect Effects 0.000 claims abstract description 32
- 230000008569 process Effects 0.000 claims abstract description 31
- 238000012216 screening Methods 0.000 claims abstract description 23
- 230000004083 survival effect Effects 0.000 claims description 17
- 230000011218 segmentation Effects 0.000 claims description 11
- 238000009360 aquaculture Methods 0.000 claims description 10
- 244000144974 aquaculture Species 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 9
- 230000007246 mechanism Effects 0.000 claims description 8
- 201000010099 disease Diseases 0.000 claims description 5
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 238000000513 principal component analysis Methods 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 230000004931 aggregating effect Effects 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 3
- 238000005192 partition Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 2
- 238000003860 storage Methods 0.000 description 8
- 241000251468 Actinopterygii Species 0.000 description 4
- 230000012447 hatching Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 235000015097 nutrients Nutrition 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 241000252233 Cyprinus carpio Species 0.000 description 1
- 241000238631 Hexapoda Species 0.000 description 1
- 206010021143 Hypoxia Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000002790 cross-validation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 235000013601 eggs Nutrition 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000035558 fertility Effects 0.000 description 1
- 230000004720 fertilization Effects 0.000 description 1
- 208000010824 fish disease Diseases 0.000 description 1
- 230000007954 hypoxia Effects 0.000 description 1
- 235000013372 meat Nutrition 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000003643 water by type Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/18—Water
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
- G06N3/0455—Auto-encoder networks; Encoder-decoder networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0475—Generative networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06N3/094—Adversarial learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/02—Knowledge representation; Symbolic representation
- G06N5/022—Knowledge engineering; Knowledge acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06316—Sequencing of tasks or work
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Chemical & Material Sciences (AREA)
- Environmental Sciences (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Development Economics (AREA)
- Biodiversity & Conservation Biology (AREA)
- Zoology (AREA)
Abstract
The invention discloses a crucian breeding whole-process monitoring method and system based on intelligent perception of water quality, comprising the following steps: acquiring a breeding workflow of current crucian breeding, matching the current crucian breeding workflow according to historical water quality monitoring parameters, and updating data; screening high-correlation water quality parameters in different breeding workflow subsections according to breeding characteristics, and setting corresponding key water quality indexes; extracting water quality monitoring parameters in different breeding stages through key water quality indexes, constructing an adaptive water quality sequence for normal breeding of crucian, carrying out fine granularity analysis on the extracted water quality monitoring parameter sequence, and obtaining deviation from the adaptive water quality sequence; and generating early warning of the crucian breeding process according to the deviation. According to the method, the high-correlation water quality factors of different stages in the crucian breeding period are screened for analysis, so that the redundancy of monitoring data is reduced, the adaptive fine granularity division is distributed for different breeding stages, and the monitoring efficiency and the accuracy are improved.
Description
Technical Field
The invention relates to the technical field of crucian breeding, in particular to a method and a system for monitoring the whole process of crucian breeding based on intelligent perception of water quality.
Background
The crucian belongs to the carp shape, the fish meat is delicious in taste and rich in nutrition, and is one of the famous high-quality edible fish in China, and the crucian is deeply favored by consumers. The crucian belongs to omnivorous fishes, has the advantages of low temperature resistance, hypoxia resistance and strong fertility, mainly feeds compound feed and aquatic insects, zooplankton and the like under natural conditions and artificial culture conditions, has culture in various places throughout the country, and has various culture modes, so that the demand of crucian fries is increased year by year. The method for breeding the crucian fries in the prior art comprises the steps of hatching the crucian eggs in a cement pond or a hatching barrel, and then carrying out water spray cultivation in the pond, which is the most common and effective mode nowadays.
The breeding process of crucian needs to ensure water quality, nutrient substances and habitat. The deep processed feed is put in the cultivation process, after the feed is soaked in water, the residual feed, excrement and cadaver are spoiled and decomposed, so that the water quality is bad, nutrient elements N, P and the like in the water are converted into harmful substances, the young crucian is caused to be ill and dead, and the survival rate of the crucian in the cultivation process is reduced. The quality of the water quality is directly related to the healthy growth and even the success or failure of the cultivation in the crucian breeding process, so that the effective data information of the cultivation water body is collected through intelligent water quality sensing to analyze the change rule of the water quality parameters, basic data is provided for the artificial, semi-automatic and automatic breeding and cultivation of the crucian, further management is perfected, and the yield and quality of the crucian are improved.
Disclosure of Invention
In order to solve the technical problems, the invention provides a crucian breeding whole-flow monitoring method and system based on intelligent water quality perception.
The invention provides a crucian breeding whole-process monitoring method based on intelligent perception of water quality, which comprises the following steps:
Acquiring a current breeding workflow for crucian breeding, acquiring water quality monitoring parameters of a target breeding water area through sensing of the Internet of things, and matching the historical water quality monitoring parameters with the breeding workflow to generate a breeding workflow with updated data;
Dividing the updated breeding workflow by utilizing different breeding stages, screening high-correlation water quality parameters in different breeding workflow subsections according to breeding characteristics, and setting key water quality indexes of different breeding stages according to the high-correlation water quality parameters;
extracting water quality monitoring parameters in different breeding stages through the key water quality indexes, constructing an adaptive water quality sequence for normal breeding of crucian, carrying out fine granularity analysis on the extracted water quality monitoring parameter sequence, and obtaining deviation from the adaptive water quality sequence;
And carrying out early warning on the crucian breeding process according to the deviation, generating early warning information of different grades, and carrying out water quality regulation and control on the target aquaculture water area through the early warning information.
In this scheme, according to historical water quality monitoring parameter and breeding the workflow and match, the workflow of breeding after the data update is generated, specifically does:
Obtaining crucian breeding data of a target breeding water area in a preset time step, preprocessing the crucian breeding data, obtaining a marked stage of crucian breeding, clustering the preprocessed crucian breeding data, and obtaining a breeding data set of the marked stage according to a clustering result;
Extracting procedure characteristics according to the breeding data set, constructing a search tag by utilizing the procedure characteristics to search the crucian breeding examples, calculating according to similarity to obtain a subset of the crucian breeding examples meeting preset standards, and aggregating different crucian breeding examples to obtain a flow rule of the current breeding measure;
creating a breeding workflow for current crucian breeding based on the breeding data set generated by the process rule driving clustering, and expanding the breeding workflow according to updating of the crucian breeding data;
Performing water quality meshing monitoring on a target aquaculture water area by combining wireless communication with sensor information acquisition, sensing water quality monitoring parameters of different partitions, and acquiring historical water quality monitoring parameters in a preset time step;
And matching the historical water quality monitoring parameters with the breeding workflow, setting data indexes according to flow nodes in the breeding workflow, and interpolating the historical water quality monitoring data into the breeding workflow by utilizing the data indexes to generate the breeding workflow with updated data.
In the scheme, high-correlation water quality parameters are screened according to breeding characteristics in different breeding workflow subsections, and key water quality indexes of different breeding stages are set according to the high-correlation water quality parameters, specifically:
Preliminary segmentation marking is carried out in the updated breeding workflow by utilizing a marking stage, neighborhood regions are preset at different primary segmentation marking positions, flow nodes in the neighborhood regions are selected, and a stage center is set based on the average value corresponding to the flow nodes of each segment after the preliminary segmentation;
Using Euclidean distance to configure membership function, judging Euclidean distance between a flow node in a neighborhood region and the center of two adjacent stages, and when any Euclidean distance is larger than or equal to a preset distance threshold value, attributing the flow node to a breeding stage with high membership;
When the two Euclidean distances are smaller than a preset distance threshold value, respectively attributing the flow nodes to two adjacent breeding stages, and after the flow nodes in all primary segmentation marking position neighborhood regions are divided, acquiring the updated division result of the breeding workflow;
Extracting breeding characteristics according to flow nodes in different breeding workflow subsections, calculating pearson correlation coefficients in water quality monitoring parameters by using the breeding characteristics, and screening the water quality monitoring parameters of the different breeding workflow subsections by using the pearson correlation coefficients;
Constructing a crucian survival rate prediction model, training the crucian survival rate prediction model by using water quality monitoring parameters of different breeding workflow subsections, reading corresponding prediction accuracy, taking maximum prediction accuracy as a target, and evaluating the importance of the water quality monitoring parameters by using fold cross verification;
Sequencing the water quality monitoring parameters of different breeding workflow subsections by using the importance degree, and selecting a preset number of high-association water quality parameters as key water quality indexes.
In the scheme, the water quality monitoring parameters of different breeding stages are extracted through the key water quality indexes, and an adaptive water quality sequence for normal breeding of crucian is constructed, specifically:
acquiring key water quality indexes corresponding to different breeding workflow subsections, extracting parameters from historical water quality monitoring parameters according to the key water quality indexes, and screening the parameters according to the survival rate of the corresponding crucian in the extracted parameters;
Acquiring the parameter scale under the key water quality index, screening the key water quality index smaller than the preset scale for marking, introducing the parameter corresponding to the marked key water quality index into a self-encoder network to acquire potential characteristic distribution, and introducing an countermeasure mechanism;
Taking an encoder part of a self-encoder network as potential feature distribution of a generator learning parameter, acquiring reconstruction data of the parameter, mapping the reconstruction data to the same position, adding a discriminator in a potential feature layer, and punishing the reconstruction data with overlarge potential feature space position distribution deviation;
expanding parameters corresponding to the marked key water quality indexes by using iterative training of the countermeasure mechanism, stopping iteration when the parameter scale accords with the preset scale, and outputting the parameters corresponding to the marked key water quality indexes after expansion;
And constructing proper water quality sequences for normal breeding of crucian in different breeding stages by using parameters obtained by parameter screening and data expansion.
In the scheme, fine granularity analysis is carried out on the extracted water quality monitoring parameter sequence, and deviation between the extracted water quality monitoring parameter sequence and an appropriate water quality sequence is obtained, specifically:
Extracting water quality monitoring parameters of different breeding stages according to the key water quality indexes, and generating water quality monitoring parameter sequences of different breeding stages by combining the monitoring time;
Generating initial weights of different breeding stages according to the historical average crucian survival rate pair, extracting diseases and accident instances of the different breeding stages according to the historical crucian breeding data, and calculating accident rates of the different breeding stages;
Determining fine granularity division degrees of different breeding stages by combining the initial weight with the accident rate, and dividing the water quality monitoring parameter sequence according to the fine granularity division degrees of different breeding stages to obtain a corresponding water quality monitoring parameter fine granularity sequence;
And calling the adaptive water quality sequence to generate a corresponding adaptive water quality fine granularity sequence, calculating the mean square distance between the water quality monitoring parameter fine granularity sequence and the adaptive water quality fine granularity sequence, and generating deviation according to the mean square distance sequence.
In this scheme, carry out the early warning of crucian breeding process according to the deviation, generate the early warning information of different grades, carry out the quality control in target aquaculture waters through the early warning information, specifically do:
The method comprises the steps of presetting deviation threshold intervals, matching early warning levels for different preset deviation threshold intervals, obtaining deviation threshold intervals where deviation falls, determining corresponding early warning levels, generating early warning information, and sending and visually displaying the early warning information according to a preset mode;
When the early warning level is greater than a preset level threshold, acquiring the maximum mean square distance between the fine granularity sequence of the water quality monitoring parameter and the proper water quality fine granularity sequence, and carrying out water quality monitoring parameter tracing according to the timestamp of the position where the maximum mean square distance is located;
and carrying out principal component analysis according to the traced water quality monitoring parameters, realizing tracing of early warning, connecting a water quality regulation and control measure related knowledge graph through a tracing result, and generating the water quality regulation and control measure based on the cultivation characteristics of the target cultivation water area.
The invention also provides a crucian breeding whole-process monitoring system based on intelligent perception of water quality, which comprises: the intelligent water quality perception-based crucian breeding full-flow monitoring method comprises a memory and a processor, wherein the memory comprises a water quality intelligent perception-based crucian breeding full-flow monitoring method program, and the following steps are realized when the water quality intelligent perception-based crucian breeding full-flow monitoring method program is executed by the processor:
Acquiring a current breeding workflow for crucian breeding, acquiring water quality monitoring parameters of a target breeding water area through sensing of the Internet of things, and matching the historical water quality monitoring parameters with the breeding workflow to generate a breeding workflow with updated data;
Dividing the updated breeding workflow by utilizing different breeding stages, screening high-correlation water quality parameters in different breeding workflow subsections according to breeding characteristics, and setting key water quality indexes of different breeding stages according to the high-correlation water quality parameters;
extracting water quality monitoring parameters in different breeding stages through the key water quality indexes, constructing an adaptive water quality sequence for normal breeding of crucian, carrying out fine granularity analysis on the extracted water quality monitoring parameter sequence, and obtaining deviation from the adaptive water quality sequence;
And carrying out early warning on the crucian breeding process according to the deviation, generating early warning information of different grades, and carrying out water quality regulation and control on the target aquaculture water area through the early warning information.
The invention discloses a crucian breeding whole-process monitoring method and system based on intelligent perception of water quality, comprising the following steps: acquiring a breeding workflow of current crucian breeding, matching the current crucian breeding workflow according to historical water quality monitoring parameters, and updating data; screening high-correlation water quality parameters in different breeding workflow subsections according to breeding characteristics, and setting corresponding key water quality indexes; extracting water quality monitoring parameters in different breeding stages through key water quality indexes, constructing an adaptive water quality sequence for normal breeding of crucian, carrying out fine granularity analysis on the extracted water quality monitoring parameter sequence, and obtaining deviation from the adaptive water quality sequence; and generating early warning of the crucian breeding process according to the deviation. According to the method, the high-correlation water quality factors of different stages in the crucian breeding period are screened for analysis, so that the redundancy of monitoring data is reduced, the adaptive fine granularity division is distributed for different breeding stages, and the monitoring efficiency and the accuracy are improved.
Drawings
FIG. 1 shows a flow chart of a crucian breeding whole-flow monitoring method based on intelligent perception of water quality;
FIG. 2 shows a flow chart of the present invention for setting key water quality indicators for different stages of breeding;
FIG. 3 shows a flow chart of the fine-grained analysis of a water quality monitoring parameter sequence in accordance with the present invention;
Fig. 4 shows a block diagram of the crucian breeding whole-process monitoring system based on intelligent perception of water quality.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
Fig. 1 shows a flow chart of the method for monitoring the whole process of crucian breeding based on intelligent perception of water quality.
As shown in fig. 1, the first aspect of the present invention provides a method for monitoring the overall process of crucian breeding based on intelligent perception of water quality, comprising:
S102, acquiring a breeding workflow of current crucian breeding, acquiring water quality monitoring parameters of a target breeding water area through sensing of the Internet of things, and matching the water quality monitoring parameters with the breeding workflow according to historical water quality monitoring parameters to generate a breeding workflow with updated data;
s104, dividing the updated breeding workflow by utilizing different breeding stages, screening high-correlation water quality parameters in different breeding workflow subsections according to breeding characteristics, and setting key water quality indexes of different breeding stages according to the high-correlation water quality parameters;
S106, extracting water quality monitoring parameters in different breeding stages through the key water quality indexes, constructing an adaptive water quality sequence for normal breeding of crucian, carrying out fine granularity analysis on the extracted water quality monitoring parameter sequence, and obtaining deviation from the adaptive water quality sequence;
s108, carrying out early warning on the crucian breeding process according to the deviation, generating early warning information of different grades, and carrying out water quality regulation and control on the target aquaculture water area through the early warning information.
The method comprises the steps of obtaining crucian breeding data of a target breeding water area in a preset time step, including breeding mode, breeding data (induced spawning, fertilization, hatching and the like), preprocessing the crucian breeding data in a data cleaning, dimension reduction and the like, obtaining a marked stage of crucian breeding, clustering the preprocessed crucian breeding data, and obtaining a breeding data set of the marked stage according to a clustering result, wherein the marked stage selects one or more of a spawning period, a hatching period and a young fish period; extracting procedure characteristics according to the breeding data set, constructing a search tag by utilizing the procedure characteristics to search the crucian breeding examples, calculating according to similarity to obtain a subset of the crucian breeding examples meeting preset standards, and aggregating different crucian breeding examples to obtain a flow rule of the current breeding measure; creating a breeding workflow for current crucian breeding based on the breeding data set generated by the process rule driving clustering, and expanding the breeding workflow according to updating of the crucian breeding data; performing water quality meshing monitoring on a target aquaculture water area by combining wireless communication with sensor information acquisition, sensing water quality monitoring parameters of different partitions, and acquiring historical water quality monitoring parameters in a preset time step; and matching the historical water quality monitoring parameters with the breeding workflow, setting data indexes according to flow nodes in the breeding workflow, and interpolating the historical water quality monitoring data into the breeding workflow by utilizing the data indexes to generate the breeding workflow with updated data.
FIG. 2 shows a flow chart of the present invention for setting key water quality indicators for different stages of breeding.
According to the embodiment of the invention, the high-correlation water quality parameters are screened in different sub-sections of the breeding workflow according to the breeding characteristics, and key water quality indexes of different breeding stages are set according to the high-correlation water quality parameters, specifically:
S202, performing preliminary segmentation marking in the updated breeding workflow by using a landmark stage, presetting neighborhood regions at different positions of the preliminary segmentation marking, selecting flow nodes in the neighborhood regions, and setting a stage center based on a mean value corresponding to the flow nodes of each segment after the preliminary segmentation;
S204, using Euclidean distance configuration membership function to judge Euclidean distance between a flow node in a neighborhood region and the center of two adjacent stages, and when any Euclidean distance is larger than or equal to a preset distance threshold value, attributing the flow node to a breeding stage with high membership;
S206, when the two Euclidean distances are smaller than a preset distance threshold, respectively attributing the flow nodes to two adjacent breeding stages, and after the flow nodes in all primary segment marking position neighborhood regions are divided, acquiring the updated division result of the breeding workflow;
S208, extracting breeding characteristics according to flow nodes in different breeding workflow subsections, calculating pearson correlation coefficients in water quality monitoring parameters by using the breeding characteristics, and screening the water quality monitoring parameters of the different breeding workflow subsections by using the pearson correlation coefficients;
s210, constructing a crucian survival rate prediction model, training the crucian survival rate prediction model by using water quality monitoring parameters of different breeding workflow subsections, reading corresponding prediction accuracy, and evaluating the importance of the water quality monitoring parameters by using fold cross verification with the aim of maximizing the prediction accuracy;
s212, sorting the water quality monitoring parameters of different breeding workflow subsections by using the importance degree, and selecting a preset number of high-correlation water quality parameters as key water quality indexes.
It should be noted that, because the preliminary division of the landmark stage cannot guarantee the accurate clustering of the data, and part of process nodes are involved in adjacent breeding stages, a neighborhood region is preset at different primary segment marking positions, when the process nodes in the neighborhood region meet the hard clustering condition, i.e. any distance is greater than or equal to a preset distance threshold, the attribution degree is calculated according to the Euclidean distance, the closer the distance is, the greater the attribution degree is, and the process nodes are divided into breeding stages with larger attribution degrees; when the process nodes in the domain interval meet the soft clustering condition, namely, the two Euclidean distances are smaller than the preset distance threshold value, the process nodes are divided into two adjacent breeding stages, so that the division of the breeding stages is more in line with the actual situation, and the accuracy of subsequent anomaly monitoring is improved.
According to the deep learning methods such as LSTM network and BP neural network, a crucian survival rate prediction model is built, the importance evaluation of water quality monitoring parameters is preferably carried out by utilizing S-fold cross validation with the aim of maximizing prediction accuracy, the water quality monitoring parameters are equally divided into S subsets, each subset is alternately used as a verification set, the rest is used as a training set, the water quality monitoring parameters are evaluated according to the accuracy of the S crucian survival rate prediction models obtained through training, the influence of randomness on the results is reduced, and the occurrence of the over-fitting phenomenon is avoided.
FIG. 3 shows a flow chart of the fine-grained analysis of a water quality monitoring parameter sequence in accordance with the present invention.
According to the embodiment of the invention, the extracted water quality monitoring parameter sequence is subjected to fine granularity analysis, and deviation from an appropriate water quality sequence is obtained, specifically:
s302, extracting water quality monitoring parameters of different breeding stages according to key water quality indexes, and generating water quality monitoring parameter sequences of different breeding stages by combining monitoring time;
S304, generating initial weights of different breeding stages according to the historical average crucian survival rate pair, extracting diseases and accident instances of the different breeding stages according to the historical crucian breeding data, and calculating accident rates of the different breeding stages;
S306, determining the fine granularity division degree of different breeding stages by combining the initial weight with the accident rate, and dividing the water quality monitoring parameter sequence according to the fine granularity division degree of different breeding stages to obtain a corresponding water quality monitoring parameter fine granularity sequence;
s308, calling the proper water quality sequence to generate a corresponding proper water quality fine granularity sequence, calculating the mean square distance between the water quality monitoring parameter fine granularity sequence and the proper water quality fine granularity sequence, and generating deviation according to the mean square distance sequence.
It should be noted that, setting adaptive fine granularity division degree for different breeding stages, effectively capturing parameter variation of a water quality monitoring parameter sequence, generating fine granularity division degree according to diseases and accident instances of different breeding stages, if the occurrence times of fish diseases, natural disaster accidents and the like in the current breeding stage are more, the larger the fine granularity division degree is, the higher the corresponding division density degree is, and realizing high-frequency fine monitoring in the breeding stage.
Acquiring key water quality indexes corresponding to different breeding workflow subsections, extracting parameters from historical water quality monitoring parameters according to the key water quality indexes, and screening the parameters according to the survival rate of the corresponding crucian in the extracted parameters; acquiring the parameter scale under the key water quality index, screening the key water quality index smaller than the preset scale for marking, introducing the parameter corresponding to the marked key water quality index into a self-encoder network to acquire potential characteristic distribution, and introducing an countermeasure mechanism; taking an encoder part of a self-encoder network as potential feature distribution of a generator learning parameter, acquiring reconstruction data of the parameter and mapping the reconstruction data to the same position, wherein the encoder part actively learns the potential feature distribution of the parameter, generating potential features through sampling, and increasing the diversity of generated samples by sampling noise; adding a discriminator in the potential feature layer, and punishing reconstruction data with overlarge potential feature space position distribution deviation; and (3) expanding parameters corresponding to the marked key water quality indexes by using iterative training of the countermeasure mechanism, stopping iteration when the parameter scale accords with the preset scale, outputting the parameters corresponding to the marked key water quality indexes after expansion, solving the problem of reduced monitoring accuracy caused by unbalanced data, and improving the robustness of crucian breeding monitoring. And constructing proper water quality sequences for normal breeding of crucian in different breeding stages by using parameters obtained by parameter screening and data expansion.
The method comprises the steps that a deviation threshold value interval is preset, early warning levels are matched for different preset deviation threshold value intervals, the corresponding early warning level is determined by obtaining the deviation threshold value interval where the deviation falls, and early warning information is generated and sent and visually displayed according to a preset mode; when the early warning level is greater than a preset level threshold, acquiring the maximum mean square distance between the fine granularity sequence of the water quality monitoring parameter and the proper water quality fine granularity sequence, and carrying out water quality monitoring parameter tracing according to the timestamp of the position where the maximum mean square distance is located; and carrying out principal component analysis according to the traced water quality monitoring parameters, realizing tracing of early warning, connecting a water quality regulation and control measure related knowledge graph through a tracing result, and generating the water quality regulation and control measure based on the cultivation characteristics of the target cultivation water area.
Fig. 4 shows a block diagram of the crucian breeding whole-process monitoring system based on intelligent perception of water quality.
The second aspect of the invention also provides a crucian breeding whole-process monitoring system 4 based on intelligent perception of water quality, which comprises: the device comprises a memory 41 and a processor 42, wherein the memory comprises a crucian breeding whole-flow monitoring method program based on intelligent water quality perception, and the method realizes the following steps when being executed by the processor:
Acquiring a current breeding workflow for crucian breeding, acquiring water quality monitoring parameters of a target breeding water area through sensing of the Internet of things, and matching the historical water quality monitoring parameters with the breeding workflow to generate a breeding workflow with updated data;
Dividing the updated breeding workflow by utilizing different breeding stages, screening high-correlation water quality parameters in different breeding workflow subsections according to breeding characteristics, and setting key water quality indexes of different breeding stages according to the high-correlation water quality parameters;
extracting water quality monitoring parameters in different breeding stages through the key water quality indexes, constructing an adaptive water quality sequence for normal breeding of crucian, carrying out fine granularity analysis on the extracted water quality monitoring parameter sequence, and obtaining deviation from the adaptive water quality sequence;
And carrying out early warning on the crucian breeding process according to the deviation, generating early warning information of different grades, and carrying out water quality regulation and control on the target aquaculture water area through the early warning information.
The third aspect of the invention also provides a computer readable storage medium, which comprises a crucian breeding whole-process monitoring method program based on intelligent water quality perception, wherein when the crucian breeding whole-process monitoring method program based on intelligent water quality perception is executed by a processor, the steps of the crucian breeding whole-process monitoring method based on intelligent water quality perception are realized.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or optical disk, or the like, which can store program codes.
Or the above-described integrated units of the invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. The crucian breeding whole-process monitoring method based on intelligent perception of water quality is characterized by comprising the following steps of:
Acquiring a current breeding workflow for crucian breeding, acquiring water quality monitoring parameters of a target breeding water area through sensing of the Internet of things, and matching the historical water quality monitoring parameters with the breeding workflow to generate a breeding workflow with updated data;
Dividing the updated breeding workflow by utilizing different breeding stages, screening high-correlation water quality parameters in different breeding workflow subsections according to breeding characteristics, and setting key water quality indexes of different breeding stages according to the high-correlation water quality parameters;
extracting water quality monitoring parameters in different breeding stages through the key water quality indexes, constructing an adaptive water quality sequence for normal breeding of crucian, carrying out fine granularity analysis on the extracted water quality monitoring parameter sequence, and obtaining deviation from the adaptive water quality sequence;
And carrying out early warning on the crucian breeding process according to the deviation, generating early warning information of different grades, and carrying out water quality regulation and control on the target aquaculture water area through the early warning information.
2. The method for monitoring the complete process of crucian breeding based on intelligent perception of water quality according to claim 1, wherein the method is characterized in that the method is used for matching with a breeding workflow according to historical water quality monitoring parameters to generate a breeding workflow with updated data, and specifically comprises the following steps:
Obtaining crucian breeding data of a target breeding water area in a preset time step, preprocessing the crucian breeding data, obtaining a marked stage of crucian breeding, clustering the preprocessed crucian breeding data, and obtaining a breeding data set of the marked stage according to a clustering result;
Extracting procedure characteristics according to the breeding data set, constructing a search tag by utilizing the procedure characteristics to search the crucian breeding examples, calculating according to similarity to obtain a subset of the crucian breeding examples meeting preset standards, and aggregating different crucian breeding examples to obtain a flow rule of the current breeding measure;
creating a breeding workflow for current crucian breeding based on the breeding data set generated by the process rule driving clustering, and expanding the breeding workflow according to updating of the crucian breeding data;
Performing water quality meshing monitoring on a target aquaculture water area by combining wireless communication with sensor information acquisition, sensing water quality monitoring parameters of different partitions, and acquiring historical water quality monitoring parameters in a preset time step;
And matching the historical water quality monitoring parameters with the breeding workflow, setting data indexes according to flow nodes in the breeding workflow, and interpolating the historical water quality monitoring data into the breeding workflow by utilizing the data indexes to generate the breeding workflow with updated data.
3. The method for monitoring the overall process of crucian breeding based on intelligent perception of water quality according to claim 1, wherein the method is characterized in that high-correlation water quality parameters are screened in different breeding workflow subsections according to breeding characteristics, and key water quality indexes of different breeding stages are set according to the high-correlation water quality parameters, specifically:
Preliminary segmentation marking is carried out in the updated breeding workflow by utilizing a marking stage, neighborhood regions are preset at different primary segmentation marking positions, flow nodes in the neighborhood regions are selected, and a stage center is set based on the average value corresponding to the flow nodes of each segment after the preliminary segmentation;
Using Euclidean distance to configure membership function, judging Euclidean distance between a flow node in a neighborhood region and the center of two adjacent stages, and when any Euclidean distance is larger than or equal to a preset distance threshold value, attributing the flow node to a breeding stage with high membership;
When the two Euclidean distances are smaller than a preset distance threshold value, respectively attributing the flow nodes to two adjacent breeding stages, and after the flow nodes in all primary segmentation marking position neighborhood regions are divided, acquiring the updated division result of the breeding workflow;
Extracting breeding characteristics according to flow nodes in different breeding workflow subsections, calculating pearson correlation coefficients in water quality monitoring parameters by using the breeding characteristics, and screening the water quality monitoring parameters of the different breeding workflow subsections by using the pearson correlation coefficients;
Constructing a crucian survival rate prediction model, training the crucian survival rate prediction model by using water quality monitoring parameters of different breeding workflow subsections, reading corresponding prediction accuracy, taking maximum prediction accuracy as a target, and evaluating the importance of the water quality monitoring parameters by using fold cross verification;
Sequencing the water quality monitoring parameters of different breeding workflow subsections by using the importance degree, and selecting a preset number of high-association water quality parameters as key water quality indexes.
4. The method for monitoring the overall process of crucian breeding based on intelligent perception of water quality according to claim 1, wherein the water quality monitoring parameters of different breeding stages are extracted by the key water quality indexes, and an appropriate water quality sequence for normal breeding of crucian is constructed, specifically:
acquiring key water quality indexes corresponding to different breeding workflow subsections, extracting parameters from historical water quality monitoring parameters according to the key water quality indexes, and screening the parameters according to the survival rate of the corresponding crucian in the extracted parameters;
Acquiring the parameter scale under the key water quality index, screening the key water quality index smaller than the preset scale for marking, introducing the parameter corresponding to the marked key water quality index into a self-encoder network to acquire potential characteristic distribution, and introducing an countermeasure mechanism;
Taking an encoder part of a self-encoder network as potential feature distribution of a generator learning parameter, acquiring reconstruction data of the parameter, mapping the reconstruction data to the same position, adding a discriminator in a potential feature layer, and punishing the reconstruction data with overlarge potential feature space position distribution deviation;
expanding parameters corresponding to the marked key water quality indexes by using iterative training of the countermeasure mechanism, stopping iteration when the parameter scale accords with the preset scale, and outputting the parameters corresponding to the marked key water quality indexes after expansion;
And constructing proper water quality sequences for normal breeding of crucian in different breeding stages by using parameters obtained by parameter screening and data expansion.
5. The method for monitoring the whole crucian breeding process based on intelligent water quality perception according to claim 1, wherein the extracted water quality monitoring parameter sequence is subjected to fine granularity analysis to obtain deviation from an adaptive water quality sequence, and the method is specifically as follows:
Extracting water quality monitoring parameters of different breeding stages according to the key water quality indexes, and generating water quality monitoring parameter sequences of different breeding stages by combining the monitoring time;
Generating initial weights of different breeding stages according to the historical average crucian survival rate pair, extracting diseases and accident instances of the different breeding stages according to the historical crucian breeding data, and calculating accident rates of the different breeding stages;
Determining fine granularity division degrees of different breeding stages by combining the initial weight with the accident rate, and dividing the water quality monitoring parameter sequence according to the fine granularity division degrees of different breeding stages to obtain a corresponding water quality monitoring parameter fine granularity sequence;
And calling the adaptive water quality sequence to generate a corresponding adaptive water quality fine granularity sequence, calculating the mean square distance between the water quality monitoring parameter fine granularity sequence and the adaptive water quality fine granularity sequence, and generating deviation according to the mean square distance sequence.
6. The method for monitoring the overall process of crucian breeding based on intelligent perception of water quality according to claim 1, wherein the method is characterized in that early warning is carried out in the process of crucian breeding according to the deviation, early warning information of different grades is generated, and water quality regulation and control of a target breeding water area are carried out through the early warning information, specifically:
The method comprises the steps of presetting deviation threshold intervals, matching early warning levels for different preset deviation threshold intervals, obtaining deviation threshold intervals where deviation falls, determining corresponding early warning levels, generating early warning information, and sending and visually displaying the early warning information according to a preset mode;
When the early warning level is greater than a preset level threshold, acquiring the maximum mean square distance between the fine granularity sequence of the water quality monitoring parameter and the proper water quality fine granularity sequence, and carrying out water quality monitoring parameter tracing according to the timestamp of the position where the maximum mean square distance is located;
and carrying out principal component analysis according to the traced water quality monitoring parameters, realizing tracing of early warning, connecting a water quality regulation and control measure related knowledge graph through a tracing result, and generating the water quality regulation and control measure based on the cultivation characteristics of the target cultivation water area.
7. A crucian breeding whole-process monitoring system based on intelligent perception of water quality is characterized in that the system comprises: the intelligent water quality perception-based crucian breeding full-flow monitoring method comprises a memory and a processor, wherein the memory comprises a water quality intelligent perception-based crucian breeding full-flow monitoring method program, and the following steps are realized when the water quality intelligent perception-based crucian breeding full-flow monitoring method program is executed by the processor:
Acquiring a current breeding workflow for crucian breeding, acquiring water quality monitoring parameters of a target breeding water area through sensing of the Internet of things, and matching the historical water quality monitoring parameters with the breeding workflow to generate a breeding workflow with updated data;
Dividing the updated breeding workflow by utilizing different breeding stages, screening high-correlation water quality parameters in different breeding workflow subsections according to breeding characteristics, and setting key water quality indexes of different breeding stages according to the high-correlation water quality parameters;
extracting water quality monitoring parameters in different breeding stages through the key water quality indexes, constructing an adaptive water quality sequence for normal breeding of crucian, carrying out fine granularity analysis on the extracted water quality monitoring parameter sequence, and obtaining deviation from the adaptive water quality sequence;
And carrying out early warning on the crucian breeding process according to the deviation, generating early warning information of different grades, and carrying out water quality regulation and control on the target aquaculture water area through the early warning information.
8. The crucian breeding whole-process monitoring system based on intelligent perception of water quality according to claim 7, wherein the water quality monitoring parameters of different breeding stages are extracted by the key water quality indexes, and an adaptive water quality sequence for normal breeding of crucian is constructed, specifically:
acquiring key water quality indexes corresponding to different breeding workflow subsections, extracting parameters from historical water quality monitoring parameters according to the key water quality indexes, and screening the parameters according to the survival rate of the corresponding crucian in the extracted parameters;
Acquiring the parameter scale under the key water quality index, screening the key water quality index smaller than the preset scale for marking, introducing the parameter corresponding to the marked key water quality index into a self-encoder network to acquire potential characteristic distribution, and introducing an countermeasure mechanism;
Taking an encoder part of a self-encoder network as potential feature distribution of a generator learning parameter, acquiring reconstruction data of the parameter, mapping the reconstruction data to the same position, adding a discriminator in a potential feature layer, and punishing the reconstruction data with overlarge potential feature space position distribution deviation;
expanding parameters corresponding to the marked key water quality indexes by using iterative training of the countermeasure mechanism, stopping iteration when the parameter scale accords with the preset scale, and outputting the parameters corresponding to the marked key water quality indexes after expansion;
And constructing proper water quality sequences for normal breeding of crucian in different breeding stages by using parameters obtained by parameter screening and data expansion.
9. The crucian breeding whole-process monitoring system based on intelligent perception of water quality according to claim 7, wherein the fine granularity analysis is performed on the extracted water quality monitoring parameter sequence to obtain deviation from an adaptive water quality sequence, specifically:
Extracting water quality monitoring parameters of different breeding stages according to the key water quality indexes, and generating water quality monitoring parameter sequences of different breeding stages by combining the monitoring time;
Generating initial weights of different breeding stages according to the historical average crucian survival rate pair, extracting diseases and accident instances of the different breeding stages according to the historical crucian breeding data, and calculating accident rates of the different breeding stages;
Determining fine granularity division degrees of different breeding stages by combining the initial weight with the accident rate, and dividing the water quality monitoring parameter sequence according to the fine granularity division degrees of different breeding stages to obtain a corresponding water quality monitoring parameter fine granularity sequence;
And calling the adaptive water quality sequence to generate a corresponding adaptive water quality fine granularity sequence, calculating the mean square distance between the water quality monitoring parameter fine granularity sequence and the adaptive water quality fine granularity sequence, and generating deviation according to the mean square distance sequence.
10. The crucian breeding whole-process monitoring system based on intelligent perception of water quality according to claim 7, wherein the early warning of the crucian breeding process is carried out according to the deviation, early warning information of different grades is generated, and water quality regulation and control of a target cultivation water area are carried out through the early warning information, specifically:
The method comprises the steps of presetting deviation threshold intervals, matching early warning levels for different preset deviation threshold intervals, obtaining deviation threshold intervals where deviation falls, determining corresponding early warning levels, generating early warning information, and sending and visually displaying the early warning information according to a preset mode;
When the early warning level is greater than a preset level threshold, acquiring the maximum mean square distance between the fine granularity sequence of the water quality monitoring parameter and the proper water quality fine granularity sequence, and carrying out water quality monitoring parameter tracing according to the timestamp of the position where the maximum mean square distance is located;
and carrying out principal component analysis according to the traced water quality monitoring parameters, realizing tracing of early warning, connecting a water quality regulation and control measure related knowledge graph through a tracing result, and generating the water quality regulation and control measure based on the cultivation characteristics of the target cultivation water area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410404533.XA CN117994064B (en) | 2024-04-07 | 2024-04-07 | Carassius auratus breeding whole-process monitoring method and system based on intelligent water quality perception |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410404533.XA CN117994064B (en) | 2024-04-07 | 2024-04-07 | Carassius auratus breeding whole-process monitoring method and system based on intelligent water quality perception |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117994064A true CN117994064A (en) | 2024-05-07 |
| CN117994064B CN117994064B (en) | 2024-07-05 |
Family
ID=90890898
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410404533.XA Active CN117994064B (en) | 2024-04-07 | 2024-04-07 | Carassius auratus breeding whole-process monitoring method and system based on intelligent water quality perception |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117994064B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100099193A1 (en) * | 2008-10-20 | 2010-04-22 | Industrial Technology Research Institute | System and method for monitoring and controlling quality of culture water and integrated water quality analyzer thereof |
| CN106998670A (en) * | 2015-03-30 | 2017-08-01 | 皇家虾业有限责任公司 | Multi-stage integrated ultra-dense shrimp production system |
| CN109711590A (en) * | 2017-10-26 | 2019-05-03 | 中国电信股份有限公司 | Fishery water quality analyzing monitoring method, device and system |
| KR20210083829A (en) * | 2019-12-27 | 2021-07-07 | 주식회사 씨뱅크 | System and Method for Analyzing Environment Data in Aquaculture using Big data System based IoT |
| CN115660601A (en) * | 2022-11-10 | 2023-01-31 | 陕西中医药大学 | Zebra fish commercial breeding management system and management method thereof |
| CN115793585A (en) * | 2022-12-07 | 2023-03-14 | 中国水产科学研究院南海水产研究所 | Cultivation water quality regulation and control method, system and medium based on prawns |
| CN116636487A (en) * | 2023-06-09 | 2023-08-25 | 青岛海兴智能装备有限公司 | Complete life cycle circulating water breeding experiment system and breeding method |
| CN116941562A (en) * | 2023-06-21 | 2023-10-27 | 中国水产科学研究院南海水产研究所 | Prawn culture water quality regulation and control method and system based on Internet of things |
-
2024
- 2024-04-07 CN CN202410404533.XA patent/CN117994064B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100099193A1 (en) * | 2008-10-20 | 2010-04-22 | Industrial Technology Research Institute | System and method for monitoring and controlling quality of culture water and integrated water quality analyzer thereof |
| CN106998670A (en) * | 2015-03-30 | 2017-08-01 | 皇家虾业有限责任公司 | Multi-stage integrated ultra-dense shrimp production system |
| US20180116184A1 (en) * | 2015-03-30 | 2018-05-03 | Royal Caridea Llc | Multi-phasic integrated super-intensive shrimp production system |
| CN109711590A (en) * | 2017-10-26 | 2019-05-03 | 中国电信股份有限公司 | Fishery water quality analyzing monitoring method, device and system |
| KR20210083829A (en) * | 2019-12-27 | 2021-07-07 | 주식회사 씨뱅크 | System and Method for Analyzing Environment Data in Aquaculture using Big data System based IoT |
| CN115660601A (en) * | 2022-11-10 | 2023-01-31 | 陕西中医药大学 | Zebra fish commercial breeding management system and management method thereof |
| CN115793585A (en) * | 2022-12-07 | 2023-03-14 | 中国水产科学研究院南海水产研究所 | Cultivation water quality regulation and control method, system and medium based on prawns |
| CN116636487A (en) * | 2023-06-09 | 2023-08-25 | 青岛海兴智能装备有限公司 | Complete life cycle circulating water breeding experiment system and breeding method |
| CN116941562A (en) * | 2023-06-21 | 2023-10-27 | 中国水产科学研究院南海水产研究所 | Prawn culture water quality regulation and control method and system based on Internet of things |
Non-Patent Citations (6)
| Title |
|---|
| BIN WU ET AL: "A Smart Aquaculture System Exploiting IoT, AI and Cloud Computing", 《 2023 IEEE INTERNATIONAL CONFERENCE ON SMART INTERNET OF THINGS (SMARTIOT)》, 1 November 2023 (2023-11-01), pages 251 - 256 * |
| JUI-HO CHEN ET AL: "Automated Monitoring System for the Fish Farm Aquaculture Environment", 《2015 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS》, 14 January 2016 (2016-01-14), pages 1161 - 1166 * |
| 刘彦伟 等: "分层泵抽式海洋养殖环境智能监测系统设计", 《浙江海洋大学学报(自然科学版)》, vol. 42, no. 3, 31 May 2023 (2023-05-31), pages 228 - 238 * |
| 宦娟;吴帆;曹伟建;李慧;刘星桥;: "基于窄带物联网的养殖塘水质监测系统研制", 农业工程学报, no. 08, 23 April 2019 (2019-04-23) * |
| 徐思维: "基于物联网的水产养殖环境远程监控系统研究", 《中国优秀硕士学位论文全文数据库农业科技辑》, no. 2, 15 February 2023 (2023-02-15), pages 1 - 108 * |
| 王克亮;杨翠容;李世忠;: "工厂化鱼类养殖池监测系统的开发", 机电工程, no. 02, 20 February 2009 (2009-02-20) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117994064B (en) | 2024-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Swearer et al. | A review of biophysical models of marine larval dispersal | |
| CN111460990B (en) | Big data-based alpine pastoral area grassland insect pest monitoring and early warning system and method | |
| CN114494837B (en) | Intelligent density identification method and system for fishery resources | |
| CN112578725A (en) | Fishery water aquaculture facility safety early warning system and method based on Internet of things | |
| CN111882138A (en) | Water quality prediction method, device, equipment and storage medium based on space-time fusion | |
| CN114493680B (en) | Fishery resource statistical method and system based on stream stab net investigation | |
| CN115240060A (en) | Starfish disaster early warning method and system | |
| CN115100513A (en) | Method and system for estimating food intake of breeding object based on computer vision recognition | |
| CN114942951A (en) | Fishing vessel fishing behavior analysis method based on AIS data | |
| Horn | Stock assessment of hake (Merluccius australis) on the Chatham Rise (HAK 4) and off the west coast of South Island (HAK 7) for the 2012–13 fishing year | |
| CN117994064B (en) | Carassius auratus breeding whole-process monitoring method and system based on intelligent water quality perception | |
| CN109359624B (en) | Neural network-based prediction method and prediction device for feeding behavior of laying hens | |
| CN116307879A (en) | Efficient cultivation method, system and medium for penaeus monodon larvae | |
| Brown‐Peterson et al. | Importance of depth and artificial structure as predictors of female Red Snapper reproductive parameters | |
| CN116090859B (en) | Method and system for evaluating ecological health of offshore island reef fishery water area | |
| Kraus et al. | Robustness of egg production methods as a fishery independent alternative to assess the Eastern Baltic cod stock (Gadus morhua callarias L.) | |
| Leigh | Stock assessment of whaler and hammerhead sharks (Carcharhinidae and Sphyrnidae) in Queensland | |
| CN109242219B (en) | Prediction method and prediction device for layer feeding behavior | |
| CN112380486B (en) | Dynamic monitoring and evaluating method and system for sea water ornamental fish culture state | |
| Cook et al. | Assessment of demersal fish stocks in Ghanaian and adjacent waters | |
| Horn | Stock assessment of hake (Merluccius australis) off the west coast of South Island (HAK 7) for the 2010–11 fishing year | |
| Devine et al. | Fisheries characterisations for barracouta (Thyrsites atun) and preliminary standardised CPUE analyses in BAR 4 and BAR 5, 1990 to 2020 | |
| Vasilakopoulos et al. | Application of data‐limited assessment methods on black anglerfish (Lophius budegassa; Spinola, 1807) stocks in the Mediterranean Sea | |
| CN116720666B (en) | Automatic monitoring method and system for ocean pasture based on big data | |
| CN116579508B (en) | Fish prediction method, device, equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |