Internet-of-things aquaculture early warning method and system based on data monitoring and storage medium

Abstract

The invention discloses an Internet of Things aquaculture early warning method and system based on data monitoring and a storage medium. Relates to the field of internet-of-things aquaculture. Environment data and fry growth data of aquaculture are obtained according to a preset interval moment; a time sequence-fry environment connected graph of the environment data and the fry growth data at each sampling moment is established, nodes of the time sequence-fry environment connected graph are used for representing the fry growth data, and directed edges are used for representing the dependency relationship between the fry growth data and the environment data; performing similarity comparison on each node and each directed edge, clustering each node and each directed edge according to a preset threshold value, and performing dimension reduction processing to obtain a thumbnail connected graph; nodes with inflection points in the thumbnail connected graph are obtained and called as abnormal points, two adjacent abnormal points are communicated to serve as an environment fluctuation interval, and if the fluctuation amplitude of the environment fluctuation interval exceeds a preset interval, early warning is conducted on the aquaculture end. The aquaculture level of the internet of things is improved.

Description

Technical Field

[0001] The present invention relates to the field of aquaculture of the Internet of Things, and more specifically to a method, system and storage medium for dynamic simulation optimization of low-temperature distillation. Background Art

[0002] Aquaculture refers to the cultivation of aquatic products such as fish, shrimp, crab, shellfish, mollusks, algae, etc. under artificial control. The cultivation methods can be divided into three categories: pond cultivation, land-based factory recirculating water cultivation and cage cultivation. The main business links include breeding selection, cultivation environment control, feeding, disease prevention and control, fishing, etc. Therefore, using modern information technology to realize the construction of China's smart fishery has become an important task in the current aquaculture field.

[0003] With the continuous progress of new generation information technologies such as the Internet of Things, big data, and artificial intelligence, it has become possible to use machines to replace manual labor in aquaculture. Among them, agricultural Internet of Things technology can sense and transmit farm information and realize the interconnection of intelligent equipment; big data and cloud computing technology complete the storage, analysis and processing of information and realize the digitization of breeding information. Artificial intelligence technology, as the most important part of intelligent breeding, simulates human thinking, learns the massive information provided by the Internet of Things and big data, analyzes and judges the problems generated, and finally completes the decision-making task to achieve precise operation of the farm. However, there is currently little research on methods for IoT breeding and rapid warning of abnormal situations. Therefore, it is urgent for technical personnel in this field to continue research to achieve comprehensive IoT breeding and efficient warning and improve breeding efficiency. Summary of the invention

[0004] In view of this, the present invention provides an IoT aquaculture early warning method, system and storage medium based on data monitoring, which realizes precise monitoring of the environment, accurate correction of data, visual expression of relationships, intelligent processing of data and timely early warning of anomalies, providing strong support for improving the scientific and intelligent level of aquaculture.

[0005] In order to achieve the above object, the present invention adopts the following technical solution:

[0006] An IoT aquaculture early warning method based on data monitoring comprises the following steps:

[0007] The sensor is used to obtain the environmental data and fry growth data of aquaculture at preset intervals, and the environmental data and fry growth data are corrected according to the periodic activity information of the water conservancy facilities around the fry;

[0008] Based on the corrected data, a time series-fry environment connectivity graph of the environmental data and fry growth data at each sampling moment is established, wherein the nodes of the time series-fry environment connectivity graph are used to represent the fry growth data, and the directed edges are used to represent the dependency relationship between the fry growth data and the environmental data;

[0009] Compare the similarity of each node and each directed edge, cluster each node and directed edge according to the preset threshold, and perform dimensionality reduction to obtain a thumbnail connected graph;

[0010] The nodes where inflection points appear in the thumbnail connected graph are obtained, which are called abnormal points. The connection between two adjacent abnormal points is used as the environmental fluctuation interval. If the fluctuation range of the environmental fluctuation interval exceeds the preset interval, an early warning will be issued to the aquaculture end.

[0011] Optionally, the sensors include water quality sensors, fish life status collection sensors, and micro-meteorological data sensors; the water quality sensors are used to collect dissolved oxygen concentration, water temperature, pH value, and ammonia nitrogen concentration; the fish life status collection sensors are used to collect the number, growth stage, and growth status of fish; the micro-meteorological data sensors are used to collect meteorological data.

[0012] Optionally, it also includes AI calculation of the fluctuation range of the environmental fluctuation range, determining environmental abnormal factors, and pushing response strategies to the client based on the abnormal factors. The response strategies include changing the amount of oxygen added, changing the feed amount of the feeder, and reducing the number of fry.

[0013] Optionally, the specific process of AI calculation is as follows:

[0014] Collect environmental data between environmental fluctuation intervals and fry growth data, and pre-process the collected data;

[0015] The relevant features of the fluctuation amplitude are extracted from the preprocessed data, and the fluctuation amplitude is determined according to the pre-set linear regression equation.

[0016] Optionally, the environmental data and the fry growth data are corrected according to the periodic activity information of the water conservancy facilities around the fry, specifically:

[0017] Periodically obtaining environmental data about the presence or absence of water conservancy equipment and fish fry growth data within a preset time period as first data and second data respectively;

[0018] A real-time multivariate matrix is ​​established with the first data and the second data, and the multivariate matrix is ​​multiplied by the transpose of the standard matrix. If the product is not a unit matrix, the environmental data around the water conservancy facilities and the fry growth data are calibrated multiple times until the product is a unit matrix.

[0019] Optionally, the environmental data around the water conservancy facilities and the fry growth data are calibrated by using a filter to filter out the redundant bands of the water conservancy equipment, and using a temperature sensor to obtain the temperature around the water conservancy equipment to compensate for the temperature.

[0020] An IoT aquaculture early warning system based on data monitoring, comprising:

[0021] Data monitoring module: used to obtain environmental data and fry growth data of aquaculture at preset intervals using sensors, and to correct the environmental data and fry growth data according to the periodic activity information of water conservancy facilities around the fry;

[0022] A time series-fry environment connectivity graph establishment module is used to establish a time series-fry environment connectivity graph of environmental data and fry growth data at each sampling moment based on the corrected data. The nodes of the time series-fry environment connectivity graph are used to represent fry growth data, and the directed edges are used to represent the dependency relationship between fry growth data and environmental data.

[0023] Time series-fry environment connectivity graph dimension reduction module: used to compare the similarity of each node and each directed edge, cluster each node and directed edge according to the preset threshold, and perform dimension reduction processing to obtain a thumbnail connectivity graph;

[0024] Aquaculture early warning module: used to obtain the nodes where inflection points appear in the thumbnail connected graph, called abnormal points, and connect the two adjacent abnormal points as the environmental fluctuation range. If the fluctuation range of the environmental fluctuation range exceeds the preset range, an early warning will be issued to the aquaculture end.

[0025] A computer storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the Internet of Things aquaculture early warning methods based on data monitoring are implemented.

[0026] It can be seen from the above technical solutions that, compared with the prior art, the present invention provides an IoT aquaculture early warning method, system and storage medium based on data monitoring, which has the following beneficial effects:

[0027] 1. By correcting the data to reduce external interference, the accuracy and reliability of the data are improved. This helps to more accurately reflect the actual growth status of the fry and lay a solid foundation for subsequent data analysis.

[0028] 2. By constructing a time series-fry environment connectivity diagram, the complex relationship between environmental data and fry growth data is visualized, which helps to understand the specific impact of different environmental factors on fry growth. This graphical representation makes data analysis more intuitive and easy to understand.

[0029] 3. Perform similarity comparison, clustering and dimensionality reduction on nodes and directed edges to obtain a thumbnail connected graph, which effectively reduces the complexity and computational complexity of data processing. At the same time, clustering helps to discover potential patterns and rules in the data, providing strong support for subsequent anomaly detection.

[0030] 4. By identifying abnormal points in the thumbnail connected graph and defining the environmental fluctuation range, this method can timely detect abnormal fluctuations in the breeding environment. When the fluctuation range exceeds the preset range, an early warning is issued in time, which helps breeders to take quick measures to avoid adverse effects of environmental deterioration on the growth of fry.

[0031] 5. The entire process realizes intelligent management of aquaculture, reduces reliance on manual intervention, and improves management efficiency and accuracy. Decisions driven by data analysis help maximize aquaculture benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0033] Figure 1 It is a schematic diagram of the process of the present invention;

[0034] Figure 2 It is a structural schematic diagram of the present invention. DETAILED DESCRIPTION

[0035] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0036] The embodiment of the present invention discloses an IoT aquaculture early warning method based on data monitoring, such as Figure 1 As shown, the following steps are included:

[0037] S1: using sensors to obtain aquaculture environmental data and fish fry growth data at preset intervals, and correcting the environmental data and fish fry growth data according to periodic activity information of water conservancy facilities around the fish fry;

[0038] S2: Based on the corrected data, a time series-fry environment connectivity graph of the environmental data and fry growth data at each sampling moment is established, wherein the nodes of the time series-fry environment connectivity graph are used to represent the fry growth data, and the directed edges are used to represent the dependency relationship between the fry growth data and the environmental data;

[0039] S3: Compare the similarity of each node and each directed edge, cluster each node and directed edge according to a preset threshold, and perform dimensionality reduction to obtain a thumbnail connected graph;

[0040] S4: Obtain the nodes where the turning points appear in the thumbnail connected graph, which are called abnormal points. Connect two adjacent abnormal points as the environmental fluctuation interval. If the fluctuation range of the environmental fluctuation interval exceeds the preset range, an early warning is issued to the aquaculture end.

[0041] Furthermore, in S1, the sensors include a water quality sensor, a fish life status collection sensor, and a micro-meteorological data sensor; the water quality sensor is used to collect dissolved oxygen concentration, water temperature, pH value, and ammonia nitrogen concentration; the fish life status collection sensor is used to collect the number, growth stage, and growth status of fish; and the micro-meteorological data sensor is used to collect meteorological data.

[0042] The environmental data and fry growth data are corrected according to the periodic activity information of the water conservancy facilities around the fry, specifically:

[0043] S11: periodically obtaining environmental data about the presence or absence of water conservancy equipment and fish fry growth data within a preset time period, as first data and second data respectively;

[0044] S12: A real-time multivariate matrix is ​​established with the first data and the second data, and the multivariate matrix is ​​multiplied by the transpose of the standard matrix. If the product is not a unit matrix, the environmental data around the water conservancy facilities and the fry growth data are calibrated multiple times until the product is a unit matrix.

[0045] The above technical solution calibrates the impact of water conservancy facility activities on the environment and fish fry growth data through mathematical methods to eliminate or reduce such impact and make the data more accurately reflect the actual situation of fish fry growth.

[0046] Specifically, construct a real-time multivariate matrix: construct the first data and the second data into real-time multivariate matrices respectively. Each row of these matrices represents data at a time point, and each column represents a data dimension (such as water temperature, dissolved oxygen, etc.).

[0047] Define the standard matrix: The standard matrix is ​​an idealized matrix of environmental and fry growth data without the influence of water conservancy facilities. This matrix can be constructed from historical data, experimental data or expert knowledge.

[0048] Matrix operation: multiply the real-time multivariate matrix by the transpose of the standard matrix. The result of this product should be a matrix close to the identity matrix. If the product is not the identity matrix, it means that the real-time data is affected by the activities of the water conservancy facilities.

[0049] Data calibration: If the product is not the identity matrix, the data of the water conservancy facility activities needs to be calibrated multiple times through some calibration algorithm (such as linear regression, neural network, etc.). The goal of calibration is to adjust the data so that the product of the calibrated real-time multivariate matrix and the standard matrix is ​​as close to the identity matrix as possible.

[0050] Iteration and verification: Repeat the above calibration process until the product approaches or reaches the preset standard of the identity matrix. Then, use the validation data set to verify whether the calibrated data accurately reflects the actual growth status of the fry.

[0051] Furthermore, in S4, it also includes AI calculation of the fluctuation range of the environmental fluctuation range, determining the environmental abnormal factors, and pushing response strategies to the client based on the abnormal factors. The response strategies include changing the amount of oxygen added, changing the feed amount of the feeder, and reducing the number of fry.

[0052] Specifically, this embodiment can identify the growth stage of aquatic species in each aquatic area, and obtain the corresponding optimal intake according to the growth stage; obtain the breeding quantity of each aquatic species, and set the corresponding initial input quantity according to the breeding quantity and the optimal intake; and set the corresponding equivalent supplement quantity for the aquatic area according to the breeding quantity.

[0053] The specific process of AI calculation is as follows:

[0054] S41: Collect environmental data and fry growth data between environmental fluctuation intervals, and pre-process the collected data;

[0055] S42: Extract relevant features of the fluctuation amplitude from the preprocessed data, and determine the fluctuation amplitude according to a pre-set linear regression equation.

[0056] In this embodiment, the environmental data around the water conservancy facilities and the fry growth data can be calibrated. The redundant bands of the water conservancy equipment can be filtered out by a filter, and the temperature sensor can be used to obtain the temperature around the water conservancy equipment to compensate for the temperature. During the operation of the water conservancy equipment, electromagnetic interference, mechanical vibration, etc. may be generated. These interferences may appear in the environmental data in the form of waveforms of specific frequencies and become redundant bands. These unnecessary signals can be removed by filters to improve the purity and accuracy of the data.

[0057] and Figure 1 Corresponding to the method shown, the present invention also discloses an IoT aquaculture early warning system based on data monitoring for Figure 1The implementation of the method, the specific structure is as follows Figure 2 As shown, including:

[0058] Data monitoring module: used to obtain environmental data and fry growth data of aquaculture at preset intervals using sensors, and to correct the environmental data and fry growth data according to the periodic activity information of water conservancy facilities around the fry;

[0059] A time series-fry environment connectivity graph establishment module is used to establish a time series-fry environment connectivity graph of environmental data and fry growth data at each sampling moment based on the corrected data. The nodes of the time series-fry environment connectivity graph are used to represent fry growth data, and the directed edges are used to represent the dependency relationship between fry growth data and environmental data.

[0060] Time series-fry environment connectivity graph dimension reduction module: used to compare the similarity of each node and each directed edge, cluster each node and directed edge according to the preset threshold, and perform dimension reduction processing to obtain a thumbnail connectivity graph;

[0061] Aquaculture early warning module: used to obtain the nodes where inflection points appear in the thumbnail connected graph, called abnormal points, and connect the two adjacent abnormal points as the environmental fluctuation range. If the fluctuation range of the environmental fluctuation range exceeds the preset range, an early warning will be issued to the aquaculture end.

[0062] Finally, this embodiment discloses a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, any one of the steps of the IoT aquaculture early warning method based on data monitoring is implemented.

[0063] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0064] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An IoT aquaculture early warning method based on data monitoring, characterized in that: The following steps are involved: The sensor is used to obtain the environmental data and fry growth data of aquaculture at preset intervals, and the environmental data and fry growth data are corrected according to the periodic activity information of the water conservancy facilities around the fry; Based on the corrected data, a time series-fry environment connectivity graph of the environmental data and fry growth data at each sampling moment is established, wherein the nodes of the time series-fry environment connectivity graph are used to represent the fry growth data, and the directed edges are used to represent the dependency relationship between the fry growth data and the environmental data; Compare the similarity of each node and each directed edge, cluster each node and directed edge according to the preset threshold, and perform dimensionality reduction to obtain a thumbnail connected graph; The nodes where inflection points appear in the thumbnail connected graph are obtained, which are called abnormal points. The connection between two adjacent abnormal points is used as the environmental fluctuation interval. If the fluctuation range of the environmental fluctuation interval exceeds the preset interval, an early warning will be issued to the aquaculture end.

2. According to claim 1, an IoT aquaculture early warning method based on data monitoring is characterized in that: The sensors include water quality sensors, fish life status collection sensors, and micro-meteorological data sensors; the water quality sensors are used to collect dissolved oxygen concentration, water temperature, pH value, and ammonia nitrogen concentration; the fish life status collection sensors are used to collect the number, growth stage, and growth status of fish; the micro-meteorological data sensors are used to collect meteorological data.

3. The IoT aquaculture early warning method based on data monitoring according to claim 1 is characterized in that: It also includes AI calculation of the fluctuation range of the environmental fluctuation range, determining environmental abnormal factors, and pushing response strategies to the client based on the abnormal factors. The response strategies include changing the amount of oxygen added, changing the feed amount of the feeder, and reducing the number of fry.

4. The IoT aquaculture early warning method based on data monitoring according to claim 3 is characterized in that: The specific process of AI calculation is as follows: Collect environmental data between environmental fluctuation intervals and fry growth data, and pre-process the collected data; The relevant features of the fluctuation amplitude are extracted from the preprocessed data, and the fluctuation amplitude is determined according to the pre-set linear regression equation.

5. The IoT aquaculture early warning method based on data monitoring according to claim 1 is characterized in that: The environmental data and fry growth data are corrected according to the periodic activity information of the water conservancy facilities around the fry, specifically: Periodically obtaining environmental data about the presence or absence of water conservancy equipment and fish fry growth data within a preset time period as first data and second data respectively; A real-time multivariate matrix is ​​established with the first data and the second data, and the multivariate matrix is ​​multiplied by the transpose of the standard matrix. If the product is not a unit matrix, the environmental data around the water conservancy facilities and the fry growth data are calibrated multiple times until the product is a unit matrix.

6. The IoT aquaculture early warning method based on data monitoring according to claim 5 is characterized in that: The environmental data around the water conservancy facilities and the growth data of fry are calibrated. A filter is used to filter out the redundant bands of the water conservancy equipment, and a temperature sensor is used to obtain the temperature around the water conservancy equipment to compensate for the temperature.

7. An IoT aquaculture early warning system based on data monitoring, characterized in that: include: Data monitoring module: used to obtain environmental data and fry growth data of aquaculture at preset intervals using sensors, and to correct the environmental data and fry growth data according to the periodic activity information of water conservancy facilities around the fry; A time series-fry environment connectivity graph establishment module is used to establish a time series-fry environment connectivity graph of environmental data and fry growth data at each sampling moment based on the corrected data. The nodes of the time series-fry environment connectivity graph are used to represent fry growth data, and the directed edges are used to represent the dependency relationship between fry growth data and environmental data. Time series-fry environment connectivity graph dimension reduction module: used to compare the similarity of each node and each directed edge, cluster each node and directed edge according to the preset threshold, and perform dimension reduction processing to obtain a thumbnail connectivity graph; Aquaculture early warning module: used to obtain the nodes where inflection points appear in the thumbnail connected graph, called abnormal points, and connect the two adjacent abnormal points as the environmental fluctuation range. If the fluctuation range of the environmental fluctuation range exceeds the preset range, an early warning will be issued to the aquaculture end.

8. A computer storage medium, characterized in that: The computer storage medium stores a computer program, which, when executed by a processor, implements the steps of an IoT aquaculture early warning method based on data monitoring as described in any one of claims 1 to 6.

Images