Aquaculture water quality intelligent detection method and device

Abstract

The invention relates to an aquaculture water quality intelligent detection method and equipment, and belongs to the technical field of water quality detection. An aquaculture water quality prediction model is constructed according to an aquaculture water quality sample characteristic change curve based on a time sequence; the water quality condition data of the current aquaculture area within the preset time are predicted through the aquaculture water quality prediction model, finally, water quality early warning is carried out according to the water quality condition data of the current aquaculture area within the preset time, and the purification capacity data of the water purification equipment within unit time are obtained. And formulating a water quality purification strategy according to the purification capacity data of the water quality purification equipment within the unit time and the water quality condition data of the current aquaculture area within the preset time. Through the aquaculture water quality prediction model, the prediction precision of the water quality in aquaculture can be more accurately predicted, a water quality purification strategy can be formulated for water quality purification, and the rationality of aquaculture monitoring and management is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of water quality detection, and in particular to an intelligent detection method and equipment for aquaculture water quality. Background Art

[0002] The water quality of aquaculture water is the foundation of the aquaculture ecosystem and is directly related to the growth and survival of aquatic organisms. For example, appropriate pH, dissolved oxygen content, ammonia nitrogen, and nitrite concentrations are important factors in maintaining the normal physiological functions of aquatic organisms such as fish, shrimp, and crabs. When water quality deteriorates, such as insufficient dissolved oxygen, it can cause breathing difficulties and metabolic blockages in aquatic organisms, thereby affecting their growth rate and health. Good water quality can reduce the growth and spread of pathogenic microorganisms, thereby reducing the risk of aquatic organisms becoming ill. Conversely, severely polluted water bodies can easily become breeding grounds for pathogens, leading to frequent disease outbreaks and causing huge losses to the aquaculture industry. Therefore, strengthening water pollution prevention and control is an important means to prevent diseases in aquatic organisms and ensure their healthy growth. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides an intelligent detection method and device for aquaculture water quality.

[0004] In order to achieve the above object, the technical solution adopted by the present invention is:

[0005] A first aspect of the present invention provides an intelligent detection method for aquaculture water quality, comprising the following steps:

[0006] Acquiring physical and chemical indicators of aquaculture, collecting physical and chemical indicator data of aquaculture water quality based on the physical and chemical indicators of aquaculture, and constructing aquaculture water quality sample data;

[0007] Constructing a time-series-based aquaculture water quality sample characteristic change curve based on the aquaculture water quality sample data, and constructing an aquaculture water quality prediction model according to the time-series-based aquaculture water quality sample characteristic change curve;

[0008] Predicting water quality data of the current aquaculture area within a preset time using the aquaculture water quality prediction model;

[0009] A water quality warning is issued based on the water quality data of the current aquaculture area within a preset time, and the purification capacity data of the water purification equipment within a unit time is obtained. A water purification strategy is formulated based on the purification capacity data of the water purification equipment within a unit time and the water quality data of the current aquaculture area within a preset time.

[0010] Furthermore, in this method, physical indicators and chemical indicators of aquaculture are obtained, and physical and chemical indicator data of aquaculture water quality are collected based on the physical and chemical indicators of aquaculture to construct aquaculture water quality sample data, which specifically includes:

[0011] Constructing aquaculture keywords, searching through big data based on the aquaculture keywords to obtain physical and chemical indicators of aquaculture, constructing a data acquisition network, and integrating data collected by data acquisition equipment into the data acquisition network;

[0012] Physical index and chemical index data of aquaculture water quality are acquired through the data acquisition network, and aquaculture water quality sample data are constructed according to the physical index and chemical index data of aquaculture water quality, and the aquaculture water quality sample data are output.

[0013] Furthermore, in this method, a time-series-based aquaculture water quality sample characteristic change curve is constructed based on the aquaculture water quality sample data, and an aquaculture water quality prediction model is constructed according to the time-series-based aquaculture water quality sample characteristic change curve, specifically:

[0014] Sorting the aquaculture water quality sample data in chronological order to obtain a time-series-based aquaculture water quality sample characteristic change curve, and calculating a Mahalanobis distance value between two adjacent data samples in the time-series-based aquaculture water quality sample characteristic change curve;

[0015] Preset a Mahalanobis distance threshold, determine whether the Mahalanobis distance value is greater than the Mahalanobis distance threshold, and when the Mahalanobis distance value is not greater than the Mahalanobis distance threshold, use the corresponding time series-based aquaculture water quality sample characteristic change curve as a training sample;

[0016] Constructing an aquaculture water quality prediction model based on a deep neural network, inputting the training samples into the aquaculture water quality prediction model, presetting a training stop condition, and determining whether the aquaculture water quality prediction model during training meets the training stop condition;

[0017] When the aquaculture water quality prediction model in the training process reaches the training stop condition, the model parameters of the aquaculture water quality prediction model are saved, and the aquaculture water quality prediction model is output.

[0018] Furthermore, in this method, the water quality data of the current aquaculture area within a preset time is predicted by the aquaculture water quality prediction model, specifically:

[0019] Acquiring water quality data of the current aquaculture area within a predetermined continuous time period, and formulating a water quality change curve based on the water quality data of the current aquaculture area within the predetermined continuous time period;

[0020] Inputting the water quality change curve into the aquaculture water quality prediction model for prediction, and obtaining the water quality change curve of the current aquaculture area within a preset time through prediction;

[0021] The water quality data of the current aquaculture area within the preset time is obtained according to the water quality change curve of the current aquaculture area within the preset time, and the water quality data of the current aquaculture area within the preset time is output.

[0022] Furthermore, in this method, a water quality warning is performed based on the water quality data of the current aquaculture area within a preset time, specifically:

[0023] Determining whether there is water quality data greater than a preset water quality index in the water quality data of the current aquaculture area within a preset time;

[0024] When water quality data of the current aquaculture area within a preset time period contains water quality data that is greater than a preset water quality index, obtaining the most recent time point at which the water quality data is greater than the preset water quality index;

[0025] A water quality warning is issued based on the most recent time point when the water quality data is greater than a preset water quality index.

[0026] Furthermore, in this method, the purification capacity data of the water purification equipment within a unit time is obtained, and a water purification strategy is formulated based on the purification capacity data of the water purification equipment within a unit time and the water quality data of the current aquaculture area within a preset time, specifically:

[0027] Acquire the purification capacity data of the water purification equipment within a unit time, and acquire the water quality data at the current time node based on the water quality data of the current aquaculture area within a preset time;

[0028] Determining whether the water quality data at the current time node is greater than a preset water quality index threshold, and when the water quality data at the current time node is greater than the preset water quality index threshold, formulating a water purification strategy based on the water quality data at the current time node and the purification capacity data of the water purification equipment within a unit time;

[0029] When the water quality data at the current time node is not greater than the preset water quality index threshold, the water quality data of the current aquaculture area within the preset time is continuously monitored.

[0030] Furthermore, in this method, a water purification strategy is formulated based on the water quality data at the current time node and the purification capacity data of the water purification equipment within a unit time, specifically:

[0031] Initializing the number of purification devices, and calculating total purification capacity data per unit time based on the number of purification devices and the purification capacity data of the water purification devices per unit time;

[0032] Obtaining purification capacity demand information within a unit time, and determining whether the total purification capacity data information within the unit time is the purification capacity demand information within the unit time;

[0033] When the total purification capacity data information within the unit time is greater than the purification capacity demand information within the unit time, output the number of purification equipment, and purify the aquaculture water quality according to the number of purification equipment;

[0034] When the total purification capacity data information within the unit time is not greater than the purification capacity demand information within the unit time, the number of purification devices is increased until it is greater than the purification capacity demand information within the unit time.

[0035] The second aspect of the present invention provides an intelligent detection device for aquaculture water quality, including a memory and a processor, wherein the memory includes an intelligent detection method program for aquaculture water quality. When the intelligent detection method program for aquaculture water quality is executed by the processor, the steps of any one of the intelligent detection methods for aquaculture water quality are implemented.

[0036] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0037] The present invention obtains physical and chemical indicators of aquaculture, collects physical and chemical indicator data of aquaculture water quality based on the physical and chemical indicators of aquaculture, constructs aquaculture water quality sample data, and then constructs an aquaculture water quality sample characteristic change curve based on a time series based on the aquaculture water quality sample data. According to the aquaculture water quality sample characteristic change curve based on the time series, an aquaculture water quality prediction model is constructed, thereby predicting the water quality data of the current aquaculture area within a preset time through the aquaculture water quality prediction model, and finally performing a water quality early warning based on the water quality data of the current aquaculture area within the preset time, and obtaining the purification capacity data of the water purification equipment within a unit time, and formulating a water purification strategy based on the purification capacity data of the water purification equipment within a unit time and the water quality data of the current aquaculture area within the preset time. The present invention can more accurately predict the prediction accuracy of water quality in aquaculture through the aquaculture water quality prediction model, and can formulate a water purification strategy for water purification, thereby improving the rationality of aquaculture monitoring and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying any creative work, they can also obtain drawings of other embodiments based on these drawings.

[0039] Figure 1 The overall flow chart of the intelligent detection method for aquaculture water quality is shown;

[0040] Figure 2 A schematic diagram of an intelligent aquaculture water quality detection device is shown. DETAILED DESCRIPTION

[0041] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0042] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0043] like Figure 1 As shown, the first aspect of the present invention provides an intelligent detection method for aquaculture water quality, comprising the following steps:

[0044] S102: Acquire physical indicators and chemical indicators of aquaculture, collect physical and chemical indicator data of aquaculture water quality based on the physical and chemical indicators of aquaculture, and construct aquaculture water quality sample data;

[0045] S104: constructing a time-series-based aquaculture water quality sample characteristic change curve based on the aquaculture water quality sample data, and constructing an aquaculture water quality prediction model according to the time-series-based aquaculture water quality sample characteristic change curve;

[0046] S106: Predicting water quality data of the current aquaculture area within a preset time using an aquaculture water quality prediction model;

[0047] S108: Issue a water quality warning based on the water quality data of the current aquaculture area within a preset time, and obtain the purification capacity data of the water purification equipment within a unit time, and formulate a water purification strategy based on the purification capacity data of the water purification equipment within a unit time and the water quality data of the current aquaculture area within a preset time.

[0048] It should be noted that the present invention can more accurately predict the water quality in aquaculture through the aquaculture water quality prediction model, and can formulate water purification strategies to purify water quality, thereby improving the rationality of aquaculture monitoring and management.

[0049] Furthermore, in this method, physical indicators and chemical indicators of aquaculture are obtained, and physical and chemical indicator data of aquaculture water quality are collected based on the physical and chemical indicators of aquaculture to construct aquaculture water quality sample data, specifically including:

[0050] Construct aquaculture keywords, search big data based on aquaculture keywords, obtain physical and chemical indicators of aquaculture, build a data collection network, and integrate the data collected by data collection equipment into the data collection network;

[0051] The physical index and chemical index data of aquaculture water quality are obtained through the data acquisition network, and aquaculture water quality sample data are constructed according to the physical index and chemical index data of aquaculture water quality, and the aquaculture water quality sample data are output.

[0052] It should be noted that the physical indicators of aquaculture include color, odor, etc., and the chemical indicators include data such as the composition and concentration of pollutant compounds.

[0053] Furthermore, in this method, a time series-based aquaculture water quality sample characteristic change curve is constructed based on aquaculture water quality sample data, and an aquaculture water quality prediction model is constructed according to the time series-based aquaculture water quality sample characteristic change curve, specifically:

[0054] By sorting the aquaculture water quality sample data in chronological order, a characteristic change curve of the aquaculture water quality sample based on the time series is obtained, and the Mahalanobis distance value between two adjacent data samples in the characteristic change curve of the aquaculture water quality sample based on the time series is calculated;

[0055] A Mahalanobis distance threshold is preset to determine whether a Mahalanobis distance value is greater than the Mahalanobis distance threshold. If no Mahalanobis distance value is greater than the Mahalanobis distance threshold, the corresponding time series-based aquaculture water quality sample characteristic change curve is used as a training sample.

[0056] An aquaculture water quality prediction model is constructed based on a deep neural network, training samples are input into the aquaculture water quality prediction model, a training stop condition is preset, and it is determined whether the aquaculture water quality prediction model reaches the training stop condition during training;

[0057] When the aquaculture water quality prediction model in the training process reaches the training stop condition, the model parameters of the aquaculture water quality prediction model are saved, and the aquaculture water quality prediction model is output.

[0058] It should be noted that when there is no situation where the Mahalanobis distance value is greater than the Mahalanobis distance threshold, the corresponding time series-based aquaculture water quality sample characteristic change curve is used as a training sample, indicating that there are no data points with large fluctuations. When there is a situation where the Mahalanobis distance value is greater than the Mahalanobis distance threshold, it indicates that there are points with large fluctuations. Such points are abnormal units. For example, when encountering natural disasters, human factors, etc., this method can improve the prediction accuracy of the aquaculture water quality prediction model.

[0059] Furthermore, in this method, the water quality data of the current aquaculture area within a preset time is predicted by the aquaculture water quality prediction model, specifically:

[0060] Acquire water quality data of the current aquaculture area within a predetermined continuous time period, and formulate a water quality change curve based on the water quality data of the current aquaculture area within the predetermined continuous time period;

[0061] Input the water quality change curve into the aquaculture water quality prediction model for prediction, and obtain the water quality change curve of the current aquaculture area within a preset time through prediction;

[0062] The water quality data of the current aquaculture area within the preset time is obtained according to the water quality change curve of the current aquaculture area within the preset time, and the water quality data of the current aquaculture area within the preset time is output.

[0063] It should be noted that water quality data includes water quality physical indicators, water quality chemical indicators, etc.

[0064] Furthermore, in this method, a water quality warning is performed based on the water quality data of the current aquaculture area within a preset time, specifically:

[0065] Determine whether there is water quality data greater than a preset water quality index in the water quality data of the current aquaculture area within a preset time;

[0066] When water quality data of the current aquaculture area within a preset time period contains water quality data that is greater than a preset water quality index, obtaining the most recent time point at which the water quality data is greater than the preset water quality index;

[0067] A water quality warning is issued based on the most recent time point when the water quality data is greater than the preset water quality index.

[0068] Furthermore, in this method, the purification capacity data of the water purification equipment within a unit time is obtained, and a water purification strategy is formulated based on the purification capacity data of the water purification equipment within a unit time and the water quality data of the current aquaculture area within a preset time, specifically:

[0069] Obtain the purification capacity data of the water purification equipment within a unit time, and obtain the water quality data at the current time node based on the water quality data of the current aquaculture area within a preset time;

[0070] Determine whether the water quality data at the current time node is greater than a preset water quality index threshold. When the water quality data at the current time node is greater than the preset water quality index threshold, formulate a water purification strategy based on the water quality data at the current time node and the purification capacity data of the water purification equipment within a unit time;

[0071] When the water quality data at the current time node is not greater than the preset water quality index threshold, the water quality data of the current aquaculture area within the preset time is continuously monitored.

[0072] It should be noted that the purification capacity data of the water purification equipment per unit time is the amount of water purified per unit time.

[0073] Furthermore, in this method, a water purification strategy is formulated based on the water quality data at the current time node and the purification capacity data of the water purification equipment within a unit time, specifically:

[0074] Initialize the number of purification equipment, and calculate the total purification capacity data within a unit time based on the number of purification equipment and the purification capacity data of the water purification equipment within a unit time;

[0075] Obtaining purification capacity demand information within a unit time, and determining whether the total purification capacity data information within the unit time meets the purification capacity demand information within the unit time;

[0076] When the total purification capacity data information within a unit time is greater than the purification capacity demand information within a unit time, the number of purification equipment is output, and the aquaculture water quality is purified according to the number of purification equipment;

[0077] When the total purification capacity data information within a unit time is not greater than the purification capacity demand information within a unit time, the number of purification devices is increased until it is greater than the purification capacity demand information within a unit time.

[0078] It should be noted that this method can improve the rationality of water purification, reduce aquatic product losses, and quickly purify water quality.

[0079] In addition, obtain the purification capacity data of water purification equipment within a unit time, including:

[0080] Obtaining characteristic data of historical purification capacity changes of water purification equipment within a unit time through big data, and constructing a purification capacity data characteristic prediction model based on a deep neural network, and inputting the characteristic data of historical purification capacity changes of water purification equipment within a unit time into the purification capacity data characteristic prediction model for learning;

[0081] Through training and learning, a purification capacity data feature prediction model is obtained, and characteristic data of purification capacity changes of water purification equipment within a preset time is obtained;

[0082] Inputting the purification capacity change characteristic data of the water purification equipment within the preset time into the trained purification capacity data characteristic prediction model for prediction;

[0083] The purification capacity data of the water purification equipment at the current timestamp is obtained through prediction, and the purification capacity data of the water purification equipment within a unit time is updated according to the purification capacity data of the water purification equipment at the current timestamp.

[0084] In addition, the purification capacity demand information within a unit time is obtained, including:

[0085] Obtain the best survival index data of each aquatic product type under each climate characteristic through big data, construct a knowledge graph, and input the best survival index data of the aquatic product under each climate characteristic into the knowledge graph for storage;

[0086] Obtaining current climate characteristics and aquatic product type data, and inputting the current climate characteristics and aquatic product type data into the knowledge graph for data matching;

[0087] Through data matching, the optimal survival index data of the current aquatic type under the current climate characteristics is obtained;

[0088] Calculate the interval time based on the most recent time node when the water quality data is greater than the preset water quality index and the current time node, and calculate the water quality data that needs to be purified based on the optimal survival index data of the current aquatic product type under the current climate characteristics and the water quality data at the current time node;

[0089] Purification capacity demand information within a unit time is formulated based on the interval time period and the water quality data that needs to be purified, and the purification capacity demand information within the unit time is output.

[0090] It should be noted that, in fact, different climatic conditions will lead to abnormal temperatures in the water quality. When the temperature changes, the concentration of polluting soluble substances in the water quality compounds will change. This method can be used to dynamically formulate the purification capacity demand information within a unit time and optimize the purification process.

[0091] like Figure 2 As shown, the second aspect of the present invention provides an aquaculture water quality intelligent detection device 4, including a memory 41 and a processor 42. The memory 41 includes an aquaculture water quality intelligent detection method program. When the aquaculture water quality intelligent detection method program is executed by the processor 42, the following steps are implemented:

[0092] Obtaining physical and chemical indicators of aquaculture, collecting physical and chemical indicator data of aquaculture water quality based on the physical and chemical indicators of aquaculture, and constructing aquaculture water quality sample data;

[0093] Based on the aquaculture water quality sample data, a time series-based aquaculture water quality sample characteristic change curve is constructed, and an aquaculture water quality prediction model is constructed according to the time series-based aquaculture water quality sample characteristic change curve;

[0094] Predict the water quality data of the current aquaculture area within a preset time through the aquaculture water quality prediction model;

[0095] Water quality warning is issued based on the water quality data of the current aquaculture area within the preset time, and the purification capacity data of the water purification equipment within a unit time is obtained. Water purification strategy is formulated based on the purification capacity data of the water purification equipment within a unit time and the water quality data of the current aquaculture area within the preset time.

[0096] Furthermore, in this system, physical and chemical indicators of aquaculture are obtained, and physical and chemical indicator data of aquaculture water quality are collected based on the physical and chemical indicators of aquaculture to construct aquaculture water quality sample data, specifically including:

[0097] Construct aquaculture keywords, search big data based on aquaculture keywords, obtain physical and chemical indicators of aquaculture, build a data collection network, and integrate the data collected by data collection equipment into the data collection network;

[0098] The physical index and chemical index data of aquaculture water quality are obtained through the data acquisition network, and aquaculture water quality sample data are constructed according to the physical index and chemical index data of aquaculture water quality, and the aquaculture water quality sample data are output.

[0099] Furthermore, in this system, a time series-based aquaculture water quality sample characteristic change curve is constructed based on aquaculture water quality sample data, and an aquaculture water quality prediction model is constructed according to the time series-based aquaculture water quality sample characteristic change curve, specifically:

[0100] By sorting the aquaculture water quality sample data in chronological order, a characteristic change curve of the aquaculture water quality sample based on the time series is obtained, and the Mahalanobis distance value between two adjacent data samples in the characteristic change curve of the aquaculture water quality sample based on the time series is calculated;

[0101] A Mahalanobis distance threshold is preset to determine whether a Mahalanobis distance value is greater than the Mahalanobis distance threshold. If no Mahalanobis distance value is greater than the Mahalanobis distance threshold, the corresponding time series-based aquaculture water quality sample characteristic change curve is used as a training sample.

[0102] An aquaculture water quality prediction model is constructed based on a deep neural network, training samples are input into the aquaculture water quality prediction model, a training stop condition is preset, and it is determined whether the aquaculture water quality prediction model reaches the training stop condition during training;

[0103] When the aquaculture water quality prediction model in the training process reaches the training stop condition, the model parameters of the aquaculture water quality prediction model are saved, and the aquaculture water quality prediction model is output.

[0104] Furthermore, in this system, the water quality prediction model for aquaculture is used to predict the water quality data of the current aquaculture area within a preset time, specifically:

[0105] Acquire water quality data of the current aquaculture area within a predetermined continuous time period, and formulate a water quality change curve based on the water quality data of the current aquaculture area within the predetermined continuous time period;

[0106] Input the water quality change curve into the aquaculture water quality prediction model for prediction, and obtain the water quality change curve of the current aquaculture area within a preset time through prediction;

[0107] The water quality data of the current aquaculture area within the preset time is obtained according to the water quality change curve of the current aquaculture area within the preset time, and the water quality data of the current aquaculture area within the preset time is output.

[0108] Furthermore, in this system, water quality warning is carried out based on the water quality data of the current aquaculture area within the preset time, specifically:

[0109] Determine whether there is water quality data greater than a preset water quality index in the water quality data of the current aquaculture area within a preset time;

[0110] When water quality data of the current aquaculture area within a preset time period contains water quality data that is greater than a preset water quality index, obtaining the most recent time point at which the water quality data is greater than the preset water quality index;

[0111] A water quality warning is issued based on the most recent time point when the water quality data is greater than the preset water quality index.

[0112] Furthermore, in this system, the purification capacity data of the water purification equipment within a unit time is obtained, and a water purification strategy is formulated based on the purification capacity data of the water purification equipment within a unit time and the water quality data of the current aquaculture area within a preset time. Specifically,

[0113] Obtain the purification capacity data of the water purification equipment within a unit time, and obtain the water quality data at the current time node based on the water quality data of the current aquaculture area within a preset time;

[0114] Determine whether the water quality data at the current time node is greater than a preset water quality index threshold. When the water quality data at the current time node is greater than the preset water quality index threshold, formulate a water purification strategy based on the water quality data at the current time node and the purification capacity data of the water purification equipment within a unit time;

[0115] When the water quality data at the current time node is not greater than the preset water quality index threshold, the water quality data of the current aquaculture area within the preset time is continuously monitored.

[0116] Furthermore, in this system, a water purification strategy is formulated based on the water quality data at the current time node and the purification capacity data of the water purification equipment within a unit time. Specifically,

[0117] Initialize the number of purification equipment, and calculate the total purification capacity data within a unit time based on the number of purification equipment and the purification capacity data of the water purification equipment within a unit time;

[0118] Obtaining purification capacity demand information within a unit time, and determining whether the total purification capacity data information within the unit time meets the purification capacity demand information within the unit time;

[0119] When the total purification capacity data information within a unit time is greater than the purification capacity demand information within a unit time, the number of purification equipment is output, and the aquaculture water quality is purified according to the number of purification equipment;

[0120] When the total purification capacity data information within a unit time is not greater than the purification capacity demand information within a unit time, the number of purification devices is increased until it is greater than the purification capacity demand information within a unit time.

[0121] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0122] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0123] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0124] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned method embodiments may be implemented by hardware associated with program instructions, and the aforementioned program may be stored in a computer-readable storage medium. When the program is executed, the program executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0125] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0126] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. An intelligent detection method for aquaculture water quality, characterized in that: The following steps are involved: Acquiring physical and chemical indicators of aquaculture, collecting physical and chemical indicator data of aquaculture water quality based on the physical and chemical indicators of aquaculture, and constructing aquaculture water quality sample data; Constructing a time-series-based aquaculture water quality sample characteristic change curve based on the aquaculture water quality sample data, and constructing an aquaculture water quality prediction model according to the time-series-based aquaculture water quality sample characteristic change curve; Predicting water quality data of the current aquaculture area within a preset time using the aquaculture water quality prediction model; A water quality warning is issued based on the water quality data of the current aquaculture area within a preset time, and the purification capacity data of the water purification equipment within a unit time is obtained. A water purification strategy is formulated based on the purification capacity data of the water purification equipment within a unit time and the water quality data of the current aquaculture area within a preset time.

2. The intelligent detection method for aquaculture water quality according to claim 1, characterized in that: Obtaining physical and chemical indicators of aquaculture, collecting physical and chemical indicator data of aquaculture water quality based on the physical and chemical indicators of aquaculture, and constructing aquaculture water quality sample data, specifically including: Constructing aquaculture keywords, searching through big data based on the aquaculture keywords to obtain physical and chemical indicators of aquaculture, constructing a data acquisition network, and integrating data collected by data acquisition equipment into the data acquisition network; Physical index and chemical index data of aquaculture water quality are acquired through the data acquisition network, and aquaculture water quality sample data are constructed according to the physical index and chemical index data of aquaculture water quality, and the aquaculture water quality sample data are output.

3. The intelligent detection method for aquaculture water quality according to claim 1, characterized in that: Based on the aquaculture water quality sample data, a time series-based aquaculture water quality sample characteristic change curve is constructed, and according to the time series-based aquaculture water quality sample characteristic change curve, an aquaculture water quality prediction model is constructed, specifically: Sorting the aquaculture water quality sample data in chronological order to obtain a time-series-based aquaculture water quality sample characteristic change curve, and calculating a Mahalanobis distance value between two adjacent data samples in the time-series-based aquaculture water quality sample characteristic change curve; Preset a Mahalanobis distance threshold, determine whether the Mahalanobis distance value is greater than the Mahalanobis distance threshold, and when the Mahalanobis distance value is not greater than the Mahalanobis distance threshold, use the corresponding time series-based aquaculture water quality sample characteristic change curve as a training sample; Constructing an aquaculture water quality prediction model based on a deep neural network, inputting the training samples into the aquaculture water quality prediction model, presetting a training stop condition, and determining whether the aquaculture water quality prediction model during training meets the training stop condition; When the aquaculture water quality prediction model in the training process reaches the training stop condition, the model parameters of the aquaculture water quality prediction model are saved, and the aquaculture water quality prediction model is output.

4. The intelligent detection method for aquaculture water quality according to claim 1, characterized in that: The aquaculture water quality prediction model is used to predict the water quality data of the current aquaculture area within a preset time, specifically: Acquiring water quality data of the current aquaculture area within a predetermined continuous time period, and formulating a water quality change curve based on the water quality data of the current aquaculture area within the predetermined continuous time period; Inputting the water quality change curve into the aquaculture water quality prediction model for prediction, and obtaining the water quality change curve of the current aquaculture area within a preset time through prediction; The water quality data of the current aquaculture area within the preset time is obtained according to the water quality change curve of the current aquaculture area within the preset time, and the water quality data of the current aquaculture area within the preset time is output.

5. The intelligent detection method for aquaculture water quality according to claim 1, characterized in that: Water quality warning is carried out based on the water quality data of the current aquaculture area within the preset time, specifically: Determining whether there is water quality data greater than a preset water quality index in the water quality data of the current aquaculture area within a preset time; When water quality data of the current aquaculture area within a preset time period contains water quality data that is greater than a preset water quality index, obtaining the most recent time point at which the water quality data is greater than the preset water quality index; A water quality warning is issued based on the most recent time point when the water quality data is greater than a preset water quality index.

6. The intelligent detection method for aquaculture water quality according to claim 1, characterized in that: Obtain the purification capacity data of the water purification equipment within a unit time, and formulate a water purification strategy based on the purification capacity data of the water purification equipment within a unit time and the water quality data of the current aquaculture area within a preset time, specifically: Acquire the purification capacity data of the water purification equipment within a unit time, and acquire the water quality data at the current time node based on the water quality data of the current aquaculture area within a preset time; Determining whether the water quality data at the current time node is greater than a preset water quality index threshold, and when the water quality data at the current time node is greater than the preset water quality index threshold, formulating a water purification strategy based on the water quality data at the current time node and the purification capacity data of the water purification equipment within a unit time; When the water quality data at the current time node is not greater than the preset water quality index threshold, the water quality data of the current aquaculture area within the preset time is continuously monitored.

7. The intelligent detection method for aquaculture water quality according to claim 6, characterized in that: A water purification strategy is formulated based on the water quality data at the current time point and the purification capacity data of the water purification equipment within a unit time, specifically: Initializing the number of purification devices, and calculating total purification capacity data per unit time based on the number of purification devices and the purification capacity data of the water purification devices per unit time; Obtaining purification capacity demand information within a unit time, and determining whether the total purification capacity data information within the unit time is the purification capacity demand information within the unit time; When the total purification capacity data information within the unit time is greater than the purification capacity demand information within the unit time, output the number of purification equipment, and purify the aquaculture water quality according to the number of purification equipment; When the total purification capacity data information within the unit time is not greater than the purification capacity demand information within the unit time, the number of purification devices is increased until it is greater than the purification capacity demand information within the unit time.

8. An intelligent detection device for aquaculture water quality, characterized in that: It comprises a memory and a processor, wherein the memory comprises a program of an intelligent detection method for aquaculture water quality, and when the program of the intelligent detection method for aquaculture water quality is executed by the processor, the steps of the intelligent detection method for aquaculture water quality as described in any one of claims 1 to 7 are implemented.

Images