Method and device for adjusting water changing angle of breeding work ship, storage medium and program product

Abstract

The invention discloses a cultivation work ship water changing angle adjusting method and device, a storage medium and a program product, and relates to the technical field of cultivation work ships, the water changing angle adjusting method comprises the following steps: obtaining a water quality parameter in a cultivation net cage, a heading parameter of a cultivation work ship and an external environment parameter; judging whether the water quality parameter meets a preset water quality standard; under the condition that the water quality parameter is lower than a preset water quality standard, processing the water quality parameter, the heading parameter and the external environment parameter by utilizing a water changing angle optimization model so as to obtain an optimal water changing angle and optimal holding time; adjusting the posture of the culture work ship to enable the included angle between the heading direction of the culture work ship and the external water flow direction to be the optimal water changing angle, and keeping the posture within the optimal maintaining time. When the water quality parameters are lower than the preset water quality standard, the water changing angle optimization model is used for processing the related parameters, the optimal water changing angle and the optimal maintaining time are obtained, and therefore the posture of the breeding work ship is adjusted to be the optimal water changing angle, and the water changing efficiency is improved.

Description

Technical Field

[0001] The present application relates to the technical field of aquaculture vessels, and in particular to a method, equipment, storage medium and program product for adjusting the water exchange angle of an aquaculture vessel. Background Art

[0002] To reduce energy consumption, aquaculture vessels spend most of their time in headwater flow during aquaculture. This minimizes the exchange efficiency between the water in the aquaculture cages and the surrounding water. Prolonged headwater flow can affect the water quality of the cages. Therefore, regular water changes are necessary during the aquaculture period. During these changes, the vessel's bow should be angled to the current for a period of time. However, the optimal angle for water changes remains uncertain.

[0003] The above content is only used to assist in understanding the technical solution of this application and does not constitute an admission that the above content is prior art. Summary of the Invention

[0004] The main purpose of this application is to provide a method, equipment, storage medium and program product for adjusting the water exchange angle of an aquaculture vessel, aiming to solve the technical problem of how to obtain the optimal water exchange angle of an aquaculture vessel.

[0005] To achieve the above-mentioned purpose, the present application proposes a method for adjusting the water exchange angle of an aquaculture vessel, wherein the aquaculture vessel comprises a bow, a midship, and a stern connected in sequence, wherein the midship is provided with an aquaculture cage, and the aquaculture cage is connected to an external water body;

[0006] The method for adjusting the water exchange angle of the aquaculture vessel comprises:

[0007] Acquiring water quality parameters in the aquaculture cage, bow parameters of the aquaculture vessel, and external environmental parameters; wherein the external environmental parameters include flow velocity and direction parameters and wind speed and direction parameters;

[0008] Determining whether the water quality parameters meet the preset water quality standards;

[0009] When the water quality parameters are lower than the preset water quality standards, a water exchange angle optimization model is used to process the water quality parameters, the heading parameters, and the external environment parameters to obtain an optimal water exchange angle and an optimal maintenance time; wherein the water exchange angle optimization model is composed of a trained BP neural network model and a genetic algorithm;

[0010] The posture of the aquaculture vessel is adjusted so that the angle between the bow direction of the aquaculture vessel and the external water flow direction is the optimal water exchange angle, and the posture is maintained within the optimal maintenance time.

[0011] In one embodiment, the step of obtaining the water quality parameters in the aquaculture cage, the heading parameters of the aquaculture vessel, and the external environment parameters includes:

[0012] Obtaining the water quality parameters, the heading parameters, the external environment parameters, the power consumption during the water change, the water change angle, and the duration of the water change;

[0013] The water quality parameter, the heading parameter, the external environment parameter, the power consumption during the water exchange, the water exchange angle, and the water exchange duration are formed into a first parameter set;

[0014] Preprocessing the first parameter set to obtain a preprocessed target parameter set;

[0015] Correspondingly, when the water quality parameter is lower than the preset standard, the step of using the water exchange angle optimization model to process the water quality parameter, the heading parameter and the external environment parameter to obtain the optimal water exchange angle and the optimal maintenance time includes:

[0016] When the water quality parameter is lower than the preset standard, the water exchange energy delay product model in the water exchange angle optimization model is used to process the water quality parameter, the heading parameter and the external environment parameter in the target parameter set to obtain an energy delay product function; wherein the water exchange energy delay product model in the water exchange angle optimization model is obtained by BP neural network training;

[0017] The energy-delay product function is iteratively optimized using a genetic algorithm in the water exchange angle optimization model to obtain the optimal water exchange angle and the optimal maintenance time.

[0018] In one embodiment, the water quality parameter and the external environment parameter are both parameter sequences during the water exchange duration;

[0019] The step of preprocessing the first parameter set to obtain a preprocessed target parameter set includes:

[0020] Performing data cleaning and data fusion on each parameter in the first parameter set to obtain a second parameter set;

[0021] Filtering the water quality parameters in the second parameter set, retaining the water quality parameters at the start and end times as a basis for determining whether to start or end the water exchange task;

[0022] Processing the external environment parameters in the second parameter set using a filtering algorithm based on a Kalman filter framework to obtain parameters representing the external environment during the water exchange period;

[0023] The target parameter set is obtained by combining the water quality parameters at the start and end times and the parameters of the external environment during the water exchange.

[0024] In one embodiment, when the water quality parameter is lower than a preset water quality standard, before the step of using a water exchange angle optimization model to process the water quality parameter, the heading parameter, and the external environment parameter to obtain an optimal water exchange angle and an optimal maintenance time, the method includes:

[0025] Acquire a historical parameter set of the aquaculture vessel during past water changes; wherein the historical parameter set includes at least historical water quality parameters, historical external environment parameters, and historical heading parameters;

[0026] Creating a water exchange dataset for aquaculture vessels based on the historical parameter set;

[0027] Construct BP neural network model;

[0028] The BP neural network model is trained and tested based on the aquaculture vessel water exchange data set to obtain a water exchange energy delay product model;

[0029] Construct genetic algorithms;

[0030] Based on the genetic algorithm, the water exchange energy delay product model is optimized and iterated to obtain the water exchange angle optimization model.

[0031] In one embodiment, the step of constructing the BP neural network model includes:

[0032] Construct the BP neural network model, set the activation function, loss function and back propagation algorithm of the BP neural network model, and randomly initialize the weights and bias of the BP neural network model.

[0033] In one embodiment, the step of training and testing the BP neural network model based on the aquaculture vessel water exchange dataset to obtain a water exchange energy delay product model includes:

[0034] The aquaculture vessel water exchange dataset is divided into a training set and a test set;

[0035] A training step, performing multiple rounds of training on the BP neural network model using the training set, and back-propagating the loss function according to a back-propagation algorithm to update the model parameters of the BP neural network model to obtain a trained BP neural network model; wherein the training set and the test set are re-partitioned in different training rounds;

[0036] A testing step, using a test set to evaluate the trained BP neural network model to obtain a model index of the trained BP neural network model; wherein the model index includes at least one of accuracy and precision;

[0037] If the model index reaches the preset model performance standard, the training and testing are terminated to obtain the water exchange energy delay product model;

[0038] If the model index is lower than the preset model performance standard, the hyperparameters of the trained BP neural network model are adjusted, and the training step and the testing step are repeated until the model index reaches the preset model performance standard to obtain the water exchange energy delay product model.

[0039] In one embodiment, the step of iteratively optimizing the water exchange energy delay product model based on the genetic algorithm to obtain the water exchange angle optimization model includes:

[0040] Construct the genetic algorithm framework, set the initial population and evolution termination conditions, and define the fitness function, selection function, crossover function, and mutation function.

[0041] In addition, to achieve the above-mentioned purpose, the present application also proposes a water exchange angle adjustment device for aquaculture vessels, the water exchange angle adjustment device comprising:

[0042] An acquisition module is used to obtain water quality parameters in the aquaculture cage, bow parameters of the aquaculture vessel, and external environmental parameters; wherein the external environmental parameters include flow velocity and direction parameters and wind speed and direction parameters;

[0043] A judgment module, used to judge whether the water quality parameters meet the preset water quality standards;

[0044] a processing module configured to process the water quality parameters, the heading parameters, and the external environment parameters using a water exchange angle optimization model to obtain an optimal water exchange angle and an optimal maintenance time when the water quality parameters are lower than a preset water quality standard; wherein the water exchange angle optimization model is composed of a trained BP neural network model and a genetic algorithm;

[0045] The adjustment module is used to adjust the posture of the aquaculture vessel so that the angle between the bow direction of the aquaculture vessel and the external water flow direction is the optimal water exchange angle, and maintain the posture within the optimal maintenance time.

[0046] In addition, to achieve the above-mentioned purpose, the present application also proposes a water exchange angle adjustment device for an aquaculture vessel, which includes: a memory, a processor, and a computer program stored on the memory and runnable on the processor, and the computer program is configured to implement the steps of the water exchange angle adjustment method for an aquaculture vessel as described above.

[0047] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium. A computer program is stored on the storage medium. When the computer program is executed by the processor, the steps of the method for adjusting the water exchange angle of the aquaculture vessel as described above are implemented.

[0048] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the method for adjusting the water exchange angle of the aquaculture vessel as described above.

[0049] One or more technical solutions proposed in this application have at least the following technical effects:

[0050] The present application adopts a method for adjusting the water exchange angle of an aquaculture vessel, wherein the aquaculture vessel includes a bow, midship and stern connected in sequence, and the midship is provided with an aquaculture cage, which is connected to the external water body; the method for adjusting the water exchange angle of the aquaculture vessel includes: obtaining water quality parameters in the aquaculture cage, bow parameters of the aquaculture vessel and external environmental parameters; wherein the external environmental parameters include flow velocity and direction parameters and wind speed and direction parameters; judging whether the water quality parameters meet the preset water quality standards; when the water quality parameters are lower than the preset water quality standards, using a water exchange angle optimization model to process the water quality parameters, bow parameters and external environmental parameters to obtain the optimal water exchange angle and the optimal maintenance time; wherein the water exchange angle optimization model is composed of a trained BP neural network model and a genetic algorithm; adjusting the posture of the aquaculture vessel so that the angle between the bow of the aquaculture vessel and the external water flow direction is the optimal water exchange angle, and maintaining the posture within the optimal maintenance time.

[0051] The present application obtains parameters such as water quality parameters, heading parameters and external environmental parameters, and automatically detects whether the water quality parameters meet the preset water quality standards, thereby realizing automatic water change detection; when the water quality parameters are lower than the preset water quality standards, the water change angle optimization model is used to process the water quality parameters, external environmental parameters and heading parameters to obtain the optimal water change angle and the optimal maintenance time, thereby facilitating the control of the posture of the aquaculture vessel and greatly improving the water change efficiency of the aquaculture vessel. Since the traditional calculation method is relatively complicated for the calculation of multiple factors such as external environmental parameters, heading parameters and water quality parameters that affect each other, it is often difficult to obtain the optimal water change angle efficiently and accurately. The water change angle optimization model adopted in this scheme uses the BP neural network model to extract and generalize the characteristic patterns of parameters such as external environmental parameters, heading parameters and water quality parameters, obtains a water change energy delay product model, and then iteratively optimizes the water change energy delay product model through a genetic algorithm, and finally obtains the water change angle optimization model. Therefore, the water change angle optimization model can achieve good prediction results of the optimal water change angle and the optimal water change time.

[0052] Because the traditional method of calculating the energy delay product is difficult to reflect the influence of multiple factors such as external environmental parameters, heading parameters and water quality parameters on the energy delay product, and the traditional calculation method often faces the challenge of high complexity and difficulty in efficiently and accurately determining the optimal parameter combination when dealing with the problem of the mutual influence of multiple factors such as external environmental parameters, heading parameters and water quality parameters. In contrast, the use of a BP neural network model can deeply analyze the complex relationship between various parameters through the powerful feature extraction and generalization capabilities of the neural network, thereby providing a more accurate water change energy delay product function, and then obtain the effect of the optimal water change angle and water change time prediction through genetic algorithm iterative optimization. In addition, compared with the traditional calculation method, the water change angle optimization model of the present application not only improves the prediction accuracy, but also has strong adaptability and robustness under different conditions; the water change angle optimization model based on neural network and genetic algorithm can automatically identify the key factors and their interaction patterns in various parameters by learning a large amount of historical data, and the genetic algorithm can automatically iteratively optimize to obtain the optimal solution, thereby more efficiently and accurately solving complex multi-parameter decision-making problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0054] In order to more clearly illustrate the embodiments of the present application 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, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0055] Figure 1 A flow chart showing the first embodiment of the method for adjusting the water exchange angle of aquaculture vessels provided in this application;

[0056] Figure 2 This is a flow chart of the third embodiment of the method for adjusting the water exchange angle of aquaculture vessels of the present application;

[0057] Figure 3 This is a schematic diagram of the module structure of the water exchange angle adjustment device for aquaculture vessels according to an embodiment of the present application;

[0058] Figure 4 This is a schematic diagram of the equipment structure of the hardware operating environment involved in the method for adjusting the water exchange angle of an aquaculture vessel in the embodiment of the present application.

[0059] The purpose, features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0060] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0061] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0062] The main solution of the embodiment of the present application is: by adopting a method for adjusting the water exchange angle of an aquaculture vessel, the aquaculture vessel includes a bow, midship and stern connected in sequence, and the midship is provided with an aquaculture cage, which is connected to the external water body; the method for adjusting the water exchange angle of the aquaculture vessel includes: obtaining water quality parameters in the aquaculture cage, bow parameters of the aquaculture vessel and external environmental parameters; wherein the external environmental parameters include flow velocity and direction parameters and wind speed and direction parameters; judging whether the water quality parameters meet the preset water quality standards; when the water quality parameters are lower than the preset water quality standards, using a water exchange angle optimization model to process the water quality parameters, bow parameters and external environmental parameters to obtain the optimal water exchange angle and the optimal maintenance time; wherein the water exchange angle optimization model is composed of a trained BP neural network model and a genetic algorithm; adjusting the posture of the aquaculture vessel so that the angle between the bow of the aquaculture vessel and the external water flow direction is the optimal water exchange angle, and maintaining the posture within the optimal maintenance time.

[0063] In this embodiment, for ease of description, the following description is made with the platform computing terminal as the execution entity.

[0064] Currently, to reduce energy consumption, aquaculture vessels spend most of their time in headwater conditions during aquaculture. This minimizes the exchange efficiency between the water in the aquaculture cages and the surrounding water. Prolonged headwater conditions can affect the water quality of the cages. Therefore, regular water changes are necessary during the aquaculture period. During these changes, the vessel's bow must be angled to the current for a period of time. However, the optimal angle for water changes remains uncertain.

[0065] Based on this, the present application provides a solution, by adopting a method for adjusting the water exchange angle of an aquaculture vessel, the aquaculture vessel includes a bow, midship and stern connected in sequence, the midship is provided with an aquaculture cage, and the aquaculture cage is connected to the external water body; the method for adjusting the water exchange angle of the aquaculture vessel includes: obtaining water quality parameters in the aquaculture cage, bow parameters of the aquaculture vessel and external environmental parameters; wherein, the external environmental parameters include flow velocity and direction parameters and wind speed and direction parameters; judging whether the water quality parameters meet the preset water quality standards; when the water quality parameters are lower than the preset water quality standards, the water exchange angle optimization model is used to process the water quality parameters, bow parameters and external environmental parameters to obtain the optimal water exchange angle and the optimal maintenance time; wherein, the water exchange angle optimization model is composed of a trained BP neural network model and a genetic algorithm; adjust the posture of the aquaculture vessel so that the angle between the bow of the aquaculture vessel and the external water flow direction is the optimal water exchange angle, and maintain the posture within the optimal maintenance time.

[0066] The present application obtains parameters such as water quality parameters, heading parameters and external environmental parameters, and automatically detects whether the water quality parameters meet the preset water quality standards, thereby realizing automatic water change detection; when the water quality parameters are lower than the preset water quality standards, the water change angle optimization model is used to process the water quality parameters, external environmental parameters and heading parameters to obtain the optimal water change angle and the optimal maintenance time, thereby facilitating the control of the posture of the aquaculture vessel and greatly improving the water change efficiency of the aquaculture vessel. Since the traditional calculation method is relatively complicated for the calculation of multiple factors such as external environmental parameters, heading parameters and water quality parameters that affect each other, it is often difficult to obtain the optimal water change angle efficiently and accurately. The water change angle optimization model adopted in this scheme uses the BP neural network model to extract and generalize the characteristic patterns of parameters such as external environmental parameters, heading parameters and water quality parameters, obtains a water change energy delay product model, and then iteratively optimizes the water change energy delay product model through a genetic algorithm, and finally obtains the water change angle optimization model. Therefore, the water change angle optimization model can achieve good prediction results of the optimal water change angle and the optimal water change time.

[0067] Because the traditional method of calculating the energy delay product is difficult to reflect the influence of multiple factors such as external environmental parameters, heading parameters and water quality parameters on the energy delay product, and the traditional calculation method often faces the challenge of high complexity and difficulty in efficiently and accurately determining the optimal parameter combination when dealing with the problem of the mutual influence of multiple factors such as external environmental parameters, heading parameters and water quality parameters. In contrast, the use of a BP neural network model can deeply analyze the complex relationship between various parameters through the powerful feature extraction and generalization capabilities of the neural network, thereby providing a more accurate water change energy delay product function, and then obtain the effect of the optimal water change angle and water change time prediction through genetic algorithm iterative optimization. In addition, compared with the traditional calculation method, the water change angle optimization model of the present application not only improves the prediction accuracy, but also has strong adaptability and robustness under different conditions; the water change angle optimization model based on neural network and genetic algorithm can automatically identify the key factors and their interaction patterns in various parameters by learning a large amount of historical data, and the genetic algorithm can automatically iteratively optimize to obtain the optimal solution, thereby more efficiently and accurately solving complex multi-parameter decision-making problems.

[0068] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of implementing the above functions, a platform computing terminal, etc. The following describes this embodiment and the following embodiments using a platform computing terminal as an example.

[0069] Based on this, the embodiment of the present application provides a method for adjusting the water change angle of a breeding vessel, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for adjusting the water exchange angle of an aquaculture vessel of the present application.

[0070] In this embodiment, the aquaculture vessel comprises a bow, a midship and a stern connected in sequence, wherein the midship is provided with an aquaculture cage, and the aquaculture cage is connected to an external water body;

[0071] The method for adjusting the water exchange angle of aquaculture vessels includes steps S10 to S50:

[0072] Step S10, obtaining water quality parameters in the aquaculture cage, bow parameters of the aquaculture vessel, and external environmental parameters; wherein the external environmental parameters include flow velocity and direction parameters and wind speed and direction parameters;

[0073] It should be noted that water quality parameters may include dissolved oxygen content, temperature, pH value, salinity, turbidity, nitrate, heavy metals, ammonia nitrogen, phosphorus and other related parameters that are crucial to the survival of the cultured objects, and may also include other factors, which are not limited here. The heading parameter is used to reflect the direction in which the head of the aquaculture vessel is pointing. The heading can be measured and obtained by using a compass, an inertial navigation system, a global positioning system, an automatic identification system and other methods. Among the external environmental parameters, the flow velocity and direction and the wind speed and direction will have a greater impact on the water exchange efficiency, so the external environmental parameters include at least one of the flow velocity and direction parameters and the wind speed and direction parameters; preferably, the external environmental parameters include the flow velocity and direction parameters and the wind speed and direction parameters. In addition, other parameters can also be obtained, which will not be repeated here.

[0074] Step S20, determining whether the water quality parameters meet the preset water quality standards;

[0075] The preset water quality standard can be a specific numerical parameter, such as a dissolved oxygen content standard of A mg / L, or a numerical range, such as a dissolved oxygen content standard within the range of [a, b] mg / L. The preset water quality standard can be preset in the platform computing terminal of the aquaculture vessel or obtained through a communication method such as a server or the internet, and is not limited here.

[0076] Step S40: When the water quality parameter is lower than a preset water quality standard, a water exchange angle optimization model is used to process the water quality parameter, the heading parameter, and the external environment parameter to obtain an optimal water exchange angle and an optimal maintenance time; wherein the water exchange angle optimization model is composed of a trained BP neural network model and a genetic algorithm;

[0077] A BP neural network is a multi-layer feedforward artificial neural network model, also known as a back-propagation neural network. Its basic components include an input layer, a hidden layer, and an output layer. Each layer has multiple nodes, each connected to all nodes in the next layer, and the connections between nodes have their own weights. The training process of a BP neural network has two phases: forward propagation and back-propagation.

[0078] After data enters the input layer, it undergoes weighted summation and activation function processing in the hidden layer before being passed to the output layer to generate the output. At the output layer, the data is compared with the preset expected value and the loss function is calculated. This is known as forward propagation. If the loss function value is too large, the loss value is propagated forward layer by layer. Each layer then adjusts its weights based on the propagated error value. This weight adjustment is updated using the backpropagation algorithm, also known as reverse propagation. This forward and reverse cycle constitutes a cycle. Repeating the preset cycles will train the corresponding BP neural network model.

[0079] Step S50, adjusting the posture of the aquaculture vessel so that the angle between the bow direction of the aquaculture vessel and the external water flow direction is the optimal water exchange angle, and maintaining the posture within the optimal maintenance time.

[0080] This embodiment provides a method for adjusting the water exchange angle of an aquaculture vessel, which realizes automatic water exchange detection by obtaining parameters such as water quality parameters, bow parameters and external environmental parameters, and automatically detecting whether the water quality parameters meet the preset water quality standards; when the water quality parameters are lower than the preset water quality standards, the water exchange angle optimization model is used to process the water quality parameters, external environmental parameters and bow parameters to obtain the optimal water exchange angle and the optimal maintenance time, thereby facilitating the control of the posture of the aquaculture vessel and greatly improving the water exchange efficiency of the aquaculture vessel. Since traditional calculation methods are more complicated for the mutual influence of multiple factors such as external environmental parameters, heading parameters and water quality parameters, it is often difficult to obtain the optimal water exchange angle efficiently and accurately. The water exchange angle optimization model adopted in this scheme uses the BP neural network model to extract and generalize the characteristic patterns of parameters such as external environmental parameters, heading parameters and water quality parameters to obtain a water exchange energy delay product model, and then iteratively optimizes the water exchange energy delay product model through a genetic algorithm to finally obtain the water exchange angle optimization model. Therefore, the water exchange angle optimization model can achieve good prediction effects of the optimal water exchange angle and the optimal water exchange time.

[0081] Because the traditional method of calculating the energy delay product is difficult to reflect the influence of multiple factors such as external environmental parameters, heading parameters and water quality parameters on the energy delay product, and the traditional calculation method often faces the challenge of high complexity and difficulty in efficiently and accurately determining the optimal parameter combination when dealing with the problem of the mutual influence of multiple factors such as external environmental parameters, heading parameters and water quality parameters. In contrast, the use of a BP neural network model can deeply analyze the complex relationship between various parameters through the powerful feature extraction and generalization capabilities of the neural network, thereby providing a more accurate water change energy delay product function, and then obtain the effect of the optimal water change angle and water change time prediction through genetic algorithm iterative optimization. In addition, compared with the traditional calculation method, the water change angle optimization model of the present application not only improves the prediction accuracy, but also has strong adaptability and robustness under different conditions; the water change angle optimization model based on neural network and genetic algorithm can automatically identify the key factors and their interaction patterns in various parameters by learning a large amount of historical data, and the genetic algorithm can automatically iteratively optimize to obtain the optimal solution, thereby more efficiently and accurately solving complex multi-parameter decision-making problems.

[0082] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction and will not be repeated hereafter. On this basis, step S10 includes steps S11 to S13:

[0083] Step S11, obtaining the water quality parameters, the heading parameters, the external environment parameters, the power consumption during the water change period, the water change angle, and the water change duration;

[0084] It should be noted that the water change duration includes the start and end time of the water change task.

[0085] Step S12, forming a first parameter set by combining the water quality parameter, the heading parameter, the external environment parameter, the power consumption during the water exchange, the water exchange angle, and the water exchange duration;

[0086] Step S13: preprocessing the first parameter set to obtain a preprocessed target parameter set;

[0087] Correspondingly, step S40 includes steps S41 to S42:

[0088] Step S41, when the water quality parameter is lower than a preset standard, using the water exchange energy delay product model in the water exchange angle optimization model to process the water quality parameter, heading parameter, and external environment parameter in the target parameter set to obtain an energy delay product function; wherein the water exchange energy delay product model in the water exchange angle optimization model is obtained by BP neural network training;

[0089] It should be noted that the energy-delay product function is used to reflect the relationship between the water exchange energy consumption and the water exchange angle and the water exchange maintenance time.

[0090] Step S42: Iteratively optimize the energy-delay product function using the genetic algorithm in the water exchange angle optimization model to obtain the optimal water exchange angle and the optimal maintenance time.

[0091] In this embodiment, by forming the collected parameters into a first parameter set, the data can be made more orderly, easier to manage, and easier to access. This helps maintain the consistency and integrity of the data; by preprocessing the parameters in the first parameter set, the parameters in the obtained target parameter set are made more consistent with the learning process of the water exchange angle optimization model, thereby improving the training efficiency of the model and improving the prediction accuracy and generalization ability of the water exchange angle optimization model obtained ultimately; by using the water exchange energy delay product model in the water exchange angle optimization model to process the water quality parameters, heading parameters, and external environmental parameters in the target parameter set, an energy delay product function that can reflect the relationship between water exchange energy consumption and water exchange angle and water exchange maintenance time is obtained, so that the genetic algorithm in the water exchange angle optimization model can be used to iteratively optimize this function and obtain an accurate optimal water exchange angle and optimal maintenance time.

[0092] Furthermore, in a feasible embodiment, the water quality parameter and the external environment parameter are both parameter sequences during the water exchange duration;

[0093] Step S13 may include steps S131 to S134:

[0094] Step S131, performing data cleaning and data fusion on each parameter in the first parameter set to obtain a second parameter set;

[0095] Among them, data cleaning includes missing value cleaning, format and content unification, logical problem cleaning and deletion of unnecessary data; data fusion refers to the fusion of multi-source data. Kalman filtering can be used as one of the data fusion methods, or it can be combined with other methods to achieve better fusion effects.

[0096] Step S132, screening the water quality parameters in the second parameter set, retaining the water quality parameters at the start and end times as a basis for determining whether to start and end the water exchange task;

[0097] Step S133: processing the external environment parameters in the second parameter set based on a filtering algorithm of a Kalman filter framework to obtain parameters characterizing the external environment during the water exchange period;

[0098] Step S134 , combining the water quality parameters at the start and end times and the parameters of the external environment during the water exchange period to obtain the target parameter set.

[0099] In this embodiment, by cleaning and fusing the parameters in the first parameter set, the noise parameters in the parameters are filtered out, and the outlier parameters are avoided from affecting the model training. The data fusion processing enables the parameters collected based on different sensors and different locations to be unified; by filtering the parameters in the second parameter set and making them into a data style that is conducive to model training, it is ensured that the water quality parameters, heading parameters and external environment parameters learned by the model have a correct correspondence, so that the model can grasp the correct rules and have a more accurate prediction capability of the optimal water exchange angle.

[0100] Based on the first embodiment of the present application, in the third embodiment of the present application, the same or similar contents as those in the first embodiment can be referred to the above introduction and will not be described in detail later. Figure 2 Before step S40, the method for adjusting the water exchange angle of the aquaculture vessel further includes steps S31 to S36:

[0101] Step S31, obtaining a historical parameter set of the aquaculture vessel during past water changes; wherein the historical parameter set at least includes historical water quality parameters, historical external environment parameters, and historical heading parameters;

[0102] Step S32, generating a water exchange data set for aquaculture vessels based on the historical parameter set;

[0103] Among them, by making the historical parameter set into a data set, each parameter is made to conform to the input format of the BP neural network model, so that the subsequent BP neural network model can efficiently read the training set and test set.

[0104] Step S33, constructing a BP neural network model;

[0105] In addition, in a feasible implementation, step S33 may include step S331:

[0106] Step S331, constructing the BP neural network model, setting the activation function, loss function and back propagation algorithm of the BP neural network model, and randomly initializing the weights and bias of the BP neural network model.

[0107] Among them, the activation function of the BP neural network model can adopt activation functions such as sigmoid function, ReLU, Tanh, Softmax, etc. The loss function can adopt loss functions such as mean square error, cross entropy loss, log likelihood loss, etc. Preferably, the loss function can adopt cross entropy loss function. The back propagation algorithm of the BP neural network model can adopt stochastic gradient descent, batch gradient descent, mini-batch gradient descent, momentum method (Momentum), RMSprop, Adam, etc. Preferably, the optimization algorithm can adopt Adam algorithm. Adam algorithm combines the advantages of both Momentum and RMSprop, can consider first-order moment estimation and second-order moment estimation at the same time, and provides bias correction, so it has good performance and ease of use. Therefore, in this embodiment, Adam can preferably be used as the optimization algorithm of the BP neural network model.

[0108] In this embodiment, by setting an activation function for the BP neural network model, nonlinear factors can be introduced into the neurons in the BP neural network model so that the model can also achieve good fitting for nonlinear function data; by setting a suitable loss function, the model can calculate the loss function and use back propagation to update the model weights so that the model can be iteratively optimized; by setting an optimization algorithm, the model parameters can be adjusted using the optimization algorithm to minimize the loss function, thereby improving the performance of the model. By random initialization, the model can obtain a random weight and bias at the initial stage, so that the weight and bias of the model can be updated later during the training process.

[0109] Step S34, training and testing the BP neural network model based on the aquaculture vessel water exchange data set to obtain a water exchange energy delay product model;

[0110] In addition, in a feasible implementation, step S34 may include steps S341 to S345:

[0111] Step S341, dividing the aquaculture vessel water exchange dataset into a training set and a test set;

[0112] Step S342, a training step, performing multiple rounds of training on the BP neural network model using the training set, and updating the model parameters of the BP neural network model according to the loss function to obtain a trained BP neural network model; wherein the training set and the test set are re-partitioned in different training rounds;

[0113] It should be noted that in order to prevent overfitting in the BP neural network model training, the training set and test set are re-divided in different training rounds.

[0114] Step S343, a testing step, performing an evaluation test on the trained BP neural network model using a test set to obtain a model index of the trained BP neural network model; wherein the model index includes at least one of accuracy and precision;

[0115] Among them, in addition to accuracy and precision, model indicators can also include recall, F1 score, area under the AUC-ROC curve, etc., and no limitation is made here.

[0116] Step S344: If the model index reaches the preset model performance standard, the training and testing are terminated to obtain the water exchange energy delay product model;

[0117] Step S345: If the model index is lower than the preset model performance standard, the hyperparameters of the trained BP neural network model are adjusted, and the training step and the testing step are repeated until the model index reaches the preset model performance standard to obtain the water exchange energy delay product model.

[0118] In this embodiment, by training the BP neural network model for a preset number of training rounds, the model parameters of the BP neural network model are fully iteratively updated during multiple rounds of training, making the model's prediction performance closer to the actual situation and improving the model's performance. The model is tested using a test set to obtain model indicators, which are then used to determine whether the trained BP neural network model meets the preset model performance standards. If the model indicators meet the preset model performance standards, training and testing are terminated to obtain the final water exchange energy delay product model. If the model indicators do not meet the preset model performance standards, the model hyperparameters are adjusted, and the training and testing steps are repeated until the model indicators meet the preset model performance standards to obtain the water exchange energy delay product model. The water exchange energy delay product model obtained through training and testing in steps S341 to S345 can effectively reflect the relationship between water exchange energy consumption, water exchange angle, and water exchange duration based on the input water quality parameters, heading parameters, and external environmental parameters, providing a more accurate optimization objective function for the subsequent genetic algorithm.

[0119] Step S35, constructing a genetic algorithm;

[0120] As an optional implementation, step S35 includes step S351:

[0121] Step S351: construct a genetic algorithm framework, set the initialization population and evolution termination conditions, and define the fitness function, selection function, crossover function, and mutation function.

[0122] It should be noted that during the water change of the aquaculture vessel, it is necessary to take into account both practicality and low energy consumption, so the fitness function is chosen to be the energy-delay product function. In the computer field, the energy-delay product is one of the more important indicators for measuring CPU performance indicators. It is a product combination of the energy and time consumed by the CPU to complete an instruction or a task. When the aquaculture vessel changes water, the lower the energy consumption, the better, because the energy consumption of the aquaculture vessel is the lowest in the top flow state, but this is the state with the lowest water change efficiency. When changing water for aquaculture vessels, not only energy consumption must be considered, but also water change efficiency. Therefore, this application uses the energy-delay product as the water change indicator for aquaculture vessels, sets it as the fitness function of the genetic algorithm, and performs iterative optimization to obtain the optimal water change angle and the optimal water change maintenance time.

[0123] Step S36: Based on the genetic algorithm, the water exchange energy delay product model is optimized and iterated to obtain the water exchange angle optimization model.

[0124] In this embodiment, the historical water quality parameters, historical bow parameters and historical external environment parameters of the aquaculture vessel during the past water changes are obtained and made into training sets and test sets, so that each parameter can be converted into a training set and test set format that can be input into the BP neural network model, and this format will be more suitable for the learning process of the model; by constructing a BP neural network model and using the training set and test set to train and test the model, a water change energy delay product model is obtained; and then a genetic algorithm is used to optimize and iterate the water change energy delay product model, and finally a water change angle optimization model is obtained.

[0125] This application also provides a water exchange angle adjustment device for aquaculture vessels, please refer to Figure 3 The aquaculture vessel water exchange angle adjustment device comprises:

[0126] The acquisition module 10 is used to obtain water quality parameters in the aquaculture cage, the heading parameters of the aquaculture vessel, and external environmental parameters; wherein the external environmental parameters include flow velocity and direction parameters and wind speed and direction parameters;

[0127] The judging module 20 is used to judge whether the water quality parameters meet the preset standards;

[0128] a processing module 40 for processing the water quality parameters, the heading parameters, and the external environment parameters using a water exchange angle optimization model to obtain an optimal water exchange angle and an optimal maintenance time when the water quality parameters are lower than a preset standard; wherein the water exchange angle optimization model is composed of a trained BP neural network model and a genetic algorithm;

[0129] The adjustment module 50 is used to adjust the posture of the aquaculture vessel so that the angle between the bow direction of the aquaculture vessel and the external water flow direction is the optimal water exchange angle, and maintain the posture within the optimal maintenance time.

[0130] The aquaculture vessel water exchange angle adjustment device provided in this application utilizes the aquaculture vessel water exchange angle adjustment method described in the aforementioned embodiment to address the technical problem of obtaining the optimal water exchange angle for aquaculture vessels. Compared to the prior art, the beneficial effects of the aquaculture vessel water exchange angle adjustment device provided in this application are the same as those of the aquaculture vessel water exchange angle adjustment method described in the aforementioned embodiment. Other technical features of the aquaculture vessel water exchange angle adjustment device are the same as those disclosed in the aforementioned embodiment and are not further detailed here.

[0131] The present application provides a water exchange angle adjustment device for an aquaculture vessel, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the water exchange angle adjustment method for the aquaculture vessel in the above-mentioned embodiment one.

[0132] Reference below Figure 4 , which shows a schematic structural diagram of a water exchange angle adjustment device for aquaculture vessels suitable for implementing an embodiment of the present application. The water exchange angle adjustment device for aquaculture vessels in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (e.g., vehicle-mounted navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 4 The water exchange angle adjustment device for aquaculture vessels shown is merely an example and should not impose any limitations on the functions and scope of use of the embodiments of the present application.

[0133] like Figure 4As shown, the aquaculture vessel water exchange angle adjustment device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. Various programs and data required for the operation of the aquaculture vessel water exchange angle adjustment device are also stored in RAM 1004. The processing device 1001, ROM 1002, and RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, hard disk, etc.; and communication devices 1009. Communication devices 1009 can allow the aquaculture vessel water exchange angle adjustment device to communicate wirelessly or wired with other devices to exchange data. While the figure shows an aquaculture vessel water exchange angle adjustment device with various systems, it should be understood that not all of the illustrated systems are required to be implemented or present. More or fewer systems may alternatively be implemented or present.

[0134] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0135] The aquaculture vessel water-change angle adjustment device provided in this application utilizes the aquaculture vessel water-change angle adjustment method described in the aforementioned embodiment to address the technical problem of obtaining the optimal water-change angle for aquaculture vessels. Compared to the prior art, the beneficial effects of the aquaculture vessel water-change angle adjustment device provided in this application are the same as those of the aquaculture vessel water-change angle adjustment method described in the aforementioned embodiment. Other technical features of the aquaculture vessel water-change angle adjustment device are the same as those disclosed in the aforementioned embodiment and are not further detailed here.

[0136] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0137] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0138] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer program) stored thereon, and the computer-readable program instructions are used to execute the method for adjusting the water exchange angle of the aquaculture vessel in the above-mentioned embodiment.

[0139] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0140] The computer-readable storage medium may be included in the aquaculture vessel water-changing angle adjustment device; or it may exist independently without being assembled into the aquaculture vessel water-changing angle adjustment device.

[0141] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the aquaculture vessel water exchange angle adjustment device, the aquaculture vessel water exchange angle adjustment device is enabled to: obtain the water quality parameters in the aquaculture cage, the bow parameters of the aquaculture vessel and the external environmental parameters; wherein the external environmental parameters include flow velocity and direction parameters and wind speed and direction parameters; determine whether the water quality parameters meet the preset water quality standards; when the water quality parameters are lower than the preset water quality standards, use the water exchange angle optimization model to process the water quality parameters, bow parameters and external environmental parameters to obtain the optimal water exchange angle and the optimal maintenance time; wherein the water exchange angle optimization model is composed of a trained BP neural network model and a genetic algorithm; adjust the posture of the aquaculture vessel so that the angle between the bow of the aquaculture vessel and the external water flow direction is the optimal water exchange angle, and maintain the posture within the optimal maintenance time.

[0142] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0143] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0144] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0145] The computer-readable storage medium provided in this application stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned method for adjusting the water exchange angle for aquaculture vessels. This computer-readable storage medium solves the technical problem of determining the optimal water exchange angle for aquaculture vessels. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are similar to those of the method for adjusting the water exchange angle for aquaculture vessels provided in the aforementioned embodiments, and are not further elaborated here.

[0146] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for adjusting the water exchange angle of an aquaculture vessel.

[0147] The computer program product provided in this application can solve the technical problem of how to obtain the optimal water exchange angle for aquaculture vessels. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the method for adjusting the water exchange angle for aquaculture vessels provided in the above embodiment, and will not be elaborated here.

[0148] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for adjusting the water exchange angle of a breeding vessel, characterized in that: The aquaculture vessel comprises a bow, a midship and a stern connected in sequence, wherein the midship is provided with an aquaculture cage, and the aquaculture cage is connected to an external water body; The method for adjusting the water exchange angle of the aquaculture vessel comprises: Acquiring water quality parameters in the aquaculture cage, bow parameters of the aquaculture vessel, and external environmental parameters; wherein the external environmental parameters include flow velocity and direction parameters and wind speed and direction parameters; Determining whether the water quality parameters meet the preset water quality standards; When the water quality parameters are lower than the preset water quality standards, a water exchange angle optimization model is used to process the water quality parameters, the heading parameters, and the external environment parameters to obtain an optimal water exchange angle and an optimal maintenance time; wherein the water exchange angle optimization model is composed of a trained BP neural network model and a genetic algorithm; The posture of the aquaculture vessel is adjusted so that the angle between the bow direction of the aquaculture vessel and the external water flow direction is the optimal water exchange angle, and the posture is maintained within the optimal maintenance time.

2. The method according to claim 1, wherein The step of obtaining the water quality parameters in the aquaculture cage, the heading parameters of the aquaculture vessel, and the external environment parameters comprises: Obtaining the water quality parameters, the heading parameters, the external environment parameters, the power consumption during the water change, the water change angle, and the duration of the water change; The water quality parameter, the heading parameter, the external environment parameter, the power consumption during the water exchange, the water exchange angle, and the water exchange duration are formed into a first parameter set; Preprocessing the first parameter set to obtain a preprocessed target parameter set; Correspondingly, when the water quality parameter is lower than the preset standard, the step of using the water exchange angle optimization model to process the water quality parameter, the heading parameter and the external environment parameter to obtain the optimal water exchange angle and the optimal maintenance time includes: When the water quality parameter is lower than the preset standard, the water exchange energy delay product model in the water exchange angle optimization model is used to process the water quality parameter, the heading parameter and the external environment parameter in the target parameter set to obtain an energy delay product function; wherein the water exchange energy delay product model in the water exchange angle optimization model is obtained by BP neural network training; The energy-delay product function is iteratively optimized using a genetic algorithm in the water exchange angle optimization model to obtain the optimal water exchange angle and the optimal maintenance time.

3. The method according to claim 2, wherein The water quality parameters and the external environment parameters are parameter sequences during the water exchange period; The step of preprocessing the first parameter set to obtain a preprocessed target parameter set includes: Performing data cleaning and data fusion on each parameter in the first parameter set to obtain a second parameter set; Filtering the water quality parameters in the second parameter set, retaining the water quality parameters at the start and end times as a basis for determining whether to start or end the water exchange task; Processing the external environment parameters in the second parameter set using a filtering algorithm based on a Kalman filter framework to obtain parameters representing the external environment during the water exchange period; The target parameter set is obtained by combining the water quality parameters at the start and end times and the parameters of the external environment during the water exchange.

4. The method according to claim 1, wherein Before the step of using a water exchange angle optimization model to process the water quality parameters, the heading parameters, and the external environment parameters to obtain an optimal water exchange angle and an optimal maintenance time when the water quality parameters are lower than a preset water quality standard, the method includes: Acquire a historical parameter set of the aquaculture vessel during past water changes; wherein the historical parameter set includes at least historical water quality parameters, historical external environment parameters, and historical heading parameters; Creating a water exchange dataset for aquaculture vessels based on the historical parameter set; Construct BP neural network model; The BP neural network model is trained and tested based on the aquaculture vessel water exchange data set to obtain a water exchange energy delay product model; Construct genetic algorithms; Based on the genetic algorithm, the water exchange energy delay product model is optimized and iterated to obtain the water exchange angle optimization model.

5. The method according to claim 4, wherein The steps of constructing the BP neural network model include: Construct the BP neural network model, set the activation function, loss function and back propagation algorithm of the BP neural network model, and randomly initialize the weights and bias of the BP neural network model.

6. The method according to claim 4, wherein The step of training and testing the BP neural network model based on the aquaculture vessel water exchange data set to obtain a water exchange energy delay product model includes: The aquaculture vessel water exchange dataset is divided into a training set and a test set; A training step, performing multiple rounds of training on the BP neural network model using the training set, and back-propagating the loss function according to a back-propagation algorithm to update the model parameters of the BP neural network model to obtain a trained BP neural network model; wherein the training set and the test set are re-partitioned in different training rounds; A testing step, using a test set to evaluate the trained BP neural network model to obtain a model index of the trained BP neural network model; wherein the model index includes at least one of accuracy and precision; If the model index reaches the preset model performance standard, the training and testing are terminated to obtain the water exchange energy delay product model; If the model index is lower than the preset model performance standard, the hyperparameters of the trained BP neural network model are adjusted, and the training step and the testing step are repeated until the model index reaches the preset model performance standard to obtain the water exchange energy delay product model.

7. The method according to claim 4, wherein The steps of constructing a genetic algorithm include: Construct the genetic algorithm framework, set the initial population and evolution termination conditions, and define the fitness function, selection function, crossover function, and mutation function.

8. A water-changing angle adjustment device for aquaculture vessels, characterized in that: The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for adjusting the water exchange angle of an aquaculture vessel according to any one of claims 1 to 7.

9. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for adjusting the water exchange angle of an aquaculture vessel according to any one of claims 1 to 7 are implemented.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the method for adjusting the water exchange angle of an aquaculture vessel according to any one of claims 1 to 7 are implemented.

Images