Intelligent control system and method for recirculating aquaculture equipment

Abstract

The invention provides an intelligent control system and method for recirculating aquaculture equipment, relates to the field of intelligent aquaculture control, and adopts an artificial intelligence analysis technology based on deep learning. Characteristic extraction is carried out on the dissolved oxygen content at multiple time points and the flow value of the water jet device to obtain the time sequence characteristic of the dissolved oxygen content and the flow time sequence characteristic of the water jet device, and the extracted time sequence characteristic of the dissolved oxygen content and the extracted flow time sequence characteristic of the water jet device are associated. And finally, the flow regulation and control direction of the water jet device is obtained through a classifier according to the associated features. Thus, by establishing the relation between the dissolved oxygen and the flow of the water jet device, the dissolved oxygen control strategy is optimized, real-time response and adjustment are achieved, and therefore the stability of the breeding environment is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent aquaculture control, and more specifically, to an intelligent control system and method for circulating water aquaculture equipment. Background Art

[0002] The pond recirculating water aquaculture model divides the pond into a flowing water fish farming area and a circulating water purification treatment area. It has the advantages of high water resource utilization efficiency, efficient land saving, and good water quality. It meets the requirements of water ecological environment protection and has been widely used and promoted in recent years.

[0003] In this farming model, the control of dissolved oxygen (DO) content is very important. Dissolved oxygen is one of the necessary conditions for the survival and growth of aquatic organisms. It affects the metabolic activities of farmed organisms and the balance of the entire aquatic ecosystem. If the dissolved oxygen content is too low, it will cause suffocation and death of farmed organisms; if it is too high, it may cause symptoms such as bubble disease. In general, maintaining an appropriate dissolved oxygen level is a key factor in ensuring successful farming. However, traditional methods usually rely on manual monitoring and manual adjustments, which may lead to fluctuations in dissolved oxygen content and poor control.

[0004] Therefore, an intelligent control solution for circulating aquaculture equipment is needed. Summary of the invention

[0005] In view of the shortcomings of the prior art, the present application provides an intelligent control system and method for circulating aquaculture equipment.

[0006] According to one aspect of the present application, an intelligent control system for circulating aquaculture equipment is provided, which includes:

[0007] A recirculating aquaculture-related data acquisition module, used to obtain the dissolved oxygen content of the aquaculture water at multiple predetermined time points within a predetermined time period and the flow value of the water ejector used for the aquaculture tank water circulation;

[0008] A dissolved oxygen content time series feature extraction module, used for extracting features of the dissolved oxygen content of the aquaculture water at the plurality of predetermined time points to obtain a dissolved oxygen content time series feature vector;

[0009] A water ejector flow time series feature extraction module, used for extracting features of the flow values ​​of the water ejector used for water circulation in the aquaculture tank at the plurality of predetermined time points to obtain a water ejector flow difference time series feature vector;

[0010] A responsiveness estimation module, used for calculating the responsiveness estimation of the dissolved oxygen content time series characteristic vector relative to the water jet flow difference time series characteristic vector to obtain a dissolved oxygen change responsiveness characteristic matrix;

[0011] The flow control direction result generating module is used to determine the flow control direction of the water ejector at the current time point based on the dissolved oxygen change responsiveness characteristic matrix.

[0012] According to another aspect of the present application, there is provided an intelligent control method for circulating aquaculture equipment, which comprises:

[0013] Obtaining the dissolved oxygen content of the aquaculture water and the flow value of the water ejector used for water circulation in the aquaculture tank at a plurality of predetermined time points within a predetermined time period;

[0014] Extracting features of dissolved oxygen content in the aquaculture water at the plurality of predetermined time points to obtain a time series feature vector of dissolved oxygen content;

[0015] Performing feature extraction on the flow values ​​of the water ejectors used for water circulation in the aquaculture tank at the plurality of predetermined time points to obtain a time series feature vector of the flow difference of the water ejectors;

[0016] Calculating the responsiveness estimate of the dissolved oxygen content time series characteristic vector relative to the water jet flow difference time series characteristic vector to obtain a dissolved oxygen change responsiveness characteristic matrix;

[0017] Based on the dissolved oxygen change responsiveness characteristic matrix, the flow control direction of the water ejector at the current time point is determined.

[0018] This application has significant technical effects due to the adoption of the above technical solutions:

[0019] The intelligent control system and method of the circulating aquaculture equipment provided by the present application adopts artificial intelligence analysis technology based on deep learning, extracts features of dissolved oxygen content and flow values ​​of water ejectors at multiple time points to obtain time series features of dissolved oxygen content and time series features of water ejector flow, associates the extracted time series features of dissolved oxygen content and time series features of water ejector flow, and finally passes the associated features through a classifier to obtain the flow control direction of the water ejector. In this way, by establishing a connection between dissolved oxygen and water ejector flow, the dissolved oxygen control strategy is optimized, and real-time response and adjustment are achieved, thereby improving the stability of the aquaculture environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0021] Figure 1This is a system block diagram of an intelligent control system for circulating aquaculture equipment according to an embodiment of the present application.

[0022] Figure 2 It is a block diagram of a dissolved oxygen content time series feature extraction module in an intelligent control system of a circulating aquaculture equipment according to an embodiment of the present application.

[0023] Figure 3 It is a block diagram of a water ejector flow timing feature extraction module in an intelligent control system of a circulating aquaculture equipment according to an embodiment of the present application.

[0024] Figure 4 It is a block diagram of a flow control direction result generation module in an intelligent control system of a circulating aquaculture equipment according to an embodiment of the present application.

[0025] Figure 5 This is a flow chart of an intelligent control method for circulating aquaculture equipment according to an embodiment of the present application.

[0026] Figure 6 is a block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0027] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0028] As mentioned in the above background technology, the recirculating aquaculture mode is a highly intensive aquaculture method, which realizes the recycling of water and the automatic control of water quality by simulating the natural water environment. This mode is increasingly valued in modern aquaculture, especially in the context of limited water resources and increasingly stringent environmental protection requirements. In the recirculating aquaculture mode, the control of dissolved oxygen (DO) is indeed a key link. Dissolved oxygen is not only a basic condition for the survival of aquatic organisms, but also has an important impact on the self-purification ability of water bodies, the decomposition of organic matter, and the cyclic transformation of nutrients such as nitrogen and phosphorus. Maintaining a suitable dissolved oxygen level can promote the healthy growth of cultured organisms, reduce the occurrence of diseases, and improve aquaculture efficiency. However, traditional methods usually rely on manual monitoring and manual adjustment, which may lead to fluctuations in dissolved oxygen content and poor control. Therefore, an intelligent control scheme for recirculating aquaculture equipment is expected, which can stabilize the dissolved oxygen content of aquaculture water by establishing a relationship between dissolved oxygen content and water ejector flow rate, and then by controlling the water ejector flow rate.

[0029] In recent years, deep learning and neural networks have been widely used in computer vision, natural language processing, text signal processing and other fields. In addition, deep learning and neural networks have also shown a level close to or even beyond that of humans in image classification, object detection, semantic segmentation, text translation and other fields. The development of deep learning and neural networks provides new solutions and solutions for the intelligent control of recirculating aquaculture equipment.

[0030] Figure 1 1 is a system block diagram of an intelligent control system for a circulating aquaculture equipment according to an embodiment of the present application. Figure 1 As shown, in the intelligent control system 100 of the circulating aquaculture equipment, it includes: a circulating aquaculture related data acquisition module 110, which is used to obtain the dissolved oxygen content of the aquaculture water at multiple predetermined time points within a predetermined time period and the flow value of the water ejector used for the aquaculture tank water circulation; a dissolved oxygen content time series feature extraction module 120, which is used to extract the dissolved oxygen content of the aquaculture water at the multiple predetermined time points to obtain the dissolved oxygen content time series feature vector; a water ejector flow time series feature extraction module 130, which is used to extract the flow value of the water ejector used for the aquaculture tank water circulation at the multiple predetermined time points to obtain the water ejector flow difference time series feature vector; a responsiveness estimation module 140, which is used to calculate the responsiveness estimation of the dissolved oxygen content time series feature vector relative to the water ejector flow difference time series feature vector to obtain the dissolved oxygen change responsiveness feature matrix; a flow control direction result generation module 150, which is used to judge the flow control direction of the water ejector at the current time point based on the dissolved oxygen change responsiveness feature matrix.

[0031] Specifically, in the technical solution of the present application, it is first necessary to obtain the dissolved oxygen content of the aquaculture water and the flow value of the water ejector used for the water circulation of the aquaculture tank at multiple predetermined time points within a predetermined time period. It should be well understood that by obtaining the dissolved oxygen content and water ejector flow data at multiple time points, it can be helpful to analyze the change trend of the dissolved oxygen content and the water ejector flow, and it can identify the correlation pattern between the dissolved oxygen content and the water ejector flow, such as the increase or decrease of the water ejector flow has a direct positive or negative impact on the dissolved oxygen content. Through this correlation pattern and the prediction of future changes in dissolved oxygen content, the system can adjust the flow of the water ejector in advance, thereby ensuring that the dissolved oxygen content of the aquaculture water remains within an appropriate range.

[0032] In an embodiment of the present application, a possible implementation method for obtaining the dissolved oxygen content of the aquaculture water at multiple predetermined time points within a predetermined time period and the flow value of the water ejector used for water circulation in the aquaculture tank can be as follows: the dissolved oxygen content of the aquaculture water at multiple time points can be obtained by collecting data using a dissolved oxygen sensor installed in the aquaculture pond; the flow value of the water ejector used for water circulation in the aquaculture tank at multiple time points can be collected by installing a flow sensor on a pipe connected to the water ejector.

[0033] Figure 2 FIG. 1 is a block diagram of a time series feature extraction unit for dissolved oxygen content in an intelligent control system of a circulating aquaculture equipment according to an embodiment of the present application. Figure 2 As shown, the dissolved oxygen content time series feature extraction module 120 includes: a dissolved oxygen content data structuring unit 121, which is used to arrange the dissolved oxygen content of the aquaculture water at the multiple predetermined time points into a dissolved oxygen content time series input vector according to the time dimension; a dissolved oxygen content time series feature generating unit 122, which is used to pass the dissolved oxygen content time series input vector through a dissolved oxygen content feature extractor to obtain the dissolved oxygen content time series feature vector.

[0034] The dissolved oxygen content changes dynamically over time, and this change may be affected by many factors, such as water temperature, aquaculture biological activities, and the operation status of the water circulation system. In order to clearly understand the dynamic changes of the dissolved oxygen content and provide an important basis for subsequent analysis and prediction, it is necessary to arrange the dissolved oxygen content of the aquaculture water at the multiple predetermined time points according to the time dimension as a dissolved oxygen content time series input vector. By arranging according to the time dimension, a time series of dissolved oxygen content can be formed, and in the subsequent steps, the block also uses time series analysis technology to process its input and output.

[0035] The dissolved oxygen content time series input vector contains the trend and pattern information of the dissolved oxygen content changing over time. In order to capture the relevant features, the dissolved oxygen content time series input vector needs to be passed through the dissolved oxygen content feature extractor to obtain the dissolved oxygen content time series feature vector. The essence of the dissolved oxygen content feature extractor in the technical solution of the present application is a convolutional neural network model using a one-dimensional convolutional layer and a fully connected layer. The one-dimensional convolutional layer can extract features of the local dissolved oxygen content changes in the time series input vector and capture the change pattern of the dissolved oxygen content in different time periods, while the fully connected layer can integrate these local features into global features for use in subsequent steps.

[0036] In an embodiment of the present application, one possible implementation method of passing the dissolved oxygen content time series input vector through a dissolved oxygen content feature extractor to obtain a dissolved oxygen content time series feature vector may be: using the fully connected layer of the dissolved oxygen content feature extractor to perform fully connected encoding on the dissolved oxygen content time series input vector using the following fully connected encoding formula to extract high-dimensional implicit features of the feature values ​​at each position in the input vector; wherein the fully connected encoding formula is:

[0037]

[0038] Where X is the dissolved oxygen content time series input vector, Y is the output vector, W is the weight matrix, B is the bias vector, Represents matrix multiplication; using the one-dimensional convolution layer of the dissolved oxygen content feature extractor to perform one-dimensional convolution encoding on the dissolved oxygen content time series input vector using the following one-dimensional convolution encoding formula to extract high-dimensional implicit correlation features between the eigenvalues ​​at each position in the input vector; wherein the one-dimensional convolution encoding formula is:

[0039]

[0040] Wherein, a is the width of the convolution kernel in the x direction, F(a) is the convolution kernel parameter vector, G(xa) is the local vector matrix operated with the convolution kernel function, w is the size of the convolution kernel, X represents the dissolved oxygen content time series input vector, and Cov(X) represents one-dimensional convolution encoding of the dissolved oxygen content time series input vector.

[0041] Figure 3 FIG. 1 is a block diagram of a water jet flow time series feature extraction module in an intelligent control system of a circulating aquaculture equipment according to an embodiment of the present application. Figure 3 As shown, the water jet flow time series feature extraction unit 130 includes: a water jet flow data structuring unit 131, which is used to arrange the flow values ​​of the water jets for water circulation in the aquaculture tank at the multiple predetermined time points according to the time dimension into a water jet flow value time series input vector; a water jet flow difference calculation unit 132, which is used to perform a difference operation on the flow values ​​of the water jets at every two adjacent time points in the water jet flow value time series input vector to obtain a water jet flow difference time series input vector; a water jet flow time series feature generation unit 133, which is used to pass the water jet flow difference time series input vector through a water jet flow feature extractor to obtain the water jet flow difference time series feature vector.

[0042] Similarly, the flow value of the water jet is not always fixed, but changes with time. In order to facilitate the analysis of the changing trend and periodic law of the water jet flow, the flow values ​​of the water jet used for water circulation in the breeding tank at the multiple predetermined time points need to be arranged according to the time dimension as a time series input vector of the water jet flow value.

[0043] Next, in order to intuitively display the change amplitude and speed of the water jet flow at different time points, which is helpful to capture the dynamic change trend of the flow, the flow values ​​of the water jet at each two adjacent time points in the water jet flow value time series input vector can be differenced to obtain the water jet flow difference time series input vector. And by focusing on the flow change value rather than the absolute value, the model can understand the flow change more accurately, so as to adjust the water jet flow more flexibly to meet the dissolved oxygen demand at different time points, thereby improving the adaptability and flexibility of the aquaculture equipment control.

[0044] In order to extract the most relevant and discriminative features from the water jet flow difference time series input vector, so as to better capture the pattern and law of the water jet flow change, it is necessary to pass the water jet flow difference time series input vector through the water jet flow feature extractor to obtain the water jet flow difference time series feature vector. In the technical solution of the present application, the essence of the water jet flow feature extractor is also a convolutional neural network model using a one-dimensional convolutional layer and a fully connected layer. Convolutional neural networks perform well in processing time series data, can effectively capture the time correlation and pattern in time series data, and are suitable for processing water jet flow difference time series input vectors. That is, the one-dimensional convolutional layer in the convolutional neural network can effectively capture the temporal locality in the data when processing time series data, and the fully connected layer in the convolutional neural network can synthesize and integrate the features extracted by the convolutional layer to obtain a higher level of abstract feature representation, which helps the model to better understand the data.

[0045] In order to establish a direct connection between the change in dissolved oxygen content and the change in water ejector flow rate, the technical solution of the present application calculates the responsiveness estimate of the dissolved oxygen content time series feature vector relative to the water ejector flow difference time series feature vector to obtain the dissolved oxygen change responsiveness feature matrix. By calculating the responsiveness estimate, the trend of the dissolved oxygen content changing with the water ejector flow rate can be clearly understood, thereby optimizing the control strategy of the water ejector to more accurately predict and control the dissolved oxygen level.

[0046] In an embodiment of the present application, a possible implementation method for calculating the responsiveness estimation of the dissolved oxygen content time series characteristic vector relative to the water jet flow difference time series characteristic vector may be: calculating the responsiveness estimation of the dissolved oxygen content time series characteristic vector relative to the water jet flow difference time series characteristic vector using the following responsiveness estimation formula to obtain the dissolved oxygen change responsiveness characteristic matrix; wherein the responsiveness estimation formula is:

[0047]

[0048] Wherein V1 represents the dissolved oxygen content time series characteristic vector, V2 represents the water jet flow difference time series characteristic vector, represents matrix multiplication, and M represents the dissolved oxygen change responsiveness characteristic matrix.

[0049] Figure 4 FIG. 1 is a block diagram of a flow control direction result generation module in an intelligent control system of a circulating aquaculture equipment according to an embodiment of the present application. Figure 4 As shown, the flow control direction result generation module 150 includes: a feature matrix dimension reduction unit 151, which is used to expand the dissolved oxygen change responsiveness feature matrix to obtain a dissolved oxygen change responsiveness feature vector; a feature vector optimization unit 152, which is used to perform vector sparse optimization on the dissolved oxygen change responsiveness feature vector based on a probability distribution entropy change metric to obtain an optimized dissolved oxygen change responsiveness feature vector; an optimized feature vector classification unit 153, which is used to pass the optimized dissolved oxygen change responsiveness feature vector through a flow classifier to obtain a classification result, and the classification result is used to indicate that the flow of the water jet at the current time point remains unchanged, the flow of the water jet increases, or the flow of the water jet decreases.

[0050] Considering that the dissolved oxygen change responsiveness characteristic matrix has a high dimension, it will consume more computing resources in the subsequent classification calculation, reducing the response speed, and the control of the water jet has a high real-time requirement. In order to improve the response speed, in the technical solution of the present application, the dissolved oxygen change responsiveness characteristic matrix is ​​expanded to obtain the dissolved oxygen change responsiveness characteristic vector. Through the expansion operation, the two-dimensional data becomes one-dimensional data, which is conducive to speeding up the calculation efficiency while retaining the key feature information.

[0051] In particular, in the technical solution of the present application, it is considered that there may be a high correlation between the dissolved oxygen content and the water jet flow rate. Since the flow rate of the water jet directly affects the dissolved oxygen content of the aquaculture water, the extracted features may contain repeated or similar information, which leads to redundancy in the feature vector. In the feature extraction process, the dissolved oxygen content time series feature vector and the water jet flow difference time series feature vector may extract similar dynamic change information. For example, the flow change may reflect the change in oxygen content to a certain extent, resulting in the duplication of features. When calculating the dissolved oxygen change responsiveness feature matrix, redundant features may be introduced because the responsiveness estimate may reflect the impact of the flow change on the dissolved oxygen content, and this impact may have been reflected in the previous features. That is, the dissolved oxygen change responsiveness feature vector has feature redundancy, which leads to the problem of inter-category squeeze relative to the class label of the classifier when it is classified and judged by the classifier, affecting the classification iteration effect. Therefore, in the technical solution of the present application, the dissolved oxygen change responsiveness feature vector is optimized by vector sparse optimization based on the probability distribution entropy change metric to obtain the optimized dissolved oxygen change responsiveness feature vector.

[0052] Specifically, in an embodiment of the present application, the dissolved oxygen change responsiveness feature vector is subjected to vector sparsification optimization based on a probability distribution entropy change metric to obtain an optimized dissolved oxygen change responsiveness feature vector, including: extracting each row vector in the prediction parameter space of the flow classifier to obtain a set of dissolved oxygen change responsiveness prediction parameter row vectors; calculating the class probability entropy degradation simulation value between the dissolved oxygen change responsiveness feature vector and each dissolved oxygen change responsiveness prediction parameter row vector in the set of dissolved oxygen change responsiveness prediction parameter row vectors to obtain a set of dissolved oxygen change responsiveness class probability entropy degradation simulation values; calculating the square root of the sum of squares of the dissolved oxygen change responsiveness class probability entropy degradation simulation values ​​to obtain a dissolved oxygen change responsiveness entropy degradation modulation value; and based on the dissolved oxygen change responsiveness entropy degradation modulation value, performing feature distribution modulation on the dissolved oxygen change responsiveness feature vector to obtain the optimized dissolved oxygen change responsiveness feature vector.

[0053] In an embodiment of the present application, another expression of performing vector sparsification optimization based on probability distribution entropy change measurement on the dissolved oxygen change responsiveness feature vector to obtain an optimized dissolved oxygen change responsiveness feature vector can be: processing the dissolved oxygen change responsiveness feature vector with the following formula to obtain an optimized dissolved oxygen change responsiveness feature vector; wherein the formula is:

[0054] P={p1,p2,...,p j ,...,p n}

[0055] Dj =Softmax(M m v c +H m p j +b m )

[0056]

[0057] Among them, P represents the set of row vectors of dissolved oxygen change responsiveness prediction parameters, p1, p2, p j 、p n represents the first, second, jth, and nth dissolved oxygen change responsiveness prediction parameter row vectors in the set of dissolved oxygen change responsiveness prediction parameter row vectors, v c represents the responsiveness characteristic vector of dissolved oxygen change, Softmax represents the normalized exponential function, M m represents the first weight matrix, H m represents the second weight matrix, b m represents the bias vector, D j represents the jth dissolved oxygen change responsiveness class probability entropy degradation simulation value of the set of dissolved oxygen change responsiveness class probability entropy degradation simulation values, t represents the dissolved oxygen change responsiveness entropy degradation modulation value, v c ⊙t represents the characteristic vector v of the response to dissolved oxygen change c Each eigenvalue of the t-th power, represents the i-th eigenvalue of the dissolved oxygen change responsiveness eigenvector, α represents a predetermined hyperparameter, represents addition by position, and V' represents the optimized characteristic vector of dissolved oxygen change responsiveness.

[0058] Specifically, in the technical solution of the present application, the entropy degradation of the dissolved oxygen change responsiveness feature vector based on the prediction parameter space of the classifier is maximized, and each row vector is first extracted from the prediction parameter space of the classifier to form a row vector set. Then, the class probability entropy degradation simulation value between the dissolved oxygen change responsiveness feature vector and each row vector in the above row vector set is calculated to measure the uncertainty or information entropy change of the dissolved oxygen change responsiveness feature vector under given parameters. Furthermore, all the dissolved oxygen change responsiveness class probability entropy degradation simulation values ​​are squared and summed, and then the square root is taken to obtain a comprehensive dissolved oxygen change responsiveness entropy degradation modulation value, which reflects the degree of entropy change of the entire system when processing the feature vector. Finally, the dissolved oxygen change responsiveness characteristic vector is adjusted according to the dissolved oxygen change responsiveness entropy degradation modulation value obtained above. Specifically, the attribute set of the dissolved oxygen change responsiveness characteristic vector is represented in a formal power series based on the dissolved oxygen change responsiveness entropy degradation modulation value, and a set aggregate bounded deviation represented as an aggregation radius based on each attribute value of the dissolved oxygen change responsiveness characteristic vector is added, so as to perform attribute selection and sparse optimization on the dissolved oxygen change responsiveness characteristic vector under a unified dissolved oxygen change responsiveness entropy degradation modulation value restriction standard, so as to ensure that the dissolved oxygen change responsiveness characteristic vector contains sufficient data but is not so cumbersome as to introduce unnecessary interference or redundancy.

[0059] Finally, the optimized dissolved oxygen change responsiveness feature vector is passed through the flow classifier to obtain a classification result, and the classification result is used to indicate that the flow of the water jet at the current time point remains unchanged, the flow of the water jet increases, and the flow of the water jet decreases. It should be well understood that the optimized dissolved oxygen change responsiveness feature vector captures the dynamic relationship between the change in dissolved oxygen content and the change in the flow of the water jet. In order to display the information in the feature matrix more directly, it needs to be input into the flow classifier. The flow classifier maps the input feature matrix to different output categories. Here, the output category corresponds to the flow state of the water jet: remain unchanged, increase or decrease. According to the output result of the flow classifier, the flow of the water jet can be automatically adjusted. This control method can more accurately predict and respond to changes in dissolved oxygen content, thereby ensuring the stability and optimization of the breeding environment.

[0060] In an embodiment of the present application, the optimized dissolved oxygen change responsiveness characteristic vector is passed through a flow classifier to obtain a classification result, and the classification result is used to indicate that the flow rate of the water jet at the current time point remains unchanged, the flow rate of the water jet increases, and the flow rate of the water jet decreases. One possible implementation method may be: using the flow classifier to process the optimized dissolved oxygen change responsiveness characteristic vector using the following classification formula to generate the classification result; wherein the classification formula is:

[0061] O=softmax{(M c , B c )|V'}

[0062] Wherein O is the classification result, V' represents the optimized dissolved oxygen change responsiveness characteristic vector, M c is the weight matrix of the fully connected layer, B c Represents the bias vector of the fully connected layer, and softmax is the normalized exponential function.

[0063] In summary, the intelligent control system 100 of the circulating aquaculture equipment based on the embodiment of the present application is explained, which adopts artificial intelligence analysis technology based on deep learning, extracts features of dissolved oxygen content and flow values ​​of water ejectors at multiple time points to obtain time series features of dissolved oxygen content and time series features of water ejector flow, and associates the extracted time series features of dissolved oxygen content and time series features of water ejector flow, and finally passes the associated features through a classifier to obtain the flow control direction of the water ejector. In this way, by establishing a connection between dissolved oxygen and water ejector flow, the dissolved oxygen control strategy is optimized, and real-time response and adjustment are achieved, thereby improving the stability of the aquaculture environment.

[0064] As described above, the intelligent control system 100 of the circulating aquaculture equipment according to the embodiment of the present application can be implemented in various terminal devices, such as a server for intelligent control of the circulating aquaculture equipment. In one example, the intelligent control system 100 of the circulating aquaculture equipment according to the embodiment of the present application can be integrated into the terminal device as a software module and / or a hardware module. For example, the intelligent control system 100 of the circulating aquaculture equipment can be a software module in the operating system of the terminal device, or can be an application developed for the terminal device; of course, the intelligent control system 100 of the circulating aquaculture equipment can also be one of the many hardware modules of the terminal device.

[0065] Alternatively, in another example, the intelligent control system 100 of the recirculating aquaculture equipment and the terminal device may also be separate devices, and the intelligent control system 100 of the recirculating aquaculture equipment may be connected to the terminal device via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0066] Figure 5 Flow chart of the intelligent control method of circulating aquaculture equipment according to the embodiment of the present application. Figure 5 As shown, in the intelligent control method of circulating water aquaculture equipment, it includes: S110, obtaining the dissolved oxygen content of the aquaculture water at multiple predetermined time points within a predetermined time period and the flow value of the water ejector used for the water circulation of the aquaculture tank; S120, performing feature extraction on the dissolved oxygen content of the aquaculture water at the multiple predetermined time points to obtain a dissolved oxygen content time series feature vector; S130, performing feature extraction on the flow value of the water ejector used for the water circulation of the aquaculture tank at the multiple predetermined time points to obtain a water ejector flow difference time series feature vector; S140, calculating the responsiveness estimation of the dissolved oxygen content time series feature vector relative to the water ejector flow difference time series feature vector to obtain a dissolved oxygen change responsiveness feature matrix; S150, judging the flow control direction of the water ejector at the current time point based on the dissolved oxygen change responsiveness feature matrix.

[0067] Here, those skilled in the art will appreciate that the specific operations of each step in the intelligent control method for circulating aquaculture equipment have been described in the above reference. Figures 1 to 4 The intelligent control system of the circulating aquaculture equipment has been introduced in detail, and therefore, its repeated description will be omitted.

[0068] In summary, the intelligent control method of the circulating aquaculture equipment based on the embodiment of the present application is explained, which adopts artificial intelligence analysis technology based on deep learning, extracts features of dissolved oxygen content and flow values ​​of water ejectors at multiple time points to obtain time series features of dissolved oxygen content and time series features of water ejector flow, and associates the extracted time series features of dissolved oxygen content and time series features of water ejector flow, and finally passes the associated features through a classifier to obtain the flow control direction of the water ejector. In this way, by establishing a connection between dissolved oxygen and water ejector flow, the dissolved oxygen control strategy is optimized, and real-time response and adjustment are achieved, thereby improving the stability of the aquaculture environment.

[0069] Below, reference Figure 6 To describe an electronic device according to an embodiment of the present application. Figure 6 is a block diagram of an electronic device according to an embodiment of the present application.

[0070] like Figure 6As shown, the electronic device 10 includes one or more processors 11 and a memory 12. The processor 11 may be a central processing unit (CPU) or other forms of processing units with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions. The memory 12 may include one or more computer program products, and the computer program products may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may run the program instructions to implement the intelligent control method of the circulating water aquaculture equipment of each embodiment of the present application described above and / or other desired functions. Various contents such as the dissolved oxygen content of the aquaculture water at multiple predetermined time points within a predetermined time period and the flow value of the water ejector used for the water circulation of the aquaculture tank may also be stored in the computer-readable storage medium.

[0071] In one example, the electronic device 10 may further include: an input device 13 and an output device 14, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0072] The input device 13 may include, for example, a keyboard, a mouse, etc. The output device 14 may output various information to the outside, including the result of determining the flow control direction of the water jet at the current time point, etc. The output device 14 may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0073] Of course, to simplify, Figure 6 Only some of the components related to the present application in the electronic device 10 are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application situations, the electronic device 10 may also include any other appropriate components.

[0074] Finally, the present application also relates to a computer-readable storage medium for implementing an intelligent control method for circulating aquaculture equipment according to one or more embodiments of the present application. The computer-readable storage medium mentioned herein includes various types of computer storage media, which can be any available medium that can be accessed by a general-purpose or special-purpose computer. For example, the computer-readable storage medium may include RAM, ROM, EPROM, E2PROM, registers, hard disks, removable disks, CD-ROMs or other optical disk storage, disk storage or other magnetic storage devices, or any other temporary or non-temporary medium that can be used to carry or store desired program code units in the form of instructions or data structures and can be accessed by a general-purpose or special-purpose computer, or a general-purpose or special-purpose processor. The description of the computer-readable storage medium according to the present application can refer to the explanation of the intelligent control method for circulating aquaculture equipment according to the present application, and no further description will be given.

[0075] The above is only a preferred embodiment of the present application and does not constitute any form of limitation to the present application. Although the present application has been disclosed as a preferred embodiment as above, it is not intended to limit the present application. Any technician familiar with the profession can make some changes or modifications to equivalent embodiments of the technical contents disclosed above without departing from the scope of the technical solution of the present application. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application still falls within the scope of the technical solution of the present application.

Claims

1. An intelligent control system for circulating aquaculture equipment, characterized in that: include: A recirculating aquaculture-related data acquisition module, used to obtain the dissolved oxygen content of the aquaculture water at multiple predetermined time points within a predetermined time period and the flow value of the water ejector used for the aquaculture tank water circulation; A dissolved oxygen content time series feature extraction module, used for extracting features of the dissolved oxygen content of the aquaculture water at the plurality of predetermined time points to obtain a dissolved oxygen content time series feature vector; A water ejector flow time series feature extraction module, used for extracting features of the flow values ​​of the water ejector used for water circulation in the aquaculture tank at the plurality of predetermined time points to obtain a water ejector flow difference time series feature vector; A responsiveness estimation module, used for calculating the responsiveness estimation of the dissolved oxygen content time series characteristic vector relative to the water jet flow difference time series characteristic vector to obtain a dissolved oxygen change responsiveness characteristic matrix; The flow control direction result generating module is used to determine the flow control direction of the water ejector at the current time point based on the dissolved oxygen change responsiveness characteristic matrix.

2. The intelligent control system of the circulating aquaculture equipment according to claim 1 is characterized in that: The dissolved oxygen content time series feature extraction module includes: A dissolved oxygen content data structuring unit, used to arrange the dissolved oxygen contents of the aquaculture water at the plurality of predetermined time points into a dissolved oxygen content time series input vector according to the time dimension; The dissolved oxygen content time series feature generating unit is used for passing the dissolved oxygen content time series input vector through the dissolved oxygen content feature extractor to obtain the dissolved oxygen content time series feature vector.

3. The intelligent control system of the circulating aquaculture equipment according to claim 2 is characterized in that: The water jet flow time series feature extraction module comprises: A water ejector flow data structuring unit, used for arranging the flow values ​​of the water ejectors for water circulation in the aquaculture tank at the plurality of predetermined time points into a water ejector flow value time series input vector according to the time dimension; A water jet flow rate difference calculation unit, used for performing difference calculation on the flow rate values ​​of the water jet at every two adjacent time points in the water jet flow rate time series input vector to obtain the water jet flow rate difference time series input vector; The water jet flow time series feature generating unit is used for passing the water jet flow difference time series input vector through the water jet flow feature extractor to obtain the water jet flow difference time series feature vector.

4. The intelligent control system of the circulating aquaculture equipment according to claim 3 is characterized in that: The dissolved oxygen content feature extractor is a first convolutional neural network model using a one-dimensional convolution kernel and a fully connected layer, and the water jet flow feature extractor is a second convolutional neural network model using a one-dimensional convolution kernel and a fully connected layer.

5. The intelligent control system of the circulating aquaculture equipment according to claim 4 is characterized in that: The responsiveness estimation module is used to: calculate the responsiveness estimation of the dissolved oxygen content time series characteristic vector relative to the water jet flow difference time series characteristic vector using the following responsiveness estimation formula to obtain the dissolved oxygen change responsiveness characteristic matrix; Wherein, the responsiveness estimation formula is: Wherein V1 represents the dissolved oxygen content time series characteristic vector, V2 represents the water jet flow difference time series characteristic vector, represents matrix multiplication, and M represents the dissolved oxygen change responsiveness characteristic matrix.

6. The intelligent control system of the circulating aquaculture equipment according to claim 5 is characterized in that: The flow control direction result generating module includes: A characteristic matrix dimension reduction unit, used for expanding the dissolved oxygen change responsiveness characteristic matrix to obtain a dissolved oxygen change responsiveness characteristic vector; A feature vector optimization unit, used for performing vector sparse optimization on the dissolved oxygen change responsiveness feature vector based on a probability distribution entropy change metric to obtain an optimized dissolved oxygen change responsiveness feature vector; The optimized feature vector classification unit is used to pass the optimized dissolved oxygen change responsiveness feature vector through a flow classifier to obtain a classification result, wherein the classification result is used to indicate that the flow of the water jet at the current time point remains unchanged, the flow of the water jet increases, or the flow of the water jet decreases.

7. The intelligent control system of the circulating aquaculture equipment according to claim 6 is characterized in that: The feature vector optimization unit is used for: Extracting each row vector in the prediction parameter space of the flow classifier to obtain a set of dissolved oxygen change responsiveness prediction parameter row vectors; Calculating the class probability entropy degradation simulation value between the dissolved oxygen change responsiveness characteristic vector and each dissolved oxygen change responsiveness prediction parameter row vector in the set of dissolved oxygen change responsiveness prediction parameter row vectors to obtain a set of dissolved oxygen change responsiveness class probability entropy degradation simulation values; Calculating the square root of the sum of squares of the dissolved oxygen change responsiveness class probability entropy degradation simulation values ​​to obtain a dissolved oxygen change responsiveness entropy degradation modulation value; Based on the dissolved oxygen change responsiveness entropy degradation modulation value, the dissolved oxygen change responsiveness characteristic vector is subjected to characteristic distribution modulation to obtain the optimized dissolved oxygen change responsiveness characteristic vector.

8. An intelligent control method for circulating aquaculture equipment, characterized in that: include: Obtaining the dissolved oxygen content of the aquaculture water and the flow value of the water ejector used for water circulation in the aquaculture tank at a plurality of predetermined time points within a predetermined time period; Extracting features of dissolved oxygen content in the aquaculture water at the plurality of predetermined time points to obtain a time series feature vector of dissolved oxygen content; Performing feature extraction on the flow values ​​of the water ejectors used for water circulation in the aquaculture tank at the plurality of predetermined time points to obtain a time series feature vector of the flow difference of the water ejectors; Calculating the responsiveness estimate of the dissolved oxygen content time series characteristic vector relative to the water jet flow difference time series characteristic vector to obtain a dissolved oxygen change responsiveness characteristic matrix; Based on the dissolved oxygen change responsiveness characteristic matrix, the flow control direction of the water ejector at the current time point is determined.

9. The intelligent control method of circulating aquaculture equipment according to claim 8, characterized in that: Extracting features of the dissolved oxygen content of the aquaculture water at the plurality of predetermined time points to obtain a time series feature vector of the dissolved oxygen content includes: Arranging the dissolved oxygen contents of the aquaculture water at the plurality of predetermined time points into a dissolved oxygen content time series input vector according to the time dimension; The dissolved oxygen content time series input vector is passed through a dissolved oxygen content feature extractor to obtain the dissolved oxygen content time series feature vector.

10. The intelligent control method of circulating aquaculture equipment according to claim 9, characterized in that: The flow values ​​of the water ejectors for water circulation in the aquaculture tank at the plurality of predetermined time points are subjected to feature extraction to obtain a time series feature vector of the flow difference of the water ejectors, including: Arranging the flow values ​​of the water ejectors for water circulation in the aquaculture tank at the plurality of predetermined time points into a water ejector flow value time series input vector according to the time dimension; Performing a difference operation on the flow values ​​of the water ejector at every two adjacent time points in the water ejector flow value time series input vector to obtain a water ejector flow difference time series input vector; The water jet flow difference time series input vector is passed through a water jet flow feature extractor to obtain the water jet flow difference time series feature vector.

Images