Method, device, equipment and program product for predicting mooring force of trash net

Abstract

The present invention provides a method, device, equipment and program product for predicting the mooring force of a pollution control net. Through an offshore characteristic prediction neural network model, a nearshore characteristic prediction neural network model, a pollutant area prediction neural network model and a mooring force prediction neural network model, the mooring force of the pollution control net can be predicted from the predicted wind speed characteristic values ​​and environmental characteristic values, helping relevant personnel to understand the mooring force of the pollution control net in a timely manner. The method has the characteristics of accurate prediction results, time-saving, labor-saving and fast speed, which greatly improves the maintenance and management efficiency of the nuclear power pollution control net.

Description

Technical Field

[0001] The present invention belongs to the field of nuclear power pollution control net management, and in particular relates to a method, device, equipment and program product for predicting the mooring force of the pollution control net. Background Art

[0002] The nuclear power pollution interception net is a pollution interception facility in the nuclear power water intake open channel, which is used to prevent garbage or organisms in the seawater from entering the water intake open channel. Since the mooring force on the pollution interception net is affected by the flow of seawater in the water intake open channel, it is also affected by the coverage state of pollutants on the pollution interception net. Therefore, how to accurately predict the mooring force of the pollution interception net and understand the changes in the mooring force of the pollution interception net in advance is an effective way to ensure that the pollution interception net is always in a reliable state at the water intake open channel and plays a normal role. Under the existing technical conditions, the prediction method of the mooring force of the pollution interception net can generally only be obtained based on weather changes or on-site observations of the pollution interception net. There are problems of inaccurate prediction and time-consuming and labor-intensive, which seriously affect the maintenance and management efficiency of the nuclear power pollution interception net. Summary of the invention

[0003] In view of this, the present invention aims to overcome the defects in the prior art and proposes a method for predicting the mooring force of a trash net.

[0004] To achieve the above object, the technical solution of the present invention is achieved as follows:

[0005] In a first aspect, the present invention discloses a method for predicting mooring force of a trash-control net, comprising:

[0006] Establish an offshore characteristic prediction neural network model, which can output predicted offshore characteristic values ​​to the nearshore characteristic prediction neural network model based on the input predicted wind speed characteristic values, wherein the predicted wind speed characteristic values ​​are used to characterize the predicted offshore wind speed state, and the offshore characteristic values ​​are used to characterize the actual state of the offshore;

[0007] A nearshore feature prediction neural network model is established. The nearshore feature prediction neural network model can output predicted nearshore feature values ​​to the mooring force prediction neural network model based on the input offshore feature values, wherein the nearshore feature values ​​are used to characterize the state of the open water intake channel at the pollution control net;

[0008] Establish a pollutant area prediction neural network model, which can output predicted pollutant area characteristic values ​​to the mooring force prediction neural network model based on the input environmental characteristic values, wherein the environmental characteristic values ​​are used to characterize the growth environment state of pollutants in the pollution-blocking net, and the pollutant area characteristic values ​​are used to characterize the coverage state of pollutants on the pollution-blocking net;

[0009] Establishing a mooring force prediction neural network model, the mooring force prediction neural network model is used to output the predicted mooring force value according to the input nearshore characteristic value and pollutant area characteristic value;

[0010] The predicted wind speed characteristic value is obtained and input into the offshore characteristic prediction neural network model, the environmental characteristic value is obtained and input into the pollutant area prediction neural network model, and the mooring force prediction value corresponding to the output of the mooring force prediction neural network model is obtained.

[0011] In one embodiment of the present invention, the environmental characteristic values ​​include: water body nutrient characteristic values, light intensity characteristic values, seawater salinity characteristic values, seawater pH characteristic values, and seawater temperature characteristic values.

[0012] In one embodiment of the present invention, the water body nutrient characteristic values ​​include water body transparency characteristic values, water body green algae content characteristic values, water body total nitrogen characteristic values ​​and water body total phosphorus characteristic values.

[0013] In one embodiment of the present invention, the pollutant area characteristic value includes the pollutant dispersion degree characteristic value, the pollutant accumulation thickness characteristic value, the pollution net mesh visibility characteristic value, the pollution net mesh adsorption characteristic value and the pollution net lifting force characteristic value.

[0014] In one embodiment of the present invention, the offshore characteristic values ​​include wave period characteristic values, wave height characteristic values, wind speed characteristic values ​​and wave level characteristic values.

[0015] In one embodiment of the present invention, the nearshore characteristic values ​​include open channel flow velocity characteristic values, wave period characteristic values, wave height characteristic values, and wave level characteristic values.

[0016] In one embodiment of the present invention, the wave level characteristic value is acquired by collecting and acquiring the wave level characteristic value through a float type tide meter.

[0017] In a second aspect, the present invention discloses a device for predicting the mooring force of a trash-control net, the device comprising:

[0018] The first establishment module is used to establish an offshore feature prediction neural network model, which can output a predicted offshore feature value to a nearshore feature prediction neural network model based on an input predicted wind speed feature value, wherein the predicted wind speed feature value is used to characterize the predicted offshore wind speed state, and the offshore feature value is used to characterize the state of the offshore;

[0019] The second establishment module is used to establish a nearshore feature prediction neural network model. The nearshore feature prediction neural network model can output predicted nearshore feature values ​​to the mooring force prediction neural network model based on the input offshore feature values, wherein the nearshore feature values ​​are used to characterize the state of the open water intake channel at the pollution control net;

[0020] The third establishment module is used to establish a pollutant area prediction neural network model. The pollutant area prediction neural network model can output predicted pollutant area characteristic values ​​to the mooring force prediction neural network model according to the input environmental characteristic values, wherein the environmental characteristic values ​​are used to characterize the growth environment state of pollutants in the pollution-blocking net, and the pollutant area characteristic values ​​are used to characterize the coverage state of pollutants on the pollution-blocking net;

[0021] A fourth building module is used to build a mooring force prediction neural network model, which is used to output a predicted mooring force prediction value based on the input nearshore characteristic value and pollutant area characteristic value;

[0022] The prediction module is used to obtain the predicted wind speed characteristic value and input it into the offshore characteristic prediction neural network model, obtain the environmental characteristic value and input it into the pollutant area prediction neural network model, and obtain the corresponding mooring force prediction value output by the mooring force prediction neural network model.

[0023] In a third aspect, the present invention discloses an electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute the above method.

[0024] In a fourth aspect, the present invention discloses a computer program product, including a computer program, which implements the above method when executed by a processor.

[0025] Compared with the prior art, the present invention has the following advantages:

[0026] The present invention discloses a method, device, equipment and program product for predicting the mooring force of a pollution control net. Through an offshore characteristic prediction neural network model, a nearshore characteristic prediction neural network model, a pollutant area prediction neural network model and a mooring force prediction neural network model, the mooring force of the pollution control net can be predicted from predicted wind speed characteristic values ​​and environmental characteristic values, helping relevant personnel to understand the mooring force of the pollution control net in a timely manner. The method has the characteristics of accurate prediction results, time-saving, labor-saving and fast speed, which greatly improves the maintenance and management efficiency of nuclear power pollution control nets. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0028] In the attached picture:

[0029] Figure 1 This is a first schematic diagram of an application scenario of a method for predicting mooring force of a pollution-control net according to an embodiment of the present invention;

[0030] Figure 2 This is a first principle schematic diagram of a method for predicting mooring force of a pollution-control net according to an embodiment of the present invention;

[0031] Figure 3 A schematic diagram of a method for predicting mooring force of a trash-control net according to an embodiment of the present invention;

[0032] Figure 4 It is a schematic diagram of another embodiment of a method for predicting mooring force of a pollution-control net according to an embodiment of the present invention;

[0033] Figure 5 It is a schematic diagram of another embodiment of a method for predicting mooring force of a pollution-control net according to an embodiment of the present invention;

[0034] Figure 6 It is a schematic diagram of another embodiment of a method for predicting mooring force of a pollution-control net according to an embodiment of the present invention;

[0035] Figure 7 This is a schematic diagram of a device for predicting mooring force of a trash-control net according to an embodiment of the present invention;

[0036] Figure 8 This is a schematic diagram of an electronic device for predicting mooring force of a trash-control net according to an embodiment of the present invention;

[0037] Fig. 9 It is a second principle schematic diagram of a method for predicting the mooring force of a pollution-control net according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0039] In the description of the present invention, it should be further explained that the terms "first", "second", etc. are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0040] Under existing technical conditions, the prediction method of the mooring force of the pollution control net can generally only be obtained based on weather conditions or on-site observation of the pollution control net. There are problems of inaccurate prediction and time-consuming and labor-intensive, which seriously affects the maintenance and management efficiency of the nuclear power pollution control net.

[0041] like Figure 2 and Fig. 9As shown, the present invention discloses a method, device, equipment and program product for predicting the mooring force of a pollution control net. Through an offshore characteristic prediction neural network model 1, a nearshore characteristic prediction neural network model 2, a pollutant area prediction neural network model 3 and a mooring force prediction neural network model 4, it is possible to obtain a predicted value of the mooring force of the pollution control net from predicted wind speed characteristic values ​​and environmental characteristic values.

[0042] like Figure 1 As shown, the present invention discloses a method for predicting the mooring force of a trash net. Its application scenario can be applied to the daily management and maintenance of the trash net of the open channel of the nuclear power plant. The method can be set in various terminal devices to realize the rapid prediction of the mooring force. The terminal can be any one of a handheld terminal, a laptop computer and a desktop computer.

[0043] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0044] In one embodiment of the present invention, Figure 3 As shown, a method for predicting the mooring force of a trash net comprises:

[0045] Step S201, establishing an offshore characteristic prediction neural network model, which can output a predicted offshore characteristic value to a nearshore characteristic prediction neural network model according to an input predicted wind speed characteristic value, wherein the predicted wind speed characteristic value is used to characterize the predicted offshore wind speed state, and the offshore characteristic value is used to characterize the actual state of the offshore;

[0046] In this embodiment, the predicted wind speed characteristic value can be obtained in advance.

[0047] In this embodiment, both the offshore feature prediction neural network model and the nearshore feature prediction neural network model are pre-trained based on historical data.

[0048] For example, both the offshore feature prediction neural network model and the nearshore feature prediction neural network model can be constructed using the transformer model.

[0049] Step S202, establishing a nearshore feature prediction neural network model, which can output predicted nearshore feature values ​​to the mooring force prediction neural network model based on the input offshore feature values, wherein the nearshore feature values ​​are used to characterize the state of the open water intake channel at the trash interception net;

[0050] In this embodiment, the mooring force prediction neural network model is pre-trained based on historical data, and the mooring force prediction neural network model can be constructed using a transformer model.

[0051] Step S203, establishing a pollutant area prediction neural network model, which can output predicted pollutant area characteristic values ​​to the mooring force prediction neural network model according to the input environmental characteristic values, wherein the environmental characteristic values ​​are used to characterize the growth environment state of pollutants in the pollution-blocking net, and the pollutant area characteristic values ​​are used to characterize the coverage state of pollutants on the pollution-blocking net;

[0052] In this embodiment, the pollutant area prediction neural network model is pre-trained based on historical data and can be constructed using a transformer model.

[0053] Step S204, establishing a mooring force prediction neural network model, the mooring force prediction neural network model is used to output a predicted mooring force prediction value according to the input nearshore characteristic value and pollutant area characteristic value;

[0054] In this embodiment, the mooring force prediction neural network model is pre-trained based on historical data and can be constructed using a transformer model.

[0055] Step S205, obtain the predicted wind speed characteristic value and input it into the offshore characteristic prediction neural network model, obtain the environmental characteristic value and input it into the pollutant area prediction neural network model, and obtain the mooring force prediction value corresponding to the output of the mooring force prediction neural network model.

[0056] like Figure 2 As shown, the offshore characteristic prediction neural network model 1, the nearshore characteristic prediction neural network model 2, the pollutant area prediction neural network model 3 and the mooring force prediction neural network model 4 form a cascade relationship. Therefore, the predicted wind speed characteristic value is obtained and input into the offshore characteristic prediction neural network model, the environmental characteristic value is obtained and input into the pollutant area prediction neural network model, and the mooring force prediction value corresponding to the output of the mooring force prediction neural network model can be obtained.

[0057] In this embodiment, the predicted wind speed characteristic value and the environmental characteristic value are obtained in advance when predicting the mooring force.

[0058] For example, when training the above transformer model:

[0059] The learning rate is set to 0.0001;

[0060] The number of training cycles can be set to 10 epochs;

[0061] The number of decoder layers and encoder layers are 24 and 12 respectively;

[0062] The input sequence length is any one of 3 days, 7 days, and 14 days;

[0063] The prediction time length can be 1 day, 3 days, or 7 days;

[0064] The optimizer is the Adam optimizer, and the initial momentum is set to 0.9.

[0065] In another embodiment of the present invention, Figure 4 As shown, the environmental characteristic values ​​include: water body nutrient characteristic values, light intensity characteristic values, seawater salinity characteristic values, seawater pH characteristic values ​​and seawater temperature characteristic values.

[0066] In this embodiment, the environmental characteristic value is used to characterize the environment that affects the growth of parasites and green algae on the pollution-control net, and the growth of parasites and green algae on the pollution-control net affects the mooring force of the pollution-control net.

[0067] As one of the characteristic values ​​for predicting the mooring force of the trash net, the environmental characteristic value fully considers the impact of the environment on the mooring force of the trash net and improves the prediction accuracy of the mooring force of the trash net.

[0068] In another embodiment of the present invention, Figure 5 As shown, the water body nutrient characteristic values ​​include the water body transparency characteristic value, the water body green algae content characteristic value, the water body total nitrogen characteristic value and the water body total phosphorus characteristic value.

[0069] In this embodiment, the water body nutrient characteristic value is used to characterize the nutrient status in seawater. Multiple monitoring points can be arranged where the pollution-blocking net is set up, and the distance between the monitoring points is not less than 500m and not more than 5km.

[0070] The water nutrient characteristic value can fully characterize the nutrient situation in the seawater where the pollution control net is set up, predict the growth of parasites and green algae on the pollution control net, and further improve the prediction accuracy of the mooring force of the pollution control net.

[0071] In another embodiment of the present invention, Figure 6 As shown, the pollutant area characteristic values ​​include the pollutant dispersion degree characteristic value, the pollutant accumulation thickness characteristic value, the pollution net mesh visibility characteristic value, the pollution net mesh adsorption characteristic value and the pollution net lifting force characteristic value.

[0072] In this embodiment, the pollutant dispersion degree characteristic value, the pollutant accumulation thickness characteristic value, the pollution screen mesh visibility characteristic value, and the pollution screen mesh adsorption characteristic value are obtained by observing the pollution screen on-site pictures and scoring by experts as label values. The scoring criteria are as follows:

[0073] Pollutant dispersion characteristic value Pollutant distribution characteristics, 0 represents a very uniform distribution, and 9 represents a very uneven distribution. Characteristic value of pollutant accumulation thickness Pollutant accumulation thickness characteristics, 0 means very little deposition, 9 means very thick deposition. Visibility characteristic value of the pollution-blocking net mesh The permeability characteristics of the trash net mesh, 0 means the mesh permeability is very good, 9 means the attachment is very poor. Trash screen mesh adsorption characteristic value The permeability characteristics of the pollution-blocking net mesh are as follows: 0 represents poor adsorption of pollutants, and 9 represents particularly strong adsorption.

[0074] The characteristic value of the lifting force of the trash net is the actual force applied to lift the trash net.

[0075] In this embodiment, a prediction model can be established to obtain training data for the pollutant area prediction neural network model 3, so that the image of the pollution control net can be used as the input of the model to obtain the corresponding pollutant discrete degree characteristic value, pollutant accumulation thickness characteristic value, pollution control net mesh visibility characteristic value, and pollution control net mesh adsorption characteristic value.

[0076] In this embodiment, by scoring the pollution-blocking net image as a label value, the difficulty of obtaining the pollutant area characteristic value can be effectively reduced, thereby improving the adaptability of the method.

[0077] Establishing a prediction model and obtaining training data for the pollutant area prediction neural network model 3 can improve the speed of obtaining model training data.

[0078] In another embodiment of the present invention, the offshore characteristic values ​​include wave period characteristic values, wave height characteristic values, wind speed characteristic values ​​and wave level characteristic values.

[0079] In another embodiment of the present invention, the nearshore characteristic values ​​include open channel flow velocity characteristic values, wave period characteristic values, wave height characteristic values, and wave level characteristic values.

[0080] In this embodiment, the wave level characteristic value is acquired by collecting data through a float-type tide level meter.

[0081] In another embodiment of the present invention, since the mooring force prediction neural network model is pre-trained based on historical data, extreme conditions can be supplemented in the historical data in the following manner:

[0082] The numerical simulation of nearshore flooding under extreme conditions uses a two-dimensional hydrodynamic model. The water depth of the large-scale model exceeds 50m, and satellite data is used. For the nearshore, the water depth data of the nautical chart is used. The storm surge uses the ADCIRC software to couple the wind field and use the astronomical tide as the boundary condition to calculate the tide level data of the project. For the large-scale wave model, the SWAN software can be used for calculation. When SWAN performs large-scale wave calculations, it directly uses the ADCIRCR model grid. And the wind field is used as the model input. When calculating the tide level and wave height, it is necessary to calibrate 1 to 3 actual storm surge measured tide level processes. ADCIRC and SWAN can be directly coupled, and the wave-current coupling problem is better considered.

[0083] The pollution-blocking net was arranged with multiple groups of net bags with different pollutant areas.

[0084] S1: Model scale requirements: The wave physics model experiment adopts the gravity similarity criterion, that is, the Froude number of the prototype and the model, two similar systems, is guaranteed to be equal. The wave period, wave speed, water depth and other parameters in the model maintain a certain proportional relationship with the prototype.

[0085] S2: Model range requirements: the main controlling wave direction of the project should be determined before the experiment, and the physical model range should ensure that the wave propagation in the main controlling wave direction of extreme weather is not restricted.

[0086] S3: Test conditions requirements.

[0087] Wave direction, traditional physical models are mainly divided into 16 directions, and physical modeling can be carried out in the traditional way.

[0088] Parameter intervals are mainly wave height and period intervals. The maximum wave height and maximum period under extreme weather conditions should be determined before determining the parameter intervals. The specific parameter intervals should be determined in combination with the total experimental time, but the wave height span should not be greater than 1m, and the period span should not be greater than 5s.

[0089] S4: Wave-making boundary. The mean wave height and period are extracted from the ADCIRC and SWAN tidal wave coupling models, and the jaonswap random wave spectrum is used to generate the wave-making boundary.

[0090] S5: Engineering water intake. To simulate engineering water intake, the model scale is first used to calculate the water intake flow required for the test, and water pumps with the same flow are arranged at the corresponding positions.

[0091] S6: Calibration point. In the ADCIRC and SWAN tidal wave coupling models, the wave height conditions in the open sea not far from the project area are extracted for wave height calibration.

[0092] S7: Data collection. Mainly collect wave height, wave period, open channel flow velocity, mooring force, etc.

[0093] In another embodiment of the present invention, Figure 7 As shown, a device for predicting the mooring force of a trash-control net is disclosed, comprising:

[0094] The first establishing module 501 is used to establish an offshore feature prediction neural network model, which can output a predicted offshore feature value to a nearshore feature prediction neural network model according to an input predicted wind speed feature value, wherein the predicted wind speed feature value is used to characterize the predicted offshore wind speed state, and the offshore feature value is used to characterize the state of the offshore;

[0095] The second establishment module 502 is used to establish a nearshore feature prediction neural network model, which can output predicted nearshore feature values ​​to the mooring force prediction neural network model based on the input offshore feature values, wherein the nearshore feature values ​​are used to characterize the state of the open water intake channel at the trash interception net;

[0096] The third establishment module 503 is used to establish a pollutant area prediction neural network model. The pollutant area prediction neural network model can output predicted pollutant area characteristic values ​​to the mooring force prediction neural network model according to the input environmental characteristic values, wherein the environmental characteristic values ​​are used to characterize the growth environment state of pollutants in the pollution-blocking net, and the pollutant area characteristic values ​​are used to characterize the coverage state of pollutants on the pollution-blocking net;

[0097] The fourth establishing module 504 is used to establish a mooring force prediction neural network model, which is used to output a predicted mooring force prediction value according to the input nearshore characteristic value and pollutant area characteristic value;

[0098] The prediction module 505 is used to obtain the predicted wind speed characteristic value and input it into the offshore characteristic prediction neural network model, obtain the environmental characteristic value and input it into the pollutant area prediction neural network model, and obtain the corresponding mooring force prediction value output by the mooring force prediction neural network model.

[0099] The present invention also discloses an electronic device, such as Figure 8 As shown, an embodiment is disclosed, which is a block diagram of an electronic device suitable for the above-mentioned method for predicting the mooring force of a pollution control net.

[0100] The electronic device 60 of this embodiment includes a processor 601, which can perform various appropriate actions and processes according to the program stored in the ROM 602 or the program loaded from the storage part 608 to the RAM 603. The processor 601 may include, for example, a general-purpose microprocessor, an instruction set processor and / or a related chipset and / or a dedicated microprocessor, etc. The processor 601 may also include an onboard memory for caching purposes. The processor 601 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present invention.

[0101] In RAM603, various programs and data required for the operation of electronic device 60 are stored. Processor 601, ROM602 and RAM603 are connected to each other through bus 604, and processor 601 performs various operations of the method flow according to the embodiment of the present invention by executing the program in ROM602 and / or RAM603. It should be noted that the program can also be stored in one or more memories other than ROM602 and RAM603, and processor 601 can also perform various operations of the method flow according to the embodiment of the present invention by executing the program stored in one or more memories.

[0102] According to an embodiment of the present invention, the electronic device 60 may further include an I / O interface 605, which is also connected to the bus 604. The electronic device 60 may further include one or more of the following components connected to the I / O interface 605: an input portion 606 including a keyboard, a mouse, etc.; an output portion 607 including a cathode ray tube, a liquid crystal display, and a speaker; a storage portion 608 including a hard disk, etc.; and a communication portion 609 including a network interface card such as a LAN card, a modem, etc. The communication portion 609 performs communication processing via a network such as the Internet. A drive 6010 is also connected to the I / O interface 605 as needed. A removable medium 6011, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 6010 as needed, so that a computer program read therefrom is installed into the storage portion 608 as needed.

[0103] Embodiments of the present invention also include a computer program product.

[0104] The computer program product includes a computer program, which contains program codes for executing the method provided by the embodiment of the present invention. When the computer program product runs on an electronic device, the program codes are used to enable the electronic device to implement the method provided by the embodiment of the present invention.

[0105] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium. The program code included in the computer program may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0106] According to an embodiment of the present invention, the program code for executing the computer program provided by the embodiment of the present invention can be written by any combination of one or more programming languages, and specifically, these computing programs can be implemented using high-level process and / or object-oriented programming languages. Programming languages ​​include but are not limited to programming languages ​​such as Java, C++, python, C language or similar. The program code can be executed completely on the user computing device, partially on the user device, partially on the remote computing device, or completely on the remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user computing device through any type of network, including a local area network or a wide area network, or can be connected to an external computing device.

[0107] The flowcharts 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 invention. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in a different order from the order 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 or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions. It can be understood by those skilled in the art that the features recorded in the various embodiments and / or claims of the present invention can be combined and / or combined in various ways, even if such a combination or combination is not explicitly recorded in the present invention. In particular, without departing from the spirit and teaching of the present invention, the features described in the various embodiments and / or claims of the present invention may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present invention.

[0108] The embodiments of the present invention are described above. However, these embodiments are only for the purpose of illustration, and are not intended to limit the scope of the present invention. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination. The scope of the present invention is limited by the attached claims and their equivalents. Without departing from the scope of the present invention, those skilled in the art may make various substitutions and modifications, which should all fall within the scope of the present invention.

Claims

1. A method for predicting mooring force of a trash-control net, characterized in that: include: Establishing an offshore characteristic prediction neural network model, the offshore characteristic prediction neural network model can output a predicted offshore characteristic value to a nearshore characteristic prediction neural network model according to an input predicted wind speed characteristic value, wherein the predicted wind speed characteristic value is used to characterize the predicted offshore wind speed state, and the offshore characteristic value is used to characterize the actual state of the offshore; Establishing the nearshore characteristic prediction neural network model, the nearshore characteristic prediction neural network model can output the predicted nearshore characteristic value to the mooring force prediction neural network model according to the input open sea characteristic value, wherein the nearshore characteristic value is used to characterize the state of the open water intake channel at the pollution control net; Establishing a pollutant area prediction neural network model, the pollutant area prediction neural network model can output predicted pollutant area characteristic values ​​to the mooring force prediction neural network model according to input environmental characteristic values, wherein the environmental characteristic values ​​are used to characterize the growth environment state of pollutants in the pollution-blocking net, and the pollutant area characteristic values ​​are used to characterize the coverage state of pollutants on the pollution-blocking net; Establishing the mooring force prediction neural network model, wherein the mooring force prediction neural network model is used to output a predicted mooring force prediction value according to the input nearshore characteristic value and the pollutant area characteristic value; The predicted wind speed characteristic value is obtained and input into the offshore characteristic prediction neural network model, the environmental characteristic value is obtained and input into the pollutant area prediction neural network model, and the mooring force prediction value corresponding to the output of the mooring force prediction neural network model is obtained.

2. A method for predicting mooring force of a trash-control net according to claim 1, characterized in that: The environmental characteristic values ​​include: water body nutrient characteristic values, light intensity characteristic values, seawater salinity characteristic values, seawater pH characteristic values ​​and seawater temperature characteristic values.

3. A method for predicting mooring force of a trash-control net according to claim 2, characterized in that: The water body nutrient characteristic values ​​include a water body transparency characteristic value, a water body green algae content characteristic value, a water body total nitrogen characteristic value, and a water body total phosphorus characteristic value.

4. A method for predicting mooring force of a trash-control net according to claim 2, characterized in that: The pollutant area characteristic values ​​include the pollutant dispersion degree characteristic value, the pollutant accumulation thickness characteristic value, the pollution net mesh visibility characteristic value, the pollution net mesh adsorption characteristic value and the pollution net lifting force characteristic value.

5. A method for predicting mooring force of a trash-control net according to claim 1, characterized in that: The offshore characteristic values ​​include wave period characteristic values, wave height characteristic values, wind speed characteristic values ​​and wave level characteristic values.

6. A method for predicting mooring force of a trash-control net according to claim 1, characterized in that: The nearshore characteristic values ​​include open channel flow velocity characteristic values, wave period characteristic values, wave height characteristic values ​​and wave level characteristic values.

7. A method for predicting mooring force of a trash-control net according to claim 5 or 6, characterized in that: The wave level characteristic value is collected and obtained by a float type tide level meter.

8. A device for predicting the mooring force of a trash-control net, characterized in that: The device comprises: The first establishment module is used to establish an offshore feature prediction neural network model, wherein the offshore feature prediction neural network model can output a predicted offshore feature value to a nearshore feature prediction neural network model according to an input predicted wind speed feature value, wherein the predicted wind speed feature value is used to characterize a predicted offshore wind speed state, and the offshore feature value is used to characterize an offshore state; The second establishment module is used to establish the nearshore characteristic prediction neural network model, which can output the predicted nearshore characteristic value to the mooring force prediction neural network model according to the input open sea characteristic value, wherein the nearshore characteristic value is used to characterize the state of the open water intake channel at the pollution control net; The third establishment module is used to establish a pollutant area prediction neural network model, which can output predicted pollutant area characteristic values ​​to the mooring force prediction neural network model according to the input environmental characteristic values, wherein the environmental characteristic values ​​are used to characterize the growth environment state of pollutants in the pollution-blocking net, and the pollutant area characteristic values ​​are used to characterize the coverage state of pollutants on the pollution-blocking net; A fourth establishing module is used to establish the mooring force prediction neural network model, wherein the mooring force prediction neural network model is used to output a predicted mooring force prediction value according to the input nearshore characteristic value and the pollutant area characteristic value; A prediction module is used to obtain the predicted wind speed characteristic value and input it into the offshore characteristic prediction neural network model, obtain the environmental characteristic value and input it into the pollutant area prediction neural network model, and obtain the mooring force prediction value corresponding to the mooring force prediction neural network model output.

9. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors are caused to perform the method according to any one of claims 1 to 7.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images