Ship trial flight route planning method and system based on storm resistance increase

Abstract

The invention provides a ship trial flight route planning method and system based on storm resistance increase, and the method comprises the steps: obtaining wind field and wave field data in trial flight time and space through constructing a storm forecasting model, dividing a plane of a trial flight region into a plurality of micro-units, and presetting a trial flight route of a ship; and based on the wind field and wave field data and in combination with related parameters in the ship trial flight process, the storm resistance increase of each micro-unit on each trial flight route and the storm resistance increase total value of each trial flight route are calculated, and the trial flight routes are screened based on the storm resistance increase. According to the technical scheme of the invention, a plurality of better trial flight routes can be quickly planned for the user to select.

Description

Technical Field

[0001] The present application relates to the technical field of ship design and manufacturing, and in particular, to a method and system for planning a ship trial route based on wind and wave resistance increase. Background Art

[0002] In the field of ship design and manufacturing, speed measurement during sea trials is a key step in evaluating the speed and power performance of ships. In order to ensure the accuracy and reliability of the speed measurement results, the selection of the sea trial route is crucial. Traditionally, the determination of the sea trial route mainly relies on the professional knowledge and rich experience of operators. They need to find areas in the nautical chart with little external interference, relatively stable wind and wave conditions, and sufficient straight-line distance as the sea trial area. However, with the increase in ship size and complexity, and the increase in users' requirements for the accuracy of sea trial data, this method that relies on manual judgment and experience has gradually revealed its limitations.

[0003] In actual sea trials, the trial sea area of ​​a ship often covers a vast sea area, where wind and wave conditions are complex and changeable, and there are significant temporal and spatial differences. It is difficult for operators to comprehensively evaluate and screen out an ideal trial sea route that meets all conditions in a short period of time. In addition, the temporal and spatial resolution of wind and wave data is low, which further increases the difficulty and uncertainty of route selection. Summary of the invention

[0004] The purpose of this application is to provide a ship trial route planning method and system based on wind and wave resistance increase, so as to obtain wind field and wave field data within the time and space of the ship trial, and provide multiple better trial routes for users to choose.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions:

[0006] A method for planning a ship trial sea route based on wind and wave resistance increase, comprising: constructing a wind and wave forecasting model based on a BP neural network model or a BP neural network model combined with an optimization algorithm; dividing the plane of a trial sea area into a plurality of micro-units, presetting a trial sea route for the ship in the trial sea area, and each preset trial sea route passing through the micro-units; acquiring wind field data and wave field data during the ship trial based on the wind and wave forecasting model, calculating the wind and wave resistance increase of each micro-unit on each preset trial sea route in combination with relevant parameters during the ship trial, accumulating the wind and wave resistance increase of all micro-units passed by the trial sea route, and obtaining the total value of the wind and wave resistance increase on the trial sea route; and selecting the trial sea route based on the wind and wave resistance increase.

[0007] In some embodiments, the process of constructing the wind and wave forecast model includes: constructing an initial wind and wave forecast model based on a BP neural network model or a BP neural network model combined with an optimization algorithm; training the initial wind and wave forecast model using a training data set, and obtaining the initial wind and wave forecast model when a termination criterion is reached; loading a test data set to test the trained initial wind and wave forecast model, and obtaining the wind and wave forecast model when the test accuracy is met.

[0008] In some embodiments, the optimization algorithm includes but is not limited to a genetic algorithm, a particle swarm algorithm, and an ant colony algorithm, which are used to optimize the initial weights and initial thresholds of the BP neural network model.

[0009] In some embodiments, the BP neural network model comprises an input layer, a hidden layer and an output layer, wherein the input layer is one layer, the number of nodes in the input layer is equal to the number of input parameters, and the input parameters include longitude and latitude range, time range, air temperature field, air pressure field, water temperature field, water depth, ocean current field, density field and topography coastline; the number of layers in the hidden layer is one or more layers, and the number of layers and nodes in the hidden layer are adjusted according to the performance and training efficiency of the BP neural network model; the output layer is one layer, the number of nodes in the output layer is equal to the number of output parameters, and the output parameters include at least wind speed, wind direction, wind and wave height, wind and wave period, wind and wave frequency, wind and wave length, swell height, swell period, swell frequency and swell length.

[0010] In some embodiments, the training data set for training the initial wind and wave forecast model comes from actual measurement data of wind and waves, numerical simulation data, and physical test data; the training termination criterion of the wind and wave forecast model is set by an error parameter (such as determination coefficient, mean square error) or the number of training times, wherein the calculation formulas of the determination coefficient and the mean square error are shown in formula (1) and formula (2), respectively.

[0011]

[0012] Among them, R 2 represents the coefficient of determination; y i represents the forecast value of the i-th group; y i0 represents the i-th group of measurements; y m represents the average value of the measured value; N represents the total number of data sets; X mse represents the mean square error.

[0013] In some embodiments, the step of dividing the plane of the trial voyage area into a plurality of micro-units and presetting the trial voyage route of the ship in the trial voyage area includes: dividing the plane of the trial voyage area into micro-units and determining a central micro-unit, wherein the micro-unit is a polygon or a circle, and the size of the micro-unit can accommodate the entire hull; taking the starting point of the ship's trial voyage as the center of the central micro-unit, setting a certain direction of the center of the central micro-unit (for example, due north) as the 0° direction, and increasing the angle in the clockwise or counterclockwise direction; presetting a plurality of trial voyage routes in the trial voyage area, the angle between adjacent preset trial voyage routes is n°, and setting the direction of the trial voyage route to the bow of the ship.

[0014] In some embodiments, the wind field data and wave field data during the ship sea trial are obtained based on the wind and wave forecast model, and the wind and wave resistance increase of each micro-unit on each preset sea trial route is calculated in combination with relevant parameters during the ship sea trial, and the wind and wave resistance increase of all micro-units passed by the sea trial route are accumulated, including: at least inputting the longitude and latitude range, time range, temperature field, pressure field, water temperature field, water depth, ocean current field, density field, topography and coastline of the sea trial time and space into the wind and wave forecast model to obtain the wind field data and wave field data in the sea trial time and space.

[0015] In some embodiments, the wind field data and wave field data of the ship during the sea trial are obtained based on the wind and wave forecast model, and the wind and wave resistance increase of each micro-unit on each preset sea trial route is calculated in combination with relevant parameters during the ship sea trial, and the wind and wave resistance increase of all micro-units passed by the sea trial route are accumulated, including: based on the wind field data and wave field data obtained during the ship sea trial, on each preset sea trial route, according to the preset sea trial start and end time and speed, the time and trajectory of the ship on the sea trial route are obtained; according to the time and trajectory, the forecast real-time wind speed, wind direction and wave direction of the ship during the sea trial are extracted from the acquired wind field data and wave field data.

[0016] In some embodiments, the relevant parameters during the ship sea trial include ship characteristics, preset speed and other parameters; the ship characteristics include at least waterline, length between perpendiculars, width, midship draft, longitudinal trim and squareness coefficient; the other parameters are based on the predicted real-time wind speed, wind direction and wave direction of the ship during the sea trial, and according to the preset sea trial bow direction and anemometer height, calculate the relative wind speed, relative wind direction, true wind speed, true wind direction, relative wind direction at a reference height, relative wind speed and wave direction of the ship in the micro unit.

[0017] In some embodiments, the calculated wind and wave resistance of each micro-unit on each of the preset trial routes is obtained by calculating the wind resistance and wave resistance: the calculation formula of the wind resistance is shown in formula (3), and the STAWAVE2 calculation formula of the wave resistance is shown in formula (4).

[0018]

[0019] Among them, R AA represents wind resistance; ρ A Indicates air density; C AA (Ψ WRref ) represents the wind resistance coefficient corresponding to the relative wind direction at the reference height; A XV Indicates the transverse projection area above the waterline of the ship including the superstructure; V WRref Indicates the relative wind speed at the reference height; C AA (0) represents the average windward drag coefficient; V G Indicates the ship's ground speed; R AW Indicates wave resistance; R AWML Indicates the increase in resistance caused by exercise; R AWRL represents the average resistance increase caused by wave reflection; A Indicates amplitude; S η (ω) represents the frequency spectrum.

[0020] In some embodiments, the screening of trial routes based on wind and wave resistance increase includes: statistically analyzing the degree of dispersion of wind and wave resistance increase values ​​between different micro-units on each preset trial route to obtain statistical parameters such as the average value, maximum value, standard deviation and variance of the wind and wave resistance increase of ships on the preset trial route; and screening the trial routes based on planning target parameters, wherein the planning target parameters include the total value and degree of dispersion of the wind and wave resistance increase of ships.

[0021] In a second aspect, the present application provides a ship trial route planning system based on wind and wave resistance increase, comprising: a model building module, a trial route planning module, a wind and wave resistance increase calculation module and a trial route screening module; wherein the model building module is used to build a wind and wave forecasting model based on a BP neural network model or a BP neural network model combined with an optimization algorithm; the trial route planning module is used to divide the plane of the trial area into a plurality of micro-units, and preset the trial route of the ship in the trial area, and each preset trial route passes through a number of the micro-units; the wind and wave resistance increase calculation module is used to obtain the wind field data and wave field data during the ship trial based on the wind and wave forecast model, and calculate the wind and wave resistance increase of each micro-unit on each preset trial route in combination with relevant parameters during the ship trial, and accumulate the wind and wave resistance increase of all micro-units passed by the trial route to obtain the total value of the wind and wave resistance increase on the trial route; the trial route screening module is used to screen the trial route based on the wind and wave resistance increase.

[0022] Compared with the prior art, the present invention has the following advantages:

[0023] The present application provides a method and system for planning a ship trial voyage route based on wind and wave resistance increase. Before the trial voyage, based on the weather, ocean environment, topography, etc. in the trial voyage time and space, the wind and wave conditions in the trial voyage time and space are obtained through a wind and wave forecast model; based on the ship characteristics, wind and wave forecasts in the trial voyage time and space, preset speed and other parameters, the wind and wave resistance increase calculation formula is used to predict the ship's wind and wave resistance increase on different trial voyage routes, and according to the user-specified planning target, multiple better trial voyage routes under the target are obtained for the user to choose. During the trial voyage, based on the ship characteristics, real-time wind and waves, measured speed and other parameters, with the help of the wind and wave resistance increase calculation formula, the wind and wave resistance increase value and trend of the ship during the trial voyage are visually displayed. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 A schematic diagram showing a flow chart of a method for planning a ship trial route based on wind and wave resistance increase according to an embodiment of the present application is shown;

[0026] Figure 2 A schematic diagram of the process of constructing a wind and wave forecast model in an embodiment of the present application is shown;

[0027] Figure 3 A schematic diagram of the ship's trial route is shown;

[0028] Figure 4 A schematic diagram showing the micro-units of the trial navigation area and the preset trial navigation routes;

[0029] Figure 5 A schematic diagram of wind direction and wind speed defined in ISO 15016 (2015) is shown;

[0030] Figure 6 It shows the interface display schematic diagram of planning the trial route and wind and wave resistance increase in the micro unit;

[0031] Figure 7 A schematic diagram of the interface display showing the real-time trial route, wind and wave resistance increase values ​​and trends.

[0032] Description of reference numerals:

[0033] 3-1 – Corrected Williamson Turn;

[0034] 3-2——Trial route;

[0035] 3-3——The end / start position of the outbound / return speed measurement voyage;

[0036] 3-4——Start / end position of the outbound / return speed measurement trip;

[0037] 4-1——Trial area microunit;

[0038] 4-2 - Hull;

[0039] 4-3——Preset trial route;

[0040] 4-4 – the angle between adjacent trial routes;

[0041] 5-1——Relative wind speed;

[0042] 5-2——True wind speed;

[0043] 5-3——Speed;

[0044] 5-4——Relative wind direction;

[0045] 5-5——True wind direction;

[0046] 5-6——heading;

[0047] 5-7 – bow;

[0048] 5-8 - Hull;

[0049] 6-1——1# better trial route;

[0050] 6-2——2# better trial route;

[0051] 6-3——3# better trial route;

[0052] 6-4 - Hull;

[0053] 6-5 – Microunit of the trial area;

[0054] 6-6——Microunit color and number;

[0055] 7-1——Real-time trial route;

[0056] 7-2——Trend curve of wind and wave resistance increase. DETAILED DESCRIPTION

[0057] The technical solutions of the specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings. These implementation methods are only used to illustrate the present application, but not to limit the present application.

[0058] The term "and / or" in this application is a description of the association relationship of associated objects, indicating that three relationships may exist, for example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. In the present invention, the symbol " / " indicates that the associated objects are in an "or" relationship, for example, "A / B" means "A or B".

[0059] The terms "first" and "second" in the specification and claims of this application are used to distinguish different objects rather than to describe a specific order of the objects. For example, "first response message" and "second response message" are used to distinguish different response messages rather than to describe a specific order of the response messages.

[0060] In the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be considered as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0061] In the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more than two. For example, multiple processing units refer to two or more processing units, etc., and multiple elements refer to two or more elements, etc.

[0062] The following is a detailed description of a ship trial route planning method and system based on wind and wave resistance increase in the present application with reference to the accompanying drawings.

[0063] Figure 1 The flowchart of the method for planning a ship trial route based on wind and wave resistance increase according to one embodiment of the present application is shown. Figure 1 As shown, the ship trial route planning method based on wind and wave resistance increase in the embodiment of the present application includes the following steps:

[0064] Based on the BP neural network model or the BP neural network model combined with the optimization algorithm, a wind and wave forecast model is constructed. The construction process of the wind and wave forecast model includes: Figure 2As shown, the design and construction of the model are realized based on computer programming languages ​​such as MATLAB, Python, and R. Specifically, a BP (back propagation) neural network model or a BP neural network model combined with an optimization algorithm can be used as the framework of the initial wind and wave forecast model. The BP neural network has good nonlinear mapping capabilities and exhibits unique advantages when processing complex and uncertain marine environmental data. In order to improve the accuracy of the forecast results, the embodiment of the present application further combines the optimization algorithm with the BP neural network to optimize the initial weights and initial thresholds of the neural network, which can effectively avoid the local optimal problem of the BP neural network model, thereby improving the forecast accuracy of the model. In one embodiment, the aforementioned optimization algorithms include but are not limited to genetic algorithms, particle swarm algorithms, and ant colony algorithms. These algorithms simulate the optimization process of nature (such as genetic evolution, swarm intelligence, etc.) to find the optimal solution or approximate optimal solution in the search space, thereby effectively avoiding the local optimal problem.

[0065] The aforementioned BP neural network model includes an input layer, a hidden layer and an output layer. In one embodiment, the input layer and the output layer of the BP neural network model are both one layer. The number of nodes in the input layer is equal to the number of input parameters. The input parameters specifically include latitude and longitude range, time range, temperature field, pressure field, water temperature field, water depth, ocean current field, density field and terrain coastline data. The number of nodes in the output layer is equal to the number of output parameters. The output parameters are usually wind fields and wave fields, specifically including but not limited to wind speed, wind direction, wind and wave height, wind and wave period, wind and wave frequency, wind and wave length, swell height, swell period, swell frequency and swell length. The resolution of the output parameters is set by the user according to actual needs. The number of layers and nodes of the hidden layer is determined by debugging to capture the inherent laws and characteristics of the data. Usually, the number of layers of the hidden layer is one or more layers, and the specific number of layers and nodes are adjusted according to model performance and training efficiency.

[0066] The training data set of the aforementioned initial wind and wave forecast model is composed of data from various sources, such as actual measurement data from wind and waves, numerical simulation data, and physical test data, which includes input parameters and output parameters. The training termination criteria of the initial wind and wave forecast model are set by error parameters (such as determination coefficient, mean square error) or the number of training times, where the calculation formulas of the determination coefficient and mean square error are shown in formula (1) and formula (2) respectively. During the training process, algorithms such as gradient descent method, Levenberg-Marquardt method, Powell-Beale conjugate gradient method or adaptive learning rate momentum gradient descent method are used to optimize the model parameters.

[0067]

[0068] Among them, R 2 represents the coefficient of determination; y i represents the forecast value of the i-th group; yi0 represents the i-th group of measurements; y m represents the average value of the measured value; N represents the total number of data sets; X mse represents the mean square error.

[0069] On the programming platform, the wind and wave forecast model is constructed according to the model type, number of model layers, number of nodes in each layer, termination criteria, and training algorithm. Then the training data set is loaded to train the model. The model that meets the termination criteria can forecast wind and wave data. If the termination criteria are not met, the weights and thresholds of the BP neural network model are updated, and the calculation error is re-estimated until the termination criteria are met. The test data set is another set of data sets with the same format as the training data set but independent data, which is used to evaluate the forecast accuracy and generalization ability of the model. Furthermore, the forecast accuracy, calculation time, etc. of the model are compared to select the optimal wind and wave forecast model.

[0070] The plane of the trial navigation area is divided into multiple micro-units, and the trial navigation routes of the ship are preset in the trial navigation area. Each preset trial navigation route passes through the micro-units. The rules for the preset routes are set as follows: Figure 3 A schematic diagram of a trial flight route of the present application is shown. Figure 3 As shown, the trial route 3-2 is specified as follows: the trial voyages shall be conducted in the same area, and for each cycle, each speed test voyage shall start and end at the same position. Between the round trips, the modified Williamson turn 3-1 or similar maneuvering method shall be used to return the ship to the opposite heading or parallel to the trial baseline, where 3-3 is the end / start position of the round / round speed test voyage, and 3-4 is the start / end position of the round / round speed test voyage. Parallel means that the deviation from the trial baseline does not exceed one ship length. During the trial, the main engine throttle, speed or pitch remains unchanged, and the duration of the speed test voyage should be the same and at least ten minutes. The speed test voyage should be conducted in the main wave direction into the waves or with the waves. Once the heading is determined, the selected track remains unchanged throughout the trial.

[0071] Divide the micro-units in the plane of the sea trial area and determine the central unit and direction. The aforementioned micro-unit can be a polygon such as a square, rectangle or hexagon or a circle, and the entire micro-unit should be able to accommodate the entire hull. Usually, the starting point of the ship's sea trial is the center of the central micro-unit, the north is the 0° direction, and the angle gradually increases in the clockwise direction.

[0072] Furthermore, the present application further defines the directions of the trial navigation area micro-units and preset trial navigation routes. Figure 4 The schematic diagram of the trial navigation area micro-unit and the preset trial navigation route is shown. Figure 4As shown, 4-1 represents a micro unit of the trial navigation area, 4-2 represents a hull, 4-3 represents a preset trial navigation route, and 4-4 represents the angle between adjacent trial navigation routes. A plurality of trial navigation routes 4-3 are preset in the trial navigation area, and the angle 4-4 between adjacent preset trial navigation routes is set to n°, and the value of n can be determined according to user needs, equipment conditions, etc. The direction of the preset trial navigation route 4-3 represents the bow direction of the ship.

[0073] Furthermore, the wind field data and wave field data during the ship sea trial are obtained based on the wind and wave forecast model. Combined with the relevant parameters during the ship sea trial, the wind and wave resistance increase of each micro-unit on each preset sea trial route is calculated. The wind and wave resistance increase of all micro-units passed by the sea trial route is accumulated to obtain the total value of the wind and wave resistance increase on the sea trial route.

[0074] Specifically, the latitude and longitude range, time range, temperature field, pressure field, water temperature field, water depth, ocean current field, density field, topography and coastline of the trial voyage time and space are input into the aforementioned selected wind and wave forecast model, and the wind field and wave field in the trial voyage time and space are obtained through the wind and wave forecast model, that is, the wind and wave forecast result is obtained. The input latitude and longitude range and time range of the trial voyage time and space can usually be set manually, and the temperature field, pressure field, water temperature field, water depth, ocean current field, density field, topography and coastline can be obtained by actual measurement, model prediction or theoretical calculation.

[0075] Based on the wind field and wave field, ship characteristics, preset speed and other parameters in the trial time and space, the wind and wave resistance increase calculation formula is used to predict the wind and wave resistance increase of the ship on the preset trial route. Specifically, based on the wind and wave forecast results obtained in the above steps, on each preset trial route, according to the preset trial start and end time and speed, the time-trajectory of the ship on the route is obtained. According to the time-trajectory, the real-time wind field and wave field during the ship's trial are extracted from the wind and wave forecast results, including the real-time wind speed, wind direction and wave direction.

[0076] Based on the predicted real-time wind speed, wind direction and wave direction during the ship's sea trial obtained in the above steps, the relative wind speed, relative wind direction, true wind speed, true wind direction, relative wind direction at the reference height, relative wind speed at the reference height, wave direction angle, etc. of the ship in the micro unit are calculated according to the preset sea trial bow direction and anemometer height. Figure 5 A schematic diagram of wind direction and wind speed defined in ISO 15016 (2015) is shown, wherein 5-1 represents relative wind speed, 5-2 represents true wind speed, 5-3 represents ship speed, 5-4 represents relative wind direction, 5-5 represents true wind direction, 5-6 represents heading, 5-7 represents bow, and 5-8 represents hull. The reference height can be selected according to the height corresponding to the wind resistance coefficient obtained from the wind tunnel test.

[0077] The aforementioned ship characteristics include at least the waterline, length between perpendiculars, width, midship draft, trim and squareness coefficient; the preset speed includes at least the ship's ground speed and water speed; other parameters include at least the anemometer height, air density and seawater density.

[0078] In one embodiment, the aforementioned wind and wave resistance increase calculation formula may be based on the wind and wave resistance increase calculation formula in ISO 15016 (2002), ISO 15016 (2015), and ITTC (7.5-04-01-01). For example, in ISO 15016 (2015), the wind resistance increase calculation formula is shown in formula (3); in ISO 15016 (2015), the wave resistance increase calculation formula STAWAVE2 is shown in formula (4).

[0079]

[0080] Among them, R AA represents wind resistance; ρ A Indicates air density; C AA (Ψ WRref ) represents the wind resistance coefficient corresponding to the relative wind direction at the reference height; A XV Indicates the transverse projection area above the waterline of the ship including the superstructure; V WRref Indicates the relative wind speed at the reference height; C AA (0) represents the average windward drag coefficient; V G Indicates the ship's ground speed; R AW Indicates wave resistance; R AWML Indicates the increase in resistance caused by exercise; R AWRL represents the average resistance increase caused by wave reflection; A Indicates amplitude; S η (ω) represents the frequency spectrum.

[0081] According to the wind and wave resistance increase calculation formula, such as formula (3) and formula (4), the wind and wave resistance increase value of each micro unit on the preset trial route is calculated, and the wind and wave resistance increase values ​​of all micro units are accumulated to obtain the total value of the wind and wave resistance increase of the ship on the preset trial route.

[0082] The trial route is selected based on the wind and wave resistance increase obtained by the above calculation. The discrete degree of wind and wave resistance increase values ​​between different micro-units on each preset trial route is statistically calculated to obtain statistical parameters such as the average value, maximum value, standard deviation and variance of the wind and wave resistance increase of the ship on the preset trial route. According to the planning goals specified by the user, such as minimization of wind and wave resistance increase, discrete degree of wind and wave resistance increase, etc., so that the ship can maintain a relatively stable navigation state during the trial, multiple better trial routes are selected from the preset trial routes.

[0083] The second aspect of the present application provides a ship trial route planning system based on wind and wave resistance increase, including a model building module, a trial route planning module, a wind and wave resistance increase calculation module and a trial route screening module. Among them, the model building module is used to build a wind and wave forecasting model based on a BP neural network model or a BP neural network model combined with an optimization algorithm.

[0084] The aforementioned BP neural network model includes an input layer, a hidden layer and an output layer. In one embodiment, the input layer and the output layer of the BP neural network model are both one layer. The number of nodes in the input layer is equal to the number of input parameters. The input parameters specifically include latitude and longitude range, time range, temperature field, pressure field, water temperature field, water depth, ocean current field, density field and terrain coastline data. The number of nodes in the output layer is equal to the number of output parameters. The output parameters are usually wind fields and wave fields, specifically including but not limited to wind speed, wind direction, wind and wave height, wind and wave period, wind and wave frequency, wind and wave length, swell height, swell period, swell frequency and swell length. The resolution of the output parameters is set by the user according to actual needs. The number of layers and nodes of the hidden layer is determined by debugging to capture the inherent laws and characteristics of the data. Usually, the number of layers of the hidden layer is one or more layers, and the specific number of layers and nodes are adjusted according to model performance and training efficiency.

[0085] The training data set of the aforementioned initial wind and wave forecast model is composed of data from various sources, such as actual measurement data from wind and waves, numerical simulation data, and physical test data, which include input parameters and output parameters. The training termination criteria of the initial wind and wave forecast model are set by error parameters (such as determination coefficient, mean square error) or the number of training times. On the programming platform, the wind and wave forecast model is constructed according to the model type, number of model layers, number of nodes in each layer, termination criteria, and training algorithm, and then the training data set is loaded to train the model. The model that meets the termination criteria is the initial wind and wave forecast model; the test data set is loaded to test the trained initial wind and wave forecast model, and the wind and wave forecast model is obtained if the test accuracy is met.

[0086] The trial voyage route planning module is used to divide the plane of the trial voyage area into multiple micro-units, and preset the trial voyage route of the ship in the trial voyage area. Each preset trial voyage route passes through several micro-units. Divide the micro-units in the plane of the trial voyage area and determine the central unit and direction. The aforementioned micro-unit can be a polygon or circle such as a square, rectangle or hexagon, and the entire micro-unit should be able to accommodate the entire hull. Usually, the starting point of the ship's trial is the center of the central micro-unit, due north is the 0° direction, and the angle gradually increases in the clockwise direction. Multiple trial voyage routes are preset in the trial voyage area, and the angle between adjacent preset trial voyage routes is set to n°. The value of n can be determined according to user needs, equipment conditions, etc. The direction of the preset trial voyage route represents the bow direction of the ship.

[0087] The wind and wave resistance increase calculation module is used to obtain the wind field data and wave field data during the ship trial based on the wind and wave forecast model, and calculate the wind and wave resistance increase of each micro-unit on each preset trial route in combination with the relevant parameters during the ship trial. The wind and wave resistance increase of all micro-units passed by the trial route is accumulated to obtain the total value of the wind and wave resistance increase on the trial route. The longitude and latitude range, time range, temperature field, pressure field, water temperature field, water depth, ocean current field, density field and topography and coastline data of the trial time and space are input into the wind and wave forecast model to obtain the wind field and wave field data in the trial time and space. Based on the wind field and wave field data in the trial time and space, ship characteristics, preset speed and other parameters, the wind and wave resistance increase of the ship on the preset trial route is calculated according to the wind and wave resistance increase calculation formula (3) and formula (4).

[0088] In the prior art, although ships are equipped with corresponding monitoring equipment to record wind and wave parameters, these data often remain at the recording level and lack the ability to be analyzed and processed in real time. Therefore, the force conditions of ships in wind and waves, especially the value and change trend of wind and wave resistance increase, cannot be displayed in real time and intuitively. This not only limits the operators' real-time evaluation and adjustment of ship performance, but also affects the integrity and accuracy of the trial data.

[0089] In one embodiment, the embodiment of the present application can also draw a trend curve of wind and wave resistance increase according to the wind and wave resistance increase value suffered by the ship in the real-time trial route obtained by the above calculation, and display it in the interface. The real-time trial route of the ship can be determined by the ship navigation system, and the real-time wind and wave resistance increase of the ship is calculated based on the characteristics of the ship, real-time wind and waves, measured speed and other parameters, with the help of the wind and wave resistance increase calculation formula. Figure 6 It shows a schematic diagram of the interface display of planning a trial voyage route and wind and wave resistance increase in a micro unit in an embodiment of the present application. Figure 7 The following is a schematic diagram showing the interface display of the real-time trial route, wind and wave resistance value and trend of this application. Figure 6 , Figure 7 As shown, the present application can indicate the wind and wave resistance increase of a ship in a micro-unit by the color and number of the micro-unit. For example, the darker the color of the micro-unit and the larger the number, the greater the wind and wave resistance increase of the ship in the micro-unit. Under different wind and wave resistance increase calculation formulas, the wind and wave resistance increase data and trends are also different. At this time, the user can switch the interface display under different wind and wave resistance increase calculation formulas and automatically save the displayed data and curves. In one embodiment, the micro-unit color, micro-unit number, and wind and wave resistance increase trend curve displayed on the interface can be set to update at regular intervals, and the update frequency can be determined based on user needs, equipment conditions, etc.

[0090] The trial route screening module is used to screen the trial routes based on the wind and wave resistance increase. The discrete degree of the wind and wave resistance increase values ​​between different micro-units on each preset trial route is statistically calculated to obtain statistical parameters such as the average value, maximum value, standard deviation and variance of the wind and wave resistance increase of the ship on the preset trial route. According to the planning goals specified by the user, such as minimization of wind and wave resistance increase, discrete degree of wind and wave resistance increase, etc., so that the ship can maintain a relatively stable navigation state during the trial, m (m≥1) better trial routes are screened from the preset trial routes, and sorted according to the planning target parameters. The sorted trial routes are displayed on the interface. The m value can be determined according to user needs, equipment conditions, etc.

[0091] like Figure 6 As shown, in the display interface, in addition to displaying m preset trial routes that meet the conditions, for example Figure 6 6-1, 6-2, and 6-3 represent the 1# preferred trial route, 2# preferred trial route, and 3# trial route, respectively. The display interface can also display the color and number 6-6 of the micro-unit to indicate the wind and wave resistance increase of the ship in the unit. For example, the darker the color of the micro-unit and the larger the number, the greater the wind and wave resistance increase value of the ship in the micro-unit. The trial route planning results may vary depending on the wind and wave resistance increase calculation formula. To this end, the user can switch the interface display under different wind and wave resistance increase calculation formulas and customize the trial route planning results. The technical solution of the present application can display the wind and wave resistance increase values ​​and trends suffered by the ship during the trial in real time, so that the operator can understand the real-time force conditions of the ship in the wind and waves. The ship's trial route planning results, wind and wave resistance increase forecast, and wind and wave resistance increase real-time situation are all visualized and archived.

[0092] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.

Claims

1. A method for planning a ship trial route based on wind and wave resistance increase, characterized in that: include: Construct a wind and wave forecast model based on the BP neural network model or the BP neural network model combined with the optimization algorithm; Dividing the plane of the trial navigation area into a plurality of micro-units, presetting the trial navigation route of the ship in the trial navigation area, and each of the preset trial navigation routes passes through the micro-units; Based on the wind and wave forecast model, wind field data and wave field data during the ship trial are obtained, and combined with relevant parameters during the ship trial, the wind and wave resistance increase of each micro-unit on each preset trial route is calculated, and the wind and wave resistance increase of all micro-units passed by the trial route are accumulated to obtain the total value of the wind and wave resistance increase on the trial route; The trial route is selected based on the increased wind and wave resistance.

2. The method for planning a ship trial route based on wind and wave resistance increase according to claim 1, characterized in that: The process of constructing the wind and wave forecast model includes: An initial wind and wave forecast model is constructed based on a BP neural network model or a BP neural network model combined with an optimization algorithm; the initial wind and wave forecast model is trained using a training data set, and the initial wind and wave forecast model is obtained when a termination standard is reached; a test data set is loaded to test the trained initial wind and wave forecast model, and the wind and wave forecast model is obtained when the test accuracy is met.

3. The method for planning a ship trial route based on wind and wave resistance increase according to claim 2, characterized in that: The optimization algorithms include genetic algorithm, particle swarm algorithm and ant colony algorithm, which are used to optimize the initial weights and initial thresholds of the BP neural network model.

4. The method for planning a ship trial route based on wind and wave resistance increase according to claim 2, characterized in that: The BP neural network model comprises an input layer, a hidden layer and an output layer, wherein: The input layer is a layer, the number of nodes in the input layer is equal to the number of input parameters, and the input parameters include latitude and longitude range, time range, air temperature field, air pressure field, water temperature field, water depth, ocean current field, density field and topographic coastline; The number of layers of the hidden layer is one or more layers, and the number of layers and nodes of the hidden layer are adjusted according to the performance and training efficiency of the BP neural network model; The output layer is one layer, the number of nodes in the output layer is equal to the number of output parameters, and the output parameters at least include wind speed, wind direction, wind wave height, wind wave period, wind wave frequency, wind wave length, swell wave height, swell wave period, swell wave frequency and swell wave length.

5. The method for planning a ship trial route based on wind and wave resistance increase according to claim 2, characterized in that: The training data set for training the initial wind and wave forecast model comes from actual measurement data of wind and waves, numerical simulation data, and physical test data; The training termination criterion of the wind and wave forecast model is set by the determination coefficient, the mean square error or the number of training times, wherein the calculation formulas of the determination coefficient and the mean square error are shown in formula (1) and formula (2) respectively. Among them, R 2 represents the coefficient of determination; y i represents the forecast value of the i-th group; y i0 represents the i-th group of measurements; y m represents the average value of the measured value; N represents the total number of data sets; X mse represents the mean square error.

6. The method for planning a ship trial route based on wind and wave resistance increase according to claim 1, characterized in that: The step of dividing the plane of the trial navigation area into a plurality of micro-units and presetting the trial navigation route of the ship in the trial navigation area comprises: Dividing the plane of the sea trial area into micro-units and determining a central micro-unit, wherein the micro-unit is polygonal or circular and the size of the micro-unit can accommodate the entire hull; Taking the starting point of the ship trial as the center of the central micro-unit, setting the first direction of the center of the central micro-unit as the 0° direction, and increasing the angle in the clockwise or counterclockwise direction; A plurality of trial navigation routes are preset in the trial navigation area, the angle between adjacent preset trial navigation routes is n°, and the direction of the trial navigation route is set as the bow direction of the ship.

7. The method for planning a ship trial route based on wind and wave resistance increase according to claim 1, characterized in that: The method of obtaining wind field data and wave field data during the ship sea trial based on the wind and wave forecast model, and calculating the wind and wave resistance increase of each micro-unit on each preset sea trial route in combination with relevant parameters during the ship sea trial, and accumulating the wind and wave resistance increase of all micro-units passed by the sea trial route, includes: At least the latitude and longitude range, time range, temperature field, pressure field, water temperature field, water depth, ocean current field, density field, topography and coastline of the trial voyage time and space are input into the wind and wave forecast model to obtain wind field data and wave field data in the trial voyage time and space.

8. The method for planning a ship trial route based on wind and wave resistance increase according to claim 7, characterized in that: The method of obtaining wind field data and wave field data during the ship sea trial based on the wind and wave forecast model, and calculating the wind and wave resistance increase of each micro-unit on each preset sea trial route in combination with relevant parameters during the ship sea trial, and accumulating the wind and wave resistance increase of all micro-units passed by the sea trial route, includes: Based on the wind field data and wave field data obtained during the ship trial, on each preset trial route, according to the preset trial start and end time and speed, the time and trajectory of the ship on the trial route are obtained; According to the time and trajectory, the forecast real-time wind speed, wind direction and wave direction during the ship's sea trial are extracted from the acquired wind field data and wave field data.

9. The method for planning a ship trial route based on wind and wave resistance increase according to claim 8, characterized in that: The relevant parameters during the ship trial include ship characteristics, preset speed and other parameters; The ship characteristics include at least waterline, length between perpendiculars, breadth, mid-air draft, trim and squareness coefficient; The other parameters are based on the predicted real-time wind speed, wind direction and wave direction of the ship during the sea trial, and according to the preset sea trial bow direction and anemometer height, the relative wind speed, relative wind direction, true wind speed, true wind direction, relative wind direction at the reference height, relative wind speed and wave direction of the ship in the micro unit are calculated.

10. The method for planning a ship trial route based on wind and wave resistance increase according to claim 9, characterized in that: The wind and wave resistance increase of each micro-unit on each of the trial routes is calculated by the calculation formula of wind resistance increase and wave resistance increase: The calculation formula for wind resistance is shown in formula (3), and the STAWAVE2 calculation formula for wave resistance is shown in formula (4). Among them, R AA represents wind resistance; ρ A Indicates air density; C AA (Ψ WRref ) represents the wind resistance coefficient corresponding to the relative wind direction at the reference height; A XV Indicates the transverse projection area above the waterline of the ship including the superstructure; V WRref Indicates the relative wind speed at the reference height; C AA (0) represents the average windward drag coefficient; V G Indicates the ship's ground speed; R AW Indicates wave resistance; R AWML Indicates the increase in resistance caused by exercise; R AWRL represents the average resistance increase caused by wave reflection; A Indicates amplitude; S η (ω) represents the frequency spectrum.

11. The method for planning a ship trial route based on wind and wave resistance increase according to claim 1, characterized in that: The selection of trial routes based on wind and wave resistance increase includes: Counting the discreteness of wind and wave resistance increase values ​​between different micro-units on each preset trial route, and obtaining the average value, maximum value, standard deviation and variance of wind and wave resistance increase values ​​of ships on the trial route; The trial voyage route is selected based on the planning target parameters, wherein the planning target parameters include the total value and discreteness of the ship's wind and wave resistance increase.

12. A ship trial route planning system based on wind and wave resistance increase, characterized in that: include: Model building module, trial route planning module, wind and wave resistance calculation module and trial route screening module; among them, The model building module is used to build a wind and wave forecast model based on a BP neural network model or a BP neural network model combined with an optimization algorithm; The trial voyage route planning module is used to divide the plane of the trial voyage area into a plurality of micro-units, and preset the trial voyage route of the ship in the trial voyage area, and each preset trial voyage route passes through a plurality of the micro-units; The wind and wave resistance increase calculation module is used to obtain the wind field data and wave field data during the ship trial based on the wind and wave forecast model, and calculate the wind and wave resistance increase of each micro-unit on each preset trial route in combination with relevant parameters during the ship trial, and accumulate the wind and wave resistance increase of all micro-units passed by the trial route to obtain the total value of the wind and wave resistance increase on the trial route; The trial voyage route screening module is used to screen the trial voyage route based on the wind and wave resistance increase.

Images