A method, device and equipment for forecasting marine targets

Abstract

The present invention discloses a method, device and equipment for forecasting marine targets, which relates to the technical field of marine environment forecasting, and is used to solve the problem in the prior art that the selection of parameters for marine targets may be biased, resulting in poor prediction results. It includes: determining the type of the wrecked target to be rescued at sea; determining a preset number of target model parameters based on the type of the wrecked target; determining the running track of the wrecked target based on the target model parameters; determining the position information of the wrecked target according to the running track, and calculating the drift track distance error, drift track angle error and drift track average distance error of the wrecked target based on the position information; and determining the optimal parameters of the wrecked target; and forecasting the drift of the wrecked target based on the optimal parameters. The present invention can improve the accuracy of parameter determination, thereby improving the accuracy of prediction results of marine targets.

Description

Technical Field

[0001] The present invention relates to the technical field of marine environment forecasting, and in particular to a method, device and equipment for forecasting marine targets. Background Art

[0002] With the expansion of the scale of marine development and the frequent maritime activities, maritime accidents have attracted more attention. Maritime accidents will bring huge disasters to coastal countries in the world in terms of politics, economy and military. Not only will they cause casualties and property losses, but they will also have adverse effects on social development. Therefore, maritime search and rescue work has received more and more attention from coastal countries. For the rapidly developing maritime transportation and fishing industries, maritime search and rescue operations can provide irreplaceable protection for the safety of personnel and property.

[0003] When encountering an emergency search and rescue incident at sea, the forecaster will first select the closest parameters for forecasting based on experience. For example, when a person falls into the water on the sea, the forecaster will select the parameters related to people based on experience: when the status of the person is uncertain, the unknown status (average value) parameter of the person who falls into the water will be given priority, and then the drift trajectory will be inferred based on the calculation method of the drift of the sea surface material. After completing the trajectory prediction of each drifting particle, the drift position and search and rescue range of the material with random statistical characteristics are obtained. This method relies heavily on the experience of the forecaster, but because the actual size of the person who falls into the water or other target objects, the shape characteristics floating on the sea surface, the load and other drift characteristics are not known, so to a certain extent, the parameter selection will bring deviations to the forecast results.

[0004] Therefore, there is an urgent need to provide a more reliable parameter selection scheme for offshore targets. Summary of the invention

[0005] The purpose of the present invention is to provide a method, device and equipment for forecasting marine targets, which are used to solve the problem in the prior art that there may be deviations in the selection of marine target parameters, resulting in poor accuracy of prediction results.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for forecasting marine targets, the method comprising:

[0008] Determine the type of distressed objects to be searched and rescued at sea;

[0009] Determining a preset number of target model parameters based on the type of the crashed target object;

[0010] Determining the running trajectory of the crashed target object based on the target model parameters;

[0011] Determine the position information of the crashed target object according to the running trajectory, and calculate the drift trajectory distance error, drift trajectory angle error and drift trajectory average distance error of the crashed target object based on the position information;

[0012] Determining optimal parameters of the crash target based on the drift trajectory distance error, the drift trajectory angle error, and the drift trajectory average distance error;

[0013] The drift of the crashed target object is predicted based on the optimal parameters.

[0014] Compared with the prior art, the present invention provides a method for forecasting marine targets, which determines the type of the wrecked target to be searched and rescued at sea; determines a preset number of target model parameters based on the type of the wrecked target; determines the running track of the wrecked target based on the target model parameters; determines the location information of the wrecked target according to the running track, and calculates the drift track distance error, drift track angle error and drift track average distance error of the wrecked target based on the location information; determines the optimal parameters of the wrecked target based on the drift track distance error, the drift track angle error and the drift track average distance error; and forecasts the drift of the wrecked target based on the optimal parameters. Selecting corresponding target model parameters based on the type of the wrecked target to be searched and rescued, and determining the optimal parameters of the wrecked target based on the drift track distance error, the drift track angle error and the drift track average distance error can improve the accuracy of parameter selection, thereby improving the accuracy of prediction results of marine targets.

[0015] In a second aspect, the present invention provides a marine target forecasting device, the device comprising:

[0016] A module for determining the type of a lost object, used to determine the type of a lost object to be searched and rescued at sea;

[0017] A target model parameter determination module, used to determine a preset number of target model parameters based on the type of the crashed target object;

[0018] A running track determination module, used for determining the running track of the crashed target object based on the target model parameters;

[0019] A distance error calculation module, used to determine the position information of the crash target according to the running trajectory, and calculate the drift trajectory distance error, drift trajectory angle error and drift trajectory average distance error of the crash target based on the position information;

[0020] An optimal parameter determination module, used to determine the optimal parameters of the crash target object based on the drift trajectory distance error, the drift trajectory angle error and the drift trajectory average distance error;

[0021] A drift prediction module is used to predict the drift of the crashed target object based on the optimal parameters.

[0022] In a third aspect, the present invention provides a marine target forecasting device, the device comprising:

[0023] A memory, a processor and a communication interface coupled to the processor; the memory stores a computer program that can be run by the processor; when the processor runs the computer program, the aforementioned marine target forecasting method is executed.

[0024] In a fourth aspect, the present invention provides a computer storage medium having instructions stored therein, which, when executed, implement the above-mentioned method for forecasting marine targets.

[0025] The technical effects achieved by the device type solution provided in the second aspect, the equipment type solution provided in the third aspect, and the computer storage medium solution provided in the fourth aspect are the same as those of the method type solution provided in the first aspect, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings described herein are used to provide a further understanding of the present invention and constitute a part 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 an improper limitation of the present invention. In the drawings:

[0027] Figure 1 A schematic diagram of a method for forecasting marine targets provided by the present invention;

[0028] Figure 2 A multi-branch tree diagram for the drift prediction model of the lost target at sea;

[0029] Figure 3 Schematic diagram of observed drift trajectory and predicted drift trajectory;

[0030] Figure 4 A schematic diagram of a marine target forecasting device provided by the present invention;

[0031] Figure 5 A schematic diagram of a marine target forecasting device provided by the present invention. DETAILED DESCRIPTION

[0032] In order to clearly describe the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, words such as "first" and "second" are used to distinguish the same items or similar items with basically the same functions and effects. For example, the first threshold and the second threshold are only used to distinguish different thresholds, and their order is not limited. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit them to be different.

[0033] It should be noted that, in the present invention, 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 present invention should not be interpreted 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.

[0034] In the present invention, "at least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, the combination of a and b, the combination of a and c, the combination of b and c, or the combination of a, b and c, where a, b, c can be single or multiple.

[0035] Next, the solution provided by the embodiments of this specification is described in conjunction with the accompanying drawings:

[0036] like Figure 1 As shown, the process may include the following steps:

[0037] Step 110: Determine the type of the wrecked object to be searched and rescued at sea.

[0038] The types of wrecked objects may include people, ships, life rafts, etc.

[0039] Step 120: Determine a preset number of target model parameters based on the type of the crashed target object.

[0040] In the calculation method of the wind pressure model, the preset number of target model parameters is 9 target model parameters. The characteristic of the Leeway-based maritime search and rescue model is that the model has 9 model parameters for each type of drifting target at sea, and the parameters are different for different types. The parameters are obtained by conducting drift tests at sea to obtain the actual drift observation trajectory of the marine target type and the marine environmental elements at the corresponding time and position. The experimental observation data are analyzed and studied using empirical statistical methods to obtain the model parameters of the marine target.

[0041] Step 130: Determine the movement trajectory of the crashed target object based on the target model parameters.

[0042] The running trajectory can represent the trajectory of the wrecked object drifting at sea.

[0043] Step 140: Determine the position information of the crashed object according to the running trajectory, and calculate the drift trajectory distance error, drift trajectory angle error and drift trajectory average distance error of the crashed object based on the position information.

[0044] In practice, the average distance error of drift trajectory can reflect the deviation between the predicted trajectory and the true value within a period of time. However, the position information of the target object fed back from the search and rescue site is often very limited, which is only one or several position information at a certain moment. Therefore, the drift trajectory distance error and the drift trajectory angle error are combined for error judgment. Assuming that in a search and rescue operation, several targets are found a certain time after the accident, the optimal parameter selection model is used for calculation, and the drift trajectory distance error and drift trajectory angle error are calculated between the observed position at a certain moment and the average position of all particles at the corresponding moment.

[0045] Step 150: Determine the optimal parameters of the crash target based on the drift trajectory distance error, the drift trajectory angle error and the drift trajectory average distance error.

[0046] The optimal parameters are used to predict the subsequent drift trajectory of marine targets.

[0047] Step 160: Predict the drift of the crashed object based on the optimal parameters.

[0048] Figure 1The method in the method is to determine the type of the wrecked object to be searched and rescued at sea; determine a preset number of target model parameters based on the type of the wrecked object; determine the running track of the wrecked object based on the target model parameters; determine the position information of the wrecked object according to the running track, and calculate the drift track distance error, drift track angle error and drift track average distance error of the wrecked object based on the position information; determine the optimal parameters of the wrecked object based on the drift track distance error, the drift track angle error and the drift track average distance error; and predict the drift of the wrecked object based on the optimal parameters. Selecting corresponding target model parameters based on the type of the wrecked object to be searched and rescued, and determining the optimal parameters of the wrecked object based on the drift track distance error, the drift track angle error and the drift track average distance error can improve the accuracy of parameter selection, thereby improving the accuracy of prediction results of marine targets.

[0049] based on Figure 1 The method, the embodiments of this specification also provide some specific implementation methods of the method, which are described below.

[0050] The technical solution provided by the present invention can be based on the existing maritime search and rescue model of the National Marine Environmental Forecast Center, develop drift prediction and source tracing analysis technology for maritime accident targets, integrate observation data, establish a parameter rapid selection module, use known target object positions (≥2) for automatic parameter matching, and improve the search and rescue initialization process.

[0051] In practical applications, the wind pressure model (Leeway) is a common method for calculating the drift trajectory of offshore targets. Based on the wind pressure calculation method, an empirical wind pressure drift model is established. Wind pressure is defined as the drift motion of offshore targets caused by wind and waves relative to the local seawater movement. It is a vector whose magnitude refers to the magnitude of the speed of the offshore drifting target relative to the local seawater movement. In the rectangular coordinate system, it can be expressed as a component in the downwind direction and a component in the crosswind direction.

[0052] The experimental observation data show that the drift direction of the target at sea is not along the wind direction, but deviates from the wind direction by a certain angle, sometimes to the left and sometimes to the right. After deviating to the left or right, it usually remains unchanged for a period of time. According to the analysis of the experimental data, there is an obvious linear relationship between wind pressure and wind speed.

[0053] In the wind pressure empirical model, the drift speed of the target at sea is the vector sum of the surface current speed and the wind pressure speed.

[0054]

[0055] in, is the drift velocity vector of the sea target, is the wind pressure velocity vector; It is the velocity vector of the surface current. The wind pressure velocity vector is divided into three components: the downwind component and the component perpendicular to the wind direction (the right component is defined as the right-side component and the left component is defined as the left-side component).

[0056]

[0057] L d =a d ×W speed +b d (3)

[0058] L cl =a cl ×W speed +b cl (4)

[0059] L cr =a cr ×W speed +b cr (5)

[0060] L d , L cr , L cl is the wind pressure speed The subscripts d, cr, and cl represent the downwind direction, right-side wind direction, and left-side wind direction, respectively; W speed : 10-meter wind speed; a is the slope parameter in %, b is the intercept parameter in cm / s.

[0061] Initial disturbance: In the actual drifting process at sea, the model parameters obtained by statistical analysis cannot fully and accurately simulate the actual drift trajectory. Even the parameters obtained by statistical analysis of observed data still have simulation errors when reporting the trajectory. In order to consider the uncertainty caused by the errors in the test data, it is necessary to perform initial disturbance on the model parameters a and b. Therefore, the wind pressure speed is calculated based on the preset number of target model parameters, which may specifically include:

[0062] The calculation formula of the model after the above disturbance is as follows:

[0063]

[0064]

[0065]

[0066] Among them, L d , L cr , L cl is the wind pressure speed The subscripts d, cr, and cl represent the downwind, right-side, and left-side wind components, respectively; W speed : 10-meter wind speed; a is the slope parameter in %, b is the intercept parameter in cm / s; ξ is a random number that obeys a normal distribution with a mean of 0 and a mean square error of 1; C is the residual difference of the linear regression equation; ε is a disturbance term that satisfies a uniform distribution.

[0067] In the wind pressure model, the wind-induced drift bias to the left or right side of the downwind direction is determined by a random function (satisfying the normal distribution of 0-1). According to the number of particles input by the forecaster (initial position x, y, randomly distributed within a certain radius range r), each initial particle is randomly assigned a left or right deviation. When calculating the longitude and latitude position of each particle, it is necessary to first calculate the drift speed of the target at sea. According to formula (1), the flow field speed and wind pressure speed are required, where the flow field speed can be obtained by interpolation of the flow field file, and the wind pressure speed needs to be calculated based on the 10-meter wind speed and wind pressure parameters. If it is biased to the left, select formulas (6) and (7) to calculate the downwind and vertical wind direction components. If it is biased to the right, select formulas (6) and (8) for the downwind L. d and the vertical wind direction component L c The calculation of wind-induced displacement L is shown in formula (9), and the wind-induced displacement angle L α (See Figure 1 ) is calculated as shown in formula (10):

[0068]

[0069]

[0070] After the wind-induced offset is calculated, it needs to be decomposed into the horizontal and vertical directions in the rectangular coordinate system. The formula is as follows:

[0071]

[0072]

[0073] Among them, L u , L v is the wind-induced offset in the x and y directions, L is the wind-induced offset, u wind is the u component of wind speed, v wind is the v component of wind speed, L α is the wind-induced deviation angle.

[0074] After obtaining the wind pressure speed, the position at the next moment can be calculated based on the position at the previous moment:

[0075]

[0076]

[0077] in, represents the latitude and longitude of the kth particle at the n+1th time (°); represents the latitude and longitude of the kth particle at the nth time (°); are the components of the wind-induced displacement of the kth particle at the nth moment in the y and x directions (m / s); are the components of the velocity of the kth particle at the nth moment in the y direction and the x direction (m / s); dt is the time interval of calculation (s); r y 、r x represents the random disturbance term; rad represents the radius of the earth 6.371×10 6 m; PI represents pi, which is 3.1415926. After calculation, the longitude and latitude information of k particles at time n+1 can be obtained.

[0078] The 9 parameters in the calculation method of the wind pressure model are fitted with the 6 parameters related to a and b using the wind pressure value L in the drift test data and the wind speed at 10 meters above the sea surface, based on the least squares algorithm, and the statistical method of univariate linear regression. The algorithm based on the statistical method requires the support of a large amount of observation data. The magnitude of the fluctuation of L deviation from the regression value is calculated, recorded as the residual standard deviation C, and the 3 parameters related to C are obtained, which are multiplied by the random number as the disturbance term in the calculation method. The correlation coefficient of L relative to the regression value is calculated to test whether the regression equation is significant, so as to determine whether the fitting of a and b is accurate. The closer the value is to 1, the more accurate the fitting parameters are, and the closer it is to 0, the less accurate the fitting parameters are.

[0079] The characteristic of the Leeway-based maritime search and rescue model is that the model has 9 model parameters for each type of drifting target at sea, and the parameters are different for different types. The parameters are obtained by conducting drift tests at sea to obtain the actual drift observation trajectory of the type of maritime target and the marine environmental elements at the corresponding time and position. The experimental observation data are analyzed and studied using empirical statistical methods to obtain the model parameters of the sea-related targets. At present, about 63 types of reliable drifting target parameters have been accumulated.

[0080] When there is observation data feedback on site, the known target position (≥2) is used to automatically match the parameters, and the multi-branch tree traversal algorithm is partially combined with the "greedy algorithm" theory of the optimal solution. The specific steps are as follows:

[0081] (1) Establish a drift prediction model for lost objects at sea;

[0082] (2) Divide the parameters in the Leeway parameter library into several subtypes according to their types, such as people, life rafts, boats, etc.;

[0083] (3) Select appropriate subtypes for actual maritime emergency search and rescue incidents, traverse and solve each parameter in the subtype, and obtain the local optimal solution;

[0084] (4) The local optimal solution of the subtype is taken as the solution to the original problem, that is, the optimal parameters with the smallest error are selected as the model parameters for subsequent calculations. The multi-branch tree of this model is as follows Figure 2 As shown in the figure, after a search and rescue incident at sea occurs, a subtype in the Leeway parameter library is selected based on the information provided on site, and the drift trajectory of all parameters contained in the subtype is calculated to obtain the drift trajectory of each parameter in the subtype. By calculating the drift trajectory distance error, the drift trajectory angle error, and the drift trajectory average distance error, the parameter with the lowest score is comprehensively selected as the optimal parameter of the drift prediction model for the accident target at sea, and the subsequent drift trajectory prediction of the target at sea is performed.

[0085] Among them, the drift trajectory distance error, the drift trajectory angle error and the drift trajectory average distance error are calculated with reference to the relevant standards of search and rescue inspection, which are explained in detail below.

[0086] The drift trajectory distance error is Figure 3 The line segment AB in the equation is calculated as shown in formula (15). O represents the starting position; A represents the forecast position; B represents the observed position; OA represents the forecast drift distance (km); OB represents the actual drift distance (km).

[0087] DE AB =R·cos -1 (siny A siny B +cosy A cosy B cos|x A -x B |) (15)

[0088] In the formula, DE AB represents the length of line segment AB (km); R represents the radius of the earth (km); y A Indicates the latitude of point A (°); y B Indicates the latitude of point B (°); x A Indicates the longitude of point A (°); x B Indicates the longitude of point B (°).

[0089] The drift trajectory angle error is Figure 3 The angle AOB in is calculated as shown in formula (16):

[0090]

[0091] Where: AE AOB represents the angle of angle AOB (°); x O Indicates the longitude of point O (°); y O Indicates the latitude of point O (°).

[0092] The calculation of the average distance error of the drift trajectory is shown in formula (17).

[0093]

[0094] Where: MDE represents the mean distance error (km); N represents the number of samples; DE i represents the distance error of the i-th sample, i=1, 2,…,N.

[0095] More specifically, when determining the optimal parameters, in the actual operational forecast process, when providing forecast sheets to relevant search and rescue units, the search and rescue elements mainly include: initial position, average trajectory, and search range. The initial position is determined based on the location of the incident or the last known location. At the beginning of the calculation, a certain number of particles are released within a certain radius at the initial position; the average position corresponding to each moment is obtained by averaging the longitude and latitude of all particles; the search range is the closed area determined by the outermost particles. The average distance error of the drift trajectory can actually reflect the deviation between the predicted trajectory and the true value within a period of time, but the location information of the target object fed back from the search and rescue site is often very limited, and is only one or several location information at a certain moment, so the drift trajectory distance error and the drift trajectory angle error are combined for error judgment. Assume that during a search and rescue operation, several targets are found a certain time after the accident occurs. The optimal parameter selection model is used for calculation. The drift trajectory distance error and drift trajectory angle error are calculated between the observation position at a certain moment and the average position of all particles at the corresponding moment. Since the time of the observation position may not match the time calculated by the model, it is necessary to interpolate the position simulated by the model according to the interval between the observation time and the model time to obtain the simulated position information corresponding to the observation time. Based on the drift trajectory distance error and drift trajectory angle error calculations of multiple observation positions, the optimal parameters are determined according to the following formula:

[0096]

[0097] Among them, S k represents the score of the kth parameter, represents the drift trajectory distance error of the kth parameter at the mth observation position, It means that after averaging the drift trajectory distance errors of each parameter for m observation positions, the smallest value among the average drift trajectory distance errors of all parameters is selected; represents the drift trajectory angle error of the kth parameter at the mth observation position, It means that after averaging the drift trajectory angle errors of each parameter for m observation positions, the smallest value among the average drift trajectory angle errors of all parameters is selected; w1 and w2 are the proportions of the drift trajectory distance error and the drift trajectory angle error, respectively.

[0098] Through the above calculations, the scores of k parameters are compared. The lower the score, the smaller the degree of error deviation from the true value. The above w1 and w2 can be determined based on the forecaster's experience. Since the deviation of the angular error of each observation position may be numerically larger, consider giving w1 a larger proportion and w2 a smaller proportion.

[0099] Based on the same idea, the present invention also provides a marine target forecasting device, such as Figure 4 As shown, the device may include:

[0100] A crash object type determination module 410 is used to determine the type of the crash object to be searched and rescued at sea;

[0101] A target model parameter determination module 420, configured to determine a preset number of target model parameters based on the type of the crashed target object;

[0102] A running track determination module 430, configured to determine the running track of the crashed target object based on the target model parameters;

[0103] A distance error calculation module 440 is used to determine the position information of the crash target according to the running trajectory, and calculate the drift trajectory distance error, drift trajectory angle error and drift trajectory average distance error of the crash target based on the position information;

[0104] An optimal parameter determination module 450, configured to determine the optimal parameters of the crash target object based on the drift trajectory distance error, the drift trajectory angle error, and the drift trajectory average distance error;

[0105] The drift prediction module 460 is used to predict the drift of the crashed target object based on the optimal parameters.

[0106] based on Figure 4 The device in the embodiment may further include some specific implementation units:

[0107] Optionally, the running trajectory determination module 430 may specifically include:

[0108] A wind pressure speed calculation unit, used to calculate the wind pressure speed according to a preset number of target model parameters;

[0109] A latitude and longitude position calculation unit, used to calculate the latitude and longitude position of the crash target at the next moment according to the wind pressure speed;

[0110] The running track determination unit is used to obtain the connection line of the average positions of multiple particles at each moment after the calculation is completed, and determine the running track of the crashed target object.

[0111] Optionally, the device may further include:

[0112] A subtype determination module, used for determining the type of the crashed object as a parameter subtype in a Leeway parameter library;

[0113] The local optimal solution determination module is used to traverse and solve each parameter in the subtype of the crash target object to obtain a local optimal solution.

[0114] Optionally, the distance error calculation module 440 may specifically include:

[0115] A unit for determining drift trajectories of parameters, used for selecting a subtype in the Leeway parameter library, calculating drift trajectories of all parameters contained in the subtype, and obtaining drift trajectories of parameters in the subtype;

[0116] The optimal parameter determination unit is used to calculate the drift trajectory distance error, the drift trajectory angle error and the drift trajectory average distance error, and based on the calculation results, comprehensively select the parameter with the lowest score as the optimal parameter of the drift prediction model for the lost target at sea.

[0117] Optionally, the optimal parameter determination unit may be specifically used to:

[0118] Using the formula:

[0119]

[0120] Calculate optimal parameters;

[0121] Among them, S k represents the score of the kth parameter, represents the drift trajectory distance error of the kth parameter at the mth observation position, It means that after averaging the drift trajectory distance errors of m observation positions for each parameter, the minimum value of the average drift trajectory distance error is selected; represents the drift trajectory angle error of the kth parameter at the mth observation position, It means that after averaging the drift trajectory angle errors of m observation positions for each parameter, the minimum value of the average drift trajectory angle error is selected; w1 and w2 are the proportions of the drift trajectory distance error and the drift trajectory angle error, respectively.

[0122] Optionally, the wind pressure velocity vector may include a downwind component and a component perpendicular to the wind direction; the component perpendicular to the wind direction includes a right lateral component and a left lateral component;

[0123] The wind pressure velocity calculation unit can be used for:

[0124] Using the formula:

[0125]

[0126]

[0127]

[0128] The downwind component, the left lateral component and the right lateral component are calculated;

[0129] Among them, L d , L cr , L cl are the downwind component, right-lateral component and left-lateral component of the wind pressure velocity, respectively. The subscripts d, cr and cl represent the downwind direction, right-lateral wind direction and left-lateral wind direction, respectively. speed represents the wind speed at 10 meters, a is the slope, b is the intercept, ξ is a random number, and ξ obeys a normal distribution with a mean of 0 and a mean square error of 1; C is the residual difference of the linear regression equation; ε is a disturbance term that satisfies uniform distribution.

[0130] Optionally, the latitude and longitude position calculation unit may be specifically used for:

[0131] After determining the wind pressure velocity, the formula is used:

[0132]

[0133]

[0134] Calculating the latitude and longitude position of the crashed object at the next moment based on the position at the previous moment;

[0135] in, represents the latitude of the kth particle at the n+1th moment, represents the longitude of the kth particle at the n+1th moment; represents the latitude of the kth particle at the nth moment, represents the longitude of the kth particle at the nth moment; represents the component of the wind-induced displacement of the kth particle at the nth moment in the y direction, represents the component of the wind-induced displacement of the kth particle at the nth moment in the x direction; represents the component of the velocity of the kth particle at the nth moment in the y direction, represents the x-direction component of the velocity of the kth particle at the nth moment; dt represents the time interval of calculation; r y 、r x are all random disturbance terms; rad represents the radius of the earth, which is 6.371×10 6 m; PI stands for pi, and its value is 3.1415926.

[0136] Based on the same idea, the embodiment of this specification also provides a marine target forecasting device. Figure 5 As shown, the device includes:

[0137] A memory, a processor and a communication interface coupled to the processor; the memory stores a computer program that can be run by the processor; when the processor runs the computer program, the aforementioned method for forecasting marine targets is executed.

[0138] like Figure 5 As shown, the processor may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present invention. The communication interface may be one or more. The communication interface may use any transceiver-like device for communicating with other devices or communication networks.

[0139] like Figure 5 As shown, the terminal device may further include a communication line. The communication line may include a path to transmit information between the components.

[0140] Optional, such as Figure 5 As shown, the terminal device may further include a memory. The memory stores a computer program executable by the processor; when the processor executes the computer program, the method provided by the embodiment of the present invention is implemented.

[0141] like Figure 5As shown, the memory may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processor through a communication line. The memory may also be integrated with the processor.

[0142] Optionally, the computer-executable instructions in the embodiment of the present invention may also be referred to as application program codes, which is not specifically limited in the embodiment of the present invention.

[0143] In a specific implementation, as an example, Figure 5 As shown, the processor may include one or more CPUs, such as Figure 5 CPU0 and CPU1 in.

[0144] In a specific implementation, as an example, Figure 5 As shown, the terminal device may include multiple processors, such as Figure 5 Each of these processors can be a single-core processor or a multi-core processor.

[0145] Based on the same idea, the embodiments of this specification also provide a computer storage medium corresponding to the above embodiments, and the computer storage medium stores instructions, and when the instructions are executed, the method in the above embodiments is implemented.

[0146] The above mainly introduces the solution provided by the embodiment of the present invention from the perspective of the interaction between the various modules. It is understandable that, in order to realize the above functions, each module includes a hardware structure and / or software unit corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0147] The embodiment of the present invention can divide the functional modules according to the above method example. For example, each functional module can be divided according to each function, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0148] The processor in this specification may also have the function of a memory. The memory is used to store computer-executable instructions for executing the solution of the present invention, and the execution is controlled by the processor. The processor is used to execute the computer-executable instructions stored in the memory, thereby implementing the method provided by the embodiment of the present invention.

[0149] The memory may be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory may exist independently and be connected to the processor through a communication line. The memory may also be integrated with the processor.

[0150] Optionally, the computer-executable instructions in the embodiment of the present invention may also be referred to as application program codes, which is not specifically limited in the embodiment of the present invention.

[0151] The method disclosed in the above embodiment of the present invention can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor may be a general-purpose processor, a digital signal processor (digital signal processing, DSP), an ASIC, a field-programmable gate array (field-programmable gate array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in the embodiment of the present invention can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0152] Although the present invention is described herein in conjunction with various embodiments, in the process of implementing the claimed invention, those skilled in the art may understand and implement other variations of the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0153] Although the present invention has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present invention. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present invention as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present invention. Obviously, those skilled in the art may make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, the present invention is intended to include such modifications and variations if they fall within the scope of the claims of the present invention and their equivalents.

Claims

1. A method for forecasting marine targets, characterized in that: include: Determine the type of distressed objects to be searched and rescued at sea; Determining a preset number of target model parameters based on the type of the crashed target object; Determining the running trajectory of the crashed target object based on the target model parameters; Determine the position information of the crashed target object according to the running trajectory, and calculate the drift trajectory distance error, drift trajectory angle error and drift trajectory average distance error of the crashed target object based on the position information; Determining optimal parameters of the crash target based on the drift trajectory distance error, the drift trajectory angle error, and the drift trajectory average distance error; Performing drift prediction on the crashed target object based on the optimal parameters; Determining the running trajectory of the crashed target object based on the target model parameters specifically includes: The wind pressure velocity is calculated according to a preset number of target model parameters; Calculate the latitude and longitude position of the crash target at the next moment according to the wind pressure speed; After the calculation is completed, the connection line of the average positions of multiple particles at each moment is obtained to determine the running trajectory of the crashed target object; The wind pressure velocity vector includes a downwind component and a component perpendicular to the wind direction; the component perpendicular to the wind direction includes a right-side component and a left-side component; The wind pressure velocity is calculated according to a preset number of target model parameters, including: Using the formula: The downwind component, the left lateral component and the right lateral component are calculated; Among them, L d , L cr , L cl are the downwind component, right-lateral component and left-lateral component of the wind pressure velocity, respectively. The subscripts d, cr and cl represent the downwind direction, right-lateral wind direction and left-lateral wind direction, respectively. speed represents the wind speed at 10 meters, a is the slope, b is the intercept, ξ is a random number, and ζ obeys a normal distribution with a mean of 0 and a mean square error of 1; C is the residual difference of the linear regression equation; ε is a disturbance term that satisfies uniform distribution; Calculating the latitude and longitude position of the crash target at the next moment according to the wind pressure speed specifically includes: After determining the wind pressure velocity, the formula is used: Calculating the latitude and longitude position of the crashed object at the next moment based on the position at the previous moment; in, represents the latitude of the kth particle at the n+1th moment, represents the longitude of the kth particle at the n+1th moment; represents the latitude of the kth particle at the nth moment, represents the longitude of the kth particle at the nth moment; represents the component of the wind-induced displacement of the kth particle at the nth moment in the y direction, represents the component of the wind-induced displacement of the kth particle at the nth moment in the x direction; represents the component of the velocity of the kth particle at the nth moment in the y direction, represents the x-direction component of the velocity of the kth particle at the nth moment; dt represents the time interval of calculation; r y 、r x All are random disturbance terms; rad represents the radius of the earth; PI represents pi.

2. The method for predicting marine targets according to claim 1, characterized in that: Before determining the position information of the crashed object according to the running trajectory and calculating the drift trajectory distance error, the drift trajectory angle error and the drift trajectory average distance error of the crashed object based on the position information, the method further includes: Determine the type of the crashed object as a parameter subtype in the Leeway parameter library; Each parameter in the subtype of the crashed target object is traversed and solved to obtain a local optimal solution.

3. The method for predicting marine targets according to claim 2, characterized in that: The determining the optimal parameters of the crash target object based on the drift trajectory distance error, the drift trajectory angle error and the drift trajectory average distance error specifically includes: Select a subtype in the Leeway parameter library, calculate the drift trajectory of all parameters contained in the subtype, and obtain the drift trajectory of each parameter in the subtype; By calculating the drift trajectory distance error, drift trajectory angle error and drift trajectory average distance error, based on the calculation results, the parameters with the lowest scores are comprehensively selected as the optimal parameters of the drift prediction model for marine accident targets.

4. The method for predicting marine targets according to claim 3, characterized in that: The method calculates the drift trajectory distance error, the drift trajectory angle error and the drift trajectory average distance error, and based on the calculation results, comprehensively selects the parameter with the lowest score as the optimal parameter of the drift prediction model for the lost target at sea. The optimal parameter of the drift prediction model for the lost target at sea specifically includes: Using the formula: Calculate optimal parameters; Among them, S k represents the score of the kth parameter, represents the drift trajectory distance error of the kth parameter at the mth observation position, It means that after averaging the drift trajectory distance errors of each parameter for m observation positions, the minimum value of the average drift trajectory distance errors of all parameters is selected; represents the drift trajectory angle error of the kth parameter at the mth observation position, It means that after averaging the drift trajectory angle errors of each parameter for m observation positions, the minimum value of the average drift trajectory angle errors of all parameters is selected; w1 and w2 are the proportions of the drift trajectory distance error and the drift trajectory angle error, respectively.

5. A marine target forecasting device, characterized in that: The device includes: A module for determining the type of a lost object, used to determine the type of a lost object to be searched and rescued at sea; A target model parameter determination module, used to determine a preset number of target model parameters based on the type of the crashed target object; A running track determination module, used for determining the running track of the crashed target object based on the target model parameters; A distance error calculation module, used to determine the position information of the crash target according to the running trajectory, and calculate the drift trajectory distance error, drift trajectory angle error and drift trajectory average distance error of the crash target based on the position information; An optimal parameter determination module, used to determine the optimal parameters of the crash target object based on the drift trajectory distance error, the drift trajectory angle error and the drift trajectory average distance error; A drift prediction module, used for predicting the drift of the crashed target object based on the optimal parameters; The running trajectory determination module specifically includes: A wind pressure speed calculation unit, used to calculate the wind pressure speed according to a preset number of target model parameters; A latitude and longitude position calculation unit, used to calculate the latitude and longitude position of the crash target at the next moment according to the wind pressure speed; A running track determination unit, used for obtaining the connection line of the average positions of multiple particles at each moment after the calculation is completed, and determining the running track of the crashed target object; The wind pressure velocity vector includes a downwind component and a component perpendicular to the wind direction; the component perpendicular to the wind direction includes a right lateral component and a left lateral component; The wind pressure velocity calculation unit is used for: Using the formula: The downwind component, the left lateral component and the right lateral component are calculated; Among them, L d , L cr , L cl are the downwind component, right-lateral component and left-lateral component of the wind pressure velocity, respectively. The subscripts d, cr and cl represent the downwind direction, right-lateral wind direction and left-lateral wind direction, respectively. speed represents the wind speed at 10 meters, a is the slope, b is the intercept, ξ is a random number, and ξ obeys a normal distribution with a mean of 0 and a mean square error of 1; C is the residual difference of the linear regression equation; ε is a disturbance term that satisfies a uniform distribution; The latitude and longitude position calculation unit is specifically used for: After determining the wind pressure velocity, the formula is used: Calculating the latitude and longitude position of the crashed object at the next moment based on the position at the previous moment; in, represents the latitude of the kth particle at the n+1th moment, represents the longitude of the kth particle at the n+1th moment; represents the latitude of the kth particle at the nth moment, represents the longitude of the kth particle at the nth moment; represents the component of the wind-induced displacement of the kth particle at the nth moment in the y direction, represents the component of the wind-induced displacement of the kth particle at the nth moment in the x direction; represents the component of the velocity of the kth particle at the nth moment in the y direction, represents the x-direction component of the velocity of the kth particle at the nth moment; dt represents the time interval of calculation; r y 、r x All are random disturbance terms; rad represents the radius of the earth; PI represents pi.

6. A marine target forecasting device, characterized in that the device include: A memory, a processor, and a communication interface coupled to the processor; The memory stores a computer program executable by the processor; When the processor runs the computer program, it executes the marine target forecasting method according to any one of claims 1 to 4.

7. A computer storage medium, characterized in that: The computer storage medium stores instructions, and when the instructions are executed, the method for forecasting marine targets according to any one of claims 1 to 4 is implemented.

Images