Corpse drift trajectory prediction method, system and device and medium

Abstract

The invention discloses a corpse drift trajectory prediction method, system and device and a medium. The method comprises the steps of performing a dummy drift field test in a tidal river reach, obtaining position information and drift speed in a dummy drift process, and obtaining a test track of dummy drift based on the position information; collecting river topographic data of the tidal reach, and obtaining water level and flow data of upstream and downstream boundaries of the tidal reach; a hydrodynamic model of the tidal reach is constructed, and the flow field condition of the tidal reach is obtained; and establishing a regression model of the drift velocity of the dummy in the tidal reach by taking the surface flow in the flow field of the tidal reach as an independent variable and the drift velocity of the dummy as a dependent variable, so as to obtain a drift trajectory prediction model for predicting the drift trajectory of the corpse on the tidal reach. According to the invention, the drifting trajectory of the corpse in the river channel can be accurately predicted, a water alarm is helped to quickly and accurately determine the position of the corpse of a drowning person, and convenience is provided for corpse fishing work.

Description

Technical Field

[0001] The present invention relates to the field of water target trajectory prediction, and in particular to a method, system, device and medium for predicting the drifting trajectory of a corpse. Background Art

[0002] The migration process of the body from entering the river to being salvaged after drifting can be divided into four stages: sinking to the river bottom, migrating along the river bottom, floating to the surface, and drifting along the surface. In each migration stage, different forces jointly affect the body, resulting in different migration paths of the body, thus affecting the final position of the body after migration. The drift of the body is affected by many factors, among which environmental factors have a decisive influence on the drift trajectory of the body.

[0003] Traditional trajectory prediction of water targets is mainly concentrated in the marine environment, and the environmental factors that affect the drift of objects are mainly total ocean currents, sea surface winds, waves and Coriolis forces. The total ocean currents include ocean currents, tides, local wind-driven currents, and rivers. In the river environment, the environmental factors of object drift mainly involve rivers and river surface winds. In terms of corpse positioning and search, the accuracy of trajectory prediction in the river environment is required to be high. It is worth noting that tidal rivers are different from traditional inland rivers. Their flow is affected by the periodicity of tides, resulting in a round-trip periodic motion. Therefore, in terms of object drift trajectory prediction, corpse trajectory prediction in tidal river sections has more complex and specific requirements.

[0004] On the other hand, the accuracy of drift trajectory prediction of water objects lies in accurately obtaining the water flow velocity. Currently, numerical models are mainly used to simulate the hydrodynamic processes of oceans and rivers. Therefore, choosing a suitable numerical model to simulate the hydrodynamic processes of tidal river sections is the key to the drift trajectory prediction model.

[0005] Cheng Liang et al. disclosed in Chinese invention patent CN112115598A a "data and model coupling analysis method for marine drift trajectory prediction". This method uses field experiments to collect marine environmental data sets, and uses physical models to predict drift trajectories, evaluates the prediction accuracy, and finally selects the optimal environmental data set and drift trajectory physical model. However, it has the following shortcomings: (1) The data of this method is completely collected through field experiments, and the constructed ocean flow field data is not real-time. Although ocean currents may have certain rules, the lack of real-time data will also cause large errors. (2) This method is carried out for the marine environment, and other existing literature has relatively little research on inland rivers, especially special river sections such as tidal river sections. The water level of tidal river sections will rise and fall periodically with the tide, and the direction of the water flow will also change periodically, which makes prediction very difficult. Summary of the invention

[0006] In order to solve at least one of the problems existing in the prior art, the present invention provides a regression model that can be used to predict the drift trajectory of corpses in a river section to be predicted, such as a tidal river section, to solve the problem that corpses in the river channel repeatedly move under the influence of tides and runoff after floating up and are difficult to accurately locate, thereby providing means for the public security organs to handle cases, narrow the search range of corpses and reduce costs. The present invention focuses on the fourth stage of the movement of objects on the water, namely the drift stage.

[0007] To achieve the purpose of the present invention, the present invention provides a method for predicting the drift trajectory of a corpse, comprising the following steps:

[0008] Conduct a field test of dummy drift in a tidal river section to obtain the position information and drift speed of the dummy during drift, and obtain the test trajectory of the dummy drift based on the position information of the dummy during drift;

[0009] Collect river channel topography data of tidal river sections, and obtain water level and flow data at the upstream and downstream boundaries of tidal river sections;

[0010] The hydrodynamic model of the tidal river section is constructed using hydrodynamic numerical software and river topography data, and the flow field of the tidal river section is obtained using the water level and flow data at the upstream and downstream boundaries of the river;

[0011] Taking the surface current in the flow field of tidal river sections as the independent variable and the drift speed of the dummy as the dependent variable, a regression model of the drift speed of the dummy in tidal river sections was established to obtain a drift trajectory prediction model for predicting the drift trajectory of the corpse in tidal river sections.

[0012] Furthermore, after establishing the regression model of the drift speed of the dummy in the tidal river section, the following steps are also included:

[0013] Based on the regression model, the dummy drift trajectory during the test is used for simulation. The simulation process is based on the initial position and start time of the test. The hydrodynamic model is used to iteratively calculate the drift distance at preset time intervals until the simulated drift trajectory ends and the terminal position of the dummy is obtained.

[0014] The simulation results are compared with the actual results. When the results meet the preset conditions, the obtained regression model is determined to be a dummy drift trajectory prediction model, which is used to predict the drift trajectory of the corpse in the tidal river section.

[0015] Furthermore, flow meters and water level meters installed upstream and downstream of the tidal river section are used to obtain water level and flow data at the upstream and downstream boundaries of the river.

[0016] Furthermore, the hydrodynamic module in the hydrodynamic numerical software was used to simulate the hydrodynamics of the tidal river section. The upstream boundary condition was the flow data of the time series during the experiment, and the downstream boundary condition was the water level data of the corresponding time series.

[0017] Furthermore, the tidal river section may be replaced by a non-tidal river section.

[0018] Furthermore, the method can be used to predict the drift trajectory of other water objects.

[0019] Furthermore, the above-water objects are not limited to floating garbage.

[0020] The present invention provides a corpse drift trajectory prediction system, which is used to implement the above method. The system includes the following modules:

[0021] The test data acquisition module is used to obtain the position information and drift speed of the dummy during the drift process when conducting field experiments in the river section, and obtain the test trajectory of the dummy drift based on the position information of the dummy during the drift process;

[0022] The river section data acquisition module is used to collect the river channel topography data of the tidal river section, and obtain the water level and flow data of the upstream and downstream boundaries of the tidal river section;

[0023] The hydrodynamic model building module is used to build a hydrodynamic model of a tidal river section using hydrodynamic numerical software and river topography data, and to obtain the flow field conditions of the tidal river section using the water level and flow data at the upstream and downstream boundaries of the river;

[0024] The prediction module constructs a module for establishing a regression model of the drift speed of the dummy in the tidal river section, taking the surface flow in the flow field of the tidal river section as the independent variable and the drift speed of the dummy as the dependent variable, so as to obtain a drift trajectory prediction model for predicting the drift trajectory of the corpse in the tidal river section.

[0025] The present invention also provides a computer device, comprising a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the aforementioned method.

[0026] The present invention also provides a computer-readable storage medium on which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, the steps of the aforementioned method are implemented.

[0027] Compared with the prior art, the beneficial effects of the present invention are:

[0028] (1) Currently, there is no relatively mature method for predicting the movement of corpses at home and abroad, which can be used to assist the police in handling drowning cases in tidal river sections. The present invention provides a drift trajectory prediction method in tidal river sections (also applicable to non-tidal river sections), which can provide a technical reference for relevant public security organs to solve cases. This method can control the search and salvage range within 1km, thereby effectively helping the police to quickly lock the specific location of the drowned person and carry out corresponding salvage or tracing work. By applying this prediction method, the police can reduce the pressure faced in the process of solving cases, while reducing the cost and time of solving cases, thereby improving the efficiency of solving cases.

[0029] (2) The present invention can collect river boundary condition data in real time by establishing a measuring station. The constructed flow field data has strong real-time performance and the predicted trajectory will be more accurate.

[0030] (3) The present invention can achieve accurate prediction of the drift of aquatic objects such as corpses in tidal river sections (or other river sections) by performing detailed and real-time simulation of the flow field. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a flow chart of the steps of a method for predicting the movement of an aquatic object provided by an embodiment of the present invention.

[0032] Figure 2 This is a map of the Pearl River front channel test area.

[0033] Figure 3 This is a schematic diagram of the dummy drift test.

[0034] Figure 4 This is the grid division map of the Pearl River front channel.

[0035] Figure 5 This is the trajectory diagram of the dummy drift test.

[0036] Figure 6 This is a schematic diagram of the effect of water flow velocity on the drift speed of the dummy.

[0037] Figure 7 This is a comparison chart between the measured trajectory and the predicted trajectory. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] The present invention provides a method for predicting the drift trajectory of a corpse, comprising the following steps:

[0040] Step 1: Conduct multiple dummy drift field tests to obtain the position information and drift speed of the dummy during drift, and obtain the test trajectory of the dummy drift based on the position information of the dummy during drift.

[0041] In some embodiments of the present invention, the dummy used in the field test described in this step can be made of plastic barrels of different specifications and shapes, and the plastic barrels are filled with fresh water. The dummy model is made so that its height and weight meet actual requirements. The density, structure and underwater posture of the dummy are ensured to be similar to those of a real corpse, and a GPS recorder is provided to record the drift trajectory of the dummy at preset time intervals (such as 10 seconds).

[0042] In some embodiments of the present invention, the position information of the dummy during the drift process obtained by the test in this step excludes the position information of the dummy with abnormal positioning, and selects the drift process segment with high continuity to obtain the longest possible drift time period. Then, the selected drift trajectory is processed to obtain the drift velocity components in the east-west direction and the north-south direction with a time interval of a preset time (such as 10s).

[0043] Step 2: Collect river topography data of tidal river sections, and use flow meters and water level gauges installed upstream and downstream of the river to obtain water level and flow data at the upstream and downstream boundaries of the river.

[0044] Step 3: Use hydrodynamic numerical software and river topography data to construct a hydrodynamic model of the tidal river section, and use the water level and flow data of the upstream and downstream boundaries of the river to drive and obtain the flow field conditions of the tidal river section.

[0045] In some embodiments of the present invention, the hydrodynamics of a tidal river section is simulated using a hydrodynamic module in a hydrodynamic numerical software, the upstream boundary condition of the tidal river section is the time series flow data during the test, and the downstream boundary condition is the water level data of the corresponding time series.

[0046] In some embodiments of the present invention, the hydrodynamic numerical software simulates the change of the water flow field within the research scope by solving the continuity equation and the momentum equation, as follows:

[0047] Continuity equation:

[0048]

[0049] Where, d is the water depth, m; t is the time, s; η and ξ represent two orthogonal curve coordinates in the horizontal direction; σ is the vertical coordinate; Q represents the source and sink terms of water per unit area caused by rainfall, evaporation, etc., m / s; U represents the average flow velocity of the water depth in the ξ direction, m / s; V represents the average flow velocity of the water depth in the η direction; ζ represents the water level, m; Respectively represent the coordinate transformation coefficients in the ξ and η directions, m.

[0050] The momentum equation in the ξ direction is:

[0051]

[0052] The momentum equation in the η direction is:

[0053]

[0054] Where f represents the Coriolis force, 1 / s; u, v, and w represent the velocity components in the x, y, and z directions in the orthogonal curvilinear coordinate system, m / s; ρ0 represents the water density, kg / m 3 ;P η and P ξ Represents the pressure gradient in the η and ξ directions, kg / m 2 s;M ξ and M η represents the momentum components of the source and sink terms in the η and ξ directions, m / s 2 ;υ v Indicates the vertical viscosity coefficient, m / s 2 ; F ξ and F η Represents the horizontal Reynolds stress in the η and ξ directions, m / s 2 .

[0055] Step 4: Use the surface flow in the tidal river obtained in step 3 as the independent variable, and the dummy drift speed obtained in step 1 as the dependent variable to establish a regression model of the dummy drift speed.

[0056] In this step, the drift velocity of the dummy in step (1) and the surface velocity in the tidal river flow field obtained in step (3) are split into two components in the east and north directions, and are respectively brought into the fitting formula for fitting.

[0057] In this step, the interference of factors such as wind and ships on the regression model of the drift speed of the tidal river section dummy is considered and regarded as a constant for fitting. The fitting formula is as follows:

[0058] U 假人 =aU 水流 +b#(2)

[0059] Where: U 假人is the drift speed of the dummy, m / s; U 水流 is the surface water velocity, m / s; a is the influence coefficient of surface water flow on drift; b is the comprehensive influence coefficient of environment such as wind, waves, ships, etc. on the drift of the dummy.

[0060] The specific values ​​of a and b are determined by formula fitting method using the drift speed and water flow velocity data recorded in the dummy drift field experiment.

[0061] Step 5: Use the experimental trajectory of the drifting dummy to verify the validity of the regression model obtained in step 4, and finally confirm it as the dummy drift trajectory prediction model for tidal river sections, which is used to predict the drift trajectory of corpses in tidal river sections.

[0062] In some embodiments of the present invention, the model is verified using the water level data of the corresponding time series of the hydrological station in the middle reaches of the tidal river. During the verification process, indicators such as Nash efficiency coefficient (NSE), mean absolute error (MAE) and root mean square error (RMSE) are used to ensure that the constructed regression model has high accuracy and credibility, and can better simulate the hydrodynamic process of the tidal river section for the prediction of the drift trajectory of the dummy.

[0063] The dummy drift trajectory during the above regression model test is used for simulation. The simulation process is based on the initial position and start time of the test, and the hydrodynamic model is used to iteratively calculate the drift distance every preset time (such as 10 seconds) until the simulated drift trajectory ends and the terminal position of the dummy is obtained. The simulation results are compared with the actual results to ensure that the error of the simulated results is less than the preset value (such as 20%) and the terminal offset distance does not exceed the preset offset distance (such as 1km). After meeting these preset conditions, the regression model is determined to be the dummy drift trajectory prediction model for the tidal river section. If the conditions are not met, the flow field data can only be re-run and the field experiment can be re-run to ensure the accuracy of the data.

[0064] In some embodiments of the present invention, the method of the present invention is universal and is not limited to predicting the drift trajectory of a dummy. The dummy can be replaced by other aquatic objects, such as corpses, floating garbage, and people. That is, in addition to predicting the drift trajectory of a dummy in a tidal river section, the method of the present invention can also be used to predict the drift trajectory of other aquatic objects such as corpses and floating garbage in a tidal river section. It is just that the size and mass of the floating object will have different drift performances, and the parameter size of the regression model will be different, that is, the values ​​of the influence coefficients a and b may be different.

[0065] In some embodiments of the present invention, in addition to being used to predict the drift trajectory of aquatic objects in a tidal river section, it can also be used to predict the drift trajectory of aquatic objects in other non-tidal river sections, by replacing the river channel topography data and the water level and flow data of the upstream and downstream boundaries collected in the aforementioned steps of the tidal river section with the topography data, water level and flow data collected from other corresponding river sections, and replacing the independent variable with the surface flow in the flow field of other corresponding river sections.

[0066] In some embodiments of the present invention, the effectiveness of the method of the present invention is verified by a specific example.

[0067] See also Figure 1 Taking the tidal river section of the Pearl River front channel as an example, this channel is located in the main river landscape area of ​​Guangzhou City, such as Figure 2 , located in a busy area with a large flow of people, drowning incidents occasionally occur. Such incidents usually require the local police to respond quickly. To solve this problem, the technical solution proposed in the present invention is used to construct a dummy drift trajectory prediction model for the Pearl River front channel to assist the police in the corresponding salvage or tracing work. Specifically, the following steps are included:

[0068] (1) Five dummy drift field tests were conducted in the Pearl River front channel. The specific location of the test area is as follows: Figure 2 A dummy model was made using plastic barrels of different sizes and shapes, and fresh water was poured into it to make it 165 cm tall and 55 kg heavy (as shown in Figure 1). Figure 3 The density, structure and horizontal posture of the dummy in the water are similar to those of a real corpse. It is equipped with a GPS track recorder and a GPS locator. The GPS track recorder records the longitude and latitude coordinates of the dummy every 10 seconds, and the GPS locator monitors the area where the dummy is located in real time to deal with unexpected situations such as the dummy getting stuck or lost. After the test, the data was screened to obtain the longest possible drift time period. Finally, 5 drift process segments were selected. The start and end times and starting positions are shown in Table 1. The trajectories are shown in Figure 5 Subsequently, the filtered drift trajectories were processed to obtain the drift velocity components in the east-west and north-south directions at 10-second intervals.

[0069] Table 1 Drift test information statistics (2022)

[0070]

[0071] (2) The RGFGRID module in Delft3D numerical software is used to divide the grid of the Pearl River front channel, such as Figure 4As shown, the divided grid is an orthogonal curve grid, and the cosine value of the grid angle is ensured to be less than 0.02. The direction of its upstream boundary is consistent with that of Renmin Bridge, and the direction of its downstream boundary is the same as that of Dongpu Bridge. The length of the waterway is about 15km, and the width ranges from 160m to 520m. The size of a single grid generated is 5 to 33m, and the total number of valid grids is 31,860. After the grid is generated, the terrain scatter data file is imported through the QUINKIN module, and the terrain data of the grid area is processed by triangulation interpolation and internal diffusion. The data generated in this way is the terrain value corresponding to the grid in the test area.

[0072] (3) After completing the production of the grid file and terrain file of the Pearl River front channel, the hydrodynamic module in the Delft3D numerical software was used to simulate the hydrodynamics of the Pearl River front channel. The direction of the upstream boundary is consistent with that of the Renmin Bridge, and the water level time series data of the Guangzhou station from June 1 to July 31, 2022 is used as the boundary condition. The downstream boundary has the same direction as the Dongpu Bridge, and the water level time series data of the Huangpu station from June 1 to July 31, 2022 is used as the boundary condition. In the selection of the turbulence model, the k-ε turbulence model was adopted, and the time step was determined to be 3s through the model stability test. Through multiple calibrations, the roughness values ​​in the horizontal and vertical directions were determined to be 0.025.

[0073] (4) The model was verified using the water level time series data provided by the Zhongda station in the Pearl River front channel. The Nash efficiency coefficient (NSE), mean absolute error (MAE) and root mean square error (RMSE) obtained by calculation were 0.94, 0.14m and 0.14 respectively, indicating that the constructed numerical model has high accuracy and credibility, can better simulate the hydrodynamic process of the Pearl River front channel, and can be used for the dummy drift trajectory prediction model. Subsequently, the flow field data of the Pearl River front channel hydrodynamic model during the test period were derived and processed to obtain the east and north water velocity components at the same time and position as the dummy trajectory.

[0074] (5) Using the 8333 sets of dummy drift speed and water flow speed data obtained in the same time period and position in steps (1) and (2), the correlation between the dummy drift speed and water flow speed was analyzed by statistical analysis. The specific results are shown in Figure 6 , and finally determined the fitting formula for the drift speed of the dummy in the front channel of the Pearl River, as shown below:

[0075] U 假人 =0.929U 水流 +0.132#(2)

[0076] Where U 假人 Indicates the drift speed of the dummy, U 水流 Indicates water flow speed.

[0077] The statistic F of regression equation (2) is 56918.53, and the corresponding significance level p = 0 < 0.05. This shows that the regression equation is statistically significant. At the same time, the coefficient of determination R 2 It is 0.88, indicating that the equation has good correlation.

[0078] (6) In order to verify the validity of the above regression model fitting formula, the regression equation (2) was used to simulate the trajectory of 5 tests. During the simulation, the flow field was decomposed into two components of the drift velocity in the east and north directions. Based on the initial position and start time of the test, the drift distance was iteratively calculated every 10 seconds until the simulated drift trajectory ended and the terminal position of the dummy was obtained. Among them, the simulated drift trajectory is U 假人 =0.929U 水流 +0.132, R 2 =0.88.

[0079] The end point offset distance and end point distance error rate of the five test trajectories simulated by the regression model are shown in Table 2. Figure 7 As shown in Table 2, in the five test simulations, JR1 has the largest total drift distance and the largest end point offset distance, while JR2 has the largest end point distance error rate. The end point offset distances of the five test simulations are all less than 1 km, and the end point distance error rates are all less than 15%. Judging from the end point error, the simulation effect is relatively accurate. This further verifies the feasibility of the regression model as a dummy drift trajectory prediction model for the tidal river section of the Pearl River front channel.

[0080] Table 2. Error statistics of regression model

[0081]

[0082] The prediction method provided in the aforementioned embodiment of the present invention comprehensively utilizes advanced numerical simulation technology and experimental data, and can accurately predict the drift trajectory of floating objects such as corpses in the predicted river section, and can help local water police quickly and accurately determine the location of the bodies of drowned people, thereby providing convenience and reference for body salvage work and police case handling.

[0083] In some embodiments of the present invention, a corpse drift trajectory prediction system is also provided, which is used to implement the method provided in the above embodiments. The system includes the following modules:

[0084] A test data acquisition module is used to obtain the position information and drift speed of the dummy during the drift process, and obtain the test trajectory of the dummy drift based on the position information of the dummy during the drift process;

[0085] The river section data acquisition module is used to collect the river channel topography data of the tidal river section, and obtain the water level and flow data of the upstream and downstream boundaries of the tidal river section;

[0086] The hydrodynamic model building module is used to build a hydrodynamic model of a tidal river section using hydrodynamic numerical software and river topography data, and to obtain the flow field conditions of the tidal river section using the water level and flow data at the upstream and downstream boundaries of the river;

[0087] The prediction module constructs a module for establishing a regression model of the drift speed of the dummy in the tidal river section, taking the surface flow in the flow field of the tidal river section as the independent variable and the drift speed of the dummy as the dependent variable, so as to obtain a drift trajectory prediction model for predicting the drift trajectory of the corpse in the tidal river section.

[0088] In some embodiments of the present invention, a computer device is further provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the method described in the aforementioned embodiment.

[0089] In some embodiments of the present invention, a computer-readable storage medium is provided on which a computer program or instruction is stored, wherein the computer program or instruction implements the steps of the method described in the aforementioned embodiment when executed by a processor.

[0090] As for a system, device and medium for predicting the drift trajectory of a corpse, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0091] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for predicting the drift trajectory of a corpse, characterized in that: The steps include: Conduct a field test of dummy drift in a tidal river section to obtain the position information and drift speed of the dummy during drift, and obtain the test trajectory of the dummy drift based on the position information of the dummy during drift; Collect river channel topography data of tidal river sections, and obtain water level and flow data at the upstream and downstream boundaries of tidal river sections; The hydrodynamic model of the tidal river section is constructed using hydrodynamic numerical software and river topography data, and the flow field of the tidal river section is obtained using the water level and flow data at the upstream and downstream boundaries of the river; Taking the surface current in the flow field of tidal river sections as the independent variable and the drift speed of the dummy as the dependent variable, a regression model of the drift speed of the dummy in tidal river sections was established to obtain a drift trajectory prediction model for predicting the drift trajectory of the corpse in tidal river sections.

2. A method for predicting the drift trajectory of a corpse according to claim 1, characterized in that: After establishing the regression model of the drift velocity of the dummy in the tidal river section, the following steps are also included: Based on the regression model, the dummy drift trajectory during the test is used for simulation. The simulation process is based on the initial position and start time of the test. The hydrodynamic model is used to iteratively calculate the drift distance at preset time intervals until the simulated drift trajectory ends and the terminal position of the dummy is obtained. The simulation results are compared with the actual results. When the results meet the preset conditions, the obtained regression model is determined to be a dummy drift trajectory prediction model, which is used to predict the drift trajectory of the corpse in the tidal river section.

3. The method for predicting the drift trajectory of a corpse according to claim 1, characterized in that: The water level and flow data at the upstream and downstream boundaries of the river are obtained using flow meters and water level gauges installed upstream and downstream of the tidal river section.

4. A method for predicting the drift trajectory of a corpse according to claim 1, characterized in that: The hydrodynamic module in the hydrodynamic numerical software was used to simulate the hydrodynamics of the tidal river section. The upstream boundary condition was the flow data of the time series during the experiment, and the downstream boundary condition was the water level data of the corresponding time series.

5. The method for predicting the drift trajectory of a corpse according to claim 1, characterized in that: The tidal river section may be replaced by a non-tidal river section.

6. A method for predicting the drift trajectory of a corpse according to claim 1, characterized in that: The method can be used to predict the drift trajectory of other water objects.

7. A method for predicting the drift trajectory of a corpse according to claims 1-6, characterized in that: The regression model is U 假人 =aU 水流 +b Where U 假人 is the drift speed of the dummy; U 水流 is the surface water velocity; a is the influence coefficient of surface water on drift; b is the comprehensive influence coefficient of the environment on the drift of the dummy.

8. A corpse drift trajectory prediction system, characterized in that: For implementing the method described in any one of claims 1 to 7, the system comprises the following modules: The test data acquisition module is used to obtain the position information and drift speed of the dummy during the drift process when conducting field experiments in the river section, and obtain the test trajectory of the dummy drift based on the position information of the dummy during the drift process; The river section data acquisition module is used to collect the river channel topography data of the tidal river section, and obtain the water level and flow data of the upstream and downstream boundaries of the tidal river section; The hydrodynamic model building module is used to build a hydrodynamic model of a tidal river section using hydrodynamic numerical software and river topography data, and to obtain the flow field conditions of the tidal river section using the water level and flow data at the upstream and downstream boundaries of the river; The prediction module constructs a module for establishing a regression model of the drift speed of the dummy in the tidal river section, taking the surface flow in the flow field of the tidal river section as the independent variable and the drift speed of the dummy as the dependent variable, so as to obtain a drift trajectory prediction model for predicting the drift trajectory of the corpse in the tidal river section.

9. A computer device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of any one of claims 1-7.

10. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: When the computer program or instruction is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images