Fishing boat dynamic drift prediction method and system based on distress analysis of south china sea waters

Abstract

This invention relates to the field of fishing vessel navigation and positioning technology, particularly a method and system for predicting the dynamic drift of fishing vessels based on distress analysis in the South China Sea. The invention constructs a dynamic drift prediction model for the target fishing vessel and a future meteorological environment simulation field for the South China Sea region. A first future meteorological environment sub-simulation field, representing the target fishing vessel's current static distress environment area, is extracted from the future meteorological environment simulation field and dynamically predicted within the dynamic drift prediction model to obtain an initial dynamic drift trajectory. A second static distress environment area, formed by the current dynamic drift of the target fishing vessel, is planned based on the initial dynamic drift trajectory to analyze the vector disturbance index of the meteorological environment. The second future meteorological environment sub-simulation field is adjusted according to the vector disturbance index and dynamically predicted again to obtain the final dynamic drift trajectory. This invention can accurately predict the route and coordinates of fishing vessels dynamically drifting due to meteorological influences when they encounter distress in the South China Sea, thereby improving search and rescue efficiency and accuracy.

Description

Technical Field

[0001] This invention relates to the field of navigation and positioning technology for fishing vessels in distress, and in particular to a method and system for predicting the dynamic drift of fishing vessels based on distress analysis in the South China Sea. Background Technology

[0002] The South China Sea, generally referring to the waters south of China, is an important maritime region for the country. While its geographical location is crucial, the vast area, complex marine conditions, and frequent maritime traffic mean that fishing vessels are frequently affected by extreme weather events such as typhoons, storms, and strong currents. This often leads to vessel malfunctions, loss of control, capsizing, or sinking, increasing the risk of casualties. The complex weather conditions cause fishing vessels to drift dynamically, necessitating accurate tracking of their drift trajectories for timely rescue. However, traditional methods for predicting the dynamic drift of fishing vessels generally only work in stable weather conditions. They are poor at analyzing constantly changing weather data, resulting in significant errors in the predicted drift. Furthermore, traditional methods struggle to consider the geological and topographical distribution of the South China Sea to further analyze the impact on fishing vessel distress, reducing the accuracy of drift predictions, lowering the quality of rescue plans, and ultimately reducing the efficiency of rescue operations for distressed fishing vessels. Summary of the Invention

[0003] This invention overcomes the shortcomings of the prior art and provides a method and system for predicting the dynamic drift of fishing vessels based on distress analysis in the South China Sea.

[0004] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0005] The first aspect of this invention provides a method for predicting the dynamic drift of fishing vessels based on distress analysis in the South China Sea, comprising the following steps:

[0006] A historical dynamic drift model of the target fishing vessel when it is in distress in the South China Sea is constructed, and the drift vector of the target fishing vessel is analyzed on a multi-dimensional geographic coordinate map based on the historical dynamic drift model to obtain the historical drift vector set of the target fishing vessel in each sub-dynamic drift region.

[0007] Several historical meteorological and environmental data of the target fishing vessel are obtained. The FCM algorithm is introduced to cluster the several historical meteorological and environmental data into a historical drift vector set to generate fuzzy clustering results. Based on the fuzzy clustering results, the state transition model in the historical dynamic drift model is adjusted to obtain the dynamic drift prediction model of the target fishing vessel.

[0008] A future meteorological environment simulation field is constructed for the South China Sea area. Based on the current distress coordinates of the target fishing vessel, a first dynamic distress environment area is planned. A first future meteorological environment sub-simulation field is extracted from the future meteorological environment simulation field and dynamic prediction is performed in the dynamic drift prediction model based on the first future meteorological environment sub-simulation field to obtain the initial dynamic drift trajectory.

[0009] The initial dynamic drift trajectory is used to plan the second dynamic distress environment area formed by the dynamic drift of the current target fishing vessel. The vector disturbance index of the meteorological environment is analyzed by the geological and topographic feature vector distribution map of the second dynamic distress environment area. The second future meteorological environment sub-simulation field is adjusted according to the vector disturbance index and dynamically predicted again to obtain the final dynamic drift trajectory and the corresponding coordinate values.

[0010] The process of planning the second dynamic distress environment area formed by the dynamic drift of the current target fishing vessel through the initial dynamic drift trajectory, analyzing the vector disturbance index of the meteorological environment through the geological and topographic feature vector distribution map of the second dynamic distress environment area, adjusting the second future meteorological environment sub-simulation field according to the vector disturbance index and re-dynamically predicting to obtain the final dynamic drift trajectory and corresponding coordinate values, specifically includes the following steps:

[0011] Based on the multidimensional geographic coordinate map, the static distress environment range of the current target fishing vessel is re-planned, and the area formed after traveling according to the initial dynamic drift trajectory is obtained to obtain the second dynamic distress environment area.

[0012] The geographic coordinate parameters of the second dynamic distress environment area are extracted by a multi-dimensional geographic coordinate map, and the geographic coordinate parameters are transmitted to the GPS satellite positioning system.

[0013] The second dynamic distress environment area is remotely located and photographed using a GPS satellite positioning system to obtain satellite terrain image data of the second dynamic distress environment area. An edge detection algorithm is then introduced to analyze and extract the satellite terrain image data to obtain the geological and terrain feature vector of the second dynamic distress environment area.

[0014] Based on geographic coordinate parameters, all geological and topographic feature vectors are marked in a multidimensional geographic coordinate map to generate a distribution map of geological and topographic feature vectors of the second dynamic distress environment area. At the same time, a geographic geomorphological knowledge graph of the South China Sea is obtained based on a big data network.

[0015] The geological and topographic feature vector distribution map and the future meteorological environment simulation field are simultaneously imported into the geographical and geomorphological knowledge graph of the South China Sea for identification, so as to obtain the vector disturbance index of the geological and topographic distribution of the second dynamic distress environment area on the future meteorological environment.

[0016] The future meteorological environment sub-simulation field in which the current target fishing vessel is located in the second dynamic distress environment area is extracted from the future meteorological environment simulation field and defined as the second future meteorological environment sub-simulation field. The meteorological environment vector of the second future meteorological environment sub-simulation field is adjusted and updated according to the vector disturbance index to obtain the adjusted and updated second future meteorological environment sub-simulation field.

[0017] The dynamic drift prediction model is used to re-analyze the adjusted and updated second future meteorological environment sub-field to obtain the final dynamic drift trajectory and coordinate values ​​of the target fishing vessel. The final dynamic drift trajectory and coordinate values ​​are then uploaded to the target fishing vessel's distress terminal.

[0018] Furthermore, in a preferred embodiment of the present invention, the step of constructing a historical dynamic drift model of the target fishing vessel when it encounters distress in the South China Sea, and analyzing the drift vector of the target fishing vessel on a multi-dimensional geographic coordinate map based on the historical dynamic drift model to obtain the historical drift vector set of the target fishing vessel in each sub-dynamic drift region, specifically includes the following steps:

[0019] Obtain the navigation log of the target fishing vessel in the South China Sea area, and extract several historical predetermined route coordinates and several actual navigation route coordinates of the target fishing vessel in the time sequence of the distress from the navigation log.

[0020] A particle filter algorithm is introduced. Based on several historical predetermined route coordinates and several actual driving route coordinates, a state transition model and an observation model of the target fishing vessel drift are constructed in the particle filter algorithm. A set of particles are initialized according to the state transition model and the observation model.

[0021] The weight of each particle is updated based on the coordinate deviation between the historical predetermined route coordinates and the actual driving route coordinates and the observation model. New particles are then resampled using the new weights. The above steps are repeated to recursively update the weights and states of the particles until all particles are updated, thereby generating the historical dynamic drift model of the target fishing vessel.

[0022] A multidimensional geographic coordinate map of the South China Sea area is obtained. A multidimensional spatial coordinate domain is constructed based on the multidimensional geographic coordinate map. Based on the historical dynamic drift model, the historical planned route and the actual driving route are dynamically fitted in the multidimensional spatial coordinate domain to extract the dynamic drift area formed between the historical planned route and the actual driving route.

[0023] The predetermined sailing time of the target fishing vessel is obtained through the navigation log. Based on the predetermined sailing time, the dynamic drift area is divided into N sub-dynamic drift areas. All drift coordinates and the distribution pattern of each drift coordinate are obtained in each sub-dynamic drift area.

[0024] By analyzing the changes and distribution patterns of the drift coordinates, the drift changes of the target fishing vessel in the dynamic drift region are obtained, and the historical drift vector set of the target fishing vessel in each sub-dynamic drift region is obtained.

[0025] Furthermore, in a preferred embodiment of the present invention, the steps of acquiring several historical meteorological environmental data of the target fishing vessel, introducing the FCM algorithm to cluster the several historical meteorological environmental data into a historical drift vector set, generating fuzzy clustering results, and adjusting the state transition model in the historical dynamic drift model based on the fuzzy clustering results to obtain the dynamic drift prediction model of the target fishing vessel specifically include the following steps:

[0026] The navigation log is used to obtain several historical meteorological and environmental data corresponding to the target fishing vessel's navigation in each sub-drift area, and the predetermined navigation time is divided into several navigation time sequence nodes.

[0027] The multidimensional specifications of the target fishing vessel are obtained, and the physical action vectors of the multidimensional specifications under different combinations of meteorological environmental conditions are obtained based on big data networks; wherein, the multidimensional specifications include the volume, weight, height and load capacity of the target fishing vessel.

[0028] Based on the historical drift vector set, the historical drift vector corresponding to each navigation timeline node is extracted. The FCM algorithm is introduced to construct the fuzzy membership matrix between each historical drift vector and different physical action vectors. Multiple clusters are set according to several historical meteorological and environmental data.

[0029] A convergence threshold is preset, the cluster center of each cluster is calculated based on the fuzzy membership matrix, the fuzzy membership degree of each cluster center is obtained, and the fuzzy membership matrix is ​​iteratively updated through the fuzzy membership degree until the convergence threshold is reached, so as to obtain the fuzzy clustering result of historical meteorological and environmental data to generate historical drift vectors.

[0030] Based on the fuzzy clustering results, the state transition model of the target fishing vessel's drift in the historical dynamic drift model is adjusted to obtain the adjusted state transition model. The adjusted state transition model is then trained and validated by resampling the states and weights of new particles to obtain the dynamic drift prediction model of the target fishing vessel.

[0031] Furthermore, in a preferred embodiment of the present invention, the construction of the future meteorological environment simulation field for the South China Sea region involves planning a first dynamic distress environment area based on the current distress coordinates of the target fishing vessel, extracting a first future meteorological environment sub-simulation field from the future meteorological environment simulation field located within the first dynamic distress environment area, and performing dynamic prediction in a dynamic drift prediction model based on the first future meteorological environment sub-simulation field to obtain the initial dynamic drift trajectory. Specifically, this includes the following steps:

[0032] Acquire several meteorological forecast data for the South China Sea region in the future time period, generate sub-models of different meteorological environment types based on the several meteorological forecast data, and perform spatial and temporal coupling on each of the sub-models to construct a future meteorological environment simulation field for the South China Sea region.

[0033] Construct a 3D model of the current fishing vessel, use GPS positioning to query the distress coordinates of the current fishing vessel on the multi-dimensional geographic coordinate map, and preset distress environment planning thresholds based on the current 3D model of the fishing vessel.

[0034] The range of the distress environment where the fishing vessel is currently located is planned in the multidimensional geographic coordinate map until the distress environment planning threshold is reached, so as to obtain the static distress environment range where the fishing vessel is currently located at the distress coordinate position.

[0035] Obtain the preset ideal navigation route of the current target fishing vessel, and plan the static distress environment range of the current target fishing vessel in the multi-dimensional geographic coordinate map according to the ideal navigation route. The area formed after the vessel travels along the ideal navigation route is obtained as the first dynamic distress environment area.

[0036] In the future meteorological environment simulation field, multiple future meteorological environment sub-simulation fields in the future time series of the current target fishing vessel in the first dynamic distress environment area are extracted and defined as the first future meteorological environment sub-simulation field. The dynamic drift prediction model of the target fishing vessel is used to perform dynamic drift prediction analysis on multiple first future meteorological environment sub-simulation fields to obtain the initial dynamic drift trajectory.

[0037] Furthermore, in a preferred embodiment of the present invention, the steps of acquiring several meteorological forecast data points for a future time period in the South China Sea, generating sub-models of different meteorological environment types based on the several meteorological forecast data points, and spatially and temporally coupling each of the sub-models to construct a future meteorological environment simulation field for the South China Sea specifically include the following steps:

[0038] Several meteorological forecast data points for the South China Sea region within a future time period are obtained. These meteorological forecast data points are then analyzed and reconstructed using meteorological environment simulation software to generate sub-state models for different meteorological environment types. The meteorological environment types include the atmosphere, ocean currents, and land.

[0039] Based on the sub-state model, the meteorological environment variable equations expressed by each meteorological environment type are extracted. The finite difference algorithm is introduced to discretize each meteorological environment variable equation to generate several discretized variable equations. Based on the several discretized variable equations, the coupled spatial grid and time step of the sub-state model of each meteorological environment type are constructed.

[0040] The coupling timing sequence of each sub-state model is set according to the time step. Based on the coupling timing sequence, the coupling spatial grid of each meteorological environment type sub-state model is matched one by one. During the grid matching process, the meteorological environment variables of each sub-state model are exchanged to obtain the meteorological environment simulation field.

[0041] Based on the coupling time series, several historical meteorological environmental data are sequentially coupled and tested in the meteorological environmental simulation field to obtain the meteorological environmental test simulation field, and several meteorological environmental benchmark simulation fields are created after standard coupling of historical meteorological environmental data.

[0042] The degree of agreement between the meteorological environment test simulation field and the meteorological environment benchmark simulation field is calculated. If the degree of agreement is less than the preset degree of agreement, the spatial coupling model and coupling time sequence of each meteorological environment type are coupled and calibrated according to the degree of agreement to obtain the future meteorological environment simulation field of the South China Sea area.

[0043] A second aspect of the present invention provides a dynamic drift prediction system for fishing vessels based on distress analysis in the South China Sea. The dynamic drift prediction system includes a memory and a processor. The memory stores a program for a dynamic drift prediction method for fishing vessels based on distress analysis in the South China Sea. When the program for a dynamic drift prediction method for fishing vessels based on distress analysis in the South China Sea is executed by the processor, the steps of the dynamic drift prediction method for fishing vessels based on distress analysis in the South China Sea as described in any one of the present invention are implemented.

[0044] This invention addresses the technical deficiencies in the prior art, and its beneficial technical effects are as follows:

[0045] A historical dynamic drift model of the target fishing vessel in the South China Sea is constructed. Based on this model, the drift vector of the target vessel is analyzed on a multi-dimensional geographic coordinate map to obtain the historical drift vector set of the target fishing vessel in each sub-dynamic drift region. Several historical meteorological environmental data points of the target fishing vessel are acquired, and the FCM algorithm is introduced to cluster these data points into the historical drift vector set, generating fuzzy clustering results. Based on these results, the state transition model in the historical dynamic drift model is adjusted to obtain the dynamic drift prediction model of the target fishing vessel. Finally, a future meteorological environment simulation field for the South China Sea region is constructed, based on the current distress coordinates of the target fishing vessel. The invention establishes a first static distress environment area. A first future meteorological environment sub-simulation field is then extracted from this area using a future meteorological environment simulation field. Based on this sub-simulation field, a dynamic drift prediction model is used to obtain an initial dynamic drift trajectory. The initial dynamic drift trajectory is then used to plan a second static distress environment area formed by the current target fishing vessel's dynamic drift, and the corresponding geological and topographic feature vector distribution map is obtained. This is used to analyze the vector disturbance index of the meteorological environment. The second future meteorological environment sub-simulation field is adjusted based on the vector disturbance index, and a new dynamic prediction is performed to obtain the final dynamic drift trajectory and corresponding coordinate values. This invention can predict the route and coordinates of a fishing vessel's dynamic drift due to meteorological influences when it encounters distress in the South China Sea. This allows search and rescue personnel to accurately locate the current dynamic distress position of the fishing vessel, thereby improving search and rescue efficiency and accuracy. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other embodiments can be obtained from these drawings without creative effort.

[0047] Figure 1 A flowchart of the first method for predicting the dynamic drift of fishing vessels based on distress analysis in the South China Sea is shown.

[0048] Figure 2 A flowchart of the second method for predicting the dynamic drift of fishing vessels based on distress analysis in the South China Sea is shown.

[0049] Figure 3 The flowchart of the third method for predicting the dynamic drift of fishing vessels based on distress analysis in the South China Sea is shown.

[0050] Figure 4 A system framework diagram of a fishing vessel dynamic drift prediction system based on distress analysis in the South China Sea is shown. Detailed Implementation

[0051] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0052] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0053] The first aspect of this invention provides a method for predicting the dynamic drift of fishing vessels based on distress analysis in the South China Sea, such as... Figure 1 As shown, it includes the following steps:

[0054] S102: Construct a historical dynamic drift model of the target fishing vessel when it is in distress in the South China Sea, and analyze the drift vector of the target fishing vessel on a multi-dimensional geographic coordinate map based on the historical dynamic drift model to obtain the historical drift vector set of the target fishing vessel in each sub-dynamic drift region.

[0055] S104: Obtain several historical meteorological and environmental data of the target fishing vessel, introduce the FCM algorithm to cluster the several historical meteorological and environmental data into a historical drift vector set, generate fuzzy clustering results, adjust the state transition model in the historical dynamic drift model based on the fuzzy clustering results, and obtain the dynamic drift prediction model of the target fishing vessel.

[0056] S106: Construct a future meteorological environment simulation field for the South China Sea area, plan the first dynamic distress environment area based on the current distress coordinates of the target fishing vessel, extract the first future meteorological environment sub-simulation field in the first dynamic distress environment area through the future meteorological environment simulation field, and make dynamic predictions in the dynamic drift prediction model based on the first future meteorological environment sub-simulation field to obtain the initial dynamic drift trajectory.

[0057] S108: The second dynamic distress environment area formed by the current target fishing vessel's dynamic drift is planned through the initial dynamic drift trajectory. The vector disturbance index of the meteorological environment is analyzed through the geological and topographic feature vector distribution map of the second dynamic distress environment area. The second future meteorological environment sub-simulation field is adjusted according to the vector disturbance index and dynamically predicted again to obtain the final dynamic drift trajectory and the corresponding coordinate values.

[0058] Furthermore, in a preferred embodiment of the present invention, the step of constructing a historical dynamic drift model of the target fishing vessel when it encounters distress in the South China Sea, and analyzing the drift vector of the target fishing vessel on a multi-dimensional geographic coordinate map based on the historical dynamic drift model to obtain the historical drift vector set of the target fishing vessel in each sub-dynamic drift region, specifically includes the following steps:

[0059] Obtain the navigation log of the target fishing vessel in the South China Sea area, and extract several historical predetermined route coordinates and several actual navigation route coordinates of the target fishing vessel in the time sequence of the distress from the navigation log.

[0060] A particle filter algorithm is introduced. Based on several historical predetermined route coordinates and several actual driving route coordinates, a state transition model and an observation model of the target fishing vessel drift are constructed in the particle filter algorithm. A set of particles are initialized according to the state transition model and the observation model.

[0061] The weight of each particle is updated based on the coordinate deviation between the historical predetermined route coordinates and the actual driving route coordinates and the observation model. New particles are then resampled using the new weights. The above steps are repeated to recursively update the weights and states of the particles until all particles are updated, thereby generating the historical dynamic drift model of the target fishing vessel.

[0062] A multidimensional geographic coordinate map of the South China Sea area is obtained. A multidimensional spatial coordinate domain is constructed based on the multidimensional geographic coordinate map. Based on the historical dynamic drift model, the historical planned route and the actual driving route are dynamically fitted in the multidimensional spatial coordinate domain to extract the dynamic drift area formed between the historical planned route and the actual driving route.

[0063] The predetermined sailing time of the target fishing vessel is obtained through the navigation log. Based on the predetermined sailing time, the dynamic drift area is divided into N sub-dynamic drift areas. All drift coordinates and the distribution pattern of each drift coordinate are obtained in each sub-dynamic drift area.

[0064] By analyzing the changes and distribution patterns of the drift coordinates, the drift changes of the target fishing vessel in the dynamic drift region are obtained, and the historical drift vector set of the target fishing vessel in each sub-dynamic drift region is obtained.

[0065] It should be noted that the environment in the South China Sea is complex and changeable, greatly increasing the likelihood of fishing vessels encountering distress while operating in the South China Sea. Furthermore, the transmission-based prediction method fails to integrate historical dynamic drift data for further analysis of the dynamic drift predictions of fishing vessels in the South China Sea. This results in mismatches and low accuracy in the final dynamic drift predictions, significantly reducing the efficiency of search and rescue operations when fishing vessels encounter distress in the South China Sea. Therefore, in order to ensure accurate dynamic prediction of the drift trajectory of fishing vessels when they encounter distress, this method conducts in-depth and reliable analysis of the historical dynamic drift behavior of fishing vessels in the South China Sea. First, a particle filter algorithm is used to calculate and analyze several historical predetermined route coordinates and several actual navigation route coordinates of the target fishing vessel at the time of distress, thereby generating a dynamic drift model describing the target fishing vessel's dynamic drift at the time of distress in the historical time. Since the target fishing vessel's actual navigation route deviates from the predetermined route, a dynamic drift region is formed between the two, and the drift vector of the target fishing vessel in this dynamic drift region is not consistent over the predetermined navigation time. This is due to the different changes in the meteorological environment in the South China Sea. Therefore, the historical drift vector set generated by the target fishing vessel in the dynamic drift region due to different meteorological environmental changes can be obtained through the historical dynamic drift model. These historical drift vector sets play a crucial training and analysis role in the dynamic drift prediction based on meteorological environmental changes. Among them, the drift vector represents the drift direction, angle, and drift distance. This method can accurately analyze the dynamic drifting behavior of target fishing vessels when they encounter distress in the South China Sea based on historical data. This provides a reliable and accurate training and analysis basis for predicting the dynamic drifting of fishing vessels in distress, and greatly improves the accuracy of dynamic prediction of fishing vessel distress.

[0066] Furthermore, in a preferred embodiment of the present invention, the acquisition of several historical meteorological environmental data of the target fishing vessel, the introduction of the FCM algorithm to cluster the several historical meteorological environmental data into a historical drift vector set, generating fuzzy clustering results, and adjusting the state transition model in the historical dynamic drift model based on the fuzzy clustering results to obtain the dynamic drift prediction model of the target fishing vessel, such as... Figure 2 As shown, the specific steps include:

[0067] S202: Obtain several historical meteorological and environmental data corresponding to the target fishing vessel's navigation in each sub-drift area through the navigation log, and divide the predetermined navigation time into several navigation time sequence nodes;

[0068] S204: Obtain multi-dimensional specification parameters of the target fishing vessel, and obtain the physical action vector of the multi-dimensional specification parameters under different combinations of meteorological environmental conditions based on big data network; wherein, the multi-dimensional specification parameters include the volume, weight, height and load capacity of the target fishing vessel;

[0069] S206: Based on the historical drift vector set, extract the historical drift vector corresponding to each navigation timeline node, introduce the FCM algorithm to construct the fuzzy membership matrix between each historical drift vector and different physical action vectors, and set up multiple clusters according to several historical meteorological environment data;

[0070] S208: Preset convergence threshold, calculate the cluster center of each cluster based on the fuzzy membership matrix, obtain the fuzzy membership degree of each cluster center, iteratively update the fuzzy membership matrix through the fuzzy membership degree until the convergence threshold is reached, and obtain the fuzzy clustering result of historical meteorological environment data to generate historical drift vectors;

[0071] S210: Based on the fuzzy clustering results, adjust the state transition model of the target fishing vessel drift in the historical dynamic drift model to obtain the adjusted state transition model. Train and verify the adjusted state transition model by resampling the states and weights of new particles to obtain the dynamic drift prediction model of the target fishing vessel.

[0072] It should be noted that the physical action vector represents the angle, direction, and magnitude of the physical effects of the meteorological environment on the target fishing vessel. Historical meteorological environmental data includes wind direction, ocean current velocity, rainfall, wave intensity, and fog concentration. Changes in the meteorological environment in the South China Sea can cause the target fishing vessel to drift significantly or slightly. For example, strong winds and turbulent ocean currents at the distress location can cause significant drift, thus forming a set of historical drift vectors for each sub-drift region within the dynamic drift area. However, due to the complex and variable meteorological environment in the South China Sea, which can fluctuate in intensity, different intensities of meteorological environmental changes result in different drift vectors for the target fishing vessel. If the historical drift vectors corresponding to each historical meteorological environmental data cannot be matched and aligned, the accuracy of the dynamic drift prediction results for the target fishing vessel may be significantly compromised, affecting the accuracy of search and rescue positioning of the distressed vessel. Therefore, this method enables precise fuzzy clustering of several historical meteorological environmental data corresponding to the target fishing vessel's navigation in each sub-drift area with the historical drift vector set of the target fishing vessel in each sub-dynamic drift area. This allows for mutual clustering and matching of the temporal changes of different meteorological environmental data with the corresponding historical drift vectors when predicting the dynamic drift of fishing vessels in distress, thereby improving the reliability and accuracy of the prediction results for dynamic drift of fishing vessels in distress caused by changes in meteorological environment. Compared with traditional prediction methods, this method significantly reduces the dynamic prediction error rate. In addition, this method can directly adjust the state transition model of the historical dynamic drift model constructed in the previous step based on its fuzzy clustering results, thereby predicting and describing the state of each particle at the next moment based on the fuzzy clustering results. On the one hand, this saves the tedious step of constructing a separate prediction model, saving computational resources and efficiency; on the other hand, it can improve prediction performance based on the improved fuzzy clustering results, further optimizing the prediction accuracy of the dynamic drift prediction model.

[0073] It should be noted that the Chinese name of the FCM algorithm is Fuzzy Clustering Algorithm. It is a clustering algorithm that allows data points to belong to multiple classes and assigns different membership degrees to each data point. It is very effective in processing data with fuzzy boundaries and can better reflect the uncertainty and fuzziness in the actual situation. Moreover, due to the fuzzy characteristics of FCM, it has less impact on noisy data points and can provide smoother clustering results, further improving the clustering accuracy and performance.

[0074] Furthermore, in a preferred embodiment of the present invention, the construction of the future meteorological environment simulation field for the South China Sea region involves planning a first dynamic distress environment area based on the current distress coordinates of the target fishing vessel, extracting a first future meteorological environment sub-simulation field from the future meteorological environment simulation field located within the first dynamic distress environment area, and performing dynamic prediction in a dynamic drift prediction model based on the first future meteorological environment sub-simulation field to obtain the initial dynamic drift trajectory. Specifically, this includes the following steps:

[0075] Acquire several meteorological forecast data for the South China Sea region in the future time period, generate sub-models of different meteorological environment types based on the several meteorological forecast data, and perform spatial and temporal coupling on each of the sub-models to construct a future meteorological environment simulation field for the South China Sea region.

[0076] Construct a 3D model of the current fishing vessel, use GPS positioning to query the distress coordinates of the current fishing vessel on the multi-dimensional geographic coordinate map, and preset distress environment planning thresholds based on the current 3D model of the fishing vessel.

[0077] The range of the distress environment where the fishing vessel is currently located is planned in the multidimensional geographic coordinate map until the distress environment planning threshold is reached, so as to obtain the static distress environment range where the fishing vessel is currently located at the distress coordinate position.

[0078] Obtain the preset ideal navigation route of the current target fishing vessel, and plan the static distress environment range of the current target fishing vessel in the multi-dimensional geographic coordinate map according to the ideal navigation route. The area formed after the vessel travels along the ideal navigation route is obtained as the first dynamic distress environment area.

[0079] In the future meteorological environment simulation field, multiple future meteorological environment sub-simulation fields in the future time series of the current target fishing vessel in the first dynamic distress environment area are extracted and defined as the first future meteorological environment sub-simulation field. The dynamic drift prediction model of the target fishing vessel is used to perform dynamic drift prediction analysis on multiple first future meteorological environment sub-simulation fields to obtain the initial dynamic drift trajectory.

[0080] It should be noted that after generating the dynamic drift prediction model, the drift trajectory of the target fishing vessel when it encounters distress can be dynamically predicted. However, due to the uneven distribution and constant changes of the meteorological environment in the South China Sea, the constantly changing meteorological environment along the ideal navigation route directly affects the accuracy of the dynamic drift prediction results. Therefore, in order to improve the accuracy of dynamic drift prediction, it is necessary to dynamically obtain the future meteorological environment field of a certain area during the target fishing vessel's journey along the ideal navigation route. Therefore, this method can first construct a future meteorological environment simulation field for the South China Sea region based on several meteorological forecast data. Since the multidimensional specifications of the fishing vessel itself in a static state are affected by the physical effects of the meteorological environment within a certain range, it is necessary to plan the static distress environment range when the target fishing vessel is at the distress coordinate position. Then, the dynamic distress environment area formed by the static distress environment range of the target fishing vessel along the ideal navigation route is analyzed to obtain the first dynamic distress environment area. This first dynamic distress environment area can reflect the meteorological environment changes that cause the target fishing vessel to drift when it is in distress. These meteorological environment changes are the necessary data conditions for the dynamic drift prediction model to predict the drift of the target fishing vessel. Therefore, the first future meteorological environment sub-simulation field where the target fishing vessel is located in the first dynamic distress environment area is finally extracted from the constructed future meteorological environment simulation field. The dynamic drift prediction model is used to perform dynamic drift prediction analysis on the first future meteorological environment sub-simulation field to obtain the initial dynamic drift trajectory. This method enables dynamic drift prediction of the impact of changes in the meteorological environment under normal navigation conditions on the distressed fishing vessel. This allows for accurate prediction of the final drift trajectory of the target fishing vessel after being affected by the meteorological environment, improving the accuracy of dynamic drift prediction, aiding in the formulation of rescue plans, and ensuring rescue efficiency.

[0081] Furthermore, in a preferred embodiment of the present invention, the acquisition of several meteorological forecast data points for the South China Sea region over a future time period, the generation of sub-models for different meteorological environment types based on the several meteorological forecast data points, and the spatial and temporal coupling of each sub-model are performed to construct a future meteorological environment simulation field for the South China Sea region, such as... Figure 3 As shown, the specific steps include:

[0082] S302: Obtain several meteorological forecast data points for the South China Sea region within a future time period, analyze and reconstruct the meteorological forecast data points using meteorological environment simulation software, and generate sub-state models for different meteorological environment types; wherein, the meteorological environment types include atmosphere, ocean currents, and land;

[0083] S304: Based on the sub-state model, extract the meteorological environment variable equations expressed by each meteorological environment type, introduce the finite difference algorithm to discretize each meteorological environment variable equation to generate several discretized variable equations, and construct the coupled spatial grid and time step of the sub-state model of each meteorological environment type according to the several discretized variable equations.

[0084] S306: Set the coupling timing sequence for each sub-state model according to the time step, perform grid docking and matching of the coupling spatial grid of each meteorological environment type sub-state model based on the coupling timing sequence, and exchange the meteorological environment variables of each sub-state model during the grid docking and matching process to obtain the meteorological environment simulation field.

[0085] S308: Based on the coupling time series, several historical meteorological environment data are coupled and tested sequentially in the meteorological environment simulation field to obtain the meteorological environment test simulation field, and several meteorological environment benchmark simulation fields are created after standard coupling of historical meteorological environment data.

[0086] S310: Calculate the degree of agreement between the meteorological environment test simulation field and the meteorological environment benchmark simulation field. If the degree of agreement is less than the preset degree of agreement, then perform coupling calibration on the spatial coupling model and coupling time sequence of each meteorological environment type according to the degree of agreement to obtain the future meteorological environment simulation field of the South China Sea area.

[0087] It should be noted that due to the rich and ever-changing meteorological environment in the South China Sea, and the dynamic drift prediction model for target fishing vessels being dynamically generated, directly importing meteorological data into this model reduces its ability to analyze the temporal dynamics of the meteorological data, increases its computational load, and may lead to errors or significant deviations in the final prediction results. This would affect the quality and efficiency of rescue plans for distressed fishing vessels. Therefore, this method generates sub-models for different meteorological environments based on several meteorological forecasts for the South China Sea region over a future time period. It then performs grid-by-grid matching of the coupling spatial grids of each sub-model according to the time step, such as grid matching between atmospheric and ocean current models. The meteorological variables include temperature, humidity, wind speed, sea surface temperature, and current velocity. Exchanging the meteorological variables of each sub-model during grid matching ensures the realism and impact of the interactions between different meteorological environments during coupling, further improving the realism and reliability of the meteorological environment simulation field. If the agreement between the meteorological environment test simulation field and the meteorological environment benchmark simulation field is less than the preset agreement, it indicates that the meteorological environment data simulation in the meteorological environment simulation field has a deviation and is therefore inaccurate. Therefore, it is necessary to perform corresponding coupling calibration on the network connection and coupling timing of its spatial coupling model to continuously update and improve the simulation performance of the future meteorological environment simulation field. This method can construct a future meteorological environment simulation field based on meteorological forecast data that can achieve dynamic simulation, thereby effectively improving the efficiency and accuracy of meteorological environment analysis of the dynamic drift prediction model, reducing computational load, improving the stability and accuracy of the prediction results of the dynamic drift prediction model, and avoiding dynamic drift prediction errors.

[0088] Furthermore, in a preferred embodiment of the present invention, the step of planning the second dynamic distress environment area formed by the dynamic drift of the current target fishing vessel through the initial dynamic drift trajectory, analyzing the vector disturbance index of the meteorological environment through the geological and topographic feature vector distribution map of the second dynamic distress environment area, adjusting the second future meteorological environment sub-simulation field according to the vector disturbance index and re-dynamically predicting to obtain the final dynamic drift trajectory and corresponding coordinate values ​​specifically includes the following steps:

[0089] Based on the multidimensional geographic coordinate map, the static distress environment range of the current target fishing vessel is re-planned, and the area formed after traveling according to the initial dynamic drift trajectory is obtained to obtain the second dynamic distress environment area.

[0090] The geographic coordinate parameters of the second dynamic distress environment area are extracted by a multi-dimensional geographic coordinate map, and the geographic coordinate parameters are transmitted to the GPS satellite positioning system.

[0091] The second dynamic distress environment area is remotely located and photographed using a GPS satellite positioning system to obtain satellite terrain image data of the second dynamic distress environment area. An edge detection algorithm is then introduced to analyze and extract the satellite terrain image data to obtain the geological and terrain feature vector of the second dynamic distress environment area.

[0092] Based on geographic coordinate parameters, all geological and topographic feature vectors are marked in a multidimensional geographic coordinate map to generate a distribution map of geological and topographic feature vectors of the second dynamic distress environment area. At the same time, a geographic geomorphological knowledge graph of the South China Sea is obtained based on a big data network.

[0093] The geological and topographic feature vector distribution map and the future meteorological environment simulation field are simultaneously imported into the geographical and geomorphological knowledge graph of the South China Sea for identification, so as to obtain the vector disturbance index of the geological and topographic distribution of the second dynamic distress environment area on the future meteorological environment.

[0094] The future meteorological environment sub-simulation field in which the current target fishing vessel is located in the second dynamic distress environment area is extracted from the future meteorological environment simulation field and defined as the second future meteorological environment sub-simulation field. The meteorological environment vector of the second future meteorological environment sub-simulation field is adjusted and updated according to the vector disturbance index to obtain the adjusted and updated second future meteorological environment sub-simulation field.

[0095] The dynamic drift prediction model is used to re-analyze the adjusted and updated second future meteorological environment sub-field to obtain the final dynamic drift trajectory and coordinate values ​​of the target fishing vessel. The final dynamic drift trajectory and coordinate values ​​are then uploaded to the target fishing vessel's distress terminal.

[0096] It should be noted that the South China Sea has complex geological topography, with numerous shoals, coral reefs, and submerged reefs. These geological features may alter or deflect the meteorological environment, thereby further affecting the dynamic drift trajectory of the target fishing vessel. Therefore, after predicting the initial dynamic drift trajectory of the target fishing vessel, it is necessary to further analyze the impact of the geological topography on the dynamic drift behavior of the target fishing vessel along the initial dynamic drift trajectory. This method re-plans the static distress environment range of the current target fishing vessel and forms a second dynamic distress environment area after it travels according to the initial dynamic drift trajectory. Then, it analyzes the satellite image data of the second dynamic distress environment area based on the GPS satellite positioning system to extract all geological and topographic feature vectors existing in the second dynamic distress environment area. Since different geological and topographical distributions will cause vector disturbance changes such as energy weakening, physical action direction shift, or direct absorption and disappearance in the future meteorological environment, the vector disturbance index of the second dynamic distress environment area for the future meteorological environment can be determined according to the geological and topographical distribution of the second dynamic distress environment area. When the vector disturbance index occurs, the original second future meteorological environment sub-simulation field will inevitably change. Therefore, it is necessary to adjust and update the meteorological environment simulation changes and states of the second future meteorological environment sub-simulation field according to the vector disturbance index, so as to ensure the timeliness, practicality, and rationality of the future meteorological environment sub-simulation field used for prediction when affected by geological and topographical factors, thereby significantly improving the accuracy of dynamic drift prediction. This method can further analyze the impact of geological topography in the South China Sea on the prediction of the dynamic drift of the target fishing vessel, thereby making the prediction results more consistent with the actual situation of distress in the South China Sea, improving the accuracy of the final prediction of the dynamic drift of the fishing vessel, effectively ensuring the quality of the rescue plan for distressed fishing vessels and the efficiency of actual rescue, and achieving high economic benefits.

[0097] Furthermore, the method for predicting the dynamic drift of fishing vessels based on distress analysis in the South China Sea also includes the following steps:

[0098] Several historical dynamic drift prediction trajectories of different target fishing vessels in the South China Sea are obtained, and the final dynamic drift area of ​​different target fishing vessels is determined based on the several historical dynamic drift prediction trajectories.

[0099] Historical meteorological environment simulation fields of each of the final dynamic drift water areas are obtained. Several energy gradient evaluation indicators of different meteorological environment types are obtained based on big data network retrieval. Deep learning algorithms are introduced to train and verify the several energy gradient evaluation indicators to obtain a meteorological environment energy gradient evaluation model.

[0100] The historical meteorological environment simulation field was evaluated using a meteorological environment energy gradient assessment model to obtain the energy gradient assessment value for each historical meteorological environment simulation field.

[0101] The Kriging interpolation algorithm is introduced to calculate the semi-variogram of the energy gradient evaluation value of each historical meteorological environment simulation field. Kriging interpolation is performed on each energy gradient evaluation value according to the semi-variogram to obtain the historical meteorological environment energy hotspot map.

[0102] A preset meteorological environment energy anomaly threshold is set, and energy hotspots with meteorological environment energy values ​​higher than the meteorological environment energy anomaly threshold in the historical meteorological environment energy hotspot map are removed. The remaining energy hotspots are then integrated and planned to obtain multiple resettlement areas.

[0103] Based on the multiple available placement areas, the placement layout points of the search and rescue drones are rationally planned, a placement layout map of the search and rescue drones is generated, and the placement layout map of the search and rescue drones is uploaded to the fishing vessel terminal.

[0104] It should be noted that fishing vessels operating in the South China Sea are prone to encountering severe weather and facing danger. Search and rescue drones can efficiently and effectively conduct rescue missions based on the dynamic drifting behavior of distressed fishing vessels, replacing human rescue efforts when they cannot reach the distress location immediately. However, search and rescue drones are easily affected by weather conditions during search and rescue missions in the South China Sea, which can lead to problems such as deviation from the search and rescue trajectory, drone damage, and malfunctions. Therefore, a reasonable deployment and layout of search and rescue drones is crucial. This method can be used to select and plan the deployment areas for search and rescue drones, thereby making the deployment and layout of search and rescue drones more rational. This will allow search and rescue drones to avoid the impact of severe weather conditions during search and rescue missions, improve search and rescue efficiency and quality, and further protect the lives of those in distress.

[0105] The second aspect of this invention provides a dynamic drift prediction system for fishing vessels based on distress analysis in the South China Sea, such as... Figure 4 As shown, the fishing vessel dynamic drift prediction system includes a memory 41 and a processor 42. The memory 41 stores a fishing vessel dynamic drift prediction method program based on distress analysis in the South China Sea. When the fishing vessel dynamic drift prediction method program based on distress analysis in the South China Sea is executed by the processor 42, any of the steps of the fishing vessel dynamic drift prediction method based on distress analysis in the South China Sea are implemented.

[0106] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for predicting the dynamic drift of a fishing vessel based on distress analysis in the South China Sea waters, characterized in that, The method comprises the following steps: constructing a historical dynamic drift model of the target fishing boat in distress in the South China Sea area, and analyzing the drift vector of the target fishing boat in the multi-dimensional geographic coordinate map according to the historical dynamic drift model to obtain a historical drift vector set of the target fishing boat in each sub-dynamic drift area; obtaining a plurality of historical meteorological environment data of the target fishing boat, introducing the FCM algorithm to cluster the plurality of historical meteorological environment data to the historical drift vector set, generating a fuzzy clustering result, adjusting a state transition model in the historical dynamic drift model based on the fuzzy clustering result, and obtaining a dynamic drift prediction model of the target fishing boat; constructing a future meteorological environment simulation field of the South China Sea area, planning a first dynamic distress environment area according to the distress coordinate position of the current target fishing boat, stripping a first future meteorological environment sub-simulation field in the first dynamic distress environment area through the future meteorological environment simulation field, and dynamically predicting in the dynamic drift prediction model based on the first future meteorological environment sub-simulation field to obtain an initial dynamic drift trajectory; planning a second dynamic distress environment area formed by the dynamic drift of the current target fishing boat through the initial dynamic drift trajectory, analyzing the vector disturbance index of the meteorological environment through the geological and topographical feature vector distribution map of the second dynamic distress environment area, adjusting the second future meteorological environment sub-simulation field according to the vector disturbance index and re-dynamically predicting to obtain a final dynamic drift trajectory and corresponding coordinate value; wherein the second dynamic distress environment area formed by the dynamic drift of the current target fishing boat through the initial dynamic drift trajectory, the vector disturbance index of the meteorological environment is analyzed through the geological and topographical feature vector distribution map of the second dynamic distress environment area, the second future meteorological environment sub-simulation field is adjusted according to the vector disturbance index and re-dynamically predicted to obtain a final dynamic drift trajectory and corresponding coordinate value, and specifically comprises the following steps: re-planning a static distress environment range of the current target fishing boat according to the area formed after the initial dynamic drift trajectory is traveled based on the multi-dimensional geographic coordinate map to obtain a second dynamic distress environment area; extracting geographic coordinate parameters of the second dynamic distress environment area through the multi-dimensional geographic coordinate map, and transmitting the geographic coordinate parameters to the GPS satellite positioning system; remote positioning and shooting the second dynamic distress environment area through the GPS satellite positioning system to obtain satellite terrain image data of the second dynamic distress environment area, introducing an edge detection algorithm to analyze and extract the satellite terrain image data to obtain geological and topographical feature vectors of the second dynamic distress environment area; marking all the geological and topographical feature vectors in the multi-dimensional geographic coordinate map based on the geographic coordinate parameters to generate a geological and topographical feature vector distribution map of the second dynamic distress environment area, and obtaining a geographic and geomorphological knowledge graph of the South China Sea area based on big data network; introducing the geological and topographical feature vector distribution map and the future meteorological environment simulation field into the geographic and geomorphological knowledge graph of the South China Sea area for identification to obtain a vector disturbance index of the geological and topographical distribution of the second dynamic distress environment area to the future meteorological environment; A future meteorological environment sub-simulation field in which the current target fishing boat is located in a second dynamic distress environment region is stripped out from the future meteorological environment simulation field, and is defined as a second future meteorological environment sub-simulation field; the meteorological environment vector of the second future meteorological environment sub-simulation field is adjusted and updated according to the vector disturbance index, so as to obtain an adjusted and updated second future meteorological environment sub-simulation field; The adjusted and updated second future meteorological environment sub-simulation field is re-analyzed by using a dynamic drift prediction model, so as to obtain a final dynamic drift trajectory of the current target fishing boat and a coordinate value of the final dynamic drift trajectory, and the final dynamic drift trajectory and the coordinate value are uploaded to a distress terminal of the target fishing boat.

2. The fishing boat dynamic drift prediction method based on distress analysis of South China Sea waters according to claim 1, characterized in that, The historical dynamic drift model of the target fishing boat in distress in the South China Sea water area is constructed, and the drift vector of the target fishing boat is analyzed on a multi-dimensional geographical coordinate map according to the historical dynamic drift model, so as to obtain a historical drift vector set of the target fishing boat in each sub-dynamic drift region, and the method comprises the following steps: A navigation log of the target fishing boat in the South China Sea water area is obtained, and a plurality of historical predetermined route coordinates and a plurality of actual running route coordinates of the target fishing boat in distress are extracted from the navigation log; A particle filtering algorithm is introduced, a state transition model and an observation model of the drift of the target fishing boat are constructed in the particle filtering algorithm based on the plurality of historical predetermined route coordinates and the plurality of actual running route coordinates, and a group of particles is initialized according to the state transition model and the observation model; The weight of each particle is updated according to the coordinate deviation between the historical predetermined route coordinates and the actual running route coordinates and the observation model, and new particles are resampled by using the new weight, and the weight and the state of the particles are recursively updated repeatedly until all the particles are updated, so as to generate the historical dynamic drift model of the target fishing boat; A multi-dimensional geographical coordinate map of the South China Sea water area is obtained, a multi-dimensional space coordinate field is constructed based on the multi-dimensional geographical coordinate map, and the historical predetermined route and the actual running route are dynamically fitted in the multi-dimensional space coordinate field based on the historical dynamic drift model, so as to extract a dynamic drift region formed between the historical predetermined route and the actual running route; The predetermined navigation time of the target fishing boat is obtained through the navigation log, the dynamic drift region is divided into N sub-dynamic drift regions based on the predetermined navigation time, all drift coordinates in each sub-dynamic drift region and the distribution pattern of each drift coordinate are obtained; The drift change of the target fishing boat in the dynamic drift region is analyzed through the change and the distribution pattern of the drift coordinates, so as to obtain a historical drift vector set of the target fishing boat in each sub-dynamic drift region.

3. The fishing boat dynamic drift prediction method based on distress analysis of South China Sea waters according to claim 1, characterized in that, A plurality of historical meteorological environment data of the target fishing boat are obtained, the plurality of historical meteorological environment data are clustered into the historical drift vector set by using an FCM algorithm, a fuzzy clustering result is generated, the state transition model in the historical dynamic drift model is adjusted based on the fuzzy clustering result, and a dynamic drift prediction model of the target fishing boat is obtained, and the method comprises the following steps: Obtain a plurality of historical meteorological environment data corresponding to each sub-drift area of the target fishing vessel through a navigation log, and divide the predetermined navigation time into a plurality of navigation time nodes; Obtain a plurality of historical meteorological environment data corresponding to each sub-drift area of the target fishing vessel through a navigation log, and divide the predetermined navigation time into a plurality of navigation time nodes; Obtain a plurality of historical meteorological environment data corresponding to each sub-drift area of the target fishing vessel through a navigation log, and divide the predetermined navigation time into a plurality of navigation time nodes; Obtain a plurality of historical meteorological environment data corresponding to each sub-drift area of the target fishing vessel through a navigation log, and divide the predetermined navigation time into a plurality of navigation time nodes; Pre-set a convergence threshold, calculate the cluster center of each cluster based on the fuzzy membership matrix, obtain the fuzzy membership of each cluster center, and update the fuzzy membership matrix through the fuzzy membership until the convergence threshold is reached, to obtain the fuzzy clustering result of the historical meteorological environment data generating the historical drift vector; 4. The fishing boat dynamic drift prediction method based on distress analysis of South China Sea waters according to claim 1, characterized in that, Based on the fuzzy clustering result, adjust the state transition model of the target fishing vessel drift in the historical dynamic drift model to obtain an adjusted state transition model, and train and verify the adjusted state transition model by resampling the state and weight of new particles to obtain a dynamic drift prediction model of the target fishing vessel. The future meteorological environment simulation field of the South China Sea water area is constructed, the first dynamic distress environment area is planned according to the distress coordinate position of the current target fishing vessel, the first future meteorological environment sub-simulation field in the first dynamic distress environment area is stripped through the future meteorological environment simulation field, and dynamic prediction is carried out in the dynamic drift prediction model based on the first future meteorological environment sub-simulation field to obtain an initial dynamic drift trajectory, which specifically includes the following steps: Obtain a plurality of weather forecast data in the future time period of the South China Sea water area, generate a sub-model of different meteorological environment types according to the plurality of weather forecast data, and spatially and temporally couple each sub-model to construct a future meteorological environment simulation field of the South China Sea water area; Construct a three-dimensional model of the current fishing vessel, query the distress coordinate position of the current fishing vessel in the multi-dimensional geographic coordinate map through the GPS positioning function, and preset a distress environment planning threshold based on the three-dimensional model of the current fishing vessel; Plan the distress environment range of the current fishing vessel in the multi-dimensional geographic coordinate map until the distress environment planning threshold is reached to obtain the static distress environment range of the current fishing vessel at the distress coordinate position; Obtain a plurality of historical meteorological environment data corresponding to each sub-drift area of the target fishing vessel through a navigation log, and divide the predetermined navigation time into a plurality of navigation time nodes; Obtain a plurality of historical meteorological environment data corresponding to each sub-drift area of the target fishing vessel through a navigation log, and divide the predetermined navigation time into a plurality of navigation time nodes; Stripping out the current target fishing boat in the first dynamic distress environment region in the future weather environment simulation field, defined as the first future weather environment sub-simulation field, through the dynamic drift prediction model of the target fishing boat, the initial dynamic drift trajectory is obtained by dynamic drift prediction analysis.

5. The fishing boat dynamic drift prediction method based on the distress analysis of the South China Sea according to claim 4, characterized in that, The method comprises the following steps: Obtaining a plurality of weather forecast data in the South China Sea water area in a future time period, generating a sub-model of different weather environment types according to the plurality of weather forecast data, and spatially and temporally coupling each sub-model to construct a future weather environment simulation field of the South China Sea water area. Based on the sub-state model, extract the weather environment variable equation expressed by each weather environment type, introduce the finite difference algorithm to discretize each weather environment variable equation to generate a plurality of discretized variable equations, and construct the coupling space grid and time step of each weather environment type sub-state model according to the plurality of discretized variable equations. According to the time step, set the coupling time sequence of each sub-state model, based on the coupling time sequence, perform one-by-one grid docking matching of the coupling space grid of each weather environment type sub-state model, and exchange the weather environment variables of each sub-state model during the grid docking matching process, to obtain a weather environment simulation field. Based on the coupling time sequence, sequentially couple test a plurality of historical weather environment data in the weather environment simulation field to obtain a weather environment test simulation field, and create a plurality of historical weather environment data standard coupled weather environment benchmark simulation field. Calculate the degree of fit between the weather environment test simulation field and the weather environment benchmark simulation field, if the degree of fit is less than the preset degree of fit, then according to the degree of fit, the spatial coupling model and the coupling time sequence of each weather environment type are coupled and calibrated to obtain the future weather environment simulation field of the South China Sea water area.

6. A dynamic drift prediction system for fishing vessels based on distress analysis in the South China Sea waters, characterized by, The fishing boat dynamic drift prediction system comprises a memory and a processor, the memory stores a fishing boat dynamic drift prediction method program based on South China Sea distress analysis, when the fishing boat dynamic drift prediction method program based on South China Sea distress analysis is executed by the processor, the fishing boat dynamic drift prediction method steps based on South China Sea distress analysis are realized.

Images