A ship intelligent management method and system based on multi-source data analysis

Abstract

The present invention discloses a ship intelligent management method and system based on multi-source data analysis, which relates to the field of ship management, including: extracting environmental characteristics of different sea areas according to big data of navigation information and sea area information; setting a multi-source sensor group at a suitable position to collect environmental data of the sea area; setting the area as a first positioning information group according to the navigation information before getting lost and the environmental characteristics of the sea area, and calculating the first positioning vector sequence; setting the information as a second positioning information group according to the change of sea area environmental data and the moving distance during the movement of the ship, and confirming the deviation coefficient of the ship's heading in combination with the nautical map; establishing a pyramid model of ship orientation positioning to assist in judging the ship's sailing direction and position. The advantages of the present invention are: effectively solving the problem of obtaining current position information for ships that are lost due to the failure of the positioning system, and assisting and guiding the ship's sailing direction.

Description

Technical Field

[0001] The present invention relates to the field of ship management, and in particular to a ship intelligent management method and system based on multi-source data analysis. Background Art

[0002] When a ship is sailing at sea, due to the vastness of the sea area, weak recognition ability and damage to positioning facilities, once the ship is lost at sea, it will be particularly difficult to find the correct return route. Especially in the process of adjusting the course, due to misoperation or navigation errors, the ship deviates from the scheduled route or destination and wastes fuel and food, which brings huge risks to the ship itself and the crew. Therefore, it is particularly important to reduce the risk of the ship after losing its way, improve the positioning ability of the ship when the positioning device function is lost, and assist and guide the ship's navigation direction. Ship management technology will become particularly important.

[0003] Existing ship positioning technology mainly focuses on optimizing positioning data such as Beidou and GPS, so that they can cope with harsh environments and improve positioning accuracy. However, due to the failure of positioning devices caused by human or natural disasters, the existing technology will be difficult to solve the problem of auxiliary positioning. At that time, it can only rely on subjective experience to make judgments, which will lead to inaccurate positioning and difficult judgments, thus causing more serious navigation crises and not conducive to ensuring the safety of ships and crew members. Summary of the invention

[0004] In order to solve the above technical problems, a method and system for intelligent ship management based on multi-source data analysis are provided. The technical solution solves the problem of auxiliary positioning caused by failure of positioning devices due to man-made or natural disasters proposed in the above background technology, which makes it difficult for existing technologies to solve the problem. At that time, it can only rely on subjective experience to make judgments, resulting in inaccurate positioning and difficult judgments, thereby causing more serious navigation crises and being not conducive to ensuring the safety of ships and crew members.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A method for intelligent ship management based on multi-source data analysis, characterized by comprising:

[0007] Extract environmental characteristics of different sea areas based on big data of navigation information and sea area information;

[0008] Based on the ship's hull structure, a multi-source sensor group is set at a suitable location to collect environmental data of the sea area;

[0009] According to the navigation information before being lost and the environmental characteristics of the sea area, the area is set as a first positioning information group, and the first positioning vector sequence is calculated;

[0010] According to the changes in the sea environment data and the moving distance during the movement of the ship, the information is set as the second positioning information group, and the deviation coefficient of the ship's heading is confirmed in combination with the navigation map;

[0011] Based on the neural network algorithm, a pyramid model of ship orientation positioning is established to assist in determining the ship's sailing direction and location.

[0012] Preferably, the extracting environmental characteristics of different sea areas based on the big data of navigation information and sea area information specifically includes:

[0013] Based on the big data of navigation information and sea area information, analyze the environmental data of different sea areas at different times, extract the environmental characteristics of different sea areas, and establish a sea area environmental characteristics database;

[0014] The marine environmental characteristics include: ocean currents, monsoons, salinity, marine life and waves;

[0015] According to the marine environment characteristic database information, mark the corresponding area on the nautical map and obtain the coordinate information of the specific location.

[0016] Preferably, the step of setting the area as the first positioning information group according to the navigation information before being lost and the environmental characteristics of the sea area, and calculating the first positioning vector sequence specifically includes:

[0017] Obtain navigation information and sea environment characteristics before the ship gets lost, and establish a sea environment characteristics data matrix;

[0018] According to the marine environment characteristic database, the theoretical indicators of the environmental characteristics of the area where the ship is lost are obtained;

[0019] According to the CRITIC weighting method, determine the index weight of the environmental characteristics of the sea area in the entire sea area environmental characteristics database;

[0020] According to the obtained weight index, a feature vector sequence of the environmental feature group of the sea area is established and defined as the first positioning vector sequence.

[0021] Preferably, the CRITIC weight method expression specifically includes:

[0022] Standardize the data matrix of environmental characteristics of the sea area before the ship got lost;

[0023] According to the standardized data matrix of the environmental characteristics of the sea area, the variability of the indicators is calculated;

[0024] According to the Pearson correlation coefficient, the conflict of indicators was calculated;

[0025] Calculate the indicator information amount based on indicator variability and indicator conflict;

[0026] According to the amount of information of the indicators, the indicator weights of the environmental characteristic data of the sea area are calculated;

[0027] The expression for standardizing the environmental characteristic data matrix of the sea area before the ship is lost is:

[0028]

[0029] Where b ij is the result of data standardization of the environmental characteristic data matrix of the sea area in the i-th row and j-th column, a ij is the environmental characteristic data matrix of the sea area in row i and column j, a jmin is the minimum data of the environmental characteristic data matrix of the sea area in the jth column, a jmax is the maximum data of the environmental characteristic data matrix of the sea area in the jth column;

[0030] The expression of the variability of the environmental characteristic data matrix index of the sea area is:

[0031]

[0032] In the formula, S j is the result of the variability of the environmental characteristic data matrix indicators of the standardized sea area. is the mean value of the environmental characteristic data matrix of the sea area after standardization in the jth column, and n is the number of rows of the environmental characteristic data matrix of the sea area after standardization;

[0033] The conflict expression of the environmental characteristic data matrix index of the sea area is:

[0034]

[0035] In the formula, R j is the conflict result of the environmental characteristic data matrix indicators of the sea area, r jk is the Pearson correlation coefficient, m is the number of columns of the environmental characteristic data matrix of the sea area;

[0036] The expression of the information content of the environmental characteristic data matrix index of the sea area is:

[0037] C j =S j R j

[0038] In the formula, C j It is the information content of the environmental characteristic data matrix indicators of the sea area;

[0039] The index weight expression of the environmental characteristic data of the sea area is:

[0040]

[0041] Where W j is the index weight of the environmental characteristic data of the sea area, C k is the information content of the environmental characteristic data matrix indicators of the kth sea area.

[0042] Preferably, the step of setting the information as the second positioning information group according to the change of the sea environment data and the moving distance during the movement of the ship, and confirming the deviation coefficient of the ship's heading in combination with the nautical map specifically includes:

[0043] Obtaining the sea environment data changes, moving distance and navigation information during the movement of the ship before the ship is lost, and setting the information as the second positioning information group;

[0044] Establishing a second positioning information group matrix according to the data of the second positioning information group;

[0045] According to the specific coordinate information of the navigation map, combined with the second positioning information group matrix, the deviation coefficient of the ship's heading is determined;

[0046] The deviation coefficient expression of the ship's heading is:

[0047]

[0048] In the formula, Z s is the deviation coefficient of the ship’s heading, X i is the matrix data of the second positioning information group in the i-th row and j-th column, is the specific coordinate information of the nautical map, and N is the number of different information types in the second positioning information group matrix.

[0049] Preferably, the pyramid model of ship orientation positioning based on the neural network algorithm is established to assist in determining the navigation direction and location of the ship, which specifically includes:

[0050] Establishing a ship orientation positioning matrix according to the first positioning vector sequence and the deviation coefficient of the ship's heading;

[0051] Based on the neural network algorithm, a pyramid model for ship orientation positioning is established;

[0052] The pyramid model based on the ship's orientation can assist in determining the ship's sailing direction and location;

[0053] The pyramid model of ship orientation positioning specifically includes:

[0054] The first level of the pyramid model is: collecting environmental data of the sea area through a multi-source sensor group;

[0055] The second layer of the pyramid model is: denoising and normalizing the collected data through the Kalman filter algorithm and data normalization formula;

[0056] The third layer of the pyramid model is: analyzing the environmental data of ship positioning and establishing the ship orientation positioning matrix;

[0057] The fourth layer of the pyramid model is: based on the ship's orientation positioning matrix and based on the neural network algorithm, it is used to assist in determining the ship's sailing direction and location.

[0058] Furthermore, the present invention proposes a ship intelligent management system based on multi-source data analysis, which is used to implement the ship intelligent management method based on multi-source data analysis as described above, including:

[0059] A feature extraction module, which is used to extract environmental features of different sea areas based on big data of navigation information and sea area information;

[0060] A data acquisition module, which is used to set a multi-source sensor group at a suitable position based on the hull structure of the ship to collect environmental data of the sea area;

[0061] A direction judgment module is used to set the area as a first positioning information group and calculate the first positioning vector sequence according to the navigation information before the ship is lost and the environmental characteristics of the sea area; set the information as a second positioning information group according to the changes in the sea area environmental data and the moving distance during the movement of the ship, and confirm the deviation coefficient of the ship's heading in combination with the nautical map; and establish a pyramid model of ship direction positioning based on a neural network algorithm to assist in judging the ship's sailing direction and location.

[0062] Preferably, the orientation determination module specifically includes:

[0063] A first positioning unit, the first positioning unit is used to set the area as a first positioning information group and calculate the first positioning vector sequence according to the navigation information before being lost and the environmental characteristics of the sea area;

[0064] A second positioning unit, the second positioning unit is used to set the information as a second positioning information group according to the change of the sea environment data and the moving distance during the movement of the ship, and to confirm the deviation coefficient of the ship's heading in combination with the nautical map;

[0065] A direction determination unit is used to establish a pyramid model for ship direction positioning based on a neural network algorithm to assist in determining the ship's sailing direction and location.

[0066] Compared with the prior art, the present invention has the following beneficial effects:

[0067] By analyzing the big data of navigation information and sea area information, extracting the environmental characteristics of different sea areas, establishing the first positioning unit and the second positioning unit, and establishing the ship orientation positioning matrix required by the neural network through the first positioning unit and the second positioning unit, a pyramid model of ship orientation positioning is established to judge and locate the sailing direction and position of a lost ship, assisting the ship commander to find the direction of the return trip as soon as possible, reducing the subjective error of ship positioning, and improving the ship's positioning capability and survival management capability. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 This is a flow chart of a method for intelligent ship management based on multi-source data analysis of the present invention;

[0069] Figure 2 The present invention sets the area as the first positioning information group and calculates the first positioning vector sequence flow chart according to the navigation information before being lost and the environmental characteristics of the sea area;

[0070] Figure 3 According to the change of the sea environment data and the moving distance of the ship during the movement of the present invention, the information is set as the second positioning information group, and the deviation coefficient flow chart of the ship's heading is confirmed in combination with the nautical map;

[0071] Figure 4 The present invention establishes a pyramid model for ship orientation positioning based on a neural network algorithm to assist in determining the navigation direction and location flow chart of the ship. DETAILED DESCRIPTION

[0072] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0073] Reference Figure 1 As shown, a ship intelligent management method based on multi-source data analysis includes:

[0074] Extract environmental characteristics of different sea areas based on big data of navigation information and sea area information;

[0075] Based on the ship's hull structure, a multi-source sensor group is set at a suitable location to collect environmental data of the sea area;

[0076] According to the navigation information before being lost and the environmental characteristics of the sea area, the area is set as a first positioning information group, and the first positioning vector sequence is calculated;

[0077] According to the changes in the sea environment data and the moving distance during the movement of the ship, the information is set as the second positioning information group, and the deviation coefficient of the ship's heading is confirmed in combination with the navigation map;

[0078] Based on the neural network algorithm, a pyramid model of ship orientation positioning is established to assist in determining the ship's sailing direction and location.

[0079] It can be explained that this solution analyzes the big data of navigation information and sea area information, extracts the environmental characteristics of different sea areas, establishes the first positioning unit and the second positioning unit, and establishes the ship orientation positioning matrix required by the neural network through the first positioning unit and the second positioning unit, thereby establishing a pyramid model of ship orientation positioning to judge and locate the sailing direction and position of a lost ship.

[0080] Reference Figure 2 As shown, the setting of the area as the first positioning information group according to the navigation information before being lost and the environmental characteristics of the sea area, and calculating the first positioning vector sequence specifically includes:

[0081] Obtain navigation information and sea environment characteristics before the ship gets lost, and establish a sea environment characteristics data matrix;

[0082] According to the marine environment characteristic database, the theoretical indicators of the environmental characteristics of the area where the ship is lost are obtained;

[0083] According to the CRITIC weighting method, determine the index weight of the environmental characteristics of the sea area in the entire sea area environmental characteristics database;

[0084] According to the obtained weight index, a feature vector sequence of the environmental feature group of the sea area is established and defined as the first positioning vector sequence.

[0085] It can be explained that there are errors between the marine environment characteristic library obtained through big data and the actual marine environment conditions, and there may even be large discrepancies. Secondly, the positioning information before being lost and the environmental characteristic data of the sea area are important bases for judging the ship. This scheme analyzes the current marine environment characteristic data and the theoretical indicators of the environmental characteristics of the area where the ship is lost, and based on the CRITIC weighting method, determines the indicator weight of the environmental characteristics of the sea area in the entire marine environment characteristic library, thereby improving the accuracy of the neural network in the final result, and can adjust and optimize the parameter values ​​of the neural network. Secondly, the CRITIC weighting method is a comprehensive measure of the objective weight of the indicator based on the comparison strength of the evaluation indicators and the conflict between the indicators, and it is a scientific evaluation that fully utilizes the objective attributes of the data itself.

[0086] Reference Figure 3 As shown, according to the change of the sea environment data and the moving distance during the movement of the ship, the information is set as the second positioning information group, and the deviation coefficient of the ship's heading is confirmed in combination with the nautical map, which specifically includes:

[0087] Obtaining the sea environment data changes, moving distance and navigation information during the movement of the ship before the ship is lost, and setting the information as the second positioning information group;

[0088] Establishing a second positioning information group matrix according to the data of the second positioning information group;

[0089] According to the specific coordinate information of the navigation map, combined with the second positioning information group matrix, the deviation coefficient of the ship's heading is determined;

[0090] The deviation coefficient expression of the ship's heading is:

[0091]

[0092] In the formula, Z s is the deviation coefficient of the ship’s heading, X i is the matrix data of the second positioning information group in the i-th row and j-th column, is the specific coordinate information of the nautical map, and N is the number of different information types in the second positioning information group matrix.

[0093] It can be explained that nautical charts are an important tool to help ships navigate. Existing nautical charts have high accuracy for fixed and frequently navigated areas. In the absence of any navigation equipment, the actual sailing direction will deviate, causing the ship to deviate from the course. Therefore, this solution calculates the deviation coefficient of the ship's heading by analyzing the specific coordinate information of the nautical map and the second positioning information group of the current position, thereby improving the subsequent training and judgment accuracy of the neural network.

[0094] Reference Figure 4 As shown, the pyramid model of ship orientation positioning based on the neural network algorithm is established to assist in determining the navigation direction and location of the ship, which specifically includes:

[0095] Establishing a ship orientation positioning matrix according to the first positioning vector sequence and the deviation coefficient of the ship's heading;

[0096] Based on the neural network algorithm, a pyramid model for ship orientation positioning is established;

[0097] The pyramid model based on the ship's orientation can assist in determining the ship's sailing direction and location;

[0098] The pyramid model of ship orientation positioning specifically includes:

[0099] The first level of the pyramid model is: collecting environmental data of the sea area through a multi-source sensor group;

[0100] The second layer of the pyramid model is: denoising and normalizing the collected data through the Kalman filter algorithm and data normalization formula;

[0101] The third layer of the pyramid model is: analyzing the environmental data of ship positioning and establishing the ship orientation positioning matrix;

[0102] The fourth layer of the pyramid model is: based on the ship's orientation positioning matrix and based on the neural network algorithm, it is used to assist in determining the ship's sailing direction and location.

[0103] It can be explained that this scheme, by setting up a pyramid model, processes and analyzes the data from low to high through the advanced process of data collection - data filtering and standardization - data analysis - result judgment, thereby realizing the judgment and assistance of the ship's navigation direction and position, and effectively improving the accuracy and reliability of the ship's navigation positioning.

[0104] Further, based on the same inventive concept as the above-mentioned ship intelligent management method based on multi-source data analysis, this solution proposes a ship intelligent management system based on multi-source data analysis, including:

[0105] A feature extraction module, which is used to extract environmental features of different sea areas based on big data of navigation information and sea area information;

[0106] A data acquisition module, which is used to set a multi-source sensor group at a suitable position based on the hull structure of the ship to collect environmental data of the sea area;

[0107] A direction judgment module is used to set the area as a first positioning information group and calculate the first positioning vector sequence according to the navigation information before the ship is lost and the environmental characteristics of the sea area; set the information as a second positioning information group according to the changes in the sea area environmental data and the moving distance during the movement of the ship, and confirm the deviation coefficient of the ship's heading in combination with the nautical map; and establish a pyramid model of ship direction positioning based on a neural network algorithm to assist in judging the ship's sailing direction and location.

[0108] Preferably, the orientation determination module specifically includes:

[0109] A first positioning unit, the first positioning unit is used to set the area as a first positioning information group and calculate the first positioning vector sequence according to the navigation information before being lost and the environmental characteristics of the sea area;

[0110] A second positioning unit, the second positioning unit is used to set the information as a second positioning information group according to the change of the sea environment data and the moving distance during the movement of the ship, and to confirm the deviation coefficient of the ship's heading in combination with the nautical map;

[0111] A direction determination unit is used to establish a pyramid model for ship direction positioning based on a neural network algorithm to assist in determining the ship's sailing direction and location.

[0112] In summary, the advantages of the present invention are: by analyzing the big data of navigation information and sea area information, extracting the environmental characteristics of different sea areas, establishing a first positioning unit and a second positioning unit, and establishing the ship orientation positioning matrix required by the neural network through the first positioning unit and the second positioning unit, thereby establishing a pyramid model of ship orientation positioning, judging and locating the sailing direction and position of a lost ship, assisting the ship commander to find the direction of the return trip as soon as possible, reducing the subjective error of ship positioning, and improving the ship's positioning capability and survival management capability.

[0113] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A ship intelligent management method based on multi-source data analysis, characterized in that: include: Extract environmental characteristics of different sea areas based on big data of navigation information and sea area information; Based on the ship's hull structure, a multi-source sensor group is set at a suitable location to collect environmental data of the sea area; According to the navigation information before being lost and the environmental characteristics of the sea area, the area is set as a first positioning information group, and the first positioning vector sequence is calculated; According to the changes in the sea environment data and the moving distance during the movement of the ship, the information is set as the second positioning information group, and the deviation coefficient of the ship's heading is confirmed in combination with the navigation map; Based on the neural network algorithm, a pyramid model of ship orientation positioning is established to assist in determining the ship's sailing direction and location.

2. A ship intelligent management method based on multi-source data analysis according to claim 1, characterized in that: The extraction of environmental characteristics of different sea areas based on the big data of navigation information and sea area information specifically includes: Based on the big data of navigation information and sea area information, analyze the environmental data of different sea areas at different times, extract the environmental characteristics of different sea areas, and establish a sea area environmental characteristics database; The marine environmental characteristics include: ocean currents, monsoons, salinity, marine life and waves; According to the marine environment characteristic database information, mark the corresponding area on the nautical map and obtain the coordinate information of the specific location.

3. A ship intelligent management method based on multi-source data analysis according to claim 2, characterized in that: The step of setting the area as the first positioning information group according to the navigation information before being lost and the environmental characteristics of the sea area, and calculating the first positioning vector sequence specifically includes: Obtain navigation information and sea environment characteristics before the ship gets lost, and establish a sea environment characteristics data matrix; According to the marine environment characteristic database, the theoretical indicators of the environmental characteristics of the area where the ship is lost are obtained; According to the CRITIC weighting method, determine the index weight of the environmental characteristics of the sea area in the entire sea area environmental characteristics database; According to the obtained weight index, a feature vector sequence of the environmental feature group of the sea area is established and defined as the first positioning vector sequence.

4. A method for intelligent ship management based on multi-source data analysis according to claim 3, characterized in that: The CRITIC weight method expression specifically includes: Standardize the data matrix of environmental characteristics of the sea area before the ship got lost; According to the standardized data matrix of the environmental characteristics of the sea area, the variability of the indicators is calculated; According to the Pearson correlation coefficient, the conflict of indicators was calculated; Calculate the indicator information amount based on indicator variability and indicator conflict; According to the amount of information of the indicators, the indicator weights of the environmental characteristic data of the sea area are calculated; The expression for standardizing the environmental characteristic data matrix of the sea area before the ship is lost is: Where b ij is the result of data standardization of the environmental characteristic data matrix of the sea area in the i-th row and j-th column, a ij is the environmental characteristic data matrix of the sea area in row i and column j, a jmin is the minimum data of the environmental characteristic data matrix of the sea area in the jth column, a jmax is the maximum data of the environmental characteristic data matrix of the sea area in the jth column; The expression of the variability of the environmental characteristic data matrix index of the sea area is: In the formula, S j is the result of the variability of the environmental characteristic data matrix indicators of the standardized sea area. is the mean value of the environmental characteristic data matrix of the sea area after standardization in the jth column, and n is the number of rows of the environmental characteristic data matrix of the sea area after standardization; The conflict expression of the environmental characteristic data matrix index of the sea area is: In the formula, R j is the conflict result of the environmental characteristic data matrix indicators of the sea area, r jk is the Pearson correlation coefficient, m is the number of columns of the environmental characteristic data matrix of the sea area; The expression of the information content of the environmental characteristic data matrix index of the sea area is: C j =S j R j In the formula, C j It is the information content of the environmental characteristic data matrix indicators of the sea area; The index weight expression of the environmental characteristic data of the sea area is: Where W j is the index weight of the environmental characteristic data of the sea area, C k is the information content of the environmental characteristic data matrix indicators of the kth sea area.

5. A method for intelligent ship management based on multi-source data analysis according to claim 4, characterized in that: The information is set as the second positioning information group according to the change of the sea environment data and the moving distance during the movement of the ship, and the deviation coefficient of the ship's heading is determined in combination with the nautical map, specifically including: Obtaining the sea environment data changes, moving distance and navigation information during the movement of the ship before the ship is lost, and setting the information as the second positioning information group; Establishing a second positioning information group matrix according to the data of the second positioning information group; According to the specific coordinate information of the navigation map, combined with the second positioning information group matrix, the deviation coefficient of the ship's heading is determined; The deviation coefficient expression of the ship's heading is: In the formula, Z s is the deviation coefficient of the ship’s heading, X i is the matrix data of the second positioning information group in the i-th row and j-th column, is the specific coordinate information of the nautical map, and N is the number of different information types in the second positioning information group matrix.

6. A method for intelligent ship management based on multi-source data analysis according to claim 5, characterized in that: The pyramid model of ship orientation positioning based on the neural network algorithm is established to assist in determining the navigation direction and location of the ship, and specifically includes: Establishing a ship orientation positioning matrix according to the first positioning vector sequence and the deviation coefficient of the ship's heading; Based on the neural network algorithm, a pyramid model for ship orientation positioning is established; The pyramid model based on the ship's orientation can assist in determining the ship's sailing direction and location; The pyramid model of ship orientation positioning specifically includes: The first level of the pyramid model is: collecting environmental data of the sea area through a multi-source sensor group; The second layer of the pyramid model is: denoising and normalizing the collected data through the Kalman filter algorithm and data normalization formula; The third layer of the pyramid model is: analyzing the environmental data of ship positioning and establishing the ship orientation positioning matrix; The fourth layer of the pyramid model is: based on the ship's orientation positioning matrix and based on the neural network algorithm, it is used to assist in determining the ship's sailing direction and location.

7. A ship intelligent management system based on multi-source data analysis, used to implement the ship intelligent management method based on multi-source data analysis as claimed in any one of claims 1 to 6, characterized in that: include: A feature extraction module, which is used to extract environmental features of different sea areas based on big data of navigation information and sea area information; A data acquisition module, which is used to set a multi-source sensor group at a suitable position based on the hull structure of the ship to collect environmental data of the sea area; A direction judgment module is used to set the area as a first positioning information group and calculate the first positioning vector sequence according to the navigation information before the ship is lost and the environmental characteristics of the sea area; set the information as a second positioning information group according to the changes in the sea area environmental data and the moving distance during the movement of the ship, and confirm the deviation coefficient of the ship's heading in combination with the nautical map; and establish a pyramid model of ship direction positioning based on a neural network algorithm to assist in judging the ship's sailing direction and location.

8. The ship intelligent management system based on multi-source data analysis according to claim 7 is characterized in that: The position determination module specifically includes: A first positioning unit, the first positioning unit is used to set the area as a first positioning information group and calculate the first positioning vector sequence according to the navigation information before being lost and the environmental characteristics of the sea area; A second positioning unit, the second positioning unit is used to set the information as a second positioning information group according to the change of the sea environment data and the moving distance during the movement of the ship, and to confirm the deviation coefficient of the ship's heading in combination with the nautical map; A direction determination unit is used to establish a pyramid model for ship direction positioning based on a neural network algorithm to assist in determining the ship's sailing direction and location.

Images