Grid-based coastal water area navigation safety early warning method and system
By constructing a grid-based multi-level evaluation factor system and fuzzy comprehensive evaluation technology, the problems of lag in dynamic risk response and limited model interpretability in navigation safety evaluation have been solved. This has enabled accurate risk assessment and real-time visual decision support for coastal waters, thereby improving the scientific nature and effectiveness of navigation safety management.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-26
- Publication Date
- 2026-03-27
AI Technical Summary
Existing general aviation safety assessment technologies suffer from lag in dynamic risk response, reliance on historical data, insufficient real-time weather forecasting and path optimization, limited model interpretability, imperfect integration of qualitative and quantitative indicators, and a lack of cross-domain collaborative assessment. These shortcomings reduce the transparency and credibility of assessment results, affecting the accuracy of general aviation safety management and the overall collaborative effectiveness.
A grid-based approach is adopted to construct a multi-level evaluation factor system. The fuzzy characteristics of the evaluation factors are quantified by the membership function. Combined with the dynamic risk level classification mechanism, the factor weights are determined by the judgment matrix, and a fuzzy relation matrix and weight vector are generated. Fuzzy operations are performed to generate a dynamic risk map, providing real-time visual decision support for ship navigation and maritime supervision.
It has improved the accuracy and timeliness of general aviation safety assessments, reduced subjective judgment bias, ensured the objectivity and transparency of assessment results, provided scientific decision-making basis and safety risk assessment tools, and optimized regulatory measures.
Smart Images
Figure CN121745694A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application belongs to the technical field of navigation safety management, and particularly relates to a grid-based coastal water navigation safety early warning method and system. BACKGROUND
[0002] The main purpose of navigation safety evaluation is to identify and analyze potential safety risks in the navigation process, propose corresponding safety measures and suggestions, reduce safety risks, and improve navigation safety.
[0003] Current navigation safety evaluation technology mainly relies on intelligent monitoring, multi-source data fusion and risk assessment model to build a dynamic control system, realizes flight path prediction and conflict warning through artificial intelligence algorithm, and improves safety by combining policy-driven standardized management. However, the existing technology still has the following shortcomings: dynamic risk response is lagging, extreme weather or sudden event evaluation relies too much on historical data, real-time weather prediction and path optimization are not integrated enough; it relies on expert experience input, is easily affected by subjective judgment, and the model has limited interpretability, which reduces the transparency and credibility of the evaluation results, in addition, the fusion mechanism of qualitative and quantitative indicators is not perfect, it is difficult to scientifically integrate into the evaluation system; the existing methods focus on a single field, and lack a cross-field collaborative evaluation framework. These shortcomings restrict the precision and global collaborative efficiency of navigation safety evaluation.
[0004] Therefore, it is urgent to develop a grid-based coastal water navigation safety early warning method and system, which can provide scientific decision-making basis for navigation safety management, clearly focus on water areas, optimize supervision measures, and also provide a safety risk assessment tool for ship navigation to improve safety management level. SUMMARY
[0005] In order to solve the above technical problems, the application provides a grid-based coastal water navigation safety early warning method and system, which can provide scientific decision-making basis for navigation safety management, clearly focus on water areas, optimize supervision measures, and also provide a safety risk assessment tool for ship navigation to improve safety management level.
[0006] The application provides a grid-based coastal water navigation safety early warning method, which comprises the following steps: S1, analyzing the navigation safety influencing factors, and constructing a navigation safety evaluation influencing factor set; S2, defining the corresponding evaluation factors according to the navigation safety evaluation influencing factor set, and obtaining an evaluation factor set; S3, dividing the target area into a plurality of grid units, and collecting real-time parameters of each evaluation factor in each grid unit in the evaluation factor set; S4. Based on the preset risk quantification criteria of each evaluation factor and the real-time parameters of each evaluation factor, calculate the membership set of each evaluation factor in each grid cell through the membership function. S5. Construct the fuzzy relation matrix for each grid cell based on the membership degree set of each evaluation factor; S6. Construct a judgment matrix based on the preset scaling values between each evaluation factor, and obtain the weight vector of the evaluation factor based on the judgment matrix; S7. Perform fuzzy operations on the fuzzy relation matrix and weight vector of each grid cell to generate the fuzzy evaluation results of each grid cell. S8. The comprehensive safety risk value of each grid cell is obtained by weighting and summing the fuzzy evaluation results of each grid cell with the preset risk level weights. S9. The risk level of each grid cell is obtained by comparing the comprehensive safety risk value with the preset risk level assignment.
[0007] Furthermore, in S1, the set of factors influencing general aviation safety evaluation includes: Seabed topography, anchorages, channels, restricted areas, water depth, traffic flow, vessel density, vessel speed, navigation aids, wind, waves, currents, tides, and sea fog.
[0008] Furthermore, in S2, the evaluation factors corresponding to the set of factors influencing general aviation safety evaluation include: The topographic relief of the seabed, the anchorage density of anchorages, the width of the channel, the area ratio of the restricted area, the water depth, traffic flow, ship density, the average ship speed, the number of navigation aids, the average wind speed, the average wave height, the average current speed, the tidal range, and the annual number of sea fogs.
[0009] Furthermore, in S4, based on the preset hazard quantification criteria for each evaluation factor and the real-time parameters of each evaluation factor, the membership set of each evaluation factor for each grid cell is calculated using the membership function, including: S41. Divide each evaluation factor into 5 risk levels: low, lower, medium, higher, and high, and define the quantitative value range corresponding to each risk level of each evaluation factor. S42. Determine the risk level of each evaluation factor based on the range of quantified values and the real-time parameters of each evaluation factor. S43. Determine whether the risk level of the evaluation factor is low or high; If the risk level of the evaluation factor is low or high, then the membership set of the evaluation factor is (1,0,0,0,0) or (0,0,0,0,1). Otherwise, determine the nearest adjacent hazard level based on the real-time parameters of the evaluation factor and the hazard level to which the evaluation factor belongs, and execute S44; S44. Based on the hazard level to which the evaluation factor belongs and the range of quantified values corresponding to adjacent hazard levels, calculate the membership set of the evaluation factor using the membership function.
[0010] Furthermore, in S44, based on the hazard level to which the evaluation factor belongs and the quantified value range corresponding to adjacent hazard levels, the membership set of the evaluation factor is calculated using a membership function. The calculation formula is as follows: ; Among them, f i (x,a,b,c) represents the membership degree of the i-th evaluation factor to its hazard level and adjacent hazard levels, a represents the lower limit of the quantitative value range corresponding to the hazard level to which the evaluation factor belongs, b represents the upper limit of the quantitative value range corresponding to the hazard level to which the evaluation factor belongs, c represents the upper limit of the quantitative value range corresponding to adjacent hazard levels, and x represents the real-time parameter of the evaluation factor.
[0011] Furthermore, in S6, a judgment matrix is constructed based on the preset scaling values between each evaluation factor. The weight vectors of the evaluation factors obtained from the judgment matrix include: S61. Construct a judgment matrix based on the preset scaling values between each evaluation factor; The expression for the judgment matrix U is as follows: U=[a ij ]; Among them, a ij Let represent the preset scale value of the i-th evaluation factor relative to the j-th evaluation factor, where i∈[1,m], j∈[1,m], and m represents the total number of evaluation factors, and satisfy a ij ×a ji =1; S62. Normalize the elements of each column of the judgment matrix to obtain the normalized judgment matrix; S63. Obtain the row sum vector by summing the rows of the normalized judgment matrix; S64. Normalize the rows and vectors to obtain the weight vector of the evaluation factors.
[0012] Furthermore, in S9, the risk level of each grid cell is obtained by comparing the comprehensive safety risk value with the preset risk level assignment, including: The hazard level closest to the comprehensive safety risk value is assigned as the hazard level of the grid cell.
[0013] Furthermore, following S9, it also includes: generating a dynamic risk color map based on a preset mapping relationship between hazard level and color, and displaying the hazard level of each grid unit in the target area.
[0014] This invention also provides a grid-based coastal waterway navigation safety early warning system for executing the aforementioned grid-based coastal waterway navigation safety early warning method, characterized in that the system includes the following modules: The evaluation factor determination module is used to analyze the factors affecting general aviation safety, construct a set of factors affecting general aviation safety evaluation, and define corresponding evaluation factors based on the set of factors affecting general aviation safety evaluation to obtain a set of evaluation factors. The data acquisition module, connected to the evaluation factor determination module, is used to divide the target area into several grid units and collect the real-time parameters of each evaluation factor in the evaluation factor set within each grid unit. The membership calculation module, connected to the data acquisition module, is used to calculate the membership set of each evaluation factor in each grid cell by means of the membership function, based on the preset risk quantification criteria of each evaluation factor and the real-time parameters of each evaluation factor. The matrix calculation module, connected to the membership calculation module, is used to construct the fuzzy relation matrix of each grid cell based on the membership set of each evaluation factor. The weight calculation module, connected to the evaluation factor determination module, is used to construct a judgment matrix based on the preset scale values between each evaluation factor, and to obtain the weight vector of the evaluation factor based on the judgment matrix. The fuzzy calculation module, connected to the matrix calculation module and the weight calculation module, is used to perform fuzzy operations on the fuzzy relation matrix and weight vector of each grid cell to generate the fuzzy evaluation results of each grid cell. The risk value calculation module, connected to the fuzzy calculation module, is used to perform weighted summation based on the fuzzy evaluation results of each grid cell and the preset hazard level weights to obtain the comprehensive safety risk value of each grid cell. The output module, connected to the risk value calculation module, is used to compare the comprehensive safety risk value with the preset hazard level assignment to obtain the hazard level of each grid cell.
[0015] The embodiments of the present invention have the following technical effects: This invention addresses the problem of single evaluation dimensions in traditional methods by constructing a multi-level evaluation factor system that comprehensively considers multiple influencing factors such as topography, hydrology, transportation, and environment. It employs membership functions to quantify the fuzzy characteristics of evaluation factors and combines this with a dynamic risk level classification mechanism to achieve a scientific characterization of the uncertainties in complex marine environments. By introducing a judgment matrix to determine factor weights, it reduces subjective judgment bias and ensures the objectivity of the evaluation results. A dynamic risk map is generated based on the calculation of the fuzzy relation matrix and weight vector, intuitively displaying the risk level distribution in different areas and providing real-time visual decision support for ship navigation path planning and maritime supervision. Based on grid management and fuzzy comprehensive evaluation technology, this invention effectively improves the accuracy and timeliness of navigation safety assessment by dividing coastal waters into fine grid units and combining real-time data acquisition with a dynamic risk assessment model. Attached Figure Description
[0016] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.
[0017] Figure 1 This is a flowchart of a grid-based navigation safety early warning method for coastal waters provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of a set of influencing factors provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of an evaluation factor set provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the evaluation calculation results of all grids in a coastal water area at a single moment, provided by an embodiment of the present invention; Figure 5 This is a schematic diagram illustrating the evaluation calculation results of a single grid in coastal waters at different times, provided by an embodiment of the present invention. Figure 6 This is a dynamic risk color map of coastal waters provided in an embodiment of the present invention. Figure 7 This is a schematic diagram of a grid-based coastal waterway navigation safety early warning system provided in an embodiment of the present invention. Detailed Implementation
[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.
[0019] This invention provides a grid-based early warning method for navigation safety in coastal waters. Figure 1 This is a flowchart of a grid-based coastal waterway navigation safety early warning method provided in an embodiment of the present invention. See also... Figure 1 The method includes the following steps: S1. Analyze the factors affecting general aviation safety and construct a set of factors affecting general aviation safety evaluation.
[0020] Specifically, there are numerous evaluation indicators for factors affecting navigation safety. The key is to select the indicators based on their magnitude of influence. The basic principle is to describe the actual situation of navigation safety in coastal waters using as few main evaluation indicators as possible.
[0021] In some embodiments, Figure 2 This is a schematic diagram of a set of influencing factors provided in an embodiment of the present invention. See also... Figure 2 The analysis of factors affecting navigation safety includes three categories: natural conditions, transportation conditions, and marine hydrological and meteorological conditions.
[0022] Among the natural conditions in coastal waters, factors such as seabed topography, anchorage, waterways, restricted areas, and water depth have a significant impact on navigation safety. These factors have multifaceted effects on navigation safety and are directly related to the safety and efficiency of ships during navigation.
[0023] (1) Seafloor topography Seafloor topography is a significant factor affecting navigation safety. Complex topography increases the difficulty and risk of ship navigation. For example, narrow straits, shoals, and reef areas can restrict ship maneuverability, increasing the risk of collisions and grounding. Furthermore, topography can influence ocean currents and tides, further increasing the uncertainty of navigation.
[0024] (2) Anchorage Anchorages are crucial areas for ships to moor and wait, directly impacting navigational safety. Anchored vessels, during weighing anchor, shifting berths, or encountering severe weather, may collide with other vessels in the channel due to improper maneuvering or equipment malfunction. When large vessels are anchored, their superstructures and masts may obstruct the view of other ships, especially at channel intersections or bends, increasing navigational difficulty and collision risk.
[0025] (3) Waterway Waterways are channels through which ships navigate, and their width, depth, and curvature directly affect navigational safety. Narrow or curved waterways restrict a ship's maneuverability, increasing the risk of collisions and grounding. Curved waterways increase the difficulty of ship maneuvering, as ships need to constantly change course to adapt to changes in the water flow. In addition, obstacles and shoals in the waterway can also pose threats to navigational safety.
[0026] (4) Restricted area Restricted areas typically refer to areas where vessel passage is restricted due to special reasons (such as underwater construction). The existence of restricted areas increases the complexity of navigation, requiring vessels to either avoid or follow specific rules when passing through them. Restricted areas limit a vessel's navigation space, increasing the difficulty of maneuvering and the risk of collision during navigation.
[0027] (5) Water depth Water depth is a key factor affecting navigation safety. Excessively shallow water can lead to ships running aground or striking the bottom. When water is shallow, it increases drag, affecting rudder effectiveness and maneuverability, thus increasing navigational risks, especially in shallow waters where the shallow-water effect is significant, increasing the ship's sinking and the probability of grounding or striking the bottom. Excessively deep water, on the other hand, can increase navigation uncertainty and risk. Therefore, regular water depth measurements and updates are necessary to account for the impact of factors such as changes in seabed topography.
[0028] Among the traffic conditions, high traffic volume and high ship density increase the frequency of encounters and the risk of collisions between ships. Ships traveling too fast or too slow may pose a threat to navigation safety. The completeness of navigation aids directly affects a ship's positioning, navigation, and collision avoidance capabilities, playing a crucial role in navigation safety.
[0029] (1) Traffic flow Traffic flow refers to the number of vessels passing through a specific body of water per unit of time. As traffic flow increases, the density of vessels within the waterway increases, leading to a higher frequency of encounters between vessels. This increases the risk of collisions, overtaking, and cross-traffic encounters, posing a direct threat to navigation safety. High traffic flow can also cause channel congestion, reducing vessel navigation efficiency and further exacerbating safety risks.
[0030] (2) Ship density Ship density refers to the number of ships per unit area of water. Excessive ship density means that the distance between ships in the water is reduced, increasing mutual influence between ships, raising the risk of collisions, affecting maneuverability, and reducing collision avoidance capabilities. In narrow channels or complex waterways, excessively high ship density poses a significant threat to navigation safety.
[0031] (3) Ship speed Maintaining a reasonable speed not only improves a ship's navigation efficiency but also provides sufficient maneuverability and time in emergencies. Excessive speed, however, can increase the risk of loss of control, especially in complex waters or adverse weather conditions. Too high a speed may make it difficult for the ship to effectively avoid collisions or respond to emergencies, and it can also cause unnecessary disturbance to the surrounding waters, affecting the navigational safety of other vessels.
[0032] (4) Navigation aids Navigational aids, including lighthouses, buoys, and navigation marks, provide ships with vital information for positioning, navigation, and collision avoidance. Well-maintained navigational aids significantly improve navigational safety. Lighthouses and buoys guide ships through channels and help them avoid shoals and reefs, while radar transponders provide accurate positioning information in adverse weather or at night. Damage or absence of navigational aids greatly hinders navigation and increases the risk of collisions and grounding.
[0033] Marine hydrometeorological conditions have multifaceted impacts on navigation safety, with wind, waves, currents, and tides being particularly significant. Strong winds and large waves can easily lead to loss of vessel control, increasing the risk of collisions and capsizing. Changes in ocean currents can cause vessels to deviate from their course, while sea fog and other weather conditions reduce visibility, increasing navigational difficulty and the risk of accidents. Accurate prediction and timely response to changes in marine hydrometeorological conditions are crucial for ensuring navigation safety.
[0034] (1) Wind Wind is a significant factor affecting navigation safety. Strong winds can cause ships to roll violently, increasing the difficulty of maneuvering and even causing them to deviate from their intended course. In extreme wind conditions, ships may face the risk of losing control, seriously threatening navigation safety. Furthermore, changes in wind direction can also adversely affect ship navigation, especially in narrow channels or complex waters, where sudden changes in wind direction can lead to collisions with surrounding obstacles.
[0035] (2) Waves The size and period of ocean waves are crucial to the safe navigation of ships. Waves not only increase drag and reduce speed, but can also cause severe pitching and rolling, affecting stability. Under extreme wave conditions, ships may even face the risk of capsizing. Furthermore, waves can influence a ship's course, causing it to deviate from its intended route.
[0036] (3) Ocean current Ocean currents are a crucial factor affecting ship navigation safety. The direction and speed of ocean currents can cause current-induced drift, requiring ships to adjust their course and speed promptly according to current conditions to maintain course stability. In complex waters or narrow channels, changes in ocean currents are more pronounced, and their impact on ship navigation safety is even greater.
[0037] (4) Tides The impact of tides on navigation safety is mainly reflected in changes in water level. The rise and fall of tides cause changes in channel depth, thus affecting the navigational capacity of ships. In shallow waters or narrow channels, the impact of tides is particularly significant, potentially leading to grounding accidents. Furthermore, tides can also affect water flow, thereby impacting the safety of ships entering and leaving port. Ships need to closely monitor tidal changes during navigation, rationally plan their voyages, and ensure navigation under suitable tidal conditions.
[0038] (5) Sea fog Sea fog and other weather phenomena reduce visibility, increasing the risk of collisions. In poor visibility conditions, ships need to slow down and rely on navigation equipment such as radar to ensure safe navigation. Low visibility significantly limits the visual range of ship operators, making it difficult for ships to detect nearby vessels, objects, and navigational aids in a timely manner, thus increasing the risk of collisions, groundings, and other accidents. In low-visibility environments, ships rely on navigation equipment such as radar and AIS, but the accuracy and reliability of these devices may be limited, and they cannot completely replace visual lookout. Furthermore, low visibility can also affect the propagation of radio waves and acoustic signals, further increasing the difficulty of navigation.
[0039] In summary, the set of factors influencing general aviation safety evaluation constructed in this embodiment includes: Seabed topography, anchorages, channels, restricted areas, water depth, traffic flow, vessel density, vessel speed, navigation aids, wind, waves, currents, tides, and sea fog.
[0040] S2. Define the corresponding evaluation factors based on the set of factors affecting general aviation safety evaluation, and obtain the set of evaluation factors.
[0041] In some embodiments, Figure 3 This is a schematic diagram of an evaluation factor set provided in an embodiment of the present invention. See also... Figure 3 Taking into account environmental factors such as natural conditions, transportation conditions, and marine hydrological and meteorological conditions in coastal waters, key influencing factors are determined. The set of evaluation factors constructed in this embodiment includes: The topographic relief of the seabed, the anchorage density of anchorages, the width of the channel, the area ratio of the restricted area, the water depth, traffic flow, ship density, the average ship speed, the number of navigation aids, the average wind speed, the average wave height, the average current speed, the tidal range, and the annual number of sea fogs.
[0042] S3. Divide the target area into several grid units and collect the real-time parameters of each evaluation factor in the evaluation factor set within each grid unit.
[0043] S4. Based on the preset risk quantification criteria of each evaluation factor and the real-time parameters of each evaluation factor, calculate the membership set of each evaluation factor in each grid cell through the membership function.
[0044] In some embodiments, S4 includes the following sub-steps: S41. Divide each evaluation factor into 5 risk levels: low, lower, medium, higher, and high, and define the quantitative value range corresponding to each risk level of each evaluation factor.
[0045] For example, suppose the quantification of terrain relief is as follows: The terrain relief is less than 2, and the danger level is "low". The terrain relief is ∈ [2,4), and the danger level is "low". The terrain relief is ∈ [4,7), and the danger level is "medium"; The terrain relief is ∈ [7,9), and the danger level is "high". The terrain relief is ≥9, and the danger level is "high".
[0046] S42. Determine the risk level of each evaluation factor based on the range of quantified values and the real-time parameters of each evaluation factor.
[0047] S43. Determine whether the risk level of the evaluation factor is low or high.
[0048] If the risk level of the evaluation factor is low or high, then the membership set of the evaluation factor is (1,0,0,0,0) or (0,0,0,0,1). Otherwise, determine the closest adjacent hazard level based on the real-time parameters of the evaluation factor and the hazard level to which the evaluation factor belongs, and execute S44.
[0049] For example, if the real-time parameter of the terrain undulation of a certain grid cell is 6, then the hazard level of the terrain undulation of that grid cell is "medium". The value range of the hazard level "medium" is [4,7), and the median value of the hazard level "medium" is 5.5. The hazard levels adjacent to "medium" include "lower" and "higher". If the real-time parameter is less than 5.5, the nearest adjacent hazard level is "lower". If the real-time parameter is greater than 5.5, the nearest adjacent hazard level is "higher". If the real-time parameter is equal to 5.5, then either "lower" or "higher" is selected as the nearest adjacent hazard level. Since the real-time parameter of the terrain undulation in this example is 6, the nearest adjacent hazard level is "higher".
[0050] S44. Based on the hazard level to which the evaluation factor belongs and the range of quantified values corresponding to adjacent hazard levels, calculate the membership set of the evaluation factor using the membership function. In some embodiments, the triangular membership function can be used to calculate the membership set of the evaluation factors, and the calculation formula is as follows: ; Among them, f i (x,a,b,c) represents the membership degree of the i-th evaluation factor to its hazard level and adjacent hazard levels, a represents the lower limit of the quantitative value range corresponding to the hazard level to which the evaluation factor belongs, b represents the upper limit of the quantitative value range corresponding to the hazard level to which the evaluation factor belongs, c represents the upper limit of the quantitative value range corresponding to adjacent hazard levels, and x represents the real-time parameter of the evaluation factor.
[0051] In some embodiments, Gaussian membership functions, sigmoid membership functions, and linear membership functions can also be selected to calculate the membership set of evaluation factors by choosing an appropriate membership function.
[0052] The membership set of the 14 evaluation factors for each grid cell is solved sequentially. For example, as shown in Table 15, it is the table of evaluation factor quantification value (i.e., real-time parameter) calculation and membership set of a certain grid cell in this embodiment.
[0053] Table 15 Calculation of Evaluation Factor Quantitative Values and Membership Degree Sets S5. Construct the fuzzy relation matrix of each grid cell based on the membership degree set of each evaluation factor.
[0054] In some embodiments, the fuzzy relation matrix is expressed as follows: ; Where R represents the fuzzy relation matrix of a certain grid cell, m represents the total number of evaluation factors (m=14), n represents the total number of hazard levels (n=5), and R1, R2, ..., R m Let r represent the membership sets of the 1st, 2nd, ..., mth evaluation factors, respectively. mn This represents the membership value of the m-th evaluation factor to the n-th hazard level.
[0055] For example, based on the data in Table 15, the fuzzy relation matrix R of a certain grid cell can be obtained as follows: .
[0056] S6. Construct a judgment matrix based on the preset scaling values between each evaluation factor, and obtain the weight vector of the evaluation factor based on the judgment matrix.
[0057] In some embodiments, S6 includes the following sub-steps: S61. Construct a judgment matrix based on the preset scaling values between each evaluation factor.
[0058] In some embodiments, the preset scaling values between the evaluation factors are set according to the actual situation, and the expression of the judgment matrix U is as follows: U=[a ij ]; Right now ; Among them, a ij Let represent the preset scale value of the i-th evaluation factor relative to the j-th evaluation factor, where i∈[1,m], j∈[1,m], and m represents the total number of evaluation factors, and satisfy a ij ×a ji =1, determines if all diagonal elements of the matrix are 1.
[0059] Furthermore, a consistency test is performed on the judgment matrix, calculating the consistency index (CI) and the consistency ratio (CR). The CI value reflects the degree of consistency of the judgment matrix. The smaller the CI value, the better the consistency of the judgment matrix, meaning the logical relationships between the elements in the matrix are more reasonable; conversely, the larger the CI value, the worse the consistency, and there may be logical contradictions or inconsistencies. The formula for calculating the consistency index CI is as follows: CI=(λ max -m) / (m-1); Where, λ max denoted by , where m represents the largest eigenvalue of the judgment matrix, and m represents the total number of evaluation factors, which is also the order of the judgment matrix.
[0060] To further determine whether the consistency of the judgment matrix is acceptable, an average random consistency index (RI) is introduced, and the consistency ratio (CR), i.e., the ratio of CI to RI, is calculated. The value of RI is derived from references and increases with the matrix order. When CR is less than 0.1, subsequent steps are performed; otherwise, the judgment matrix needs to be corrected, i.e., the preset scaling values between each evaluation factor are adjusted until the consistency requirements are met.
[0061] S62. Normalize the elements of each column of the judgment matrix to obtain the normalized judgment matrix.
[0062] In some embodiments, the normalization of the judgment matrix can be performed using methods such as the sum-product method, the square root method, or the eigenvalue method. In this embodiment, the sum-product method is used, that is, the elements of each column of the judgment matrix are normalized to obtain the normalized judgment matrix. The calculation formula is as follows: ; Among them, a ij ' represents the normalized scale value of the i-th evaluation factor relative to the j-th evaluation factor. The normalized judgment matrix is obtained based on the normalized scale value of the i-th evaluation factor relative to the j-th evaluation factor.
[0063] S63. Obtain the row sum vector by summing the rows of the normalized judgment matrix.
[0064] In some embodiments, the calculation formula is as follows: ; Among them, w i ' represents the vector that determines the row sum of the i-th row of the matrix.
[0065] S64. Normalize the rows and vectors to obtain the weight vector of the evaluation factors.
[0066] In some embodiments, the calculation formula is as follows: ; Among them, w i Let represent the normalized row sum vector of the i-th evaluation factor.
[0067] Based on the normalized row sum vector of each evaluation factor, the weight vector w of the evaluation factor is obtained, as exemplarily shown below: .
[0068] S7. Perform fuzzy operations on the fuzzy relation matrix and weight vector of each grid cell to generate the fuzzy evaluation results of each grid cell.
[0069] In some embodiments, the calculation formula for fuzzy computation is as follows: B=w T ×R; Where B represents the fuzzy evaluation result of a certain grid cell, w represents the weight vector, R represents the fuzzy relation matrix of the grid cell, and T represents the transpose matrix.
[0070] For example, the calculation formula for the fuzzy evaluation result of a certain grid cell in this embodiment is as follows: .
[0071] S8. The comprehensive safety risk value of each grid unit is obtained by weighting and summing the fuzzy evaluation results of each grid unit with the preset risk level weights.
[0072] In some embodiments, the preset hazard level weight can be [1,2,3,4,5] corresponding to [low, lower, medium, higher, high].
[0073] For example, in this embodiment, the comprehensive security risk value of a certain grid cell is: 0.529×1+0.244×2+0.061×3+0.135×4+0.031×5=1.895.
[0074] S9. The risk level of each grid cell is obtained by comparing the comprehensive safety risk value with the preset risk level assignment.
[0075] In some embodiments, the preset hazard level can be assigned as [1,2,3,4,5] corresponding to [low, lower, medium, higher, high].
[0076] In some embodiments, the hazard level closest to the comprehensive safety risk value is assigned as the hazard level of the grid cell.
[0077] For example, if the overall safety risk value of a certain grid cell is 1.895, and the hazard level closest to the overall safety risk value of this grid cell is assigned a value of 2, which is "lower", then the hazard level of this grid cell is "lower".
[0078] Furthermore, in some embodiments, it may also include: generating a dynamic risk color map based on a preset mapping relationship between hazard level and color, and displaying the hazard level of each grid unit in the target area.
[0079] For example, in this embodiment, the evaluation and calculation of several grid cells in the target area are performed on an hourly basis, and the risk of each grid is determined according to five levels: low, lower, medium, higher, and high, thereby determining the hazard level of the dynamic grid. In practical applications, a computer system is used to calculate the hazard level over different time spans.
[0080] Using the three-hour period from 7:00 to 9:00 on April 11, 2022 as a time unit, the grid cell numbers were recorded. The quantitative values of evaluation factors such as topographic relief, anchorage density, channel width, area percentage, water depth, traffic flow, vessel density, average speed, number of navigation aids, average wind speed, average wave height, average current velocity, variation range, and annual sea fog number were calculated sequentially. This process further formed a membership set and constructed a fuzzy relation matrix for each grid. The grid evaluation results were then calculated based on the derived weight vectors. Figure 4 This is a schematic diagram illustrating the evaluation calculation results of all grids in a coastal water area at a single moment, provided by an embodiment of the present invention.
[0081] Similarly, using the time series from April 10th to 20th, 2022 as the axis and 3 hours as the time unit, the evaluation results of a grid at 88 moments in this time series were calculated, and the results are as follows. Figure 5 This is a schematic diagram illustrating the evaluation calculation results of a single grid in a coastal water area at different times, provided by an embodiment of the present invention.
[0082] Furthermore, Figure 6 This is a dynamic risk color map of coastal waters provided in an embodiment of the present invention. See also: Figure 6 Based on the evaluation results and risk levels calculated above, spatial graphics and attribute data are linked and assigned values through the grid cell sequence number. The grid color classification is set according to the risk level to obtain the geospatial risk five-color thematic map of the sea area grid.
[0083] This invention addresses the problem of single evaluation dimensions in traditional methods by constructing a multi-level evaluation factor system that comprehensively considers multiple influencing factors such as topography, hydrology, transportation, and environment. It employs membership functions to quantify the fuzzy characteristics of evaluation factors and combines this with a dynamic risk level classification mechanism to achieve a scientific characterization of the uncertainties in complex marine environments. By introducing a judgment matrix to determine factor weights, it reduces subjective judgment bias and ensures the objectivity of the evaluation results. A dynamic risk map is generated based on the calculation of the fuzzy relation matrix and weight vector, intuitively displaying the risk level distribution in different areas and providing real-time visual decision support for ship navigation path planning and maritime supervision. Based on grid management and fuzzy comprehensive evaluation technology, this invention effectively improves the accuracy and timeliness of navigation safety assessment by dividing coastal waters into fine grid units and combining real-time data acquisition with a dynamic risk assessment model.
[0084] This invention also provides a grid-based coastal waterway navigation safety early warning system for executing the aforementioned grid-based coastal waterway navigation safety early warning method. Figure 7 This is a schematic diagram of a grid-based coastal waterway navigation safety early warning system provided in an embodiment of the present invention. See also... Figure 7The system includes the following modules: The evaluation factor determination module is used to analyze the factors affecting general aviation safety, construct a set of factors affecting general aviation safety evaluation, and define corresponding evaluation factors based on the set of factors affecting general aviation safety evaluation to obtain a set of evaluation factors. The data acquisition module, connected to the evaluation factor determination module, is used to divide the target area into several grid units and collect the real-time parameters of each evaluation factor in the evaluation factor set within each grid unit. The membership calculation module, connected to the data acquisition module, is used to calculate the membership set of each evaluation factor in each grid cell by means of the membership function, based on the preset risk quantification criteria of each evaluation factor and the real-time parameters of each evaluation factor. The matrix calculation module, connected to the membership calculation module, is used to construct the fuzzy relation matrix of each grid cell based on the membership set of each evaluation factor. The weight calculation module, connected to the evaluation factor determination module, is used to construct a judgment matrix based on the preset scale values between each evaluation factor, and to obtain the weight vector of the evaluation factor based on the judgment matrix. The fuzzy calculation module, connected to the matrix calculation module and the weight calculation module, is used to perform fuzzy operations on the fuzzy relation matrix and weight vector of each grid cell to generate the fuzzy evaluation results of each grid cell. The risk value calculation module, connected to the fuzzy calculation module, is used to perform weighted summation based on the fuzzy evaluation results of each grid cell and the preset hazard level weights to obtain the comprehensive safety risk value of each grid cell. The output module, connected to the risk value calculation module, is used to compare the comprehensive safety risk value with the preset hazard level assignment to obtain the hazard level of each grid cell.
[0085] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the technical solutions of the embodiments of the present invention.
Claims
1. A grid-based early warning method for navigation safety in coastal waters, characterized in that, The method includes the following steps: S1. Analyze the factors affecting general aviation safety and construct a set of factors affecting general aviation safety evaluation; S2. Define the corresponding evaluation factors based on the set of factors affecting general aviation safety evaluation, and obtain the set of evaluation factors; S3. Divide the target area into several grid units and collect the real-time parameters of each evaluation factor in the set of evaluation factors in each grid unit. S4. Based on the preset risk quantification criteria of each evaluation factor and the real-time parameters of each evaluation factor, calculate the membership set of each evaluation factor in each grid cell through the membership function. S5. Construct the fuzzy relation matrix for each grid cell based on the membership degree set of each evaluation factor; S6. Construct a judgment matrix based on the preset scaling values between each evaluation factor, and obtain the weight vector of the evaluation factor based on the judgment matrix; S7. Perform fuzzy operations on the fuzzy relation matrix of each grid cell and the weight vector to generate fuzzy evaluation results for each grid cell; S8. The comprehensive safety risk value of each grid cell is obtained by weighting and summing the fuzzy evaluation results of each grid cell with the preset risk level weights. S9. The risk level of each grid cell is obtained by comparing the comprehensive safety risk value with the preset risk level assignment.
2. The grid-based coastal waterway navigation safety early warning method according to claim 1, characterized in that, In S1, the set of factors influencing navigation safety evaluation includes: Seabed topography, anchorages, channels, restricted areas, water depth, traffic flow, vessel density, vessel speed, navigation aids, wind, waves, currents, tides, and sea fog.
3. The grid-based coastal waterway navigation safety early warning method according to claim 2, characterized in that, In S2, the evaluation factors corresponding to the set of factors affecting navigation safety evaluation include: The topographic relief of the seabed, the anchorage density of anchorages, the width of the channel, the area ratio of the restricted area, the water depth, traffic flow, ship density, the average ship speed, the number of navigation aids, the average wind speed, the average wave height, the average current speed, the tidal range, and the annual number of sea fogs.
4. The grid-based coastal waterway navigation safety early warning method according to claim 1, characterized in that, In step S4, based on the preset hazard quantification criteria for each evaluation factor and the real-time parameters of each evaluation factor, the membership set of each evaluation factor for each grid cell is calculated using a membership function, including: S41. Divide each evaluation factor into 5 risk levels: low, lower, medium, higher, and high, and define the quantitative value range corresponding to each risk level of each evaluation factor. S42. Determine the risk level of each evaluation factor based on the range of quantified values and the real-time parameters of each evaluation factor; S43. Determine whether the risk level of the evaluation factor is low or high; If the risk level of the evaluation factor is low or high, then the membership set of the evaluation factor is (1,0,0,0,0) or (0,0,0,0,1). Otherwise, determine the closest adjacent hazard level based on the real-time parameters of the evaluation factor and the hazard level to which the evaluation factor belongs, and execute S44; S44. Based on the hazard level to which the evaluation factor belongs and the range of quantified values corresponding to adjacent hazard levels, calculate the membership set of the evaluation factor using a membership function.
5. The grid-based coastal waterway navigation safety early warning method according to claim 4, characterized in that, In step S44, based on the hazard level to which the evaluation factor belongs and the quantification value range corresponding to adjacent hazard levels, the membership set of the evaluation factor is calculated using a membership function. The calculation formula is as follows: ； Among them, f i (x,a,b,c) represents the membership degree of the i-th evaluation factor to its hazard level and adjacent hazard levels, a represents the lower limit of the quantitative value range corresponding to the hazard level to which the evaluation factor belongs, b represents the upper limit of the quantitative value range corresponding to the hazard level to which the evaluation factor belongs, c represents the upper limit of the quantitative value range corresponding to adjacent hazard levels, and x represents the real-time parameter of the evaluation factor.
6. The grid-based coastal waterway navigation safety early warning method according to claim 5, characterized in that, In step S6, a judgment matrix is constructed based on the preset scaling values between each evaluation factor, and the weight vector of the evaluation factor is obtained based on the judgment matrix, including: S61. Construct a judgment matrix based on the preset scaling values between each evaluation factor; The expression for the judgment matrix U is as follows: U=[a ij ]; Among them, a ij Let represent the preset scale value of the i-th evaluation factor relative to the j-th evaluation factor, where i∈[1,m], j∈[1,m], and m represents the total number of evaluation factors, and satisfy a ij ×a ji =1; S62. Normalize each column element of the judgment matrix to obtain a normalized judgment matrix; S63. Obtain the row sum vector by summing the rows of the normalized judgment matrix; S64. Normalize the rows and vectors to obtain the weight vector of the evaluation factors.
7. A grid-based coastal waterway navigation safety early warning method according to claim 6, characterized in that, In step S9, the risk level of each grid cell is obtained by comparing the comprehensive safety risk value with the preset risk level assignment, including: The hazard level closest to the comprehensive safety risk value is assigned as the hazard level of the grid cell.
8. The grid-based coastal waterway navigation safety early warning method according to claim 1, characterized in that, Following S9, the method further includes: generating a dynamic risk color map based on a preset mapping relationship between hazard level and color, and displaying the hazard level of each grid unit in the target area.
9. A grid-based coastal waterway navigation safety early warning system, used to execute the grid-based coastal waterway navigation safety early warning method according to any one of claims 1-8, characterized in that, The system includes the following modules: The evaluation factor determination module is used to analyze the factors affecting general aviation safety, construct a set of factors affecting general aviation safety evaluation, and define corresponding evaluation factors based on the set of factors affecting general aviation safety evaluation to obtain a set of evaluation factors. The data acquisition module, connected to the evaluation factor determination module, is used to divide the target area into several grid units and collect the real-time parameters of each evaluation factor in the evaluation factor set within each grid unit. The membership calculation module, connected to the data acquisition module, is used to calculate the membership set of each evaluation factor in each grid cell by means of the membership function, based on the preset risk quantification criteria of each evaluation factor and the real-time parameters of each evaluation factor. The matrix calculation module, connected to the membership calculation module, is used to construct the fuzzy relation matrix of each grid cell based on the membership set of each evaluation factor. The weight calculation module, connected to the evaluation factor determination module, is used to construct a judgment matrix based on the preset scaling values between each evaluation factor, and to obtain the weight vector of the evaluation factor based on the judgment matrix. The fuzzy calculation module, connected to the matrix calculation module and the weight calculation module, is used to perform fuzzy operations on the fuzzy relation matrix of each grid cell and the weight vector to generate fuzzy evaluation results for each grid cell. The risk value calculation module, connected to the fuzzy calculation module, is used to perform a weighted summation based on the fuzzy evaluation results of each grid cell and the preset hazard level weights to obtain the comprehensive safety risk value of each grid cell. The output module, connected to the risk value calculation module, is used to compare the comprehensive safety risk value with the preset hazard level assignment to obtain the hazard level of each grid unit.