Ship navigation meteorological disaster risk forecasting method and device

Abstract

The invention discloses a ship navigation meteorological disaster risk forecasting method and device, relates to the technical field of marine traffic meteorological influence forecasting, and aims to solve the technical problem of poor pertinence of ship navigation meteorological disaster risk forecasting. The method comprises the following steps: acquiring hydro-meteorological forecast data of a target area; the hydrometeorological forecast data is real-time dynamically updated meteorological element forecast for a future time period; obtaining a ship navigation comprehensive risk evaluation model which is constructed in advance based on target factors at least including hydro meteorology, channel natural environment and navigation capability; based on the hydrometeorological forecast data of the target area, utilizing the ship navigation comprehensive risk evaluation model to carry out rolling forecast on the meteorological disaster risk of ship navigation of the target area; the meteorological disaster risks at least comprise main meteorological disasters influencing ship navigation, risk levels and risk probabilities; and the pertinence of ship navigation meteorological disaster risk forecasting service is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of forecasting meteorological impact on marine traffic, in particular to a method and device for forecasting meteorological disaster risk for ship navigation. Background Art

[0002] Severe weather such as sea fog, strong winds, and large waves have a direct impact on the safety of port ship navigation. The complex natural environment of the waterway, the ever-expanding port operation scale and navigation capacity have further increased the impact and sensitivity of meteorological factors on the safety of port ship navigation. Under the same weather conditions, different ports, waterways, and ships have different resistance capabilities, which determines that different risk defense measures need to be taken in the face of the same weather, which brings greater challenges to the forecast of ship navigation risks.

[0003] At present, the meteorological risk forecasting and warning technology for maritime transportation mainly focuses on meteorological element forecasting and risk level threshold research. There is very little research on comprehensive risk forecasting technology of meteorological disasters based on industry impact. There are many technologies based on fuzzy comprehensive evaluation method to judge port safety risks, navigation environment safety, etc., but they have not been applied in meteorological disaster risk forecasting.

[0004] In view of this, there is an urgent need for more advanced methods for forecasting the risk of meteorological disasters for ship navigation, which should take into account risk factors in more dimensions, so as to improve the pertinence and practicality of the forecast of the risk of meteorological disasters for ship navigation and solve the problem that the existing marine traffic meteorological forecasting technology cannot be directly applied to the forecast of the risk of meteorological disasters for ship navigation. Summary of the invention

[0005] The purpose of the present invention is to provide a method and device for forecasting the risk of meteorological disasters for ship navigation, by using an evaluation model that takes into account risk factors such as meteorological factors, natural environment of the waterway and navigability, and combining the hydrological and meteorological forecast data of the target area, to make a rolling forecast of the risk of meteorological disasters for ship navigation in the target area, thereby improving the pertinence and practicality of the forecast of the risk of meteorological disasters for ship navigation; and overcoming the problem that the existing marine traffic meteorological forecast technology cannot be directly applied to the forecast of the risk of meteorological disasters for ship navigation.

[0006] In order to achieve the above object, the present invention provides the following technical solutions: In a first aspect, the present invention provides a method for forecasting meteorological disaster risks for ship navigation, which may include: Obtaining hydrological and meteorological forecast data for the target area; the hydrological and meteorological forecast data is a real-time and dynamically updated forecast of meteorological elements for future periods; Obtaining a pre-built comprehensive risk assessment model for ship navigation; the comprehensive risk assessment model for ship navigation is an assessment model constructed based on target factors including at least hydrological and meteorological factors, natural environment of the waterway, and navigability; Based on the hydrological and meteorological forecast data of the target area, the comprehensive risk assessment model for ship navigation is used to make a rolling forecast of the meteorological disaster risk for ship navigation in the target area; the meteorological disaster risk at least includes the main meteorological disasters affecting ship navigation, risk level and risk probability.

[0007] Preferably, before obtaining the pre-built ship navigation comprehensive risk assessment model, the following steps may be included: Constructing the comprehensive risk assessment model for ship navigation; The constructing of the comprehensive risk assessment model for ship navigation comprises: Acquire multi-source data on ship navigation, wherein the multi-source data at least includes hydrological and meteorological data, waterway natural environment data, and industry data of ports and port areas; Based on the multi-source data, a comprehensive risk assessment index system for target indicators of ship navigation risk is established; the target indicators at least include hydrological meteorology, natural environment of the waterway and navigation capacity; the comprehensive risk assessment index system includes an indicator layer, a criterion layer and a target layer; Based on the comprehensive risk assessment indicator system, combined with a preset indicator evaluation mechanism, a target evaluation indicator weight set is established; the preset indicator evaluation mechanism at least includes a preset scoring method and a trigonometric function fuzzy number method; According to the target evaluation index weight set, the comprehensive risk evaluation index system and the target meteorological threshold index, the fuzzy membership comprehensive evaluation method is used to establish the comprehensive risk evaluation model for ship navigation.

[0008] Preferably, the target layer is a comprehensive risk index evaluation layer; the indicators in the criterion layer may include hydrological and meteorological indicators, waterway natural environment indicators and navigation capacity indicators; The indicators in the indicator layer are sub-indicators of each indicator in the criterion layer; the sub-indicators of the hydrological and meteorological indicators may include wind force, visibility, waves and short-term heavy rainfall; the sub-indicators of the waterway natural environment indicators may include the ratio of ship length to channel width, the ratio of channel water depth to ship draft, channel length and navigation grade; the sub-indicators of the navigation capacity indicators may include cargo throughput, number of berths and dock length.

[0009] Preferably, the establishment of a target evaluation indicator weight set based on the comprehensive risk evaluation indicator system and in combination with a preset indicator evaluation mechanism may include: Based on the preset scoring method, a first determination matrix of the importance of the indicator layer relative to the criterion layer and a second determination matrix of the importance of the criterion layer relative to the target layer are constructed; the first determination matrix includes a determination matrix for the hydrological and meteorological criterion layer, a determination matrix for the waterway natural environment criterion layer and a determination matrix for the navigability criterion layer; the first determination matrix is ​​used to indicate the importance of the sub-indicators of each indicator in the criterion layer relative to each indicator; the second determination matrix is ​​used to indicate the importance of each indicator in the criterion layer relative to the target layer; Using the trigonometric function fuzzy number method, the fuzzy comprehensive degree of each indicator in the first determination matrix and the second determination matrix at its layer is obtained to obtain the fuzzy comprehensive degree data of each indicator; Based on the fuzzy comprehensive degree data of each indicator, the possibility matrix of each layer is constructed; Based on the possibility matrix of each layer, the indicator weight corresponding to each indicator in each layer is calculated to obtain the target evaluation indicator weight set.

[0010] Preferably, the construction of the possibility matrix of each layer based on the fuzzy comprehensive degree data of each indicator may include: Using the formula: ; Calculate the possibility of comparing two indicators; among them, Indicates the possibility of index i and index j, represents the fuzzy comprehensive degree of index i, Represents the fuzzy comprehensiveness of index j; Using the formula: ; Construct the possibility matrix of each layer; among them, Represents the possibility matrix of each layer, Indicates the fuzzy comprehensiveness of index 1, Indicates the fuzzy comprehensive degree of index 2, Represents the fuzzy comprehensive degree of index n.

[0011] Preferably, the establishment of the ship navigation comprehensive risk assessment model by using the fuzzy membership comprehensive evaluation method according to the target evaluation index weight set, the comprehensive risk assessment index system and the target meteorological threshold index may include: Establishing a membership function model of preset indicator levels; the preset indicator levels may include at least a minor risk level, a general risk level, a major risk level, a significant risk level, and a very major risk level; Using the membership function model, the membership vector of each indicator level is calculated; According to the membership vector of each indicator level, combined with the target evaluation indicator weight set, the comprehensive risk evaluation indicator system and the target meteorological threshold indicator, an evaluation vector of the indicator layer relative to the criterion layer is established to obtain an evaluation vector of the criterion layer; Based on the evaluation vector of the criterion layer, in combination with the target evaluation index weight set, the comprehensive risk evaluation index system and the target meteorological threshold index, an evaluation vector of the criterion layer relative to the target layer is established to obtain an evaluation vector of the target layer; Determining a meteorological disaster risk assessment value based on the assessment vector of the target layer; Based on the value range of the meteorological disaster risk assessment value, construct an objective function for meteorological disaster risk probability forecasting within the value range; and use the objective function as a meteorological disaster risk probability forecasting function of the comprehensive risk assessment model for ship navigation; Based on the objective function and the meteorological disaster risk assessment value, the comprehensive risk assessment model for ship navigation is established.

[0012] Preferably, determining the meteorological disaster risk assessment value based on the assessment vector of the target layer may include: Using the formula: ; The meteorological disaster risk assessment value is calculated; among them, Indicates the meteorological disaster risk assessment value, Indicates the rating level, Represents the matrix transpose of the target layer evaluation vector.

[0013] Preferably, constructing the objective function of the meteorological disaster risk probability forecast within the value range based on the value range of the meteorological disaster risk assessment value may include: Using the formula: ; Constructing an objective function for the probability forecast of meteorological disaster risk within the value range, the function is a monotonically increasing binary linear compression function; wherein Indicates the probability of meteorological disaster risk, Represents any value within the range of meteorological disaster risk assessment values.

[0014] Preferably, the acquisition of multi-source data on ship navigation may include: Obtaining hydrological and meteorological data for a target period from a meteorological big data cloud platform, wherein the hydrological and meteorological data include smart grid data for the responsible sea area and smart grid data for the land surface; the smart grid data for the responsible sea area at least includes visibility forecast data, 10-meter wind speed forecast data, and wave height forecast data for the responsible sea area; the smart grid data for the land surface at least includes short-term heavy rainfall data; Acquire the natural environment data of the waterway from the data management center of the Port and Shipping Administration; the natural environment data of the waterway at least includes the length of the waterway, the energy level, the water depth of the waterway and the width of the waterway; The industrial data of ports and port areas are obtained from the Data Management Center of the National Statistical Yearbook Office; the industrial data of ports and port areas at least include cargo throughput, number of berths and length of wharf.

[0015] In a second aspect, the present invention provides a device for forecasting meteorological disaster risks for ship navigation, which may include: A first acquisition module, the first acquisition module is used to acquire hydrological and meteorological forecast data of the target area; the hydrological and meteorological forecast data is a real-time and dynamically updated forecast of meteorological elements for a future period; A second acquisition module, the second acquisition module is used to acquire a pre-built ship navigation comprehensive risk assessment model; the ship navigation comprehensive risk assessment model is an assessment model constructed based on target factors including at least hydrological and meteorological factors, natural environment of the waterway, and navigability; A rolling forecast module, which is used to make a rolling forecast of the meteorological disaster risk for ship navigation in the target area based on the hydrological and meteorological forecast data of the target area and using the comprehensive risk assessment model for ship navigation; the meteorological disaster risk at least includes the main meteorological disasters that affect ship navigation, risk levels and risk probabilities.

[0016] Compared with the prior art, the method for forecasting the risk of meteorological disasters for ship navigation provided by the present invention obtains the hydrometeorological forecast data of the target area; the hydrometeorological forecast data is a real-time and dynamically updated forecast of meteorological elements for future time periods; further obtains a pre-constructed comprehensive risk assessment model for ship navigation; the comprehensive risk assessment model for ship navigation is an assessment model constructed based on target factors including at least hydrometeorology, natural environment of the waterway and navigability; finally, based on the hydrometeorological forecast data of the target area, the comprehensive risk assessment model for ship navigation is used to roll the meteorological disaster risk for ship navigation in the target area. The meteorological disaster risk at least includes the main meteorological disasters that affect the navigation of ships, the risk level and the risk probability. Thus, the evaluation model constructed in advance based on the target factors of hydrometeorology, natural environment of the waterway and navigation capacity is used to forecast the meteorological disaster risk of ship navigation in the target area in combination with the hydrometeorological forecast data of the target area. The hydrometeorology, natural environment of the waterway and navigation capacity of the target area are fully considered, which greatly improves the pertinence and practicality of the forecast of meteorological disaster risk of ship navigation. The problem that the existing marine traffic meteorological forecast technology cannot be directly applied to the forecast of meteorological disaster risk of ship navigation is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 A schematic diagram of the main process of the method for forecasting meteorological disaster risks for ship navigation provided by the present invention; Figure 2 A schematic diagram of the main process of constructing a comprehensive risk assessment model for ship navigation in the method for forecasting the risk of meteorological disasters for ship navigation provided by the present invention; Figure 3 A schematic diagram of a three-layer evaluation index system in a comprehensive risk evaluation index system for ship navigation in a method for forecasting meteorological disaster risk for ship navigation provided by the present invention; Figure 4 A schematic diagram of the probability distribution of meteorological disaster risks for ship navigation in the method for forecasting meteorological disaster risks for ship navigation provided by the present invention; Figure 5 This is a schematic diagram of the structure of the device for forecasting meteorological disaster risks for ship navigation provided by the present invention.

[0018] Reference numerals: 310 - target layer, 320 - criterion layer, 330 - indicator layer. DETAILED DESCRIPTION

[0019] In order to facilitate the clear description of the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second" and the like are used to distinguish the same items or similar items with substantially the same functions and effects. For example, the first threshold and the second threshold are only used to distinguish different thresholds, and do not limit their order of precedence. Those skilled in the art can understand that the words "first", "second" and the like do not limit the quantity and execution order, and the words "first", "second" and the like do not necessarily limit them to be different.

[0020] It should be noted that, in the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0021] In the present invention, "at least one" means one or more, and "plurality" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the associated objects in the previous time are in an "or" relationship. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can mean: a, b, c, the combination of a and b, the combination of a and c, the combination of b and c, or the combination of a, b and c, where a, b, c can be single or multiple.

[0022] In the existing technology, the meteorological risk forecasting and warning technology for maritime transportation is mainly based on meteorological element forecasting and risk level thresholds. There are few comprehensive risk forecasting technologies for meteorological disasters that affect the ship navigation industry, such as the natural environment of the waterway and navigation capacity. As a result, this meteorological risk forecasting technology cannot be directly applied to the risk forecasting of meteorological disasters for ship navigation. In other words, if the navigation risk forecast is given by only considering weather factors without considering the natural environment of the waterway and navigation capacity, there will be problems with poor prediction pertinence and practicality.

[0023] In view of this, the present invention provides a method and device for predicting the risk of meteorological disasters for ship navigation, and establishes a comprehensive risk assessment model for ship navigation by considering the comprehensive influencing factors of three factors, namely hydrological meteorology, natural environment of waterways, and navigation capacity, on the safety of ship navigation. By using this model, combined with the hydrological and meteorological forecast data of the target area, a rolling forecast of the meteorological disaster risk for ship navigation in the target area is made, thereby improving the pertinence and practicality of the forecast of meteorological disaster risks for ship navigation.

[0024] Next, the technical solution of the present invention is described in detail with reference to the accompanying drawings: In the first aspect, the present invention provides a method for forecasting the risk of meteorological disasters for ship navigation, please refer to Figure 1 , Figure 1 This is a schematic diagram of the main process of the method for forecasting the risk of meteorological disasters for ship navigation provided by the present invention; the executor of the method is a server or terminal equipped with the method for forecasting the risk of meteorological disasters for ship navigation provided by the present invention, such as a service platform for forecasting the risk of meteorological disasters for ship navigation or a handheld forecaster.

[0025] exist Figure 1 The methods may include: Step 110: Obtain hydrological and meteorological forecast data for the target area; the hydrological and meteorological forecast data is a real-time and dynamically updated forecast of meteorological elements for future time periods.

[0026] In step 110, the hydrological and meteorological forecast data of the target area can be the real-time hydrological and meteorological real-time dynamically updated forecast data released on the meteorological big data cloud platform, or the real-time hydrological and meteorological real-time dynamically updated forecast data released by other official forecast platforms, which has certain pertinence and credibility. It should be noted that the dynamic update forecast of hydrological and meteorological elements includes hydrological and meteorological elements such as smart grid strong winds, visibility, waves, and short-term heavy rainfall.

[0027] Step 120: Obtain a pre-constructed comprehensive risk assessment model for ship navigation; the comprehensive risk assessment model for ship navigation is an assessment model constructed based on target factors including at least hydrological and meteorological factors, natural environment of the waterway, and navigability.

[0028] In step 120, a pre-constructed comprehensive risk assessment model for ship navigation is obtained; the model is an evaluation model constructed based on target factors including at least hydrometeorology, natural environment of the waterway and navigability. Since the target factors of hydrometeorology, natural environment of the waterway and navigability are taken into consideration in the process of constructing the comprehensive risk assessment model for ship navigation, it is possible to combine port and navigation meteorological threshold indicators such as strong winds, low visibility, waves and short-term heavy rainfall, use fuzzy membership comprehensive evaluation method, and establish a comprehensive risk assessment model for meteorological disasters for ship navigation based on the comprehensive risk assessment indicator system, thereby improving the pertinence and practicality of risk forecasting.

[0029] Step 130: Based on the hydrological and meteorological forecast data of the target area, using the comprehensive risk assessment model for ship navigation, a rolling forecast of the meteorological disaster risk for ship navigation in the target area is conducted; the meteorological disaster risk includes at least the main meteorological disasters affecting ship navigation, risk levels and risk probabilities.

[0030] In step 130, based on the dynamic update forecast of hydrological and meteorological elements such as strong winds, visibility, waves, and short-term heavy rainfall in the smart grid, the comprehensive risk assessment model for ship navigation is connected to realize a rolling forecast of the comprehensive risk of meteorological disasters for ship navigation, including the forecast of the comprehensive risk forecast value, risk level, and risk probability of meteorological disasters for ship navigation, thereby improving the pertinence and practicality of the risk forecast.

[0031] Based on this, the method for forecasting the risk of meteorological disasters for ship navigation provided by the present invention realizes the use of an evaluation model pre-constructed based on target factors such as hydrometeorology, natural environment of the waterway and navigation capacity, combined with the hydrometeorological forecast data of the target area, to forecast the risk of ship navigation in the target area, thereby greatly improving the pertinence and practicality of the forecast of the risk of meteorological disasters for ship navigation; and solves the problem that the existing marine traffic meteorological forecast technology cannot be directly applied to the forecast of the risk of meteorological disasters for ship navigation.

[0032] Preferably, before step 120, that is, before obtaining the pre-built ship navigation comprehensive risk assessment model, it may include building a ship navigation comprehensive risk assessment model. Figure 2 , Figure 2 A schematic diagram of the main process of constructing a comprehensive risk assessment model for ship navigation in the method for forecasting meteorological disaster risks for ship navigation provided by the present invention.

[0033] exist Figure 2 In the process of building a comprehensive risk assessment model for ship navigation, the following aspects can be included: Step 210: Acquire multi-source data on ship navigation, where the multi-source data at least includes hydrological and meteorological data, waterway natural environment data, and industry data of ports and port areas.

[0034] In step 210, obtaining multi-source data on ship navigation may include: obtaining hydrological and meteorological data for a target period from a meteorological big data cloud platform, the hydrological and meteorological data including intelligent grid data for the responsible sea area and intelligent grid data for the land surface; the intelligent grid data for the responsible sea area at least includes visibility forecast data for the responsible sea area, 10-meter wind speed forecast data and wave height forecast data; the intelligent grid data for the land surface at least includes short-term heavy rainfall data.

[0035] The natural environment data of the waterway shall be obtained from the data management center of the Port and Shipping Administration; the natural environment data of the waterway shall at least include the length of the waterway, the energy level, the water depth of the waterway and the width of the waterway.

[0036] The industrial data of ports and port areas are obtained from the Data Management Center of the National Statistical Yearbook Office; the industrial data of ports and port areas at least include cargo throughput, number of berths and length of wharf.

[0037] The specific data sources are shown in Table 1. Table 1 is the multi-source data of ship navigation, that is, the data source used to construct the comprehensive risk assessment model for ship navigation.

[0038] Table 1 Multi-source data on ship navigation

[0039] Based on this, the data on hydrological meteorology, natural environment of the waterway and navigation capacity required to construct a comprehensive risk assessment model for ship navigation were obtained.

[0040] Step 220: Based on multi-source data, a comprehensive risk assessment index system for ship navigation risk target indicators is established; the target indicators include at least hydrological meteorology, waterway natural environment and navigation capacity; the comprehensive risk assessment index system includes an indicator layer, a criterion layer and a target layer.

[0041] In step 220, unlike sailing in open seas, during the navigation of ships in ports, there are more and more complex factors affecting the safety of ship navigation in ports due to the limited navigation waters, insufficient water depth, insufficient channel width, large traffic flow, frequent passing ships, and high navigation density. In order to scientifically and reasonably evaluate the navigation safety risks of ships entering and leaving the port, a comprehensive risk evaluation index system of ship navigation risk target indicators considering the three indicator factors of hydrological meteorology, natural environment of the channel, and navigation capacity can be established through field research, literature study, industry information collection, etc.

[0042] Preferably, please refer to Figure 3 , Figure 3 A schematic diagram of a three-layer evaluation index system in a comprehensive risk evaluation index system for ship navigation in the method for forecasting meteorological disaster risks for ship navigation provided by the present invention.

[0043] exist Figure 3 In the present invention, the comprehensive risk assessment index system may include an index layer 330, a criterion layer 320 and a target layer 310. That is, the target layer 310 is a comprehensive risk index assessment layer; the indicators in the criterion layer 320 include hydrological and meteorological indicators, waterway natural environment indicators and navigation capacity indicators; the indicators in the index layer 330 are sub-indicators of each indicator in the criterion layer 320; the sub-indicators of hydrological and meteorological indicators include wind force, visibility, waves and short-term heavy rainfall; the sub-indicators of waterway natural environment indicators include the ratio of ship length to channel width, the ratio of channel water depth to ship draft, channel length and navigation grade; the sub-indicators of navigation capacity indicators include cargo throughput, number of berths and wharf length.

[0044] Preferably, based on the multi-source data, a comprehensive risk assessment index system for ship navigation risk target indicators is established, which may include: based on the hydrological and meteorological data, in combination with industry and local standards, a comprehensive risk assessment index system for hydrological and meteorological indicators is established; the hydrological and meteorological indicators include at least wind speed, visibility, waves and short-term heavy rainfall.

[0045] Furthermore, based on the waterway natural environment data and combined with the navigation safety evaluation standards, a comprehensive risk evaluation index system for waterway natural environment indicators is established; the waterway natural environment indicators at least include the ratio of ship length to channel width, the ratio of channel water depth to ship draft, channel length and navigation grade.

[0046] Furthermore, based on the industry data of the ports and port areas, combined with the indicator data of 23 ports across the country in the China Statistical Yearbook, a comprehensive risk assessment index system for navigation capacity indicators is established; the navigation capacity indicators at least include cargo throughput, number of berths and terminal length.

[0047] Specifically, the impact of hydrological meteorology, natural environment of waterways and navigability is explained as follows: 1. Hydrology and meteorology There are many hydrological and meteorological conditions that affect ship navigation. The indicators mainly consider the four types of indicators that have a greater impact on navigation safety: wind, waves, visibility, and short-term heavy rainfall. The relevant industry and local standards for maritime traffic meteorological conditions were investigated to determine the level thresholds of the four types of hydrological and meteorological indicators, as shown in Tables 2 to 5.

[0048] Table 2 Wind impact levels

[0049] Table 3 Visibility impact levels

[0050] Table 4 Wave impact levels

[0051] Table 5 Impact levels of short-term heavy rainfall

[0052] 2. Natural environment of waterway The natural environment of the waterway, such as waterway depth, length, width, and navigation grade, will affect navigation safety to varying degrees. Four indicators, namely, “ratio of ship length to waterway width”, “ratio of waterway depth to ship draft”, “waterway length (km)”, and “navigation grade (10,000 tons)”, are selected to represent the natural environment of the waterway. The impact levels of the four indicators are determined by referring to relevant literature on navigation safety evaluation, as shown in Table 6.

[0053] Table 6 Impact levels of waterway natural environment indicators

[0054] 3. Navigation Capacity Navigation capacity refers to the number of ships and flow that a port channel can accommodate and pass through. The size of navigation capacity directly affects the transportation efficiency and economic benefits of the channel. Here, port scale-related data such as "cargo throughput", "number of berths", and "length of wharf" are used to measure navigation capacity.

[0055] Based on the indicator data of 23 ports across the country in the 2023 China Statistical Yearbook, the three types of indicators are graded, see Table 7.

[0056] Table 7 Impact levels of navigation capacity indicators

[0057] Based on this, the present invention constructs a comprehensive risk assessment index system, so that a target assessment index weight set can be established based on the comprehensive risk assessment index system.

[0058] Step 230: Based on the comprehensive risk assessment indicator system, combined with a preset indicator evaluation mechanism, a target evaluation indicator weight set is established; the preset indicator evaluation mechanism at least includes a preset scoring method and a trigonometric function fuzzy number method.

[0059] In step 230, determining the weight of the evaluation index is to determine the importance of each index in the index layer relative to each criterion in the criterion layer, and the importance of each criterion in the criterion layer relative to the target layer. The traditional classical method is to construct a pairwise comparison judgment matrix, and select 1~9 and its reciprocal as the scale value of the comparison result. This method has the characteristics of clarity, simplicity and ease of implementation, but it limits the pertinence of the evaluation to a certain extent, and limits the value of the importance degree evaluation to a fixed and limited number, ignoring the ambiguity of the expert's thinking process during the evaluation. The pertinence of fuzzy evaluation does not lie in converting fuzzy problems into precise numbers as soon as possible, but in retaining its ambiguity to the greatest extent in mathematical operations. Therefore, the present invention provides a weight determination method based on triangular fuzzy numbers and preset scoring methods. It should be noted that the preset scoring method can be a scoring method based on industry or national standards combined with expert experience, or it can be a scoring method based on an authoritative evaluation agency.

[0060] It should be noted that triangular fuzzy numbers express an interval concept, giving the upper and lower limits of the possibility interval and the middle limit with the greatest possibility of taking values. Through the membership function of triangular fuzzy numbers, the possibility of different parameters within the entire interval is obtained. Compared with the traditional hierarchical analysis method that gives all possibilities to a specific value, it is more reasonable to use the interval range in triangular fuzzy numbers as a scale value to describe the degree of importance.

[0061] Preferably, based on the comprehensive risk assessment index system and in combination with a preset index evaluation mechanism, a target evaluation index weight set is established, which may include: based on a preset scoring method, constructing a first judgment matrix of the importance of the index layer relative to the criterion layer and a second judgment matrix of the importance of the criterion layer relative to the target layer; the first judgment matrix includes a hydrological and meteorological criterion layer judgment matrix, a waterway natural environment criterion layer judgment matrix and a navigability criterion layer judgment matrix; the first judgment matrix is ​​used to indicate the importance of each indicator in the criterion layer corresponding to the sub-indicators of each indicator; the second judgment matrix is ​​used to indicate the importance of each indicator in the criterion layer relative to the target layer; using the trigonometric fuzzy number method, the fuzzy comprehensiveness of each indicator in the first judgment matrix and the second judgment matrix at its layer is obtained to obtain fuzzy comprehensiveness data for each indicator.

[0062] Furthermore, based on the fuzzy comprehensive degree data of each indicator, the possibility matrix of each layer is constructed; based on the possibility matrix of each layer, the indicator weight corresponding to each indicator in each layer is calculated to obtain the target evaluation indicator weight set.

[0063] Specifically, firstly, based on the preset scoring method, the importance of the indicator layer to the criterion layer and the criterion layer to the target layer can be compared with each other and the comparison interval can be given, so as to obtain the judgment matrix of different levels: please refer to Tables 8 to 11. It should be noted that, in each indicator in Tables 8 to 11, l represents its lower limit value, m represents its middle value, and u represents its upper limit value; the value range of l, m, and u is 0 to 1.

[0064] Table 8 Hydrometeorological criteria layer determination matrix

[0065] Table 9 Waterway natural environment criteria layer judgment matrix

[0066] Table 10 Navigability Criteria Layer Judgment Matrix

[0067] Table 11 Judgment layer decision matrix

[0068] It should be noted that Tables 8 to 10 are the first judgment matrix, which indicates the importance of the sub-indicators of each indicator in the criterion layer relative to each indicator; Table 11 is the second judgment matrix, which indicates the importance of each indicator in the criterion layer relative to the target layer.

[0069] Furthermore, the fuzzy comprehensive degree of each indicator in Tables 8 to 11 at its level can be expressed using the following formula: (1) The fuzzy comprehensive degree of each indicator in its layer is calculated; among them, represents the fuzzy comprehensive degree of the i-th index in the judgment matrix, Tabular rows, In the table, n represents the number of indicators.

[0070] Furthermore, based on the fuzzy comprehensive degree data of each indicator, constructing the possibility matrix of each layer may include using the formula: (2) Calculate the possibility of comparing two indicators; among them, Indicates the possibility of index i and index j, represents the fuzzy comprehensive degree of index i, Represents the fuzzy comprehensiveness of index j.

[0071] Then use the formula: (3) Construct the possibility matrix of each layer; among them, Represents the possibility matrix of each layer, Indicates the fuzzy comprehensiveness of index 1, Indicates the fuzzy comprehensive degree of index 2, Represents the fuzzy comprehensive degree of index n.

[0072] Based on this, the indicator weight vector of each layer can be calculated based on the established possibility matrix.

[0073] For example, the formula can be used: (4) Calculate the initial weight component of the i-th indicator.

[0074] Furthermore, after normalizing the initial weight components of the current layer indicators, the weights of each indicator in the current layer are obtained: (5) Based on this, a target evaluation index weight set was constructed.

[0075] As a more specific example, for example, the preset scoring method scores the target layer as follows: ; Then, using formula (1) to formula (5), the weights of each indicator in the criterion layer (hydrometeorology, waterway natural environment, and navigability) can be calculated, and the following results are obtained: ; ; ; ; ; ; Based on this, the weights of the hydro-meteorological index, waterway natural environment index, and navigation capacity index in the criterion layer are 0.54, 0.28, and 0.18, respectively. Similarly, the weights of the sub-indicators of the hydro-meteorological index, visibility, wind, waves, and short-term heavy rainfall, are 0.18, 0.36, 0.26, and 0.2, respectively; the weights of the sub-indicators of the waterway natural environment index, the ratio of ship length to channel width, the ratio of channel depth to draft, channel length, and channel grade, are 0.6, 0.1, 0.1, and 0.2, respectively; the weights of the sub-indicators of the navigation capacity index, cargo throughput, number of berths, and dock length, are 0.3, 0.5, and 0.2, respectively.

[0076] In summary, based on the comprehensive risk assessment indicator system, combined with a preset indicator evaluation mechanism including at least a preset scoring method and a trigonometric function fuzzy number method, a target evaluation indicator weight set can be obtained.

[0077] Step 240: Based on the target evaluation index weight set, the comprehensive risk evaluation index system and the target meteorological threshold index, a fuzzy membership comprehensive evaluation method is used to establish a comprehensive risk evaluation model for ship navigation.

[0078] In step 240, the membership comprehensive evaluation method converts the qualitative evaluation into a quantitative evaluation according to the membership theory of fuzzy mathematics, that is, it uses fuzzy mathematics to make an overall evaluation of things or objects that are negated by multiple variables. It has the characteristics of clear results and strong systematicity, can well solve fuzzy and difficult to determine problems, and is suitable for solving various uncertain problems.

[0079] This method quantifies the fuzziness of the evaluation object by defining a membership function, thereby obtaining a comprehensive evaluation result. Membership plays a vital role in the membership comprehensive evaluation method; it indicates the degree to which a thing belongs to a specific attribute or concept, and usually takes a value between 0 and 1; 0 means it does not match or does not belong to the evaluation set at all, and 1 means it completely matches or belongs to the evaluation set. By setting a membership function to calculate the degree of membership of a variable to a certain evaluation set, fuzzy concepts can be converted into a mathematically processable form, thereby achieving accurate description and processing of fuzzy information.

[0080] Preferably, a comprehensive risk assessment model for ship navigation is established based on the target evaluation index weight set, the comprehensive risk assessment index system and the target meteorological threshold index using the fuzzy membership comprehensive evaluation method, which can include: first establishing a membership function model for preset index levels; the preset index levels include at least a smaller risk level, a general risk level, a larger risk level, a major risk level and an extremely large risk level; and then using the membership function model to calculate the membership vector of each index level.

[0081] Furthermore, according to the membership vector of each indicator level, combined with the target evaluation indicator weight set, the comprehensive risk assessment indicator system and the target meteorological threshold indicator, an evaluation vector of the indicator layer relative to the criterion layer is established, that is, the criterion layer evaluation vector is obtained; based on the criterion layer evaluation vector, combined with the target evaluation indicator weight set, the comprehensive risk assessment indicator system and the target meteorological threshold indicator, an evaluation vector of the criterion layer relative to the target layer is established, that is, the target layer evaluation vector is obtained.

[0082] Furthermore, based on the evaluation vector of the target layer, the meteorological disaster risk assessment value is determined; based on the value range of the meteorological disaster risk assessment value, the objective function of the meteorological disaster risk probability forecast within the value range is constructed; and the objective function is used as the meteorological disaster risk probability forecast function of the comprehensive risk assessment model for ship navigation.

[0083] Finally, based on the objective function and meteorological disaster risk assessment value, a comprehensive risk assessment model for ship navigation is established.

[0084] For example, the comprehensive risk assessment model for meteorological disasters in ship navigation established using the membership evaluation method can be completed using the following steps.

[0085] Step 1: First, establish a five-level evaluation vocabulary: small risk (level 1), general risk (level 2), large risk (level 3), major risk (level 4), and extremely large risk (level 5). Secondly, establish the membership function corresponding to different levels of indicator data. The membership functions of different levels in the model are defined as follows: (6) (7) (8) (9) (10) In formulas (6) to (10), x represents the risk level, Represents the membership functions of different levels in the model.

[0086] Furthermore, the membership vectors of different indicator levels can be calculated according to the membership function: ; ; ; ; .

[0087] It should be noted that r1 means that when the index level is 1, the membership of smaller risk is 1, that is, the probability of smaller risk is 1; the membership of general risk is 0.5, that is, the probability of general risk is 0.5; the membership of larger risk, major risk, and extremely large risk are all 0. And so on for r2, r3, r4, and r5.

[0088] The second step is to establish an evaluation matrix.

[0089] For m indicators at a certain level (except for the hydrological and meteorological indicators corresponding to the hydrological and meteorological criteria), the evaluation matrix R can be established based on the membership functions of the m indicator levels; for example, for the three indicators at the navigation capacity level, the evaluation matrix R can be established based on the membership functions of the three indicator levels: (11) The third step is to establish the evaluation vector of the indicator layer relative to the criterion layer.

[0090] Suppose the evaluation matrix composed of k indicator layers under a certain criterion layer indicator is , the indicator weight vector is , then the evaluation vector of the k-index layer is for: (12) The hydrological and meteorological index layer is an exception. Different types of severe weather (such as strong winds, heavy fog, short-term heavy rainfall, etc.) usually occur independently. In order to highlight the impact of a single severe weather and prevent low-risk factors from weakening the impact of high-risk factors when considering multiple types of weather factors at the same time, the membership vector with the highest risk level among the four types of hydrological and meteorological elements is taken as the evaluation vector of the hydrological and meteorological index layer. That is: (13) For example, in the hydrological and meteorological conditions of a certain channel, the visibility level is 3, the strong wind level is 5, the wave level is 4, and the short-term heavy rainfall level is 1. Then the evaluation vector of the hydrological and meteorological index layer is .

[0091] The fourth step is to establish the evaluation matrix and evaluation vector of the criterion layer relative to the target.

[0092] Assume that the evaluation matrix composed of the criterion layer is , It represents the evaluation matrix of hydrological meteorology, natural environment of waterway and navigability; the weight vector of criterion layer is , then the evaluation vector of the target layer is for: (14) Finally, the evaluation vector Normalize and use the formula: (15) Get the final meteorological disaster risk assessment vector .

[0093] Step 5: Determine the meteorological disaster risk assessment value.

[0094] By rating level As a weight vector, through the evaluation vector Weighted summation to obtain the meteorological disaster risk assessment value .

[0095] That is, based on the evaluation vector of the target layer, determining the meteorological disaster risk evaluation value may include using the formula: (16) The meteorological disaster risk assessment value is calculated; among them, represents the meteorological disaster risk assessment value, Indicates the rating level, Represents the matrix transpose of the target layer evaluation vector.

[0096] Step 6: Establish a meteorological disaster risk probability function.

[0097] Based on the value range of meteorological disaster risk assessment value, constructing the objective function of meteorological disaster risk probability forecast within the value range may include using the formula: (17) The objective function of the meteorological disaster risk probability forecast within the value range is constructed, which is a monotonically increasing binary linear compression function; Indicates the probability of meteorological disaster risk, ' represents any value within the range of meteorological disaster risk assessment value.

[0098] It should be noted that the meteorological disaster risk assessment value The value range is between 1 and 5. We construct a quadratic compression function (Formula 17) that is monotonically increasing in the interval [1,5] and passes through the points (1,0) and (5,1). Mapped on 0-100%. This function is used as a meteorological disaster risk probability forecast function. The meteorological disaster risk value is brought into the function to calculate the probability of meteorological disaster risk for ship navigation.

[0099] For details, please refer to Figure 4 , Figure 4 A schematic diagram of the probability distribution of meteorological disaster risk for ship navigation provided by the method for forecasting meteorological disaster risk for ship navigation provided by the present invention. Figure 4In the figure, the horizontal axis represents the comprehensive risk value, and the vertical axis represents the comprehensive risk probability. Figure 4 It represents the corresponding comprehensive risk assessment value when the comprehensive risk value range is between 1 and 5.

[0100] Furthermore, the risk levels can be divided, that is, the seventh step can be carried out to divide the comprehensive risk levels.

[0101] Based on the changing law of the comprehensive risk probability function, the comprehensive risk value is divided into 5 levels as the comprehensive risk level, see Table 12 for details.

[0102] Table 12 Classification of meteorological disaster risk levels

[0103] Following the same specific example in step 230, data calculations can be performed according to formulas (6) to (17) to perform a comprehensive risk forecast of meteorological disasters for ship navigation.

[0104] The membership function determines the membership evaluation vectors of different levels as follows: r1=(1, 0.5, 0, 0, 0), r2=(0.5, 1, 0.5, 0, 0), r3=(0, 0.5, 1, 0.5, 0), r4=(0, 0, 0.5, 1, 0.5), r5=(0, 0, 0, 0.5, 1).

[0105] If the visibility level of a waterway is 3, the gale level is 5, the wave level is 4, and the short-term heavy rainfall level is 1, the hydrological and meteorological evaluation vector is: ; If the ratio of ship length to channel width in the waterway natural environment index is 4, the ratio of channel water depth to ship draft is 5, the waterway length is 2, and the navigation level is 5, then the waterway natural environment index layer evaluation matrix is ​​established based on the membership vector: ; Then the evaluation vector of the natural environment of the waterway is for: ; If the cargo throughput level in the navigation capacity index is 3, the number of berths level is 4, and the wharf length level is 5, then the navigation capacity index layer evaluation matrix is ​​established based on the membership vector: ; Then the evaluation vector of navigability is for: ; Finally, the evaluation vectors of hydrological meteorology, natural environment of waterway, and navigability can be obtained through the above calculations, and the criterion layer evaluation matrix is ​​constructed accordingly. : ; Evaluation vector of the target layer for: ; Finally, the evaluation vector Normalize and get the final meteorological disaster risk assessment vector .

[0106]

[0107] By rating level As a weight vector, through the evaluation vector Weighted summation to obtain the meteorological disaster risk assessment value : ; Substitute the risk assessment value into the compression formula The meteorological disaster risk probability is 96.6%.

[0108] According to the meteorological disaster risk level classification in Table 14, it can be determined that the comprehensive meteorological disaster risk level for ship navigation in this waterway is level 5, and the meteorological disaster risk probability is 96.6%.

[0109] Based on this, the method for forecasting meteorological disaster risks for ship navigation provided by the present invention establishes a comprehensive risk evaluation index system for ship navigation risk target indicators by considering factors such as hydrometeorological factors, waterway natural environment, and navigation capacity that have an impact on ship navigation, and determines the indicator weights by using a preset scoring method and a triangular fuzzy number method; further combining port and navigation meteorological threshold indicators such as strong winds, low visibility, waves, and short-term heavy rainfall, and using a fuzzy membership comprehensive evaluation method, a comprehensive risk evaluation model for ship navigation is established based on the comprehensive risk evaluation index system; thereby, the model can be used to predict the risk of ship navigation, which can improve its pertinence and practicality.

[0110] Preferably, in step 130, based on the hydrological and meteorological forecast data of the target area, a rolling forecast of the meteorological disaster risk for ship navigation in the target area is made using a comprehensive risk assessment model for ship navigation; the comprehensive risk forecast of meteorological disasters for ship navigation can be made in the following manner.

[0111] Specifically, the meteorological big data cloud platform can be used to access the smart grid's strong wind, visibility, wave and short-term heavy rainfall forecast data in real time, and based on the dynamic forecast of hydrological and meteorological data, it can be brought into the comprehensive risk assessment model of meteorological disasters for ship navigation to achieve a rolling forecast of the comprehensive risk of meteorological disasters for ship navigation.

[0112] The forecast time limit of the ship navigation meteorological disaster risk forecast product equipped with the method for forecasting the ship navigation meteorological disaster risk provided by the present invention is: 6 hours every 0-24 hours, 12 hours every 24-72 hours, and 24 hours every 72-168 hours in the future, and spatially every 5km waterway section; the targeted nature of the forecast of the ship navigation meteorological disaster risk is improved.

[0113] The main forecast contents of the product are detailed in Table 13.

[0114] Table 13 Contents of meteorological disaster risk forecast products for ship navigation

[0115] Furthermore, in order to further verify the prediction pertinence and practicality of the method for forecasting the risk of meteorological disasters for ship navigation provided by the present invention, the applicant obtained the hydrological and meteorological forecast data from September 6 to September 13, and used the method for forecasting the risk of meteorological disasters for ship navigation provided by the present invention to make a rolling forecast of the risk of meteorological disasters for ship navigation, and obtained the forecast results in Tables 14 to 16. It should be noted that in Table 14, 1 corresponds to risk level I, 2 corresponds to risk level II, 3 corresponds to risk level III, 4 corresponds to risk level IV, and 5 corresponds to risk level V.

[0116] Table 14 Comprehensive risk level of meteorological disasters for ship navigation in Fangchenggang area reported from September 6, 2024

[0117] Table 15 Comprehensive risk probability of meteorological disasters for ship navigation reported from September 6, 2024

[0118] Table 16 Major meteorological disasters affecting ship navigation reported from September 6, 2024

[0119] From the forecast results shown in Tables 14 to 16, it can be concluded without a doubt that the change trend of the forecast of meteorological disaster risk for ship navigation reported since September 6 is basically consistent with the typhoon forecast trend. The meteorological disaster risk level of the three waterways in Fangchenggang District reached Level 5 in some periods from 14:00 on the 6th to 08:00 on the 8th, with a risk probability of more than 90%. The Level 5 risk of some sections of the Sanya Channel and Dongwan Channel in Fangchenggang District lasted for a long time and had a greater impact. The meteorological disaster risk level was low (Level 1-2) from 08:00 on the 8th to 08:00 on the 13th, and the impact of meteorological disasters was small, which was generally conducive to navigation.

[0120] In terms of the main types of meteorological disasters, as shown in Table 16, from the 6th to the 8th, the main impacts were strong winds, visibility and waves; after the 8th, strong winds and waves had basically no impact, and visibility had little impact on navigation.

[0121] It can be seen that the method for forecasting the risk of meteorological disasters for ship navigation provided by the present invention can make rolling forecasts on the risk factors for ship navigation in the target area (comprehensive risk forecast value of meteorological disasters, risk level forecast value and risk probability forecast value) based on the hydrological and meteorological forecast data of the target area, thereby improving the targeted nature of the forecast of the risk of meteorological disasters for ship navigation.

[0122] In the second aspect, the present invention provides a device for forecasting the risk of meteorological disasters for ships, please refer to Figure 5 , Figure 5 A schematic diagram of the structure of the device for forecasting meteorological disaster risks for ship navigation provided by the present invention.

[0123] exist Figure 5 In the embodiment, the device may include: The first acquisition module 510 is used to acquire hydrological and meteorological forecast data of the target area; the hydrological and meteorological forecast data is a real-time and dynamically updated forecast of meteorological elements for a future period of time.

[0124] The second acquisition module 520 is used to acquire a pre-built comprehensive risk assessment model for ship navigation; the comprehensive risk assessment model for ship navigation is an assessment model constructed based on target factors including at least hydrological and meteorological factors, natural environment of the waterway, and navigability.

[0125] The rolling forecast module 530 is used to make a rolling forecast of the meteorological disaster risk for ship navigation in the target area based on the hydrological and meteorological forecast data of the target area and using the comprehensive risk assessment model for ship navigation; the meteorological disaster risk at least includes the main meteorological disasters affecting ship navigation, risk level and risk probability.

[0126] Based on this, the device for forecasting the risk of meteorological disasters for ship navigation provided by the present invention first obtains the hydrometeorological forecast data of the target area through the first acquisition module 510; the hydrometeorological forecast data is a real-time and dynamically updated forecast of meteorological elements for future time periods; further, the pre-constructed comprehensive risk assessment model for ship navigation is obtained through the second acquisition module 520; the comprehensive risk assessment model for ship navigation is an evaluation model constructed based on target factors including at least hydrometeorology, natural environment of the waterway and navigability; finally, the rolling forecast module 530 is used to make a rolling forecast of the meteorological disaster risk for ship navigation in the target area based on the hydrometeorological forecast data of the target area and the comprehensive risk assessment model for ship navigation; the meteorological disaster risk at least includes the main meteorological disasters that affect ship navigation, risk level and risk probability; the pertinence of the forecast of meteorological disaster risk for ship navigation is improved; and the problem that the existing marine traffic meteorological forecast technology cannot be directly applied to the forecast of meteorological disaster risk for ship navigation is solved.

[0127] Although the present invention is described herein in conjunction with various embodiments, in the process of implementing the claimed invention, those skilled in the art may understand and implement other variations of the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit may implement several functions listed in a claim. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0128] Although the present invention has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present invention. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present invention as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present invention. Obviously, those skilled in the art may make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, the present invention is intended to include such modifications and variations if they fall within the scope of the claims of the present invention and their equivalents.

Claims

1. A method for predicting meteorological disaster risks for ship navigation, characterized in that: include: Obtain hydrological and meteorological forecast data for the target area; The hydrological and meteorological forecast data is a real-time and dynamically updated forecast of meteorological elements for future periods; Obtain a pre-built comprehensive risk assessment model for ship navigation; The comprehensive risk assessment model for ship navigation is an assessment model constructed based on target factors including at least hydrological and meteorological factors, natural environment of the waterway, and navigation capacity; Based on the hydrological and meteorological forecast data of the target area, the comprehensive risk assessment model for ship navigation is used to make a rolling forecast of the meteorological disaster risk for ship navigation in the target area; the meteorological disaster risk at least includes the main meteorological disasters affecting ship navigation, risk level and risk probability.

2. The method for forecasting the risk of meteorological disasters for ship navigation according to claim 1, characterized in that: Before obtaining the pre-built ship navigation comprehensive risk assessment model, it includes: Constructing the comprehensive risk assessment model for ship navigation; The constructing of the comprehensive risk assessment model for ship navigation comprises: Acquire multi-source data on ship navigation, wherein the multi-source data at least includes hydrological and meteorological data, waterway natural environment data, and industry data of ports and port areas; Based on the multi-source data, a comprehensive risk assessment index system for target indicators of ship navigation risk is established; the target indicators at least include hydrological meteorology, natural environment of the waterway and navigation capacity; the comprehensive risk assessment index system includes an indicator layer, a criterion layer and a target layer; Based on the comprehensive risk assessment indicator system, combined with a preset indicator evaluation mechanism, a target evaluation indicator weight set is established; the preset indicator evaluation mechanism at least includes a preset scoring method and a trigonometric function fuzzy number method; According to the target evaluation index weight set, the comprehensive risk evaluation index system and the target meteorological threshold index, the fuzzy membership comprehensive evaluation method is used to establish the comprehensive risk evaluation model for ship navigation.

3. The method for forecasting the risk of meteorological disasters for ship navigation according to claim 2, characterized in that: The target layer is a comprehensive risk index evaluation layer; the indicators in the criterion layer include hydrological and meteorological indicators, waterway natural environment indicators and navigation capacity indicators; The indicators in the indicator layer are sub-indicators of each indicator in the criterion layer; the sub-indicators of the hydrological and meteorological indicators include wind force, visibility, waves and short-term heavy rainfall; the sub-indicators of the waterway natural environment indicators include the ratio of ship length to channel width, the ratio of channel water depth to ship draft, channel length and navigation grade; the sub-indicators of the navigation capacity indicators include cargo throughput, number of berths and dock length.

4. The method for forecasting the risk of meteorological disasters for ship navigation according to claim 3, characterized in that: Based on the comprehensive risk assessment indicator system, combined with the preset indicator evaluation mechanism, a target evaluation indicator weight set is established, including: Based on the preset scoring method, a first determination matrix of the importance of the indicator layer relative to the criterion layer and a second determination matrix of the importance of the criterion layer relative to the target layer are constructed; the first determination matrix includes a determination matrix for the hydrological and meteorological criterion layer, a determination matrix for the waterway natural environment criterion layer and a determination matrix for the navigability criterion layer; the first determination matrix is ​​used to indicate the importance of the sub-indicators of each indicator in the criterion layer relative to each indicator; the second determination matrix is ​​used to indicate the importance of each indicator in the criterion layer relative to the target layer; Using the trigonometric function fuzzy number method, the fuzzy comprehensive degree of each indicator in the first determination matrix and the second determination matrix at its layer is obtained to obtain the fuzzy comprehensive degree data of each indicator; Based on the fuzzy comprehensive degree data of each indicator, the possibility matrix of each layer is constructed; Based on the possibility matrix of each layer, the indicator weight corresponding to each indicator in each layer is calculated to obtain the target evaluation indicator weight set.

5. The method for forecasting the risk of meteorological disasters for ship navigation according to claim 4, characterized in that: The fuzzy comprehensive degree data based on each indicator is used to construct the possibility degree matrix of each layer, including: Using the formula: ； Calculate the possibility of comparing two indicators; among them, Indicates the possibility of index i and index j, represents the fuzzy comprehensive degree of index i, represents the fuzzy comprehensive degree of index j; Using the formula: ； Construct the possibility matrix of each layer; among them, Represents the possibility matrix of each layer, Indicates the fuzzy comprehensiveness of index 1, Indicates the fuzzy comprehensive degree of index 2, Represents the fuzzy comprehensive degree of index n.

6. The method for forecasting the risk of meteorological disasters for ship navigation according to claim 2, characterized in that: The comprehensive risk assessment model for ship navigation is established by using the fuzzy membership comprehensive evaluation method according to the target evaluation index weight set, the comprehensive risk assessment index system and the target meteorological threshold index, including: Establishing a membership function model of preset indicator levels; the preset indicator levels include a relatively small risk level, a general risk level, a relatively large risk level, a major risk level, and a very large risk level; Using the membership function model, the membership vector of each indicator level is calculated; According to the membership vector of each indicator level, combined with the target evaluation indicator weight set, the comprehensive risk evaluation indicator system and the target meteorological threshold indicator, an evaluation vector of the indicator layer relative to the criterion layer is established to obtain an evaluation vector of the criterion layer; Based on the evaluation vector of the criterion layer, in combination with the target evaluation index weight set, the comprehensive risk evaluation index system and the target meteorological threshold index, an evaluation vector of the criterion layer relative to the target layer is established to obtain an evaluation vector of the target layer; Determining a meteorological disaster risk assessment value based on the assessment vector of the target layer; Based on the value range of the meteorological disaster risk assessment value, construct an objective function for meteorological disaster risk probability forecasting within the value range; and use the objective function as a meteorological disaster risk probability forecasting function of the comprehensive risk assessment model for ship navigation; Based on the objective function and the meteorological disaster risk assessment value, the comprehensive risk assessment model for ship navigation is established.

7. The method for forecasting the risk of meteorological disasters for ship navigation according to claim 6, characterized in that: The step of determining the meteorological disaster risk assessment value based on the assessment vector of the target layer includes: Using the formula: ； The meteorological disaster risk assessment value is calculated; among them, represents the meteorological disaster risk assessment value, Indicates the rating level, Represents the matrix transpose of the target layer evaluation vector.

8. The method for forecasting the risk of meteorological disasters for ship navigation according to claim 6, characterized in that: The step of constructing an objective function of meteorological disaster risk probability forecasting within the value range based on the value range of the meteorological disaster risk assessment value includes: Using the formula: ； Constructing an objective function for the probability forecast of meteorological disaster risk within the value range; wherein Indicates the probability of meteorological disaster risk, Represents any value within the range of meteorological disaster risk assessment values.

9. The method for forecasting the risk of meteorological disasters for ship navigation according to claim 2, characterized in that: The obtaining of multi-source data on ship navigation includes: Obtaining hydrological and meteorological data for a target period from a meteorological big data cloud platform, wherein the hydrological and meteorological data include smart grid data for the responsible sea area and smart grid data for the land surface; the smart grid data for the responsible sea area at least includes visibility forecast data, 10-meter wind speed forecast data, and wave height forecast data for the responsible sea area; the smart grid data for the land surface at least includes short-term heavy rainfall data; Acquire the natural environment data of the waterway from the data management center of the Port and Shipping Administration; the natural environment data of the waterway at least includes the length of the waterway, the energy level, the water depth of the waterway and the width of the waterway; The industrial data of ports and port areas are obtained from the Data Management Center of the National Statistical Yearbook Office; the industrial data of ports and port areas at least include cargo throughput, number of berths and length of wharf.

10. A device for forecasting the risk of meteorological disasters for ship navigation, characterized in that: include: A first acquisition module, the first acquisition module is used to acquire hydrological and meteorological forecast data of a target area; The hydrological and meteorological forecast data is a real-time and dynamically updated forecast of meteorological elements for future periods; A second acquisition module, the second acquisition module is used to acquire a pre-built ship navigation comprehensive risk assessment model; The comprehensive risk assessment model for ship navigation is an assessment model constructed based on target factors including at least hydrological and meteorological factors, natural environment of the waterway, and navigation capacity; A rolling forecast module, which is used to make a rolling forecast of the meteorological disaster risk for ship navigation in the target area based on the hydrological and meteorological forecast data of the target area and using the comprehensive risk assessment model for ship navigation; the meteorological disaster risk at least includes the main meteorological disasters that affect ship navigation, risk levels and risk probabilities.

Images