Navigation mark guiding intelligent system based on marine ship navigation

Abstract

The invention relates to the technical field of navigation mark guidance of ship navigation, and particularly discloses an intelligent navigation mark guidance system based on marine ship navigation, which comprises a navigation mark attenuation analysis module, a ship risk calculation module, a collision risk extraction module and a ship navigation early warning module, by fusing data of a navigation mark body state sensor and an environment sensor, a photoelectric output attenuation model of a battery under a low-temperature working condition is established, and an effective visual distance attenuation factor of light intensity is accurately calculated, so that dynamic quantitative evaluation of actual luminous efficiency of the navigation mark is realized, the reliability and timeliness of navigation mark information are fundamentally improved, and the application prospect is wide. And the effective guiding range of the navigation mark under the current weather and sea condition can be truly reflected. By analyzing the trajectory deviation degree of a ship in a risk area, abnormal navigation behaviors are identified, and collision risk prefactors are extracted, so that early identification and quantitative evaluation of risks are realized.

Description

Technical Field

[0001] This invention belongs to the field of ship navigation aid guidance technology, and relates to an intelligent system for ship navigation aid guidance at sea. Background Technology

[0002] As a crucial navigational aid for safe ship navigation, the range of a beacon's light directly impacts a ship's positioning, obstacle avoidance, and route planning. In winter, persistently low temperatures can cause the actual usable capacity of lithium iron phosphate batteries to drop significantly to 60% of their nominal value. If the intelligent management system mechanically calculates and issues warnings based on the rated light intensity at full battery capacity, it will lead to serious navigational misjudgments. The actual light intensity may have already been reduced to insufficient levels, meaning the ship cannot effectively recognize the beacon's light, greatly shortening the pilot's reaction time. In foggy conditions with already low visibility, this significantly increases the risk of the ship veering off course, running aground, or even colliding.

[0003] However, existing technologies still have significant shortcomings and drawbacks in such scenarios. First, most intelligent navigation beacon systems lack the ability to accurately diagnose the actual usable capacity of batteries online. Their power estimation models are often based on calibration data under ideal temperature conditions, failing to deeply integrate real-time temperature, discharge rate, and battery health status for dynamic correction. This results in capacity estimates deviating significantly from the true value in low-temperature environments, creating the illusion that "the data is intact but the energy is depleted." Second, the systems generally judge battery status based on rated voltage or preset thresholds, but battery voltage plateaus drift at low temperatures, further amplifying the error of traditional voltage-based capacity estimation. More critically, most existing intelligent navigation beacon management systems have failed to establish a real-time mapping model and feedback adjustment mechanism between "battery capacity and light intensity." The system still assumes a stable energy supply and defaults to light intensity reaching the nominal value, thus calculating safe visibility based on erroneous light intensity data, but is unable to autonomously lower the expected light intensity value or trigger low energy warnings. In essence, it is providing invalid navigation data to ships using flawed assumptions. Summary of the Invention

[0004] In view of the problems existing in the prior art, the present invention provides an intelligent system for guiding navigation marks at sea to solve the above-mentioned technical problems.

[0005] To achieve the above and other objectives, the technical solution adopted by the present invention is as follows:

[0006] This invention provides an intelligent navigation beacon-based system for ships at sea, the system comprising:

[0007] Navigational Beacon Attenuation Analysis Module: Real-time data collection of navigational beacon working status and surrounding environment data is performed using navigational beacon status sensor group and environmental sensor to obtain navigational beacon status data and environmental status data; photoelectric output attenuation modeling of navigational beacon battery under low temperature conditions is performed on navigational beacon status data and environmental status data to obtain light intensity effective visible distance attenuation factor data.

[0008] Ship risk calculation module: Based on the light intensity effective visibility distance attenuation factor data, dynamically evaluate the actual visibility distance of navigation marks under environmental coupling to obtain dynamic actual visibility distance data of navigation marks; calculate the risk area for ship intrusion based on the dynamic actual visibility distance data of navigation marks to obtain ship intrusion risk area data;

[0009] Collision risk extraction module: Based on the data of the ship entering the risk area, the module performs real-time navigation trajectory deviation analysis to obtain the ship trajectory deviation risk coefficient; based on the ship trajectory deviation risk coefficient, the module extracts collision risk antecedent factors to obtain a collision risk antecedent factor set.

[0010] Ship navigation early warning module: Based on the collision risk pre-factor set, it performs multi-level early warning threshold dynamic evaluation to generate ship navigation risk early warning level; according to the early warning level, it generates corresponding early warning instructions and sends them to the ship autopilot system to execute intelligent early warning for maritime ship navigation.

[0011] As described above, the intelligent navigation beacon-based system for maritime vessels provided by this invention has at least the following beneficial effects:

[0012] This invention acquires navigation aid physical state data and environmental state data; models the photoelectric output attenuation of the navigation aid battery under low-temperature conditions based on the navigation aid physical state data and environmental state data, obtaining light intensity effective visibility distance attenuation factor data; dynamically evaluates the actual visibility distance of the navigation aid under environmental coupling based on the light intensity effective visibility distance attenuation factor data, obtaining dynamic actual visibility distance data of the navigation aid; calculates the ship intrusion risk zone based on the dynamic actual visibility distance data of the navigation aid, obtaining ship intrusion risk zone data; and analyzes the ship's real-time navigation trajectory deviation based on the ship intrusion risk zone data, obtaining the ship's trajectory deviation. The system employs a trajectory deviation risk coefficient; based on this coefficient, collision risk precursor factors are extracted to obtain a collision risk precursor factor set; multi-level early warning threshold dynamic assessment is performed based on this collision risk precursor factor set to generate a ship navigation risk early warning level; by fusing data from navigation mark body state sensors and environmental sensors, a photoelectric output attenuation model under low-temperature battery conditions is established, accurately calculating the effective visible distance attenuation factor of light intensity, thus achieving a dynamic quantitative assessment of the actual luminous efficacy of the navigation mark, fundamentally improving the reliability and timeliness of navigation mark information, and accurately reflecting the effective guidance range of the navigation mark under current weather and sea conditions. By analyzing the trajectory deviation of ships within risk areas, abnormal navigation behaviors are identified, and collision risk precursor factors are extracted, enabling the capture of potential dangerous trends before accidents occur, achieving early risk identification and quantitative assessment. This provides key environmental perception and risk pre-control capabilities for realizing advanced ship autonomous navigation and is an essential component of building intelligent maritime infrastructure. Attached Figure Description

[0013] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a schematic diagram showing the connections of the various modules in the system of the present invention.

[0015] Figure 2 This is a flowchart illustrating the ship risk calculation module of the present invention.

[0016] Figure 3 This is a flowchart illustrating the collision risk extraction module of the present invention. Detailed Implementation

[0017] The following description, in conjunction with the implementation of this invention, is merely an example and illustration of the concept of this invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the inventive concept or exceed the scope defined in these claims, all of which should fall within the protection scope of this invention.

[0018] Example 1

[0019] Please see Figures 1-3 As shown, the intelligent navigation aid system for ships at sea includes a navigation aid attenuation analysis module, a ship risk calculation module, a collision risk extraction module, and a ship navigation early warning module.

[0020] The modules described above are connected via wired and / or wireless means to enable data transmission between them.

[0021] Navigational Beacon Attenuation Analysis Module: Real-time data collection of navigational beacon working status and surrounding environment data is performed using navigational beacon status sensor group and environmental sensor to obtain navigational beacon status data and environmental status data; photoelectric output attenuation modeling of navigational beacon battery under low temperature conditions is performed on navigational beacon status data and environmental status data to obtain light intensity effective visible distance attenuation factor data.

[0022] Furthermore, the operational logic of the beacon attenuation analysis module is as follows:

[0023] The navigation beacon status data is obtained by collecting data on battery voltage, battery temperature, real-time output light intensity, and LED operating current through the navigation beacon status sensor group; environmental status data is obtained by collecting ambient temperature, seawater temperature, air humidity, and real-time visibility through environmental sensors.

[0024] The battery capacity decay coefficient under low-temperature conditions is calculated based on battery temperature and ambient temperature data to obtain the effective battery capacity decay coefficient; the light intensity output decay ratio is calculated based on the effective battery capacity decay coefficient and real-time output light intensity data to obtain the light intensity output decay ratio data.

[0025] Based on the light intensity output attenuation ratio data and real-time visibility data, atmospheric transmittance correction calculation is performed to obtain the effective visible distance attenuation factor data.

[0026] In the specific implementation process, the calculation of the effective capacity decay coefficient of the battery is first based on the battery temperature and ambient temperature data, and then calculated using the low-temperature battery capacity decay model: the quantitative relationship between temperature difference and capacity decay is adopted, the difference between battery temperature and ambient temperature is used as the input parameter, and the capacity decay ratio is determined through the pre-calibrated decay curve. The specific calculation process is to multiply the difference between battery temperature and ambient temperature by the battery low-temperature decay coefficient, and then perform a weighted calculation with the baseline capacity percentage to obtain the effective capacity decay coefficient of the battery.

[0027] Subsequently, the light intensity output attenuation ratio is calculated based on the battery's effective capacity attenuation coefficient and real-time output light intensity data. This is achieved by multiplying the battery's effective capacity attenuation coefficient by the current light intensity value and then dividing by the rated light intensity value. Finally, atmospheric transmittance correction is calculated based on the light intensity output attenuation ratio and real-time visibility data. Using an exponential relationship model between visibility and atmospheric transmittance, the light intensity output attenuation ratio is multiplied by an atmospheric transmittance correction factor. This atmospheric transmittance correction factor is calculated by the ratio of the real-time visibility value to the baseline visibility value, ultimately yielding the effective visible distance attenuation factor data.

[0028] Ship risk calculation module: Based on the light intensity effective visibility distance attenuation factor data, dynamically evaluate the actual visibility distance of navigation marks under environmental coupling to obtain dynamic actual visibility distance data of navigation marks; calculate the risk area for ship intrusion based on the dynamic actual visibility distance data of navigation marks to obtain ship intrusion risk area data;

[0029] Furthermore, the operational logic of the ship risk calculation module is as follows:

[0030] Based on the effective visible distance attenuation factor data, the nominal light intensity of the navigation mark is attenuated and corrected to obtain the actual effective light intensity data of the navigation mark.

[0031] The real-time visibility parameters in the environmental status data are obtained, and the atmospheric transmittance correction calculation is performed on the actual effective light intensity data of the navigation mark based on the real-time visibility parameters to obtain the light intensity data after atmospheric attenuation.

[0032] The atmospheric attenuated light intensity data is subjected to visual recognition threshold conversion processing to obtain the dynamic actual visible distance data of the navigation mark.

[0033] Centered on the geographical location of the navigation mark, a circular safety warning area is constructed based on the dynamic actual visibility distance data of the navigation mark to obtain the initial safety warning area data; the boundary of the initial safety warning area is blurred based on real-time sea state data to obtain the data of ships entering the risk area.

[0034] In this embodiment of the invention, the nominal light intensity of the navigation beacon is attenuated and corrected based on the effective visibility distance attenuation factor data: A mathematical model for light intensity attenuation is used, multiplying the nominal light intensity value provided in the navigation beacon equipment specifications by the attenuation factor, while simultaneously considering the light decay characteristic curve of the LED light source and the equipment aging coefficient, to obtain the actual effective light intensity data of the navigation beacon after equipment performance attenuation correction. Subsequently, real-time visibility parameters from environmental state data are acquired, and atmospheric transmittance correction calculations are performed based on the Cosmed atmospheric transmittance theory model. The real-time visibility value is converted into an atmospheric transmittance coefficient, which is then weighted and fused with the actual effective light intensity data of the navigation beacon, with the weights dynamically adjusted according to the visibility level, to obtain the light intensity data after atmospheric attenuation.

[0035] Furthermore, the atmospheric attenuated light intensity data undergoes visual recognition threshold conversion processing. The specific processing steps include:

[0036] Obtain standard visual recognition threshold parameters, and calculate the basic visible distance based on the light intensity data after atmospheric attenuation to obtain basic visible distance data; perform day and night visual adaptation correction on the basic visible distance data based on the real-time visibility parameters in the environmental state data to obtain light-adapted visible distance data.

[0037] Based on the real-time visibility parameters, atmospheric scattering effect correction is applied to the illumination-adapted visibility distance data to obtain scattering-corrected visibility distance data.

[0038] Based on the device sensor type parameters and visual adaptability level parameters, visual sensitivity differential adjustments are made to the scattering correction visual distance data to obtain the dynamic actual visual distance data of the navigation mark.

[0039] In this embodiment of the invention, when performing visual recognition threshold conversion processing on light intensity data after atmospheric attenuation, standard visual recognition threshold parameters are first obtained from the visual perception database. These parameters include basic optical parameters such as the minimum recognizable light intensity value for the human eye and the sensitivity threshold of the device sensor. Based on the comparative analysis of the light intensity data after atmospheric attenuation and the standard threshold parameters, a basic visible distance is calculated using a light intensity attenuation ratio calculation model: the measured light intensity value is compared with the standard recognition threshold, and then multiplied by the distance correction factor corresponding to the atmospheric attenuation coefficient to obtain the basic visible distance data.

[0040] Subsequently, based on real-time visibility parameters from environmental condition data, day-night visual adaptation corrections are performed on the basic visibility distance data. An adaptive light intensity adjustment algorithm is employed, using an ambient light sensor to acquire the current ambient illuminance value. Based on the dark and light adaptation characteristics of human vision, a day-night visual sensitivity correction coefficient is calculated. The basic visibility distance is multiplied by this correction coefficient, and atmospheric transmittance compensation is calculated in conjunction with real-time visibility parameters. The transmittance correction factor is obtained by calculating the ratio of the visibility value to the standard visibility baseline value, ultimately yielding the light-adapted visibility distance data.

[0041] Further atmospheric scattering effect corrections were applied to the illumination-adapted visibility distance data based on real-time visibility parameters. Using the Mie scattering theory model, the scattering influence coefficients of particles of different sizes on light waves were calculated. Through the negative exponential relationship between visibility values ​​and scattering coefficients, a scattering effect correction factor was derived. The illumination-adapted visibility distance data was then multiplied by the scattering correction factor to obtain the visibility distance data corrected for atmospheric scattering effects.

[0042] Finally, visual sensitivity was differentially adjusted based on the device sensor type parameters and visual adaptability level parameters to correct the scattering-corrected visual distance data. According to the characteristic curves of the sensor type, its spectral response function and signal-to-noise ratio characteristics were extracted, and the device sensitivity correction coefficient was calculated. Simultaneously, based on the observer's visual adaptability level, including different modes such as naked-eye observation and optical instrument-assisted observation, the corresponding visual sensitivity adjustment coefficient was obtained from the visual adaptability reference table. The scattering-corrected visual distance data, the device sensitivity correction coefficient, and the visual sensitivity adjustment coefficient were weighted and fused to calculate the final dynamic actual visual distance data of the navigation mark.

[0043] Furthermore, the detailed analysis process for data on ships entering risk areas is as follows:

[0044] Acquire precise positioning data of navigation marks, calculate the safety radius based on the dynamic actual visible distance data of the navigation marks, and obtain safety warning radius data; use the precise positioning data of the navigation marks as the center, and construct the geometric shape of a circular area based on the safety warning radius data to obtain the initial circular safety area data;

[0045] Based on the wave height parameter in real-time sea state data, the additional wave impact is calculated on the safety warning radius data to obtain the additional wave impact radius data; based on the ocean current velocity parameter in real-time sea state data, the current direction and velocity correction is calculated on the additional wave impact radius data to obtain the corrected ocean current impact radius data.

[0046] The ocean current influence correction radius data and the safety warning radius data are overlaid and fused to obtain the comprehensive safety radius data; based on the comprehensive safety radius data, the initial circular safety area data is subjected to boundary expansion processing to obtain the ship intrusion risk area data.

[0047] In this embodiment of the invention, precise positioning data of navigation marks is acquired based on the Global Positioning System (GPS), including latitude and longitude coordinates with millimeter-level accuracy. Simultaneously, combined with dynamic actual visibility data of the navigation marks, a safety radius is calculated using a safety factor weighted calculation method: the dynamic actual visibility value of the navigation mark is multiplied by a preset safety factor, where the safety factor is determined according to the safety margin standard stipulated by the International Maritime Organization (IMO), to obtain the safety warning radius data. Then, using the precise positioning data of the navigation mark as the center, a circular safety area is constructed based on the safety warning radius data using a circular domain generation algorithm from computer graphics. This area represents a circular geographical boundary centered on the navigation mark and extending to the safety warning radius. Furthermore, wave height parameters from real-time sea state data are introduced, and a wave impact quantification model is used to calculate the additional wave impact. By using the ratio of wave height to ship draft and combining it with wave period parameters, the ship displacement correction caused by waves is calculated. This correction is added to the safety warning radius to obtain the additional wave impact radius data. Simultaneously, based on the ocean current velocity parameters in real-time sea state data, a vector decomposition method is used to calculate the impact of ocean currents on ship tracks: the ocean current velocity is decomposed into radial and tangential components; based on the angle between the ocean current direction and the normal of the safety zone boundary, the additional offset caused by the ocean current is calculated; and the wave impact additional radius data is corrected for flow direction and velocity to obtain the ocean current impact correction radius data. Finally, a radius superposition algorithm is used to weight and fuse the ocean current impact correction radius data with the safety warning radius data, where the weight coefficients are dynamically adjusted according to the sea state level to obtain comprehensive safety radius data. Based on this comprehensive safety radius data, geographic information system buffer analysis technology is used to perform boundary expansion processing on the initial circular safety zone data to generate the final multi-level ship intrusion risk zone data.

[0048] Furthermore, the calculation logic for illumination-adapted visual distance data is as follows:

[0049] Standard visual recognition threshold parameters are obtained from the visual perception parameter database. These parameters include the minimum light intensity value that the human eye can recognize and the sensitivity threshold of the device sensor. A light intensity comparison analysis is performed based on the light intensity data after atmospheric attenuation and the standard visual recognition threshold parameters. The basic visible distance data is calculated by the light intensity attenuation ratio.

[0050] The system acquires real-time visibility parameters from environmental status data, determines day and night status based on the solar intensity change curve, and generates day and night mode identifiers. Based on the day and night mode identifiers, the system selects the corresponding visual adaptation correction coefficients to perform visual sensitivity adaptive correction on the basic visual distance data, thereby obtaining preliminary adapted visual distance data.

[0051] Based on the real-time visibility parameters in the environmental status data, atmospheric transmittance compensation calculations are performed on the preliminary adaptive visibility distance data to obtain illumination-adapted visibility distance data.

[0052] In this embodiment of the invention, standard visual recognition threshold parameters calibrated according to the International Commission on Illumination (ICI) standards are obtained from a visual perception parameter database. This parameter database includes the minimum luminous intensity value that the human eye can recognize and the sensitivity threshold of the device's sensors. Based on a comparative analysis of the luminous intensity data after atmospheric attenuation and the standard visual recognition threshold parameters, a luminous intensity attenuation ratio calculation model is adopted: the ratio of the measured luminous intensity value after atmospheric attenuation to the standard recognition threshold is calculated, and multiplied by the distance correction factor corresponding to the atmospheric attenuation coefficient to obtain the basic visible distance data.

[0053] Subsequently, real-time visibility parameters from the environmental status data are acquired, and day / night status is determined based on the solar intensity variation curve. Ambient light intensity data continuously collected using a photometer is matched with preset day / night threshold curves. When the light intensity is below the preset threshold, a night mode identifier is generated; when it is above the preset threshold, a day mode identifier is generated. Based on the day / night mode identifiers, corresponding visual adaptation correction coefficients are selected from a visual adaptation parameter lookup table. The daytime coefficient ranges from 1.0 to 1.2, and the nighttime coefficient ranges from 2.0 to 3.0. The basic visibility distance data is multiplied by this correction coefficient to obtain preliminary adapted visibility distance data. Finally, based on the real-time visibility parameters from the environmental status data, atmospheric transmittance compensation is calculated for the preliminary adapted visibility distance data. Using the Cossid atmospheric transmittance model, the real-time visibility value is input into the transmittance calculation formula to obtain the atmospheric transmittance correction factor. This correction factor is then weighted and fused with the preliminary adapted visibility distance data, where the weighting coefficients are dynamically adjusted according to the visibility level, ultimately outputting the light-adapted visibility distance data.

[0054] Collision risk extraction module: Based on the data of the ship entering the risk area, the module performs real-time navigation trajectory deviation analysis to obtain the ship trajectory deviation risk coefficient; based on the ship trajectory deviation risk coefficient, the module extracts collision risk antecedent factors to obtain a collision risk antecedent factor set.

[0055] The operation logic of the collision risk extraction module is as follows:

[0056] The real-time latitude and longitude coordinates of the ship are obtained based on the data from the Automatic Identification System (AIS) and the intrusion status is determined by combining the data on the ship's intrusion into the risk area, and a ship intrusion status identifier is generated.

[0057] When the vessel enters the confirmed state, the preset safe channel centerline data is extracted, and the lateral deviation distance is calculated based on the vessel's real-time latitude and longitude coordinates to obtain the channel lateral deviation distance data.

[0058] Based on historical ship track data, the heading trend is analyzed, and the heading deviation angle is calculated by combining the preset safe navigation channel direction to obtain real-time heading deviation angle data;

[0059] The lateral deviation distance data and real-time heading deviation angle data of the waterway are weighted and fused to obtain the risk coefficient of the ship trajectory deviation.

[0060] Based on the risk coefficient of ship trajectory deviation, and combined with real-time ship speed data, distance data to the nearest navigation mark data, and visibility change rate data, a multi-dimensional risk factor integration is performed to obtain a collision risk antecedent factor set.

[0061] In this embodiment of the invention, the latitude and longitude coordinates of a ship are acquired in real time based on the data stream of the Automatic Identification System (AIS). A spatial analysis method using a Geographic Information System (GIS) is employed to overlay and analyze the ship's real-time position with data indicating the ship has entered a risky area. A point-area inclusion relationship judgment algorithm is used to generate a ship intrusion status identifier, a Boolean value where True indicates an intrusion status. When the identifier confirms an intrusion status, preset safe channel centerline data is extracted from the electronic nautical chart database. A spatial geometric calculation method is then used to calculate the vertical distance from the ship's real-time position to the channel centerline, yielding the lateral deviation distance data from the channel.

[0062] Simultaneously, based on the historical ship track database, a time series analysis method is used to model the ship's heading trend. A sliding window algorithm is employed to extract the heading change patterns of the most recent track points. Combined with a preset safe channel direction vector, the angle between the ship's actual heading and the standard channel direction is calculated, yielding real-time heading deviation angle data. Subsequently, the channel lateral deviation distance data and real-time heading deviation angle data are weighted and fused. A multi-factor risk assessment model is used, with distance deviation weight coefficients and heading deviation weight coefficients set based on maritime expert experience. The ship's trajectory deviation risk coefficient is then calculated through weighted summation.

[0063] Finally, based on the ship trajectory deviation risk coefficient, and combined with real-time ship speed data obtained from the Automatic Identification System (AIS), distance data to the nearest navigation mark obtained from the radar system, and visibility change rate data obtained from meteorological sensors, a multi-dimensional risk factor integration algorithm is adopted: First, each factor is normalized, converting the speed value into a speed risk coefficient, the distance value into a proximity risk coefficient, and the visibility change rate into a visibility risk coefficient; then, the analytic hierarchy process (AHP) is used to determine the weight of each factor, and a comprehensive collision risk value is obtained through weighted fusion calculation; finally, all risk factors and their weight coefficients are stored as a collision risk pre-factor set.

[0064] The collision risk extraction module also includes:

[0065] The ship trajectory deviation risk coefficient is normalized to obtain a standardized ship trajectory deviation risk coefficient.

[0066] Based on the real-time speed data of ships obtained by the Automatic Identification System, the speed hazard level is classified according to the real-time speed data to obtain the speed risk coefficient.

[0067] The ship's current position is obtained through the GPS positioning system. Combined with the navigation mark position data on the electronic nautical chart, the actual distance between the ship and the nearest navigation mark is calculated to obtain the nearest navigation mark distance data.

[0068] Based on continuous real-time visibility data acquired by environmental sensors, visibility change trend analysis is performed to obtain visibility change rate data;

[0069] The speed risk coefficient, the nearest beacon distance data, and the visibility change rate data are processed to be dimensionless to obtain standardized speed risk values, standardized distance risk values, and standardized visibility change risk values.

[0070] Based on the experience weight of maritime experts, a comprehensive collision risk index is obtained by weighted and integrated calculation of standardized ship trajectory deviation risk coefficient, standardized speed risk value, standardized distance risk value and standardized visibility change risk value.

[0071] The comprehensive collision risk index is combined with each standardized risk value to form a set of collision risk preconditions.

[0072] In this embodiment of the invention, the ship trajectory deviation risk coefficient is first normalized. A min-max normalization method is used to map the original risk coefficient to a range of 0-1. Risk coefficient threshold values ​​are set, with a minimum risk threshold of 0.2 and a maximum risk threshold of 0.8. A linear transformation formula is then used to convert the actual risk value into a standardized ship trajectory deviation risk coefficient. Simultaneously, based on the real-time data stream from the Automatic Identification System (AIS), ship speed information is extracted. A speed hazard level classification model is used: the speed value is divided into multiple risk intervals, and an interval mapping algorithm is used to convert the actual speed into the corresponding speed risk coefficient.

[0073] The ship's current latitude and longitude coordinates are obtained through a GPS positioning system. Combined with navigational aid location data stored in an electronic nautical chart database, the actual distance between the ship and the nearest navigational aid is calculated using a great circle distance algorithm, yielding the nearest navigational aid distance data. Based on continuous real-time visibility monitoring data acquired through an environmental sensor network, time series analysis is used to analyze visibility change trends. The visibility change rate (%) is obtained by calculating the ratio of the change in visibility value per unit time to the initial visibility value.

[0074] Subsequently, the speed risk coefficient, nearest beacon distance data, and visibility change rate data were dimensionless and standardized using the Z-score method: the mean and standard deviation of each parameter were calculated, and the original data were subtracted from the mean and divided by the standard deviation to obtain standardized speed risk values, standardized distance risk values, and standardized visibility change risk values ​​that conform to a normal distribution. Based on the set trajectory deviation weights of 0.3, speed risk weights of 0.25, distance risk weights of 0.25, and visibility risk weights of 0.2, a weighted fusion algorithm was used to calculate the weighted sum of the standardized ship trajectory deviation risk coefficient and the three standardized risk values ​​to obtain the comprehensive collision risk index.

[0075] The logic for generating the ship intrusion status identifier is as follows:

[0076] The system receives real-time navigation data packets from ships via the Automatic Identification System (AIS), extracts the ship's latitude and longitude coordinates from the data packets to obtain the ship's real-time positioning data, obtains the set of area boundary coordinates from the data of ships entering risk areas, and performs coordinate system transformation based on the latitude and longitude coordinates in the ship's real-time positioning data to obtain the ship's position coordinates and area boundary coordinates in a unified coordinate system.

[0077] Based on the ship's position coordinates and the area boundary coordinates in a unified coordinate system, the spatial position relationship between the ship and the risk area is calculated to obtain the ship's relative position data in the area. Based on the ship's relative position data in the area, a Boolean logic judgment is made on whether the ship has entered the risk area, and a ship intrusion status identifier is generated.

[0078] In this embodiment of the invention, a real-time navigation data packet of a ship is received through an Automatic Identification System (AIS), and latitude and longitude coordinate information is extracted from the message data using a data parsing algorithm. Subsequently, the set of regional boundary coordinates stored in the data on ships entering risk areas is obtained. A coordinate system transformation algorithm is used to uniformly convert the latitude and longitude coordinates and regional boundary coordinates in the real-time positioning data of the ship into a plane rectangular coordinate system. Through coordinate transformation matrix calculation, it is ensured that all spatial data are under the same measurement system, resulting in accurate ship position coordinates and regional boundary coordinates in a unified coordinate system.

[0079] Based on spatial data in a unified coordinate system, a computational geometry analysis method is used to calculate the spatial positional relationship between ships and risk areas. First, a polygonal geometric model of the risk area is constructed. The ray casting algorithm is then used to calculate the inclusion relationship between the ship's position and the polygonal region. By calculating the distance and azimuth from the ship's position to each boundary segment, relative positional data of the ship within the region, including relative distance, azimuth relationship, and inclusion status, is obtained. Finally, based on the relative positional data of the ship within the region, Boolean logic is applied: if the ship's position is inside the polygonal risk area or its distance from the boundary is less than a safety threshold, it is determined to be intruding; otherwise, it is considered non-intruding. This generates a binary ship intrusion status identifier, where 1 indicates intrusion and 0 indicates non-intrusion.

[0080] Ship navigation early warning module: Based on the collision risk pre-factor set, it performs multi-level early warning threshold dynamic evaluation to generate ship navigation risk early warning level; according to the early warning level, it generates corresponding early warning instructions and sends them to the ship autopilot system to execute intelligent early warning for maritime ship navigation.

[0081] The ship navigation early warning module specifically includes the following steps:

[0082] Standardized ship trajectory deviation risk coefficient, standardized speed risk value, standardized distance risk value, and standardized visibility change risk value are extracted from the collision risk antecedent factor set. Risk factor weight allocation is calculated to obtain a weighted risk factor set.

[0083] Based on the parameters of maritime safety regulations, the weighted risk factor set is dynamically classified into threshold levels, and a first-level warning threshold, a second-level warning threshold, and a third-level warning threshold are set to generate multi-level dynamic warning thresholds.

[0084] By comparing and analyzing the weighted risk factor set with the multi-level dynamic early warning thresholds step by step, the highest triggering early warning level is determined, and a ship navigation risk early warning level is generated.

[0085] In this embodiment of the invention, firstly, standardized vessel trajectory deviation risk coefficients, standardized speed risk values, standardized distance risk values, and standardized visibility change risk values ​​are extracted from the set of collision risk antecedent factors. A weighted allocation model based on the analytic hierarchy process (AHP) is used for calculation: the importance weight coefficients of each risk factor are obtained from a maritime expert experience database; each standardized risk value is multiplied by its corresponding weight coefficient and then summed to obtain a weighted risk factor set. Subsequently, the weighted risk factor set is dynamically divided into threshold levels, and a ternary quartile method is used to set multi-level warning thresholds: the upper quartile of historical risk data is taken as the first-level warning threshold (lower risk); the median is taken as the second-level warning threshold (medium risk); and the lower quartile is taken as the third-level warning threshold (higher risk). The threshold levels are dynamically adjusted according to real-time sea conditions. Finally, the weighted risk factor set is compared and analyzed with the multi-level dynamic early warning thresholds step by step. The priority judgment logic is from high to low. First, the three-level early warning thresholds are compared. If the weighted risk value exceeds the threshold, a high-risk early warning level is generated. Otherwise, the second-level early warning thresholds are compared, and so on, until the highest triggering early warning level is determined. Finally, the ship navigation risk early warning level data is output.

[0086] It should be noted that the interval and threshold sizes are set for ease of comparison. The size of the threshold depends on the amount of sample data and the base number set by those skilled in the art for each set of sample data, as long as it does not affect the proportional relationship between the parameter and the quantized value. Furthermore, the above formulas are all dimensionless calculations, and the formulas are derived from software simulations using a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0087] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0088] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0089] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A maritime navigation aid-guided intelligent system, characterized in that, include: Navigational Beacon Attenuation Analysis Module: Real-time data collection of navigational beacon working status and surrounding environment data is performed using navigational beacon status sensor group and environmental sensor to obtain navigational beacon status data and environmental status data; photoelectric output attenuation modeling of navigational beacon battery under low temperature conditions is performed on navigational beacon status data and environmental status data to obtain light intensity effective visible distance attenuation factor data. Ship risk calculation module: Based on the light intensity effective visibility distance attenuation factor data, dynamically evaluate the actual visibility distance of navigation marks under environmental coupling to obtain dynamic actual visibility distance data of navigation marks; Based on the actual visible distance data of the navigation mark, the risk area of ​​the vessel entering the risk area is calculated to obtain the data of the vessel entering the risk area. Collision risk extraction module: Based on the data of the ship entering the risk area, the module performs real-time navigation trajectory deviation analysis of the ship to obtain the ship trajectory deviation risk coefficient; Based on the ship trajectory deviation risk coefficient, collision risk precursor factors are extracted to obtain a collision risk precursor factor set. Ship navigation early warning module: Based on the aforementioned collision risk pre-factor set, performs multi-level early warning threshold dynamic evaluation to generate ship navigation risk early warning levels; Based on the aforementioned warning level, a corresponding warning instruction is generated and sent to the ship's autopilot system to execute intelligent warnings for maritime navigation.

2. The intelligent navigation aid system for ships at sea based on claim 1, characterized in that, The operating logic of the beacon attenuation analysis module is as follows: The navigation beacon status data is obtained by collecting data on battery voltage, battery temperature, real-time output light intensity, and LED operating current through the navigation beacon status sensor group; environmental status data is obtained by collecting ambient temperature, seawater temperature, air humidity, and real-time visibility through environmental sensors. The battery capacity decay coefficient under low-temperature conditions is calculated based on battery temperature and ambient temperature data to obtain the effective battery capacity decay coefficient; the light intensity output decay ratio is calculated based on the effective battery capacity decay coefficient and real-time output light intensity data to obtain the light intensity output decay ratio data. Based on the light intensity output attenuation ratio data and real-time visibility data, atmospheric transmittance correction calculation is performed to obtain the effective visible distance attenuation factor data.

3. The intelligent navigation beacon-based system for maritime vessels according to claim 1, characterized in that, The operational logic of the ship risk calculation module is as follows: Based on the effective visible distance attenuation factor data, the nominal light intensity of the navigation mark is attenuated and corrected to obtain the actual effective light intensity data of the navigation mark. The real-time visibility parameters in the environmental status data are obtained, and the atmospheric transmittance correction calculation is performed on the actual effective light intensity data of the navigation mark based on the real-time visibility parameters to obtain the light intensity data after atmospheric attenuation. The light intensity data after atmospheric attenuation is processed by visual recognition threshold conversion to obtain the dynamic actual visible distance data of the navigation mark. Using the geographical location of the navigation mark as the center, a circular safety warning zone is constructed based on the dynamic actual visible distance data of the navigation mark, thus obtaining the initial safety warning zone data; Based on real-time sea state data, the boundaries of the initial safety warning area are blurred to obtain data on ships entering the risk area.

4. The intelligent navigation aid system for ships at sea based on claim 3, characterized in that, The atmospheric attenuated light intensity data undergoes visual recognition threshold conversion processing. The specific processing steps include: Obtain standard visual recognition threshold parameters, and calculate the basic visible distance based on the light intensity data after atmospheric attenuation to obtain basic visible distance data; perform day and night visual adaptation correction on the basic visible distance data based on the real-time visibility parameters in the environmental state data to obtain light-adapted visible distance data. Based on the real-time visibility parameters, atmospheric scattering effect correction is applied to the illumination-adapted visibility distance data to obtain scattering-corrected visibility distance data. Based on the device sensor type parameters and visual adaptability level parameters, visual sensitivity differential adjustments are made to the scattering correction visual distance data to obtain the dynamic actual visual distance data of the navigation mark.

5. The intelligent navigation aid system for ships at sea based on claim 3, characterized in that, The detailed analysis process of data on ships entering risk areas is as follows: Acquire precise positioning data of navigation marks, calculate the safety radius based on the dynamic actual visible distance data of the navigation marks, and obtain safety warning radius data; use the precise positioning data of the navigation marks as the center, and construct the geometric shape of a circular area based on the safety warning radius data to obtain the initial circular safety area data; Based on the wave height parameter in real-time sea state data, the additional wave impact is calculated on the safety warning radius data to obtain the additional wave impact radius data; based on the ocean current velocity parameter in real-time sea state data, the current direction and velocity correction is calculated on the additional wave impact radius data to obtain the corrected ocean current impact radius data. The ocean current impact correction radius data and the safety warning radius data are overlaid and fused to obtain the comprehensive safety radius data; Based on the comprehensive safety radius data, the initial circular safety area data is expanded to obtain data on ships entering the risk area.

6. The intelligent navigation aid system for maritime vessels according to claim 4, characterized in that, The calculation logic for illumination-adaptive visibility distance data is as follows: Standard visual recognition threshold parameters are obtained from the visual perception parameter database. These parameters include the minimum light intensity value that the human eye can recognize and the sensitivity threshold of the device sensor. A light intensity comparison analysis is performed based on the light intensity data after atmospheric attenuation and the standard visual recognition threshold parameters. The basic visible distance data is calculated by the light intensity attenuation ratio. Acquire real-time visibility parameters from environmental status data, determine day and night status based on solar intensity change curves, and generate day and night mode identifiers; Based on the day and night mode identifier, select the corresponding visual adaptation correction coefficient, perform visual sensitivity adaptive correction on the basic visual distance data, and obtain preliminary adapted visual distance data. Based on the real-time visibility parameters in the environmental status data, atmospheric transmittance compensation calculations are performed on the preliminary adaptive visibility distance data to obtain illumination-adapted visibility distance data.

7. The intelligent navigation aid system for ships at sea based on claim 1, characterized in that, The operation logic of the collision risk extraction module is as follows: The real-time latitude and longitude coordinates of the ship are obtained based on the data from the Automatic Identification System (AIS) and the intrusion status is determined by combining the data on the ship's intrusion into the risk area, and a ship intrusion status identifier is generated. When the vessel enters the confirmed state, the preset safe channel centerline data is extracted, and the lateral deviation distance is calculated based on the vessel's real-time latitude and longitude coordinates to obtain the channel lateral deviation distance data. Based on historical ship track data, the heading trend is analyzed, and the heading deviation angle is calculated by combining the preset safe navigation channel direction to obtain real-time heading deviation angle data; The lateral deviation distance data and real-time heading deviation angle data of the waterway are weighted and fused to obtain the risk coefficient of the ship trajectory deviation. Based on the risk coefficient of ship trajectory deviation, and combined with real-time ship speed data, distance data to the nearest navigation mark data, and visibility change rate data, a multi-dimensional risk factor integration is performed to obtain a collision risk antecedent factor set.

8. The intelligent navigation beacon-based system for maritime vessels according to claim 7, characterized in that, The collision risk extraction module also includes: The ship trajectory deviation risk coefficient is normalized to obtain a standardized ship trajectory deviation risk coefficient. Based on the real-time speed data of ships obtained by the Automatic Identification System, the speed hazard level is classified according to the real-time speed data to obtain the speed risk coefficient. The ship's current position is obtained through the GPS positioning system. Combined with the navigation mark position data on the electronic nautical chart, the actual distance between the ship and the nearest navigation mark is calculated to obtain the nearest navigation mark distance data. Based on continuous real-time visibility data acquired by environmental sensors, visibility change trend analysis is performed to obtain visibility change rate data; The speed risk coefficient, the nearest beacon distance data, and the visibility change rate data are processed to be dimensionless to obtain standardized speed risk values, standardized distance risk values, and standardized visibility change risk values. Based on the experience weight of maritime experts, a comprehensive collision risk index is obtained by weighted and integrated calculation of standardized ship trajectory deviation risk coefficient, standardized speed risk value, standardized distance risk value and standardized visibility change risk value. The comprehensive collision risk index is combined with each standardized risk value to form a set of collision risk preconditions.

9. The intelligent navigation aid system for maritime vessels according to claim 7, characterized in that, The logic for generating the ship intrusion status identifier is as follows: The system receives real-time navigation data packets from ships via the Automatic Identification System (AIS), extracts the ship's latitude and longitude coordinates from the data packets to obtain the ship's real-time positioning data, obtains the set of area boundary coordinates from the data of ships entering risk areas, and performs coordinate system transformation based on the latitude and longitude coordinates in the ship's real-time positioning data to obtain the ship's position coordinates and area boundary coordinates in a unified coordinate system. Based on the ship's position coordinates and the area boundary coordinates in a unified coordinate system, the spatial position relationship between the ship and the risk area is calculated to obtain the ship's relative position data in the area. Based on the ship's relative position data in the area, a Boolean logic judgment is made on whether the ship has entered the risk area, and a ship intrusion status identifier is generated.

10. The intelligent navigation aid system for ships at sea according to claim 1, characterized in that, The ship navigation early warning module specifically includes the following steps: Standardized ship trajectory deviation risk coefficient, standardized speed risk value, standardized distance risk value, and standardized visibility change risk value are extracted from the collision risk antecedent factor set. Risk factor weight allocation is calculated to obtain a weighted risk factor set. Based on the parameters of maritime safety regulations, the weighted risk factor set is dynamically classified into threshold levels, and a first-level warning threshold, a second-level warning threshold, and a third-level warning threshold are set to generate multi-level dynamic warning thresholds. By comparing and analyzing the weighted risk factor set with the multi-level dynamic early warning thresholds step by step, the highest triggering early warning level is determined, and a ship navigation risk early warning level is generated.

Images