A marine visibility early warning method based on real-time data monitoring

Abstract

The present invention belongs to the field of marine visibility monitoring and relates to data analysis technology. Specifically, it is a marine visibility early warning method based on real-time data monitoring, which includes a monitoring and early warning sub-method and a processing and decision-making sub-method. The method comprises the following steps: real-time monitoring and analysis of the marine visibility of marine vessels: marking marine vessels as monitoring objects, dividing the monitoring area into L1 sector-shaped areas of equal area with the monitoring object as the center, and sorting the sector-shaped areas counterclockwise according to the navigation direction of the monitoring object to obtain the serial numbers of the sector-shaped areas; the present invention can combine multiple risk influencing parameters of marine vessels during navigation to perform a comprehensive analysis to obtain a risk assessment coefficient, accurately assess and provide feedback on the navigation risk of marine vessels through the risk assessment coefficient, and promptly issue an early warning when there is a navigation risk, so that the management personnel of the marine vessels can promptly take countermeasures to avoid the risk.

Description

Technical Field

[0001] The present invention belongs to the field of marine visibility monitoring, relates to data analysis technology, and specifically is a marine visibility early warning method based on real-time data monitoring. Background Art

[0002] The main factors affecting visibility at sea include fog, snow, rain, etc. When visibility is good, ships can clearly observe surrounding objects, navigation marks and other ships to ensure navigation safety; when visibility is poor, such as due to fog, rain, snow, etc., the ship's vision is limited and it is unable to detect and avoid other ships or obstacles in time, increasing the risk of collision, grounding, etc.

[0003] Patent publication number CN101672768B discloses a method for acquiring the atmospheric horizontal visibility field under dense fog conditions at sea. This method effectively overcomes shortcomings of existing technologies, such as the scarcity of observation data from offshore atmospheric visibility stations and the inability of satellite remote sensing methods to determine whether clouds are grounded. It provides a fast and quantitative offshore atmospheric horizontal visibility field for various maritime activities and has broad application prospects. However, this method cannot combine multiple parameters such as offshore visibility, observed obstacles, and historical accident data for comprehensive risk analysis, resulting in a lack of assurance of the accuracy of risk assessment results for ships.

[0004] In response to the above technical problems, this application proposes a solution. Summary of the Invention

[0005] The purpose of the present invention is to provide a marine visibility early warning method based on real-time data monitoring, which is used to solve the problem that the existing technology cannot combine multiple parameters such as marine visibility, observed obstacles and historical accident data to conduct comprehensive risk analysis;

[0006] The technical problem to be solved by the present invention is: how to provide a maritime visibility early warning method based on real-time data monitoring that can combine multiple parameters such as maritime visibility, observed obstacles, and historical accident data for comprehensive risk analysis.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A marine visibility warning method based on real-time data monitoring includes a monitoring and warning sub-method and a processing and decision-making sub-method.

[0009] The monitoring and early warning sub-method includes the following steps:

[0010] Step S1: Real-time monitoring and analysis of the visibility of marine vessels at sea: mark the marine vessel as the monitoring object, draw a circle with the monitoring object as the center and r1 as the radius, mark the resulting circular area as the monitoring area, divide the monitoring area into L1 sectors of equal area with the monitoring object as the center, and sort the sectors counterclockwise according to the navigation direction of the monitoring object to obtain the serial number of the sector; perform visibility analysis on the sector to obtain the visibility value NJ of the monitoring object;

[0011] Step S2: Detect and analyze obstacles to marine vessels: obtain the obstacle coefficient ZA of the sector area; sum and average the obstacle coefficients ZA of all sector areas to obtain the obstacle risk value ZF;

[0012] Step S3: Analyze historical accidents in the navigation area of ​​ocean vessels: retrieve the number of historical accidents that occurred in the monitoring area in the recent M1 years and mark it as the historical accident value LS, and mark the number of historical accidents that occurred in the fan-shaped area as the regional accident value;

[0013] Step S4: Evaluate and analyze the navigation risk of ocean vessels: numerically calculate the visibility value NJ, the obstacle risk value ZF, and the accident risk value LS to obtain the risk assessment coefficient FX of the monitored object; use the risk assessment coefficient FX to determine whether the navigation risk of the monitored object meets the requirements, and execute the processing decision sub-method if it does not meet the requirements.

[0014] Furthermore, in step S1, the specific process of performing visibility analysis on the sector area includes: obtaining the satellite electrical signal of the monitoring area, converting the satellite electrical signal into a digital signal, outputting the original image data, and then performing geometric correction, projection transformation, sensor radiation correction, planetary reflectivity calculation, atmospheric condition judgment and classification; finally, combining the measured visibility data to generate the visibility level of each sector area, and summing and averaging the visibility levels of all sector areas to obtain the visibility value NJ of the monitored object.

[0015] Furthermore, in step S2, the process of obtaining the obstacle coefficient ZA within the sector area includes: detecting obstacle targets within the sector area by radar and obtaining obstacle quantity values ​​and obstacle distance values, and obtaining the obstacle coefficient ZA of the monitored object within the sector area by numerically calculating the obstacle quantity values ​​and obstacle distance values, where the obstacle quantity value is the number of obstacle targets found in the sector area, and the obstacle distance value is the average of the straight-line distance values ​​between all obstacle targets in the sector area and the monitored object.

[0016] Furthermore, the specific process of determining whether the navigation risk of the monitored object meets the requirements includes: comparing the risk assessment coefficient FX with the preset risk assessment threshold FXmax: if the risk assessment coefficient FX is less than the risk assessment threshold FXmax, then it is determined that the navigation risk of the monitored object meets the requirements; if the risk assessment coefficient FX is greater than or equal to the risk assessment threshold FXmax, then it is determined that the navigation risk of the monitored object does not meet the requirements, and the processing decision sub-method is executed.

[0017] Furthermore, the decision-making sub-method includes the following steps:

[0018] Step P1: Risk data statistics are collected for the sector area of ​​the monitored object: visibility risk areas, obstacle risk areas, and accident risk areas in the sector area are marked respectively; the serial numbers of all visibility risk areas, obstacle risk areas, and accident risk areas constitute a distribution set;

[0019] Step P2: Analyze the risk distribution of the monitored object: Calculate the variance of the distribution set to obtain the dispersion coefficient, and use the dispersion coefficient to determine whether the monitored object has risk concentration. If it has risk concentration, execute step P3;

[0020] Step P3: Conduct risk avoidance decision analysis on the monitored object: obtain the decision performance value of the monitored object, and compare the decision performance value with the preset decision performance threshold: if the decision performance value is less than the decision performance threshold, generate a steering processing signal and send the steering processing signal to the manager's mobile terminal; if the decision performance value is greater than or equal to the decision performance threshold, generate a speed reduction processing signal and send the speed reduction processing signal to the manager's mobile terminal.

[0021] Furthermore, in step P1, the sector-shaped areas are sorted in order of visibility levels from small to large to obtain a visibility sequence, the first L2 sector-shaped areas in the visibility sequence are intercepted and marked as visibility risk areas, the sector-shaped areas are arranged in order of obstacle coefficient ZA values ​​from large to small to obtain an obstacle sequence, the first L2 sector-shaped areas in the obstacle sequence are intercepted and marked as obstacle risk areas, the sector-shaped areas are arranged in order of regional accident values ​​from large to small to obtain an accident sequence, the first L2 sector-shaped areas in the accident sequence are intercepted and marked as accident risk areas.

[0022] Furthermore, in step P2, the specific process of determining whether the monitored object has risk concentration includes: comparing the dispersion coefficient with a preset dispersion threshold: if the dispersion coefficient is greater than or equal to the dispersion threshold, it is determined that the monitored object does not have risk concentration, a risk warning signal is generated and the risk warning signal is sent to the mobile phone terminal of the manager; if the dispersion coefficient is less than the dispersion threshold, it is determined that the monitored object has risk concentration, and step P3 is executed.

[0023] Furthermore, in step P3, the process of obtaining the decision performance value includes: marking the sector-shaped area that is marked as the visibility risk area, the obstacle risk area, and the accident risk area as the risk overlap area, summing up the serial numbers of all risk overlap areas and taking the average value to obtain the risk distribution value, and marking the absolute value of the difference between the risk distribution value and L1 / 2 as the decision performance value.

[0024] The present invention has the following beneficial effects:

[0025] The monitoring and early warning sub-method can combine multiple risk impact parameters of marine vessels during navigation to conduct a comprehensive analysis to obtain a risk assessment coefficient. The risk assessment coefficient can be used to accurately assess and provide feedback on the navigation risk of marine vessels, and timely issue early warnings when there are navigation risks, so that marine vessel managers can take timely countermeasures to avoid risks.

[0026] The processing decision sub-method can be used to conduct processing decision analysis on the monitored object when the navigation risk does not meet the requirements, and the risk concentration state of the monitored object can be fed back through the dispersion coefficient. When the monitored object has risk concentration, the risk distribution value can be generated by the serial number of the repeatedly marked sector area. The final immediate processing plan can be screened through the risk distribution value to improve the effectiveness of the system's risk avoidance measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0028] Figure 1 This is a flow chart of a method according to embodiment 1 of the present invention;

[0029] Figure 2 This is a flow chart of the method of embodiment 2 of the present invention. DETAILED DESCRIPTION

[0030] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0031] A marine visibility warning method based on real-time data monitoring includes a monitoring and warning sub-method and a processing and decision-making sub-method.

[0032] Example 1: Figure 1 As shown, the monitoring and early warning sub-method includes the following steps:

[0033] Step S1: Real-time monitoring and analysis of the visibility of marine vessels at sea: mark the marine vessel as the monitoring object, draw a circle with the monitoring object as the center and r1 as the radius, r1 is a numerical constant, and the specific value of r1 is set by the management personnel, mark the obtained circular area as the monitoring area, divide the monitoring area into L1 sector areas of equal area with the monitoring object as the center, L1 is a numerical constant, and the specific value of L1 is set by the management personnel, and sort the sector areas counterclockwise according to the navigation direction of the monitoring object to obtain the sequence number of the sector areas; perform visibility analysis on the sector areas: obtain the satellite electrical signal of the monitoring area, convert the satellite electrical signal into a digital signal, output the original image data, and then perform geometric correction, projection transformation, sensor radiation correction, planetary reflectivity calculation, atmospheric condition discrimination and classification; finally, based on the measured visibility data, use the visibility space extension and atmospheric parameter solution method to perform quantitative visibility calculation to obtain the visibility level of each sector area, and sum and average the visibility levels of all sector areas to obtain the visibility value NJ of the monitoring object;

[0034] Step S2: Detect and analyze obstacles to marine vessels: Detect obstacles within a sector area using radar, and obtain the obstacle coefficient ZA of the monitored object within the sector area using the formula ZA=k1×SL-k2×JL, where k1 and k2 are proportional coefficients, and k1>k2>1, SL and JL are the number of obstacles and the distance to the obstacle in the sector area, respectively. The number of obstacles is the number of obstacles found within the sector area, and the distance to the obstacle is the average of the straight-line distances between all obstacles and the monitored object within the sector area. Sum and average the obstacle coefficients ZA of all sector areas to obtain the obstacle risk value ZF.

[0035] Step S3: Analyze historical accidents in the navigation area of ​​ocean vessels: retrieve the number of historical accidents that occurred in the monitoring area in the recent M1 years and mark it as the historical accident value LS, and mark the number of historical accidents that occurred in the fan-shaped area as the regional accident value;

[0036] Step S4: Evaluate and analyze the navigation risks of marine vessels: Obtain the risk assessment coefficient FX of the monitored object through the formula FX = c1×ZF + c2×LS - c3×NJ, where c1, c2, and c3 are all proportionality coefficients, and c1 > c2 > c3 > 1. The risk assessment coefficient FX is a value reflecting the level of navigation risk of the monitored object. The larger the value of the risk assessment coefficient FX, the higher the navigation risk level of the monitored object under the current state, and the higher the danger of continuing to navigate according to the current heading and state; Compare the risk assessment coefficient FX with the preset risk assessment threshold FXmax: If the risk assessment coefficient FX is less than the risk assessment threshold FXmax, it is determined that the navigation risk of the monitored object meets the requirements; If the risk assessment coefficient FX is greater than or equal to the risk assessment threshold FXmax, it is determined that the navigation risk of the monitored object does not meet the requirements, and the processing decision sub-method is executed; Combine multiple risk impact parameters during the navigation of marine vessels for comprehensive analysis to obtain the risk assessment coefficient, and accurately evaluate and feedback the navigation risk of marine vessels through the risk assessment coefficient. When there is a navigation risk, give an early warning in a timely manner so that the management personnel of marine vessels can take corresponding measures to avoid risks in a timely manner.

[0037] Embodiment 2: As Figure 2 shown, the processing decision sub-method includes the following steps:

[0038] Step P1: Statistically analyze the risk data of the fan-shaped area of the monitored object: Sort the fan-shaped areas in ascending order of visibility level to obtain the visibility sequence, intercept the first L2 fan-shaped areas of the visibility sequence and mark them as visibility risk areas. L2 is a numerical constant, and the specific value of L2 is set by the management personnel themselves, and L2 < L1; Sort the fan-shaped areas in descending order of the obstacle coefficient ZA value to obtain the obstacle sequence, intercept the first L2 fan-shaped areas of the obstacle sequence and mark them as obstacle risk areas, sort the fan-shaped areas in descending order of the regional accident value to obtain the accident sequence, and intercept the first L2 fan-shaped areas of the accident sequence and mark them as accident risk areas; The set composed of the serial numbers of all visibility risk areas, obstacle risk areas, and accident risk areas is the distribution set;

[0039] Step P2: Analyze the risk distribution of the monitored object: Calculate the variance of the distribution set to obtain the dispersion coefficient, and compare the dispersion coefficient with the preset dispersion threshold: If the dispersion coefficient is greater than or equal to the dispersion threshold, it is determined that the monitored object does not have risk concentration, generate a risk warning signal and send the risk warning signal to the mobile terminal of the management personnel; If the dispersion coefficient is less than the dispersion threshold, it is determined that the monitored object has risk concentration, and execute Step P3;

[0040] Step P3: Perform risk avoidance decision analysis on the monitored object: mark the sector areas marked as visibility risk areas, obstacle risk areas and accident risk areas as risk overlap areas, sum and average the serial numbers of all risk overlap areas to obtain the risk distribution value, mark the absolute value of the difference between the risk distribution value and L1 / 2 as the decision performance value, and compare the decision performance value with the preset decision performance threshold: if the decision performance value is less than the decision performance threshold, generate a steering processing signal and send the steering processing signal to the manager's mobile terminal; if the decision performance value is greater than or equal to the decision performance threshold, generate a speed reduction processing signal and send the speed reduction processing signal to the manager's mobile terminal; when the navigation risk does not meet the requirements, perform a processing decision analysis on the monitored object, and use the dispersion coefficient to provide feedback on the risk concentration state of the monitored object. When the monitored object has risk concentration, the serial numbers of the repeatedly marked sector areas are used to generate the risk distribution value, and the final immediate processing plan is screened by the risk distribution value to improve the effectiveness of the system's risk avoidance measures.

[0041] A method for early warning of marine visibility based on real-time data monitoring performs real-time monitoring and analysis on the marine visibility of marine vessels during operation: the marine vessel is marked as the monitoring object, a circle is drawn with the monitoring object as the center and r1 as the radius, the obtained circular area is marked as the monitoring area, and the monitoring area is divided into L1 sector-shaped areas of equal area with the monitoring object as the center; visibility analysis is performed on all sector-shaped areas to obtain the visibility value NJ of the monitoring object; obstacle targets of marine vessels are detected and analyzed to obtain the obstacle risk value ZF of the monitoring object; historical accident analysis is performed on the navigation area of ​​marine vessels to obtain the historical accident value LS of the monitoring object; and the visibility value is analyzed. NJ, obstacle risk value ZF and historical accident value LS are numerically calculated to obtain the risk assessment coefficient FX, and the risk assessment coefficient is used to determine whether the navigation risk of the monitored object meets the requirements. When the requirements are not met, the risk data of the fan-shaped area of ​​the monitored object is statistically analyzed and a distribution set is generated. The variance of the distribution set is calculated to obtain the dispersion coefficient. The dispersion coefficient is used to determine whether the monitored object has risk concentration. When the monitored object has risk concentration, a risk avoidance decision analysis is performed on the monitored object and a decision performance value is obtained. The decision performance value is used to generate a speed reduction processing signal or a steering processing signal and send it to the mobile phone terminal of the manager.

[0042] The above content is merely an example and explanation of the structure of the present invention. Those skilled in the art may make various modifications or additions to the described specific embodiments or replace them in a similar manner. As long as they do not deviate from the structure of the invention or exceed the scope defined by the claims, they should all fall within the scope of protection of the present invention.

[0043] The above formulas are all obtained by collecting a large amount of data and performing software simulation to obtain a formula that is close to the actual value. The coefficients in the formula are set by those skilled in the art based on actual conditions; for example: the formula FX = c1 × ZF + c2 × LS - c3 × NJ; those skilled in the art collect multiple groups of sample data and set a corresponding risk assessment coefficient for each group of sample data; the set risk assessment coefficients and the collected sample data are substituted into the formula, and any three formulas form a three-variable linear equation system. The calculated coefficients are screened and averaged to obtain the values ​​of c1, c2, and c3 as 3.51, 2.85, and 2.27, respectively;

[0044] The size of the coefficient is to quantify each parameter to obtain a specific numerical value, which is convenient for subsequent comparison. The size of the coefficient depends on the amount of sample data and the preliminary setting of the corresponding risk assessment coefficient for each set of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantified value, such as the risk assessment coefficient is proportional to the value of the obstacle risk value.

[0045] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the present invention. In this specification, schematic representations of these terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

[0046] The preferred embodiments of the present invention disclosed above are intended only to help illustrate the present invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the present invention to specific embodiments. Obviously, many modifications and variations are possible based on the contents of this specification. These embodiments are selected and described in detail in this specification to better explain the principles and practical applications of the present invention, thereby enabling those skilled in the art to better understand and utilize the present invention. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A marine visibility early warning method based on real-time data monitoring, characterized in that: It includes monitoring and early warning sub-method and processing and decision-making sub-method; The monitoring and early warning sub-method includes the following steps: Step S1: Real-time monitoring and analysis of the visibility of marine vessels at sea: mark the marine vessel as the monitoring object, draw a circle with the monitoring object as the center and r1 as the radius, mark the resulting circular area as the monitoring area, divide the monitoring area into L1 sectors of equal area with the monitoring object as the center, and sort the sectors counterclockwise according to the navigation direction of the monitoring object to obtain the serial number of the sector; perform visibility analysis on the sector to obtain the visibility value NJ of the monitoring object; Step S2: Detect and analyze obstacles to marine vessels: obtain the obstacle coefficient ZA of the sector area; sum and average the obstacle coefficients ZA of all sector areas to obtain the obstacle risk value ZF; Step S3: Analyze historical accidents in the navigation area of ​​ocean vessels: retrieve the number of historical accidents that occurred in the monitoring area in the recent M1 years and mark it as the historical accident value LS, and mark the number of historical accidents that occurred in the fan-shaped area as the regional accident value; Step S4: Evaluate and analyze the navigation risk of the marine vessel: numerically calculate the visibility value NJ, the obstacle risk value ZF, and the accident risk value LS to obtain the risk assessment coefficient FX of the monitored object; determine whether the navigation risk of the monitored object meets the requirements based on the risk assessment coefficient FX, and execute the processing decision sub-method if it does not meet the requirements; The decision-making sub-method includes the following steps: Step P1: Risk data statistics are collected for the sector area of ​​the monitored object: visibility risk areas, obstacle risk areas, and accident risk areas in the sector area are marked respectively; the serial numbers of all visibility risk areas, obstacle risk areas, and accident risk areas constitute a distribution set; Step P2: Analyze the risk distribution of the monitored object: Calculate the variance of the distribution set to obtain the dispersion coefficient, and use the dispersion coefficient to determine whether the monitored object has risk concentration. If it has risk concentration, execute step P3; Step P3: Perform risk avoidance decision analysis on the monitored object: Obtain the decision performance value of the monitored object and compare it with a preset decision performance threshold. If the decision performance value is less than the decision performance threshold, generate a steering processing signal and send the steering processing signal to the administrator's mobile terminal; if the decision performance value is greater than or equal to the decision performance threshold, generate a speed reduction processing signal and send the speed reduction processing signal to the administrator's mobile terminal. In step P1, the sector areas are sorted in order of visibility level from small to large to obtain a visibility sequence, the first L2 sector areas in the visibility sequence are intercepted and marked as visibility risk areas, the sector areas are arranged in order of obstacle coefficient ZA values ​​from large to small to obtain an obstacle sequence, the first L2 sector areas in the obstacle sequence are intercepted and marked as obstacle risk areas, the sector areas are arranged in order of regional accident values ​​from large to small to obtain an accident sequence, the first L2 sector areas in the accident sequence are intercepted and marked as accident risk areas; In step P3, the process of obtaining the decision performance value includes: marking the sector-shaped area that is marked as the visibility risk area, the obstacle risk area, and the accident risk area as the risk overlap area, summing up the serial numbers of all risk overlap areas and taking the average value to obtain the risk distribution value, and marking the absolute value of the difference between the risk distribution value and L1 / 2 as the decision performance value.

2. The method for early warning of marine visibility based on real-time data monitoring according to claim 1, characterized in that: In step S1, the specific process of performing visibility analysis on the sector area includes: obtaining the satellite electrical signal of the monitoring area, converting the satellite electrical signal into a digital signal, outputting the original image data, and then performing geometric correction, projection transformation, sensor radiation correction, planetary reflectivity calculation, atmospheric condition judgment and classification; finally, combining the measured visibility data to generate the visibility level of each sector area, and summing and averaging the visibility levels of all sector areas to obtain the visibility value NJ of the monitored object.

3. The method for early warning of marine visibility based on real-time data monitoring according to claim 2, characterized in that: In step S2, the process of obtaining the obstacle coefficient ZA in the sector area includes: detecting obstacle targets in the sector area by radar and obtaining obstacle quantity values ​​and obstacle distance values, and obtaining the obstacle coefficient ZA of the monitored object in the sector area by numerically calculating the obstacle quantity values ​​and obstacle distance values. The obstacle quantity value is the number of obstacle targets found in the sector area, and the obstacle distance value is the average of the straight-line distance values ​​between all obstacle targets in the sector area and the monitored object.

4. A method for early warning of marine visibility based on real-time data monitoring according to claim 3, characterized in that: The specific process of determining whether the navigation risk of the monitored object meets the requirements includes: comparing the risk assessment coefficient FX with the preset risk assessment threshold FXmax: if the risk assessment coefficient FX is less than the risk assessment threshold FXmax, then it is determined that the navigation risk of the monitored object meets the requirements; if the risk assessment coefficient FX is greater than or equal to the risk assessment threshold FXmax, then it is determined that the navigation risk of the monitored object does not meet the requirements, and the processing decision sub-method is executed.

5. The method for early warning of marine visibility based on real-time data monitoring according to claim 4, characterized in that: In step P2, the specific process of determining whether the monitored object has risk concentration includes: comparing the dispersion coefficient with the preset dispersion threshold: if the dispersion coefficient is greater than or equal to the dispersion threshold, it is determined that the monitored object does not have risk concentration, and a risk warning signal is generated and sent to the mobile phone terminal of the manager; if the dispersion coefficient is less than the dispersion threshold, it is determined that the monitored object has risk concentration, and step P3 is executed.

Images