Marine fuel leakage control method and system

Abstract

The invention provides a marine fuel leakage control method and system, and belongs to the technical field of ship engineering.The method comprises the steps that multi-physics field data are collected, and the multi-physics field data comprise marine fuel concentration data, temperature data and pressure data; performing feature extraction on the marine fuel concentration data, the temperature data and the pressure data to obtain marine fuel leakage feature parameters; the marine fuel leakage characteristic parameters are input into a marine fuel leakage early warning model for prediction, and the marine fuel leakage probability and the marine fuel leakage position are obtained; and generating a marine fuel leakage control instruction based on the marine fuel leakage probability and / or the marine fuel leakage position. According to the method, the leakage probability and position of the marine fuel are accurately predicted, and the safety of ships and personnel is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of ship engineering, and in particular to a method and system for controlling leakage of marine fuel. Background Art

[0002] With the growing global demand for clean energy, marine fuel cells, as a highly efficient and environmentally friendly power source, are increasingly being used in the marine sector. Common fuel cell fuels, such as hydrogen, are flammable and explosive, and safety issues during storage, transportation, and use have become a key factor restricting the large-scale application of marine fuel cells.

[0003] Existing marine fuel cell safety assurance technologies, including hydrogen leak monitoring, suffer from numerous shortcomings. Many conventional technologies rely on a single type of sensor, such as hydrogen concentration sensors, to monitor leaks. This approach fails to fully capture the multi-physics information underlying system operation. When environmental factors are complex or hydrogen leaks interact with other physical phenomena, incomplete data can easily lead to missed or misjudgment. For example, in areas with frequent temperature and pressure fluctuations, such as a ship's engine room, a single hydrogen concentration sensor may not accurately distinguish between normal concentration fluctuations and those caused by leaks, delaying the identification of potential hazards. When troubleshooting potential faults, conventional technologies struggle to provide real-time and comprehensive monitoring of the fuel cell system's operating status. In many cases, the problem can only be identified after a fault occurs, through manual inspection or limited equipment diagnostics, failing to detect potential faults at their earliest stages. This results in a high number of downtimes due to system failures, severely impacting the continuity and stability of ship operations and increasing operating costs. For example, traditional monitoring methods may fail to detect localized overheating within a fuel cell stack until the fault severely impacts battery performance or even causes a safety incident.

[0004] Therefore, how to accurately predict and efficiently respond to marine fuel leakage to ensure the safety of life and property of ships and their personnel is a technical problem that needs to be solved urgently. Summary of the Invention

[0005] In view of this, it is necessary to provide a method and system for controlling marine fuel leakage, which can be used to accurately predict and efficiently respond to marine fuel leakage, so as to ensure the safety of life and property of the ship and its personnel.

[0006] To achieve the above objectives, in a first aspect, the present invention provides a method for controlling marine fuel leakage, comprising: Collecting multi-physics field data, wherein the multi-physics field data includes marine fuel concentration data, temperature data, and pressure data; performing feature extraction on the marine fuel concentration data, temperature data, and pressure data to obtain marine fuel leakage characteristic parameters; Inputting the marine fuel leakage characteristic parameters into a marine fuel leakage early warning model for prediction to obtain a marine fuel leakage probability and a marine fuel leakage location; A bunker fuel leakage control instruction is generated based on the bunker fuel leakage probability and / or the bunker fuel leakage location.

[0007] In a possible implementation, the marine fuel leakage characteristic parameters include marine fuel concentration change rate, temperature gradient, and pressure fluctuation amplitude; The feature extraction of the multi-physical field data to obtain the marine fuel leakage characteristic parameters includes: Calculating a difference in marine fuel concentration between adjacent time points using the collected marine fuel concentration data, and determining a marine fuel concentration change rate based on the marine fuel concentration difference and a time difference between adjacent time points; Calculating the temperature difference between adjacent spatial points using the collected temperature data, and determining the temperature gradient based on the temperature difference and the position difference between the adjacent spatial points; Performing Fourier transform on the collected pressure data to obtain frequency domain pressure data, and determining the pressure fluctuation amplitude based on the frequency domain pressure data.

[0008] In one possible implementation, the marine fuel leakage warning model includes a fuel leakage probability determination model. Then, when the marine leakage characteristic parameters are input into the marine fuel leakage warning model for prediction, the marine fuel leakage probability is obtained, including: An initial fuel leakage probability determination model is constructed using the marine fuel concentration change rate, temperature gradient, and pressure fluctuation amplitude as independent variables of the marine fuel leakage early warning model and the marine fuel leakage probability as the dependent variable of the marine fuel leakage early warning model. The initial fuel leakage probability determination model includes a regression coefficient to be determined. The fuel leakage probability determination model is obtained by solving the regression coefficient using the least square method with the minimum sum of square errors between the predicted value of the fuel leakage probability and the actual value of the fuel leakage probability as the solution goal.

[0009] In a possible implementation, the fuel leakage probability determination model is:

[0010] Where, is the fuel leakage probability; is the intercept; 、 、 is the regression coefficient; is the rate of change of marine fuel concentration; is the temperature gradient; is the pressure fluctuation amplitude; is the error term.

[0011] In a possible implementation, the marine fuel leakage early warning model includes a fuel leakage location determination model, and the fuel leakage location determination model is:

[0012]

[0013]

[0014] Where, is the maximum posterior probability; The fuel leak location; Z j The posterior probability of the region after observing the characteristic parameters of marine fuel leakage; is the likelihood function; 、 、 Z j The mean, variance and random value of the rate of change of marine fuel concentration in the region; 、 、 Z j The mean, variance, and random value of the temperature gradient within the region; 、 、 Z j The mean, variance and random value of the pressure fluctuation amplitude within the region; is the prior probability of fuel leakage in the region Zi.

[0015] In a possible implementation, generating a marine fuel leakage control instruction based on the marine fuel leakage probability includes: Determining whether the marine fuel leakage probability is greater than a leakage probability threshold; When the marine fuel leakage probability is greater than a leakage probability threshold, a fuel supply cut-off instruction is generated to instruct an emergency cut-off valve actuator installed on the marine fuel supply pipeline to drive the valve to close.

[0016] In a possible implementation, generating a marine fuel leakage control instruction based on the marine fuel leakage probability further includes: When the marine fuel leakage probability is greater than the leakage probability threshold, a first ventilation control instruction is generated to enable the first ventilation device to be turned on according to the indicated turning-on parameter.

[0017] In one possible implementation, generating a marine fuel leakage control instruction based on a marine fuel leakage location includes: The cabin where the leakage area is located is determined based on the marine fuel leakage location, and a second ventilation control instruction is generated based on the cabin where the leakage area is located. The second ventilation control instruction is used to control the second ventilation device and the third ventilation device arranged opposite to each other in the cabin where the leakage area is located.

[0018] In a possible implementation, the method further includes: generating an audible and visual alarm signal based on the marine fuel leakage probability and / or the marine fuel leakage location; and / or, The bunker fuel leakage probability and / or bunker fuel leakage location is sent to a terminal device.

[0019] In a second aspect, the present invention further provides a marine fuel leakage control system, comprising: A data acquisition module, configured to acquire multi-physics field data, wherein the multi-physics field data includes marine fuel concentration data, temperature data, and pressure data; a characteristic parameter extraction module, configured to extract characteristics of the marine fuel concentration data, temperature data, and pressure data to obtain characteristic parameters of marine fuel leakage; A probability and location prediction module, configured to input the marine fuel leakage characteristic parameters into a marine fuel leakage early warning model for prediction, thereby obtaining a marine fuel leakage probability and a marine fuel leakage location; The leakage control module is configured to generate a marine fuel leakage control instruction based on the marine fuel leakage probability and / or the marine fuel leakage location.

[0020] The beneficial effects of the present invention are as follows: the marine fuel leakage control method provided by the present invention can comprehensively reflect the operating status of the marine fuel cell system by collecting multi-physical field data, which helps to fully understand the working status of each part of the system and avoid misjudgment caused by missing or inaccurate single data; by extracting features from multi-physical field data, noise and redundant information are removed, thereby improving data quality; using the extracted characteristic parameters, the marine fuel leakage probability and marine fuel leakage location are predicted through a marine fuel leakage early warning model, the fuel leakage risk is predicted in advance, and finally control instructions are generated to comprehensively protect the safety of ships and personnel life and property. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 work.

[0022] Figure 1A schematic flow chart of an embodiment of a method for controlling marine fuel leakage provided by the present invention; Figure 2 For the present invention Figure 1 A schematic flow chart of an embodiment of S102; Figure 3 A schematic flow chart of an embodiment of a process for determining a marine fuel leak location provided by the present invention; Figure 4 This is a structural schematic diagram of an embodiment of the marine fuel leakage control system provided by the present invention. DETAILED DESCRIPTION

[0023] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making any creative efforts shall fall within the scope of protection of the present invention.

[0024] The terms "first," "second," and so on, used in the embodiments of the present invention are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, technical features designated as "first" or "second" may explicitly or implicitly include at least one such feature.

[0025] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0026] The present invention provides a method and system for controlling marine fuel leakage, which are described below.

[0027] Figure 1 A flow chart of an embodiment of the marine fuel leakage control method provided by the present invention is as follows: Figure 1 As shown, methods for controlling marine fuel leaks include: S101: Collect multi-physics field data, where the multi-physics field data includes marine fuel concentration data, temperature data, and pressure data.

[0028] The multi-physical field data is collected by corresponding sensors, specifically, the sensors include fuel concentration sensors, temperature sensors and pressure sensors.

[0029] In a specific embodiment of the present invention, the fuel is hydrogen, and the fuel concentration sensor is a hydrogen sensor.

[0030] S102: extracting features from the marine fuel concentration data, temperature data, and pressure data to obtain marine fuel leakage characteristic parameters; Before predicting the probability and location of marine fuel leaks, feature extraction is performed on multi-physics field data to improve data quality and obtain more reliable prediction data.

[0031] S103: Inputting the marine fuel leakage characteristic parameters into the marine fuel leakage early warning model for prediction, and outputting the predicted marine fuel leakage probability and location.

[0032] By comprehensively considering the mutual influence of multiple physical factors, the marine fuel leakage early warning model can more accurately predict fuel leakage.

[0033] S104: Generate a marine fuel leakage control instruction based on the marine fuel leakage probability and / or the marine fuel leakage location.

[0034] When the risk of fuel leakage is predicted, effective measures should be taken promptly to stop further fuel leakage, reduce fuel concentration, and prevent accidents from occurring or expanding.

[0035] Compared with the existing technology, the present invention can comprehensively reflect the operating status of the marine fuel cell system by collecting multi-physical field data, which helps to fully understand the working status of each part of the system and avoid misjudgment caused by missing or inaccurate single data; by extracting features from multi-physical field data, noise and redundant information are removed, thereby improving data quality; using the extracted characteristic parameters, the probability and location of marine fuel leakage are predicted through a multi-physical field coupled marine fuel leakage early warning model, the fuel leakage risk is predicted in advance, and finally control instructions are generated to comprehensively protect the safety of ships and personnel life and property.

[0036] In one embodiment of the present invention, the characteristic parameters of marine fuel leakage include marine fuel concentration change rate, temperature gradient and pressure fluctuation amplitude; Figure 2 As shown in the figure, feature extraction is performed on the multi-physics field data to obtain the characteristic parameters of marine fuel leakage, including: S201: Calculating a difference in marine fuel concentration between adjacent time points using the collected marine fuel concentration data, and determining a marine fuel concentration change rate based on the marine fuel concentration difference and the time difference between the adjacent time points; Specifically, the fuel concentration change rate is:

[0037] in, for The fuel concentration at the time, for The fuel concentration at the time, is the time difference between adjacent time points, is the fuel concentration change rate.

[0038] S202: Calculating the temperature difference between adjacent spatial points using the collected temperature data, and determining a temperature gradient based on the temperature difference and the time difference between adjacent time points; Specifically, the temperature gradient is:

[0039] in, and is the temperature value measured by two adjacent sensors, is the position difference between two adjacent sensors, is the temperature gradient.

[0040] S203: Performing Fourier transform on the collected pressure data to obtain frequency domain pressure data, and determining the pressure fluctuation amplitude based on the frequency domain pressure data.

[0041] By performing Fourier transform on the pressure data collected by the pressure sensor, the time domain data is converted to the frequency domain, and the spectrum amplitude within a specific frequency range is obtained. The spectrum amplitude is then used to represent the pressure fluctuation amplitude:

[0042] in, is the pressure spectrum in the frequency domain, is the time domain pressure data, is the frequency, When collected Pressure data points , after discrete Fourier transform, the frequency domain data is obtained ,pass exist arrive Maximum amplitude within the frequency range As the pressure fluctuation amplitude.

[0043] It is understandable that, in order to improve the accuracy of the fuel leakage characteristic parameters, before executing step S102 , it further includes: performing pre-processing operations such as filtering, denoising, and normalization on the multi-physical field data.

[0044] In one embodiment of the present invention, the marine fuel leakage warning model includes a fuel leakage probability determination model. Then, in step S103, inputting the marine leakage characteristic parameters into the marine fuel leakage warning model for prediction to obtain the marine fuel leakage probability includes: The rate of change of marine fuel concentration , temperature gradient and pressure fluctuation amplitude As the independent variable of the marine fuel leakage early warning model, the probability of marine fuel leakage As the dependent variable of the marine fuel leakage early warning model, an initial fuel leakage probability determination model is constructed, wherein the initial fuel leakage probability determination model includes the regression coefficient to be determined. 、 、 The initial fuel leakage probability determination model is as follows:

[0045] Where, is the intercept; is the error term.

[0046] The fuel leakage probability determination model is obtained by solving the regression coefficient using the least square method with the minimum sum of square errors between the predicted value and the actual value of the fuel leakage probability as the solution goal.

[0047] Specifically, the minimum sum of squares of the errors between the predicted value and the actual value of the fuel leakage probability is:

[0048] Where, The intercept and regression coefficient that minimize the sum of squared errors between the predicted fuel leak probability and the actual fuel leak probability; is the predicted value of fuel leakage probability; is the actual value of fuel leakage probability; n is the number of calculations.

[0049] In one embodiment of the present invention, the marine fuel leakage early warning model includes a fuel leakage location determination model, which is:

[0050]

[0051]

[0052] Where, is the maximum posterior probability; The fuel leak location; Z j The posterior probability of the region after observing the characteristic parameters of marine fuel leakage; is the likelihood function; 、 、 Z j The mean, variance and random value of the rate of change of marine fuel concentration in the region; 、 、 Z j The mean, variance, and random value of the temperature gradient within the region; 、 、 Z j The mean, variance and random value of the pressure fluctuation amplitude within the region; is the prior probability of fuel leakage in the region Zi.

[0053] Based on the above formula, if Figure 3 As shown, obtaining the bunker fuel leakage location in step S103 includes: S301: Divide the ship space into multiple areas and obtain the prior probability of marine fuel leakage in each area; Among them, the ship space is divided into multiple areas, including , then the prior probability of fuel leakage in each area is .

[0054] S302: Determine likelihood probability using the marine fuel concentration change rate, temperature gradient, pressure fluctuation amplitude, and likelihood function; S303: Calculate the posterior probability of each region in the feature data set based on the prior probability and the likelihood probability, and determine the region with the largest posterior probability as the marine fuel leakage location.

[0055] In one embodiment of the present invention, generating a marine fuel leakage control instruction based on the marine fuel leakage probability in step S104 includes: Determine whether the probability of marine fuel leakage is greater than a leakage probability threshold; When the probability of marine fuel leakage is greater than a leakage probability threshold, a fuel supply cut-off instruction is generated to instruct an emergency cut-off valve actuator installed on the marine fuel supply pipeline to drive the valve to close.

[0056] The fuel supply cut-off instruction is an instruction in the form of an electrical signal.

[0057] In some practical application scenarios, in addition to cutting off the fuel supply, in order to further avoid safety accidents, it is also necessary to ventilate the cabin to reduce the hydrogen concentration in the cabin. Based on this, in some embodiments of the present invention, generating the marine fuel leakage control instruction based on the marine fuel leakage probability in step S104 also includes: When the marine fuel leakage probability is greater than the leakage probability threshold, a first ventilation control instruction is generated to enable the first ventilation device to be turned on according to the indicated turning-on parameter.

[0058] Preferably, in order to improve ventilation efficiency, the opening parameter is the maximum speed of the fan in the first ventilation device.

[0059] In a specific embodiment of the present invention, the leakage probability threshold is preset to , when the predicted probability of marine fuel leakage When a fuel leak occurs, a command to shut off the fuel supply is generated and sent as an electrical signal to the emergency shut-off valve actuator installed on the fuel supply pipeline. Upon receiving the command, the emergency shut-off valve actuator drives the valve to close rapidly. When the command to shut off the fuel supply is generated, a command to start the ventilation equipment is also generated and transmitted via a communication line to the ventilation equipment controller. Upon receiving the command, the ventilation equipment controller activates the forced exhaust ventilation equipment, causing the fan to run at maximum speed to accelerate air circulation in the cabin.

[0060] In one embodiment of the present invention, generating a marine fuel leakage control instruction based on the marine fuel leakage location in step S104 includes: The cabin where the leakage area is located is determined based on the location of the ship fuel leakage, and a second ventilation control instruction is generated based on the cabin where the leakage area is located. The second ventilation control instruction is used to control the second ventilation equipment and the third ventilation equipment arranged opposite to each other in the cabin where the leakage area is located.

[0061] The embodiment of the present invention simultaneously controls the second ventilation device and the third ventilation device that are arranged opposite to each other in the cabin where the leakage area is located. By adjusting the wind direction of the second ventilation device and the third ventilation device, a directional airflow is formed to accelerate the speed of discharging the fuel out of the cabin.

[0062] In order to ensure that when a fuel leak occurs, the staff / maintenance personnel are notified immediately and take protective measures in a timely manner, in one embodiment of the present invention, the marine fuel leakage control method further includes: generating an audible and visual alarm signal based on the probability of a bunker fuel leak and / or the location of a bunker fuel leak; and / or, The bunker fuel leak probability and / or bunker fuel leak location is transmitted to a terminal device.

[0063] It is understandable that when the fuel leak probability When the leakage probability threshold is reached or exceeded, an audible and visual alarm signal is first generated. For the visual signal, warning lights installed in key locations on the ship, such as corridors, cabin entrances, and the control center, are controlled to flash at a specific frequency, such as 3-5 times per second, emitting a strong and eye-catching red light to attract the attention of on-site personnel. For the audible alarm, a high-decibel siren is activated to emit a sharp alarm sound, typically set at 80-120 decibels to ensure clear hearing even in the noisy ship environment. By utilizing the ship's existing communication networks, such as satellite communications, 4G / 5G communications, or very high frequency (VHF), a connection is established with the terminal device of the responsible personnel. Once the connection is established with the terminal device, detailed warning information is pushed to the responsible personnel, enabling them to react quickly and take appropriate countermeasures, thereby improving the efficiency of the emergency response and helping to reduce the damage caused by the accident.

[0064] In summary, the marine fuel leakage control method proposed in the embodiment of the present invention: 1. By combining multi-physics field data fusion with prediction technology, a new marine fuel leakage warning model is constructed. The model can simulate the leakage diffusion, temperature field and pressure field changes and their mutual influence under different working conditions of hydrogen, realize the accurate prediction of fuel leakage risk, accurately predict the probability and location of fuel leakage, and combine with the control execution module to take measures such as cutting off the fuel supply and starting ventilation in time, greatly reducing the risk of serious accidents such as explosion and fire caused by fuel leakage, and comprehensively protecting the safety of ships and personnel and property. 2. By real-time monitoring of the operating status of the fuel cell system, potential faults and hidden dangers are discovered and warned in time, reducing the number of suspensions due to system failures and ensuring the continuity and stability of ship operations. 3. When an abnormality is detected, an audible and visual alarm is quickly issued and information is pushed to the terminal of the responsible personnel. The control execution module simultaneously starts the corresponding control instructions, greatly shortening the time from discovering the problem to taking countermeasures, improving the efficiency of emergency response, and effectively curbing the development of accidents.

[0065] In order to better implement the marine fuel leakage control method in the embodiment of the present invention, based on the marine fuel leakage control method, correspondingly, Figure 4 As shown, an embodiment of the present invention further provides a marine fuel leakage control system, the marine fuel leakage control system 400 comprising: The data acquisition module 401 is used to acquire multi-physics field data, including marine fuel concentration data, temperature data, and pressure data; The characteristic parameter extraction module 402 is used to extract characteristics of the marine fuel concentration data, temperature data and pressure data to obtain characteristic parameters of marine fuel leakage; The probability and location prediction module 403 is used to input the marine fuel leakage characteristic parameters into the marine fuel leakage early warning model for prediction, thereby obtaining the marine fuel leakage probability and the marine fuel leakage location; The leakage control module 404 is configured to generate a bunker fuel leakage control instruction based on the bunker fuel leakage probability and / or the bunker fuel leakage location.

[0066] Those skilled in the art will appreciate that all or part of the process flow of the above-described method embodiment can be implemented by instructing related hardware (such as a processor, controller, etc.) through a computer program, and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a magnetic disk, an optical disk, a read-only memory, or a random access memory.

[0067] The above describes in detail the marine fuel leakage control method and system provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only intended to help understand the method and core concept of the present invention. At the same time, those skilled in the art will find that the specific implementation methods and application scopes may vary based on the concepts of the present invention. In summary, the contents of this specification should not be construed as limiting the present invention.

Claims

1. A method for controlling marine fuel leakage, characterized in that: include: Collecting multi-physics field data, wherein the multi-physics field data includes marine fuel concentration data, temperature data, and pressure data; performing feature extraction on the marine fuel concentration data, temperature data, and pressure data to obtain marine fuel leakage characteristic parameters; Inputting the marine fuel leakage characteristic parameters into a marine fuel leakage early warning model for prediction to obtain a marine fuel leakage probability and a marine fuel leakage location; A bunker fuel leakage control instruction is generated based on the bunker fuel leakage probability and / or the bunker fuel leakage location.

2. The method for controlling marine fuel leakage according to claim 1, characterized in that: The marine fuel leakage characteristic parameters include marine fuel concentration change rate, temperature gradient and pressure fluctuation amplitude; The feature extraction of the multi-physical field data to obtain the marine fuel leakage characteristic parameters includes: Calculating a difference in marine fuel concentration between adjacent time points using the collected marine fuel concentration data, and determining a marine fuel concentration change rate based on the marine fuel concentration difference and a time difference between adjacent time points; Calculating the temperature difference between adjacent spatial points using the collected temperature data, and determining the temperature gradient based on the temperature difference and the position difference between the adjacent spatial points; Performing Fourier transform on the collected pressure data to obtain frequency domain pressure data, and determining the pressure fluctuation amplitude based on the frequency domain pressure data.

3. The method for controlling marine fuel leakage according to claim 2, characterized in that: The marine fuel leakage early warning model includes a fuel leakage probability determination model. The marine fuel leakage characteristic parameters are input into the marine fuel leakage early warning model for prediction to obtain the marine fuel leakage probability, including: An initial fuel leakage probability determination model is constructed using the marine fuel concentration change rate, temperature gradient, and pressure fluctuation amplitude as independent variables of the marine fuel leakage early warning model and the marine fuel leakage probability as the dependent variable of the marine fuel leakage early warning model. The initial fuel leakage probability determination model includes a regression coefficient to be determined. The fuel leakage probability determination model is obtained by solving the regression coefficient using the least square method with the goal of minimizing the sum of square errors between the predicted value of the fuel leakage probability and the actual value of the fuel leakage probability.

4. The method for controlling marine fuel leakage according to claim 3, wherein: The fuel leakage probability determination model is: Where, is the probability of marine fuel leakage; is the intercept; 、 、 is the regression coefficient; is the rate of change of marine fuel concentration; is the temperature gradient; is the pressure fluctuation amplitude; is the error term.

5. The method for controlling marine fuel leakage according to claim 2, wherein: The marine fuel leakage early warning model includes a fuel leakage location determination model, which is: Where, is the maximum posterior probability; The fuel leak location; Z j The posterior probability of the region after observing the characteristic parameters of marine fuel leakage; is the likelihood function; 、 、 Z j The mean, variance and random value of the rate of change of marine fuel concentration in the region; 、 、 Z j The mean, variance, and random value of the temperature gradient within the region; 、 、 Z j The mean, variance and random value of the pressure fluctuation amplitude within the region; is the prior probability of fuel leakage in the region Zi.

6. The method for controlling marine fuel leakage according to claim 1, wherein: Generating a marine fuel leakage control instruction based on the marine fuel leakage probability includes: Determining whether the marine fuel leakage probability is greater than a leakage probability threshold; When the marine fuel leakage probability is greater than a leakage probability threshold, a fuel supply cut-off instruction is generated to instruct an emergency cut-off valve actuator installed on the marine fuel supply pipeline to drive the valve to close.

7. The method for controlling marine fuel leakage according to claim 6, wherein: Generating a marine fuel leakage control instruction based on the marine fuel leakage probability further includes: When the marine fuel leakage probability is greater than the leakage probability threshold, a first ventilation control instruction is generated to enable the first ventilation device to be turned on according to the indicated turning-on parameter.

8. The method for controlling marine fuel leakage according to claim 1, wherein: Generates bunker fuel leak control instructions based on bunker fuel leak location, including: The cabin where the leakage area is located is determined based on the marine fuel leakage location, and a second ventilation control instruction is generated based on the cabin where the leakage area is located. The second ventilation control instruction is used to control the second ventilation device and the third ventilation device arranged opposite to each other in the cabin where the leakage area is located.

9. The method for controlling marine fuel leakage according to any one of claims 1 to 8, characterized in that: The method further comprises: generating an audible and visual alarm signal based on the marine fuel leakage probability and / or the marine fuel leakage location; and / or, The bunker fuel leakage probability and / or bunker fuel leakage location is sent to a terminal device.

10. A marine fuel leakage control system, characterized in that: include: A data acquisition module, configured to acquire multi-physics field data, wherein the multi-physics field data includes marine fuel concentration data, temperature data, and pressure data; a characteristic parameter extraction module, configured to extract characteristics of the marine fuel concentration data, temperature data, and pressure data to obtain characteristic parameters of marine fuel leakage; A probability and location prediction module, configured to input the marine fuel leakage characteristic parameters into a marine fuel leakage early warning model for prediction, thereby obtaining a marine fuel leakage probability and a marine fuel leakage location; The leakage control module is configured to generate a marine fuel leakage control instruction based on the marine fuel leakage probability and / or the marine fuel leakage location.

Images