A method for monitoring and fault detection of ship fuel

Abstract

The present invention discloses a method for monitoring and fault detection of ship fuel, comprising the steps of obtaining current wave data and a current ship motion state, preprocessing the current wave data and the current ship motion state, and transmitting them to a cloud and a distributed database respectively through a wireless communication protocol; establishing a nonlinear wave model according to the data stored in the cloud, solving the nonlinear wave model, and constructing a model rule base; constructing a ship fuel adjustment strategy through the model rule base, monitoring the ship fuel and providing a fault alarm, updating the distributed database according to the monitoring and fault alarm results, and optimizing the ship fuel adjustment strategy using a genetic algorithm; solving the nonlinear wave model, achieving accurate simulation in a complex wave environment, and improving the prediction accuracy of fuel consumption; in addition, constructing a ship fuel adjustment strategy and optimizing the genetic algorithm improve the stability of fuel consumption and the navigation efficiency of the ship.

Description

Technical Field

[0001] The present invention relates to the technical field of ship automation control and monitoring, and in particular to a ship fuel monitoring and fault detection method. Background Art

[0002] As a key node in the global transportation network, ships play a very important role in the field of marine engineering in terms of energy efficiency management and fault detection. With the rapid expansion of the shipping industry, how to effectively monitor and optimize ship fuel use to achieve economic and environmental benefits has become a core research issue. In the traditional technical framework, ship fuel monitoring mainly relies on periodic manual inspections and conventional sensor data collection. Although this method can provide a certain degree of fuel management support, it often lacks real-time and high precision. In addition, during the navigation of the ship, the waves in the marine environment have a significant impact on the ship's movement and fuel consumption. Traditional fuel consumption adjustment methods often cannot effectively cope with complex sea conditions.

[0003] In recent years, although new progress has been made in the research on ships, there are still deficiencies in the real-time performance, environmental adaptability and intelligent decision-making of ships. First, the traditional linear wave theory (such as Airy wave theory) is only applicable to waves with small amplitudes and long wavelengths, and it is difficult to accurately describe the complex waves in the real ocean environment. Secondly, the real-time and accuracy of existing ship monitoring in dealing with complex dynamic sea conditions are low, making it difficult to achieve precise control of fuel consumption and unable to meet the requirements of modern ship transportation for efficiency, safety and sustainable development. Finally, when ships are sailing over long distances, the untimely adjustment of fuel consumption strategies will lead to excessive or slow fuel consumption, which makes the level of intelligence low when responding to emergencies. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides a ship fuel monitoring and fault detection method to solve the problems raised in the background technology.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a ship fuel monitoring and fault detection method, comprising:

[0007] Acquire current wave data and current ship motion state, pre-process the current wave data and current ship motion state, and transmit the pre-processed wave data and ship motion state to the cloud and the distributed database respectively through a wireless communication protocol;

[0008] A nonlinear wave model is established according to the data stored in the cloud, and a model rule library is constructed by solving the nonlinear wave model;

[0009] The ship fuel adjustment strategy is constructed through the model rule base, the ship fuel is monitored and fault alarms are given, the distributed database is updated according to the monitoring and fault alarm results, and the ship fuel adjustment strategy is optimized using a genetic algorithm.

[0010] As a preferred solution of the ship fuel monitoring and fault detection method of the present invention, the current wave data and the current ship motion state are obtained, and the current wave data and the current ship motion state are preprocessed, including:

[0011] The current wave data is obtained through the wave radar system, and the current ship motion status is obtained through the inertial measurement unit;

[0012] Before obtaining the current wave data and the current ship motion status, define the data sampling points and extract the mean and standard deviation of the historical wave height;

[0013] Convert the current wave data into a wave time series signal and convert the current ship motion status into JSON format.

[0014] As a preferred solution of the ship fuel monitoring and fault detection method of the present invention, the pre-processed wave data and ship motion status are transmitted to the cloud and the distributed database respectively through the wireless communication protocol, including:

[0015] Define long-distance wide area networks and short-distance wide area networks based on the distance between the current geographical location and the destination;

[0016] The long-distance wide area network transmits the current wave data converted into a wave time series signal to the cloud through the LoRaWAN protocol, and transmits the current ship motion status converted into the JSON format to the distributed database; the short-distance wide area network uses a wireless network transmission method to transmit the current wave data converted into a wave time series signal to the cloud, and transmits the current ship motion status converted into the JSON format to the distributed database.

[0017] As a preferred solution of the ship fuel monitoring and fault detection method of the present invention, a nonlinear wave model is established based on the data stored in the cloud, including:

[0018] According to the wave time series signals in the cloud, the nonlinear interaction and high-order effects of waves are considered, and an improved high-order nonlinear wave equation is obtained.

[0019] As a preferred solution of the ship fuel monitoring and fault detection method of the present invention, it also includes:

[0020] The high-order nonlinear wave equation is discretized, and residual value calculation is performed on the discretized high-order nonlinear wave equation.

[0021] As a preferred solution of the ship fuel monitoring and fault detection method of the present invention, wherein: by solving the nonlinear wave model, a model rule base is constructed, including:

[0022] The wave time series signal is transformed by fast Fourier transform of adaptive window to obtain the signal spectrum;

[0023] According to the signal spectrum, calibrating the wave nonlinear amplitude effect, velocity coupling effect and water flow diffusion coefficient in the nonlinear wave model;

[0024] The calibrated nonlinear wave model is solved using the semi-implicit finite volume method to obtain the wave height change rate and the ship's rolling angular velocity.

[0025] A model rule base is constructed according to the wave height change rate and the ship rolling angular velocity.

[0026] As a preferred solution of the ship fuel monitoring and fault detection method of the present invention, wherein: through the model rule base, a ship fuel adjustment strategy is constructed to monitor the ship fuel and alarm for faults, including:

[0027] Define the real-time fuel consumption rate and set the threshold of the ship's roll angular velocity, judge the wave height change rate and ship's roll angular velocity in the rule base, and build a ship fuel adjustment strategy.

[0028] As a preferred solution of the ship fuel monitoring and fault detection method of the present invention, the construction of the ship fuel adjustment strategy includes:

[0029] If the wave height change rate is a positive number and the ship's roll angular velocity exceeds the set ship's roll angular velocity threshold, the real-time fuel consumption rate is taken as the maximum fuel consumption rate;

[0030] If the wave height change rate is negative and the ship's roll angular velocity is lower than the set ship's roll angular velocity threshold, the real-time fuel consumption rate will be used as the minimum fuel consumption rate;

[0031] If the wave height change rate is zero and the ship's roll angular velocity is exactly equal to the set ship's roll angular velocity threshold, the real-time fuel consumption rate remains unchanged.

[0032] As a preferred solution of the ship fuel monitoring and fault detection method of the present invention, wherein: monitoring the ship fuel and fault alarming, and updating the distributed database according to the monitoring and fault alarming results, include:

[0033] Convert the wave height change rate into wave height. When the wave height exceeds the mean and standard deviation of the historical wave height, or the residual value calculated after the high-order nonlinear wave equation is discretized exceeds the original high-order nonlinear wave equation, an alarm is issued.

[0034] The alarm is divided into monitoring alarm and fault alarm. The monitoring alarm is when the wave height exceeds the mean and standard deviation of the historical wave height. The fault alarm is when the residual value calculated after the discretization of the high-order nonlinear wave equation exceeds the original high-order nonlinear wave equation, and the distributed database is updated.

[0035] As a preferred solution of the ship fuel monitoring and fault detection method of the present invention, wherein: optimizing the ship fuel adjustment strategy by using a genetic algorithm includes:

[0036] The wave height change rate, ship rolling angular velocity and real-time fuel consumption rate in the fuel adjustment strategy are encoded into chromosomes to randomly generate the initial population;

[0037] According to the number of fault alarm triggering and the current ship fuel adjustment strategy, define the current ship's fuel consumption stability and ship navigation stability;

[0038] The fuel consumption stability and navigation stability of the current ship are evaluated and assigned to the randomly generated initial population to obtain the fitness value;

[0039] By judging the convergence of the fitness value, the current optimal ship fuel adjustment strategy is obtained.

[0040] Compared with the prior art, the invention has the following beneficial effects:

[0041] 1. The present invention solves the improved high-order nonlinear wave model through the fast Fourier transform of the adaptive window and the semi-implicit finite volume method to achieve accurate simulation of the complex wave environment and improve the prediction accuracy of fuel consumption;

[0042] 2. The long-distance and short-distance wide area network are processed separately to optimize the efficiency and stability of data collection and transmission, ensuring real-time data updates and timely fuel strategy adjustments;

[0043] 3. The fuel consumption rate is defined by building a model rule base, and a genetic algorithm is used to optimize the ship fuel strategy, which achieves flexible response to variable sea conditions and improves the stability of fuel consumption and ship navigation efficiency;

[0044] 4. Monitor and warn the currently collected wave data based on historical wave data, and establish fault alarms for the improved high-order nonlinear wave model through residual value judgment. This not only improves the correlation between the collected data equipment and the model, but also reduces the lag problem of the ship's warning and improves the intelligence of the ship. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. 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 creative work. Among them:

[0046] Figure 1 This is an overall flow chart of a ship fuel monitoring and fault detection method according to an embodiment of the present invention;

[0047] Figure 2 A comparison diagram of fuel consumption fluctuation ranges under different methods of the ship fuel monitoring and fault detection method according to an embodiment of the present invention;

[0048] Figure 3 A fuel consumption fluctuation trend diagram of a ship fuel monitoring and fault detection method according to an embodiment of the present invention;

[0049] Figure 4 This is an enlarged diagram of the fluctuation range of the open sea and the near sea of ​​the ship fuel monitoring and fault detection method according to an embodiment of the present invention;

[0050] Figure 5 A comparison diagram of the wave height change rate and the ship rolling angular velocity measurement accuracy of the ship fuel monitoring and fault detection method according to an embodiment of the present invention;

[0051] Figure 6 This is a comparison diagram of data transmission and fault response performance of a ship fuel monitoring and fault detection method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0053] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0054] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0055] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0056] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0057] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0058] Reference Figure 1 , which is the first embodiment of the present invention, provides a ship fuel monitoring and fault detection method, comprising:

[0059] S1, obtaining current wave data and current ship motion state, preprocessing the current wave data and current ship motion state, and transmitting the preprocessed wave data and ship motion state to the cloud and distributed database respectively through wireless communication protocol;

[0060] Furthermore, the current wave data is obtained through the wave radar system, and the current ship motion state is obtained through the inertial measurement unit;

[0061] Specifically, the wave radar system is deployed at the bow and stern of the ship, capable of 360° scanning, with each radar capable of measuring within ±0.01 meters and a frequency range from 0.1Hz to 10Hz;

[0062] Specifically, an inertial measurement unit is installed at the center of the hull, and the built-in three-axis accelerometer and gyroscope of the inertial measurement unit are ±0.001g and ±0.01° / s respectively;

[0063] It should be explained that the three-axis accelerometer is used to measure the acceleration of the ship, and the gyroscope is used to measure the rotation rate of the ship;

[0064] It should be noted that through the deployment of wave radar systems and inertial measurement units, wave data of different scales and frequencies as well as ship motion status can be captured;

[0065] Furthermore, before obtaining the current wave data and the current ship motion status, the data sampling points are defined to extract the mean and standard deviation of the historical wave height;

[0066] It should be noted that the definition of data sampling points is not only to extract the mean and standard deviation of historical wave heights from wave data, but also to identify the wave height change curve through the mean and standard deviation, so as to predict future wave conditions and improve the accuracy of monitoring and alarming;

[0067] Furthermore, the current wave data is converted into a wave time series signal, and the current ship motion state is converted into a JSON format;

[0068] It needs to be explained that JSON (JavaScript Object Notation) is a lightweight data exchange format that is easy for humans and machines to read and write. The JSON format is flexible and can be easily expanded to include more wave data or new attributes, which is convenient for upgrading and maintaining data acquisition equipment.

[0069] Furthermore, long-distance wide area networks and short-distance wide area networks are defined according to the distance between the current geographical location and the destination;

[0070] Furthermore, the long-range wide area network transmits the current wave data converted into wave time series signals to the cloud through the LoRaWAN protocol, and transmits the current ship motion status converted into JSON format to the distributed database;

[0071] It needs to be explained that LoRaWAN (Long Range Wide Area Network) is a low-power, wide-area network protocol that allows data transmission over long distances;

[0072] It should be noted that the current wave data is transmitted to the cloud because the wave data not only needs to be analyzed in real time, but also needs to be used as backup data for subsequent research on the navigation area; and the current ship motion state can be obtained by analyzing the current wave data, so it is stored in the distributed database as update or call data;

[0073] Furthermore, the short-range wide area network uses wireless network transmission to transmit the current wave data converted into wave time series signals to the cloud, and transmits the current ship motion status converted into JSON format to the distributed database;

[0074] It should be noted that when a ship is far from the shore or in the open sea, short-distance transmission is low-cost and has a small coverage range. Although it saves costs, it will cause the cloud to fail to receive data or cause data loss. Long-distance transmission is used to ensure that data can cover a larger distance and reach the cloud for storage. Similarly, if the ship is close to the shore or in the offshore area, long-distance transmission can cover the coverage of data transmission, but the cost is higher. Among them, these two methods cannot completely prevent data loss;

[0075] S2. Establish a nonlinear wave model based on the data stored in the cloud, and build a model rule library by solving the nonlinear wave model;

[0076] Furthermore, according to the wave time series signal in the cloud, the nonlinear interaction and high-order effects of waves are considered, and an improved high-order nonlinear wave equation is obtained;

[0077] Specifically, the improved high-order nonlinear wave equation is expressed as:

[0078] (1)

[0079] in, stands for wave displacement, which indicates the change in height of the wave surface; is the flow velocity, which represents the velocity of the fluid in the wave medium; is the water depth, which refers to the water depth under static conditions and is a constant; For time, is a spatial variable, indicating the spatial position along the wave propagation direction; is the acceleration due to gravity, usually taken as 9.81 m / s², which is one of the driving forces of wave motion; is the wave nonlinear amplitude effect, which reflects the nonlinear influence of wave height on wave propagation. is the velocity coupling effect, which reflects the nonlinear influence of flow velocity on its own changes. is the water flow diffusion coefficient, which is used to describe the diffusion effect of flow velocity, that is, the expansion or dissipation of flow velocity in space;

[0080] Furthermore, the high-order nonlinear wave equation is discretized, and the residual value of the discretized high-order nonlinear wave equation is calculated;

[0081] Specifically, the improved high-order nonlinear wave equation is discretized, that is, formula (1), which is expressed as:

[0082] (2)

[0083] in, is the wavefront displacement The updated value of is the flow rate The updated value of Represents the periodic displacement of the wave surface; Indicates periodic changes in flow velocity;

[0084] It should be noted that by capturing the nonlinear periodic behavior in waves and currents, reference data is provided for the subsequent definition of ship navigation stability;

[0085] Specifically, the residual value of the discretized high-order nonlinear wave equation is calculated to obtain:

[0086] (3)

[0087] in, is expressed as the time step, represents the wavefront displacement residual, represents the flow rate residual;

[0088] Furthermore, the wave time series signal is transformed by fast Fourier transform with adaptive window to obtain the signal spectrum;

[0089] It needs to be explained that FFT is a classic signal processing tool used to analyze the spectral components of time series signals;

[0090] Specifically, the formula for obtaining the signal spectrum is:

[0091] (4)

[0092] in, is the representation of the wave time series signal in the frequency domain, that is, the amplitude and phase of the wave time series signal at the kth frequency; is the discretization representation of the wave time series signal; w is an adaptive window used to weight the wave time series signal to reduce spectrum leakage; represents the Fourier basis function, which is used to convert the wave time domain signal into the wave frequency domain; is the total number of samples of the wave time series signal;

[0093] Furthermore, the wave nonlinear amplitude effect, velocity coupling effect and water flow diffusion coefficient in the nonlinear wave model are calibrated according to the signal spectrum;

[0094] Specifically, in each time step in the frequency domain, all wavefront displacements are updated and flow rate u;

[0095] It should be explained that the semi-implicit finite volume method captures the physically conservative properties by performing volume integration on the convection and diffusion terms in space, and implicitly processes some variables in time, so that it has better numerical stability when dealing with highly nonlinear and rigid problems.

[0096] Furthermore, the calibrated nonlinear wave model is solved using the semi-implicit finite volume method to obtain the wave height change rate and the ship rolling angular velocity;

[0097] Specifically, the semi-implicit finite volume method is solved as follows:

[0098] (5)

[0099] Specifically, assuming that the rolling motion of the ship is directly related to the velocity and height change rate of the waves, we get:

[0100] (6)

[0101] Among them, the solution is is the ship's rolling angular velocity; is the wave height change rate;

[0102] It should be noted that the improved high-order nonlinear wave equations are solved by adaptive window fast Fourier transform and semi-implicit finite volume method, which achieves accurate simulation of complex wave environment and improves the prediction accuracy of fuel consumption;

[0103] Furthermore, a model rule base is constructed based on the wave height change rate and the ship rolling angular velocity;

[0104] Specifically, the cloud updates wave data in real time through the wave height change rate, and the distributed database fills the ship's roll angular velocity into the database as a reference field for the ship's motion status;

[0105] S3. Build a ship fuel adjustment strategy through the model rule base, monitor the ship fuel and alarm for faults, update the distributed database according to the monitoring and fault alarm results, and use genetic algorithms to optimize the ship fuel adjustment strategy;

[0106] Furthermore, the real-time fuel consumption rate is defined and the threshold of the ship's rolling angular velocity is set, the wave height change rate and the ship's rolling angular velocity in the rule base are judged, and the ship's fuel adjustment strategy is constructed;

[0107] Specifically, the ship rolling angular velocity threshold is obtained by the maximum value of the rolling angular velocity of all ships in the distributed database;

[0108] It should be noted that the ship's rolling angular velocity will change as the database is updated during the fault alarm;

[0109] Specifically, Expressed as , Expressed as , the real-time fuel consumption rate is expressed as ;

[0110] Furthermore, the ship fuel adjustment strategy is constructed as follows:

[0111] Condition 1: If the wave height change rate is a positive number, and the ship's rolling angular velocity Exceeds the set ship roll angular velocity threshold , the real-time fuel consumption rate is taken as the maximum fuel consumption rate;

[0112] Condition 2: If the wave height change rate is negative and the ship's roll angular velocity is lower than the set ship's roll angular velocity threshold, the real-time fuel consumption rate is taken as the minimum fuel consumption rate;

[0113] Condition 3: If the wave height change rate is zero and the ship's roll angular velocity is exactly equal to the set ship's roll angular velocity threshold, the real-time fuel consumption rate remains unchanged;

[0114] It should be noted that under normal navigation conditions, the wave height change rate is balanced, represented by zero here. When the ship's roll angular velocity accelerates, that is, exceeds the set ship roll velocity threshold, it means that the waves are large and the ship cannot maintain high-speed navigation, so it is necessary to reduce the real-time fuel consumption rate to reduce the navigation cost; when the ship's roll angular velocity slows down, that is, is lower than the set ship roll velocity threshold, it means that the waves are small and the ship needs to maintain high-speed navigation, otherwise it will increase the navigation time, so the fuel consumption rate can be increased;

[0115] Furthermore, the wave height change rate is converted into wave height. When the wave height exceeds the mean and standard deviation of the historical wave height, or the residual value calculated after the high-order nonlinear wave equation is discretized exceeds the original high-order nonlinear wave equation, an alarm is issued;

[0116] It should be noted that wave heights exceeding the mean and standard deviation of historical wave heights indicate extreme weather or anomalies;

[0117] Specifically, the residual value of the original nonlinear wave equation is calculated. or When the residual value exceeds the original high-order nonlinear wave equation, a fault alarm is issued;

[0118] Specifically, the prediction value of the original nonlinear wave equation is:

[0119] (7)

[0120] in, is the predicted wave height, is the predicted value of flow velocity;

[0121] It should be noted that the residual value of the original nonlinear wave equation can be obtained through the predicted value;

[0122] Furthermore, the alarm is divided into monitoring alarm and fault alarm. The monitoring alarm is when the wave height exceeds the mean and standard deviation of the historical wave height. The fault alarm is when the residual value calculated after the discretization of the high-order nonlinear wave equation exceeds the original high-order nonlinear wave equation, and the distributed database is updated.

[0123] It should be noted that when the wave height exceeds the mean and standard deviation of the historical wave height, it only indicates extreme weather or anomalies, but the residual value of the model is not abnormal. Only fuel needs to be monitored and no fuel fault alarm is triggered. On the contrary, when the residual value of the model is abnormal, it means that the model encounters problems during the calculation process, or the model receives parameters or makes errors in conversion. Then the model rule base constructed by the model and the ship fuel adjustment strategy constructed by the model rule base will also be wrong accordingly, so a fuel fault alarm is required instead of a monitoring alarm. The distributed data is updated because the ship motion status in it belongs to call data, not real-time data. When a fault occurs, the wave height, which is part of the wave data, will be sent to the cloud for real-time update. The ship motion status in the distributed database requires analysis of the wave data, which is delayed and not real-time, so there is no need to update the cloud, only the distributed database needs to be updated.

[0124] Furthermore, considering that monitoring alarms and fault alarms may occur at the same time, a genetic algorithm is used to encode the wave height change rate, ship rolling angular velocity, and real-time fuel consumption rate in the fuel adjustment strategy into chromosomes to randomly generate the initial population;

[0125] Specifically, each population contains chromosomes (wave height change rate, ship roll angular velocity, and real-time fuel consumption rate), and each population represents a possible fuel adjustment strategy, that is, a random combination;

[0126] Furthermore, according to the number of fault alarm triggering and the current ship fuel adjustment strategy, the current ship fuel consumption stability and ship navigation stability are defined;

[0127] It should be noted that the ship's navigation stability can be defined based on the periodic displacement of the wave surface and the periodic change of the flow velocity obtained previously;

[0128] Furthermore, the fuel consumption stability and navigation stability of the current ship are evaluated and assigned to the randomly generated initial population to obtain the fitness value;

[0129] Specifically, the assessment is expressed as a stability score consisting of 1 to 10 points;

[0130] Furthermore, by judging the convergence of the fitness value, the current optimal ship fuel adjustment strategy is obtained;

[0131] It should be noted that the higher the stability score, the higher the fitness value. The one with the highest fitness value is taken as the best population, that is, the maximum fitness value no longer increases, indicating that the optimal solution has been found, and the optimal solution is taken as the optimal ship fuel adjustment strategy.

[0132] Reference Figures 2 to 6 , which is the second embodiment of the present invention, and this embodiment provides a method for monitoring and fault detection of ship fuel, including: the simulation experiment is intended to verify the effectiveness of the method for monitoring and fault detection of ship fuel in the scheme of the present invention, and its goal is to improve fuel efficiency, reduce failure rate, and improve adaptability in complex sea conditions. The simulation experiment is carried out on a medium-sized cargo ship with a loaded cargo weight of 25,000 tons, covering two typical navigation environments of open sea and near sea;

[0133] The long-distance sailing route starts from Shanghai Port, passes through the Taiwan Strait, crosses the South China Sea, and ends at Singapore Port. This route is the main international shipping channel from China to Southeast Asia. The expected wave height is between 2 and 4 meters, and the wind speed can reach 30 to 50 kilometers per hour. It passes through typhoon-prone areas, and the sea conditions are complex and changeable. It takes about 12 days. The simulation experiment focuses on fuel consumption and stability during long-distance sailing.

[0134] Offshore route: From Shanghai Port to Qingdao Port, sailing along the coastline of the East China Sea, this route is the main short-distance route in China. Although it is offshore sailing, in order to compare the effectiveness of the experiment, it is set that the sailing process will encounter sudden severe convective weather and tropical cyclones. The expected wave height is between 1 and 2.5 meters, the wind speed is 15 to 35 kilometers per hour, and the weather conditions are changeable. It takes about 3 days and focuses on the optimization of fuel consumption in short-distance transportation.

[0135] The wave radar system is deployed at the bow and stern of the ship and can perform 360° scanning. The measurement accuracy of each radar is within ±0.01 meters and the frequency range is from 0.1Hz to 10Hz. The inertial measurement unit is installed in the center of the hull, and the built-in three-axis accelerometer and gyroscope of the inertial measurement unit are ±0.001g and ±0.01° / s respectively. The communication module is: RAK7258 LoRaWAN gateway, which is set to collect 10 times per second to ensure that wave data and ship motion status can be transmitted to the cloud and distributed database in real time; Apache Cassandra is used as a distributed database; based on the processing process of the solution of the present invention, the ship motion status data in the Cassandra database is finally updated;

[0136] Three methods were used to compare with the solution of the present invention, and the simulation experimental data were shown in Table 1 and Table 2;

[0137] Table 1: Ocean voyages

[0138]

[0139] Table 2: Coastal navigation

[0140]

[0141] First, the simulation experimental data in Tables 1 and 2 show that the method of the present invention has significant advantages in both open sea and near-shore navigation environments; compared with traditional methods, the stability of fuel consumption, sensitivity of fault detection and adaptability of the present invention are significantly improved; in open sea and near-shore routes, the ship stability score is not less than 9 points, which is significantly higher than other traditional methods, indicating that the method has stronger adaptability in ship stability under complex sea conditions; in addition, reference Figures 2 to 4 , the fuel adjustment strategy after multiple optimizations not only significantly reduces the fluctuation range of fuel consumption but also improves the accuracy of fuel prediction. In the open sea voyage, the fluctuation range of fuel consumption is ±5%, and in the near sea is ±2%, which is much lower than the traditional method; the method of the present invention also improves the fuel utilization efficiency. The fuel consumption rate in the open sea voyage is reduced by about 37.7% compared with the traditional method, and the fuel consumption rate in the near sea voyage is reduced by about 37.1%, which reduces carbon emissions and improves the economy and environmental protection of the ship; reference Figure 5 The present invention has a measurement accuracy of 98% for the wave height change rate and the ship's rolling angular velocity in open sea and offshore sailing, which is 7-12% higher than other methods; finally, refer to Figure 6 The present invention is also superior to the other three methods in terms of data transmission and fault response time and speed, reducing the lag problem of ships in early warning and improving the intelligence of ships;

[0142] In summary, the experiment verified the effectiveness and innovation of the method of the present invention. The method showed excellent performance in both complex open sea and stable offshore navigation environments, and provided a reliable and efficient solution for promoting the development of intelligent fuel monitoring technology and the economy and environmental protection of marine transportation.

[0143] It should be understood by those skilled in the art that the embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes. The schemes in the embodiments of the present application may be implemented in various computer languages, for example, object-oriented programming language Java and literal scripting language JavaScript, etc.

[0144] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0145] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0146] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0147] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0148] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for monitoring and fault detection of ship fuel, characterized in that: include: Acquire current wave data and current ship motion state, pre-process the current wave data and current ship motion state, and transmit the pre-processed wave data and ship motion state to the cloud and the distributed database respectively through a wireless communication protocol; A nonlinear wave model is established according to the data stored in the cloud, and a model rule library is constructed by solving the nonlinear wave model; By solving the nonlinear wave model, a model rule library is constructed, including: The wave time series signal is transformed by fast Fourier transform of adaptive window to obtain the signal spectrum; According to the signal spectrum, calibrating the wave nonlinear amplitude effect, velocity coupling effect and water flow diffusion coefficient in the nonlinear wave model; The calibrated nonlinear wave model is solved using the semi-implicit finite volume method to obtain the wave height change rate and the ship's rolling angular velocity. Constructing a model rule library according to the wave height change rate and the ship rolling angular velocity; By using the model rule base, a ship fuel adjustment strategy is constructed to monitor the ship fuel and provide fault alarms. According to the monitoring and fault alarm results, the distributed database is updated, and a genetic algorithm is used to optimize the ship fuel adjustment strategy. Through the model rule base, a ship fuel adjustment strategy is constructed to monitor the ship fuel and provide fault alarms, including: Define the real-time fuel consumption rate and set the threshold of the ship's roll angular velocity, judge the wave height change rate and ship's roll angular velocity in the rule base, and build a ship fuel adjustment strategy.

2. The ship fuel monitoring and fault detection method according to claim 1, characterized in that: Acquiring current wave data and current ship motion state, and preprocessing the current wave data and current ship motion state, including: The current wave data is obtained through the wave radar system, and the current ship motion status is obtained through the inertial measurement unit; Before obtaining the current wave data and the current ship motion status, define the data sampling points and extract the mean and standard deviation of the historical wave height; Convert the current wave data into a wave time series signal and convert the current ship motion status into JSON format.

3. The ship fuel monitoring and fault detection method according to claim 1, characterized in that: The pre-processed wave data and ship motion status are transmitted to the cloud and distributed database respectively through wireless communication protocols, including: Define long-distance wide area networks and short-distance wide area networks based on the distance between the current geographical location and the destination; The long-distance wide area network transmits the current wave data converted into a wave time series signal to the cloud through the LoRaWAN protocol, and transmits the current ship motion status converted into the JSON format to the distributed database; the short-distance wide area network uses a wireless network transmission method to transmit the current wave data converted into a wave time series signal to the cloud, and transmits the current ship motion status converted into the JSON format to the distributed database.

4. The ship fuel monitoring and fault detection method according to claim 3, characterized in that: Based on the data stored in the cloud, a nonlinear wave model is established, including: According to the wave time series signals in the cloud, the nonlinear interaction and high-order effects of waves are considered, and an improved high-order nonlinear wave equation is obtained.

5. The ship fuel monitoring and fault detection method according to claim 4, characterized in that: Also includes: The high-order nonlinear wave equation is discretized, and residual value calculation is performed on the discretized high-order nonlinear wave equation.

6. The ship fuel monitoring and fault detection method according to claim 1, characterized in that: The construction of the ship fuel adjustment strategy includes: If the wave height change rate is a positive number and the ship's roll angular velocity exceeds the set ship's roll angular velocity threshold, the real-time fuel consumption rate is taken as the maximum fuel consumption rate; If the wave height change rate is negative and the ship's roll angular velocity is lower than the set ship's roll angular velocity threshold, the real-time fuel consumption rate will be used as the minimum fuel consumption rate; If the wave height change rate is zero and the ship's roll angular velocity is exactly equal to the set ship's roll angular velocity threshold, the real-time fuel consumption rate remains unchanged.

7. The ship fuel monitoring and fault detection method according to any one of claims 2, 4 and 6, characterized in that: Monitoring and fault alarming of ship fuel, and updating the distributed database according to the monitoring and fault alarming results, including: Convert the wave height change rate into wave height. When the wave height exceeds the mean and standard deviation of the historical wave height, or the residual value calculated after the high-order nonlinear wave equation is discretized exceeds the original high-order nonlinear wave equation, an alarm is issued. The alarm is divided into monitoring alarm and fault alarm. The monitoring alarm is when the wave height exceeds the mean and standard deviation of the historical wave height. The fault alarm is when the residual value calculated after the discretization of the high-order nonlinear wave equation exceeds the original high-order nonlinear wave equation, and the distributed database is updated.

8. The ship fuel monitoring and fault detection method according to claim 7, characterized in that: The ship fuel adjustment strategy is optimized by using a genetic algorithm, including: The wave height change rate, ship rolling angular velocity and real-time fuel consumption rate in the fuel adjustment strategy are encoded into chromosomes to randomly generate the initial population; According to the number of fault alarm triggering and the current ship fuel adjustment strategy, define the current ship's fuel consumption stability and ship navigation stability; The fuel consumption stability and navigation stability of the current ship are evaluated and assigned to the randomly generated initial population to obtain a fitness value; and the current optimal ship fuel adjustment strategy is obtained by judging the convergence of the fitness value.

Images