A monitoring method and system for remote ship management

Abstract

The present invention relates to the technical field of ship monitoring, and discloses a monitoring method and system for remote management of ships, the method comprising: collecting operating parameters of the ship; analyzing the operating parameters and monitoring the operating status of the ship; obtaining a plurality of sample sets according to the operating parameters, and calculating a comprehensive index for the sample sets; preprocessing the sample sets, and screening parameter combinations from the preprocessed sample sets according to the comprehensive index; eliminating operating parameters other than the parameter combination in the sample sets to obtain an optimized sample set, using the optimized sample set as a training set, training a deep learning model, obtaining a trained deep learning model, and realizing monitoring of the future operating status of the ship; triggering an early warning mechanism according to the future operating status of the ship; obtaining the parameter combination as a training set through the comprehensive index, reducing the noise of the training data, so that the model focuses on the changes of key parameters during the training and prediction process, and improving the accuracy of the prediction.

Description

Technical Field

[0001] The present invention relates to the technical field of ship monitoring, and in particular to a monitoring method for remote management of ships. Background Art

[0002] With the development of the maritime transport industry, ships, as an important means of transportation, play a vital role in international trade. However, due to the complexity and uncertainty of the marine environment, ships may face various risks during operation, including mechanical failures, operational errors, etc., which may have a serious impact on the safety and efficiency of ships. Therefore, it is particularly important to establish an effective ship remote monitoring system. Traditional ship monitoring methods mainly rely on manual inspections and reports by ship personnel, which has problems such as poor timeliness and incomplete information. In recent years, with the development of Internet of Things technology and big data analysis technology, more and more studies have begun to explore how to use these advanced technologies to improve ship remote monitoring methods. Existing ship remote monitoring systems usually use sensors to collect various operating parameters of the ship, and use mature machine learning models to predict the operating status to obtain prediction results. Although these technologies provide strong support for remote management of ships, they also bring some new challenges. For example, although ship positioning technology can provide accurate location information, due to the particularity of the marine environment, GPS signals may be interfered or shielded, resulting in inaccurate positioning. Although video surveillance can provide intuitive visual information, due to the limitations of shipborne equipment, the quality and real-time performance of video streaming are often unsatisfactory. In addition, although satellite communications provide reliable communication guarantees for remote ship management, the problems of high costs and unstable signals still exist. More importantly, existing ship remote monitoring systems usually collect a large number of operating parameters, including many parameters that have little or no direct impact on the ship's operating status. These additional parameters not only increase the complexity of data processing, but may also cause delays and errors in the monitoring system. In addition, not only is training time-consuming, but it is also prone to overfitting, resulting in low prediction accuracy. Summary of the invention

[0003] In order to solve the above technical problems, the present invention provides a monitoring method for remote management of a ship to monitor the operating status of the ship.

[0004] The present invention provides a monitoring method for remote ship management, comprising:

[0005] Step S100, collecting operating parameters of the ship;

[0006] Step S200, analyzing the operating parameters and monitoring the operating status of the ship;

[0007] Step S210, obtaining a number of sample sets according to the operating parameters, and calculating a comprehensive index for the sample sets;

[0008] Step S220, preprocessing the sample set, and screening parameter combinations from the preprocessed sample set according to the comprehensive index;

[0009] Step S230, eliminating the operating parameters other than the parameter combination in the sample set to obtain an optimized sample set, using the optimized sample set as a training set to train the deep learning model to obtain a trained deep learning model to achieve monitoring of the future operating status of the ship;

[0010] Step S300, triggering an early warning mechanism according to the future operating status of the ship.

[0011] Furthermore, step S210, obtaining a plurality of sample sets according to the operating parameters and calculating a comprehensive index for the sample sets, specifically includes the following steps:

[0012] Step S211, obtaining initial parameters related to the operating state from the operating parameters to form a sample set, and determining initial weights according to the initial parameters;

[0013] Step S212, calculating the health index of each initial parameter;

[0014] Step S213, calculating a comprehensive index according to the health index and the initial weight.

[0015] Further, step S213, calculating the comprehensive index according to the health index and the initial weight, specifically includes the following steps:

[0016] Step S2131, determining a health threshold according to the operating parameters;

[0017] Step S2132, calculating the health index of each initial parameter according to the health threshold;

[0018] Step S2133, calculating the health index of each sample set according to the health index of each initial parameter and the initial weight of each initial parameter;

[0019] Step S2134, calculating the comprehensive index of each sample set according to the health index of each sample set and the initial weight of each initial parameter in each sample set.

[0020] Further, the parameter combination is screened from the preprocessed sample set according to the comprehensive index, which specifically includes the following steps:

[0021] Step S221, determining a first risk level threshold and a second risk level threshold;

[0022] Step S222, compare the comprehensive index with the first risk level threshold and the second risk level threshold. If the comprehensive index is less than the first risk level threshold, the sample set is at a low risk level; if the comprehensive index is greater than or equal to the first risk level threshold and less than or equal to the second risk level threshold, the sample set is at a medium risk level; if the comprehensive index is greater than the second risk level threshold, the sample set is at a high risk level;

[0023] Step S223, calculating the mean, variance, maximum value, and minimum value of each initial parameter in the sample set at the low risk level, the medium risk level, and the high risk level;

[0024] Step S224, calculating the mean change, variance change, maximum change, and minimum change of each initial parameter at the low risk level, medium risk level, and high risk level;

[0025] Step S225, respectively arranging the mean change, variance change, maximum change, and minimum change of each initial parameter from high to low, and selecting the first k initial parameters as key parameters;

[0026] Step S2226, assigning an importance index of L to the key parameter, and assigning an importance index of M to the remaining initial parameters in the sample set except the key parameter, where L>M;

[0027] Step S227, calculating the optimization weight according to the initial weight and the comprehensive index, and calculating the evaluation comprehensive value according to the actual value of the initial parameter, the optimization weight and the importance index;

[0028] Step S228, sort the evaluation comprehensive values ​​from high to low, and select the first Q initial parameters as the parameter combination.

[0029] Furthermore, the optimization weight is calculated based on the initial weight and the comprehensive index, specifically including the following steps:

[0030] Step S231, calculating the average value of the comprehensive index of the sample set;

[0031] Step S232, calculating the optimized weight according to the average value of the comprehensive index, the initial weight and the comprehensive index.

[0032] Further, the optimized sample set is used as a training set to train the deep learning model, which also includes updating the weight function;

[0033] The updated weight function includes an initial updated weight term and a parameter combination term;

[0034] The updated weight function is:

[0035]

[0036] Where W represents the update weight function, represents the initial update weight term, Represents the combination of parameters Input the neural network function to generate the adjustment factor, represents a parameter combination, X represents the operating parameters in the parameter combination, and n represents the maximum number of operating parameters in the parameter combination.

[0037] Furthermore, the calculation formula of the health index is:

[0038]

[0039]

[0040] In the formula, represents the health index of the i-th initial parameter in the sample set, a represents the lower bound of the health threshold, b represents the upper bound of the health threshold, represents the i-th initial parameter in the sample set, p represents the adjustment variable, represents the health index of the dth sample set, R represents the maximum number of initial parameters in the sample set, Represents the initial weight of the i-th initial parameter.

[0041] Furthermore, the calculation formula for the optimization weight is:

[0042] ;

[0043] In the formula, represents the optimization weight of the i-th initial parameter, represents the initial weight of the i-th initial parameter, Represents the average value of the comprehensive index, represents the comprehensive index of the dth sample set, Represents the adjustment factor.

[0044] Furthermore, the calculation formula of the comprehensive index is:

[0045]

[0046] In the formula, is the adjustment coefficient, and e represents the base of the natural logarithm.

[0047] The present invention also provides a monitoring system for remote management of a ship, which is used to execute a monitoring method for remote management of a ship, and includes the following modules:

[0048] Operation parameter collection module: used to collect the operation parameters of the ship;

[0049] Monitoring module: connected to the operation parameter collection module, used to analyze the operation parameters and monitor the operation status of the ship;

[0050] Early warning module: connected to the monitoring module, used to trigger the early warning mechanism according to the operating status of the ship.

[0051] The embodiments of the present invention have the following technical effects:

[0052] The present invention obtains parameter combinations through comprehensive indexes, eliminates other initial parameters and retains key parameters as training sets, reduces the noise of training data, and enables the model to focus on changes in key parameters during training and prediction. By learning the characteristics of key parameters, the prediction results are more accurate, thereby improving the accuracy of prediction.

[0053] The amount of training data is reduced, the model prediction speed is accelerated, the complexity of the model is reduced, and the generalization ability of the model is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 is a flow chart of a monitoring method for remote management of a ship provided by an embodiment of the present invention;

[0056] Figure 2 It is a structural diagram of a monitoring system for remote management of ships provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0057] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0058] Figure 1 1 is a flow chart of a monitoring method for remote ship management provided by an embodiment of the present invention. Figure 1 , including:

[0059] Step S100, collecting the operating parameters of the ship.

[0060] Operating parameters include but are not limited to: engine speed, cooling water temperature, fuel pressure, cabin humidity, main bearing vibration amplitude, ship heading, wind speed, wave height, sea water temperature, etc., which are collected in real time through sensors installed on the ship.

[0061] In addition, ship GPS coordinates, video surveillance data, satellite call records, and satellite signal strength are collected as auxiliary information; ship GPS coordinates help monitor whether the ship deviates from the scheduled route, which is critical to ship safety and efficiency. If the ship deviates from the route, it may encounter adverse weather conditions or enter dangerous waters. Video surveillance data provides a real-time view of the ship's surroundings and is very useful for identifying potential safety hazards. Satellite call records and satellite signal strength can be used to monitor the stability and reliability of the communication system, which is critical for communication with shore-based facilities in emergency situations.

[0062] Step S200, analyzing the operating parameters and monitoring the operating status of the ship.

[0063] The collected operating parameters are analyzed using machine learning models to identify the operating status of the ship.

[0064] Analyze the operating parameters, including the following modules:

[0065] Step S210, obtaining a plurality of sample sets according to the operating parameters, and calculating a comprehensive index for the sample sets, specifically includes the following steps:

[0066] Step S211, obtaining initial parameters related to the operating state from the operating parameters to form a sample set, and determining initial weights according to the initial parameters;

[0067] Engine speed, cooling water temperature, fuel pressure, ship heading, wind speed, wave height, and sea water temperature are selected as initial parameters from the operating parameters.

[0068] The initial parameters are the results of analysis based on domain expert knowledge and operating parameters. For example, the engine speed and cooling water temperature are closely related to the performance and health of the engine; the fuel pressure is crucial to the stable operation of the engine; for this reason, an initial weight of 0.3 is assigned to the engine speed, an initial weight of 0.25 is assigned to the fuel pressure, and an initial weight of 0.1 is assigned to the cooling water temperature; the ship's heading, wind speed, and wave height reflect the impact of the external environment on the ship's navigation; the seawater temperature is also a crucial parameter for evaluating the efficiency of the cooling system. The ship's heading, wind speed, and wave height are each assigned an initial weight of 0.1, and the seawater temperature is assigned an initial weight of 0.05.

[0069] Step S212, calculating the health index of each initial parameter;

[0070] Step S213, calculating the comprehensive index according to the health index and the initial weight, specifically includes the following steps:

[0071] Step S2131, determining a health threshold according to the operating parameters;

[0072] By analyzing the operating parameters, a health threshold [a, b] is determined for each initial parameter, which reflects the ideal working range of the initial parameter. For example, the health threshold of each initial parameter is: engine speed: [1200, 1800] RPM, cooling water temperature: [70, 90] °C, fuel pressure: [4, 6] bar, ship heading: [0, 360] °, wind speed: [0, 20] m / s, wave height: [0, 5] m, sea water temperature: [10, 30] °C.

[0073] Step S2132, calculating the health index of each initial parameter according to the health threshold;

[0074] Step S2133, calculating the health index of each sample set according to the health index of each initial parameter and the initial weight of each initial parameter;

[0075] Step S2134, calculating the comprehensive index of each sample set according to the health index of each sample set and the initial weight of each initial parameter in each sample set.

[0076] The calculation formula of the health index is:

[0077] ;

[0078]

[0079] In the formula, represents the health index of the i-th initial parameter in the sample set, a represents the lower bound of the health threshold, b represents the upper bound of the health threshold, represents the i-th initial parameter in the sample set, p represents the adjustment variable, represents the health index of the dth sample set, R represents the maximum number of initial parameters in the sample set, Represents the initial weight of the i-th initial parameter.

[0080] Among them, p is determined by the experience of domain experts, preferably The adjustment variable is used to control the impact of the initial parameters that deviate from the health threshold on the health index. Specifically, if an initial parameter is less than a or greater than b, A certain penalty value is given to the initial parameter, so that the initial parameter causes the health index to decrease faster, and the final health index is close to 0, avoiding the initial parameter that deviates from the health threshold from affecting the health index calculation.

[0081] The calculation formula of the comprehensive index is:

[0082]

[0083] In the formula, is the adjustment coefficient, e represents the base of the natural logarithm, is an exponential function, when When it is close to 1, the value of the exponential function is close to 1, ensuring Being close to 0 means that the health index has a smaller negative impact on the comprehensive index. When the health index gradually deviates from 1, the value of the exponential function decreases. An increase indicates an increase in the negative impact on the comprehensive index.

[0084] Step S220, preprocessing the sample set, and screening parameter combinations from the preprocessed sample set according to the comprehensive index;

[0085] The sample set is preprocessed, missing values ​​and outliers are deleted, and a preprocessed sample set is obtained.

[0086] The parameter combination is selected from the pre-processed sample set according to the comprehensive index, which specifically includes the following steps:

[0087] Step S221, determining a first risk level threshold and a second risk level threshold;

[0088] The operating parameters are analyzed to obtain a first risk level threshold and a second risk level threshold.

[0089] Step S222, compare the comprehensive index with the first risk level threshold and the second risk level threshold. If the comprehensive index is less than the first risk level threshold, the sample set is at a low risk level; if the comprehensive index is greater than or equal to the first risk level threshold and less than or equal to the second risk level threshold, the sample set is at a medium risk level; if the comprehensive index is greater than the second risk level threshold, the sample set is at a high risk level;

[0090] In this embodiment, the first risk level threshold is preferably 75, the second risk level threshold is preferably 85, and the third risk level threshold is preferably 99.

[0091] If the comprehensive index is less than 75, the sample set is at a low risk level; if the comprehensive index is greater than or equal to 75 and less than or equal to 85, the sample set is at a medium risk level; if the comprehensive index is greater than 99, the sample set is at a high risk level.

[0092] Step S223, calculating the mean, variance, maximum value, and minimum value of each initial parameter in the sample set at the low risk level, the medium risk level, and the high risk level.

[0093] According to the comprehensive index of each sample set, the risk level of each sample set is obtained. The mean, variance, maximum value and minimum value of the initial parameters in the sample sets at low risk level, medium risk level and high risk level are calculated respectively.

[0094] Step S224, calculating the mean change, variance change, maximum change, and minimum change of each initial parameter at the low risk level, medium risk level, and high risk level.

[0095] Calculate the changes of the initial parameters at low risk level, medium risk level and high risk level (mean change, variance change, maximum change, minimum change). If the change changes significantly, it means that the initial parameters have a significant impact on the ship's operating status. For example, if the mean change of an initial parameter at a high risk level is much higher than that at a low risk level, it means that the current initial parameter is closely related to the high risk status of the ship.

[0096] The amount of change can help identify initial parameters that exhibit different performance at different risk levels, providing a basis for the selection of subsequent key parameters.

[0097] Step S225, respectively arranging the mean change, variance change, maximum change, and minimum change of each initial parameter from high to low, and selecting the first k initial parameters as key parameters;

[0098] Selecting initial parameters with significant changes as key parameters means that these initial parameters show significant changes under different risk levels and have high sensitivity to changes in the ship's operating status, thereby focusing on initial parameters that have a significant impact on the ship's operating status, thereby improving the prediction accuracy and efficiency of subsequent models. To this end, this embodiment preferably selects the first k initial parameters as key parameters, k=5.

[0099] Step S2226, assigning an importance index of L to the key parameter, and assigning an importance index of M to the remaining initial parameters in the sample set except the key parameter, where L>M;

[0100] This embodiment considers that key parameters are of high importance to the monitoring of the ship's operating status. Therefore, this embodiment assigns a higher importance index L to the key parameters, preferably L=0.8, and assigns a lower importance index M, L=0.3, to the remaining initial parameters in the sample set except the key parameters.

[0101] Step S227, calculating the optimization weight according to the initial weight and the comprehensive index, and calculating the evaluation comprehensive value according to the actual value of the initial parameter, the optimization weight and the importance index;

[0102] The calculation of optimization weights includes:

[0103] Step S231, calculating the average value of the comprehensive index of the sample set;

[0104] Step S232, calculating the optimized weight according to the average value of the comprehensive index, the initial weight and the comprehensive index.

[0105] The calculation formula for the optimization weight is:

[0106]

[0107] In the formula, represents the optimization weight of the i-th initial parameter, represents the initial weight of the i-th initial parameter, Represents the average value of the comprehensive index, represents the comprehensive index of the dth sample set, is the adjustment factor.

[0108] The calculation of the optimized weights takes into account the difference between the comprehensive index of the sample set and the historical average comprehensive index, so that the weights of the initial parameters and key parameters can be dynamically adjusted at different risk levels to better reflect the importance of the ship's operating status. When the comprehensive index of the sample set is at a high risk level, the weights of the key parameters will be increased, and the subsequent model will pay more attention to the changes in the key parameters, so that risk factors can be identified in a timely manner.

[0109] The calculation formula for the comprehensive evaluation value is:

[0110] ;

[0111] in, represents the comprehensive evaluation value of the i-th initial parameter, Represents the importance index of the i-th initial parameter.

[0112] Step S228, sort the evaluation comprehensive values ​​from high to low, and select the first Q initial parameters as the parameter combination.

[0113] By selecting key parameters with significant changes to form parameter combinations, the model can focus more on parameters that have a significant impact on the ship's operating status, thereby improving the model's prediction accuracy. Reducing the number of parameters can reduce the time and computing resources required for model training and prediction, and improve the system's response speed and efficiency.

[0114] Step S230, eliminating the operating parameters other than the parameter combination in the sample set to obtain an optimized sample set, using the optimized sample set as a training set to train the deep learning model to obtain a trained deep learning model to achieve monitoring of the future operating status of the ship;

[0115] The parameter combination is obtained by comprehensive index calculation, and the initial parameters other than the parameter combination in the sample set are eliminated to obtain the optimized sample set. The optimized sample set includes the parameter combination and the operating status of the key parameters. The parameter combination includes each key parameter and its value at each moment, and also includes the operating status at each moment.

[0116] This embodiment obtains parameter combinations through a comprehensive index, eliminates the remaining initial parameters and retains key parameters as a training set. On the one hand, it reduces the noise of the training data so that the model can focus on the changes in key parameters during training and prediction. By learning the characteristics of key parameters, the prediction results are more accurate. On the other hand, it reduces the amount of training data, speeds up the model prediction speed, reduces the complexity of the model, and improves the generalization ability of the model.

[0117] The deep learning model is preferably a neural network model.

[0118] The training process also includes updating the weight function; the updated weight function includes an initial updated weight term and a parameter combination term;

[0119] The updated weight function is:

[0120]

[0121] Where W represents the update weight function, represents the initial update weight term, Represents the combination of parameters Input the neural network function to generate the adjustment factor, represents a parameter combination, X represents the operating parameters in the parameter combination, and n represents the maximum number of operating parameters in the parameter combination.

[0122] Since the update weight function takes into account the combination of ship parameters, the model can better capture the changes in the ship's operating status and ensure good performance under different operating conditions.

[0123] When the ship's operating status changes suddenly, the model can quickly adjust the model weights and respond in time, which is very important for real-time monitoring and early warning.

[0124] After the model is trained through the above training set and the updated weight function, the real-time operating parameters of the ship to be predicted are input into the trained deep learning model to output the future operating state of the ship. The future operating state may include: future normal operating state and future abnormal operating state.

[0125] The output of the model uses the Sigmod activation function to realize probability output, and the state with the highest output probability is selected as the future operating state. For example, the output of the model is [0.75, 0.25], which means that the probability of the model predicting the normal operation state in the future is 75%, and the probability of the abnormal operation state in the future is 25%. The final output is that the future operation state of the ship is normal.

[0126] Step S300, triggering an early warning mechanism according to the future operating status of the ship.

[0127] Based on the above output results, the warning threshold is set, and for example, the warning threshold is 45%. When the probability of abnormal operation in the future in the prediction results is greater than or equal to 45%, the ship deviates from the scheduled route by more than 1 nautical mile, video surveillance finds that an unidentified ship is approaching the surrounding waters, and the satellite strength signal is lower than -80dBm, any of the above situations will trigger the warning mechanism immediately.

[0128] The early warning mechanism includes but is not limited to: sending text messages, email notifications, activating emergency plans, etc.

[0129] After receiving the warning message, relevant personnel will decide whether to take further action based on the warning notification and probability value, such as conducting inspections, adjusting routes, or activating emergency plans.

[0130] The ship's operating parameters, initial parameters, key parameters and the model's prediction of the ship's future operating status are all visualized in the monitoring center, and managers can remotely manage the ship through the monitoring center.

[0131] Figure 2 is a structural diagram of a monitoring system for remote ship management provided by an embodiment of the present invention, referring to Figure 2 This embodiment also provides a monitoring system for remote ship management, including the following modules:

[0132] Operation parameter collection module: used to collect the operation parameters of the ship;

[0133] Monitoring module: connected to the operation parameter collection module, used to analyze the operation parameters and monitor the operation status of the ship;

[0134] Early warning module: connected to the monitoring module, used to trigger the early warning mechanism according to the operating status of the ship.

[0135] This embodiment also provides an electronic device, which includes one or more processors and a memory.

[0136] The processor may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0137] The memory may include one or more computer program products, and the computer program product may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor may run the program instructions to implement a monitoring method for remote management of a ship and / or other desired functions of any embodiment of the present application described above. Various contents such as initial external parameters, thresholds, etc. may also be stored in the computer-readable storage medium.

[0138] In one example, the electronic device may further include: an input device and an output device, and these components are interconnected through a bus system and / or other forms of connection mechanisms (not shown). The input device may include, for example, a keyboard, a mouse, etc. The output device may output various information to the outside, including early warning information, braking force, etc. The output device may include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto, etc.

[0139] In addition, the electronic device may further include any other appropriate components according to specific application scenarios.

[0140] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of a monitoring method for remote management of a ship provided in any embodiment of the present application.

[0141] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0142] In addition, an embodiment of the present application may also be a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the processor executes the steps of a monitoring method for remote management of a ship provided in any embodiment of the present application.

[0143] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0144] It should be noted that the terms used in the present invention are only for describing specific embodiments, rather than limiting the scope of the present application. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of more restrictions, the elements defined by the sentence "include one..." do not exclude the presence of other identical elements in the process, method or device including the elements.

[0145] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship 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 orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0146] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. A monitoring method for remote ship management, characterized in that: The following steps are involved: Step S100, collecting operating parameters of the ship; Step S200, analyzing the operating parameters and monitoring the operating status of the ship; Step S210, obtaining a number of sample sets according to the operating parameters, and calculating a comprehensive index for the sample sets; specifically includes the following steps: Step S211, obtaining initial parameters related to the operating state from the operating parameters to form a sample set, and determining initial weights according to the initial parameters; Step S212, calculating the health index of each initial parameter; Step S213, calculating the comprehensive index according to the health index and the initial weight; specifically includes the following steps: Step S2131, determining a health threshold according to the operating parameters; Step S2132, calculating the health index of each initial parameter according to the health threshold; Step S2133, calculating the health index of each sample set according to the health index of each initial parameter and the initial weight of each initial parameter; Step S2134, calculating a comprehensive index of each sample set according to the health index of each sample set and the initial weight of each initial parameter in each sample set; Step S220, preprocessing the sample set, and screening parameter combinations from the preprocessed sample set according to the comprehensive index; Step S221, determining a first risk level threshold and a second risk level threshold; Step S222, compare the comprehensive index with the first risk level threshold and the second risk level threshold. If the comprehensive index is less than the first risk level threshold, the sample set is at a low risk level; if the comprehensive index is greater than or equal to the first risk level threshold and less than or equal to the second risk level threshold, the sample set is at a medium risk level; if the comprehensive index is greater than the second risk level threshold, the sample set is at a high risk level; Step S223, calculating the mean, variance, maximum value, and minimum value of each initial parameter in the sample set at the low risk level, the medium risk level, and the high risk level; Step S224, calculating the mean change, variance change, maximum change, and minimum change of each initial parameter at the low risk level, medium risk level, and high risk level; Step S225, respectively arranging the mean change, variance change, maximum change, and minimum change of each initial parameter from high to low, and selecting the first k initial parameters as key parameters; Step S226, assigning an importance index of L to the key parameter, and assigning an importance index of M to the remaining initial parameters in the sample set except the key parameter, where L>M; Step S227, calculating the optimization weight according to the initial weight and the comprehensive index, and calculating the evaluation comprehensive value according to the actual value of the initial parameter, the optimization weight and the importance index; Step S228, arranging the evaluation comprehensive values ​​from high to low, and selecting the first Q initial parameters as the parameter combination; Step S230, eliminating the operating parameters other than the parameter combination in the sample set to obtain an optimized sample set, using the optimized sample set as a training set to train the deep learning model to obtain a trained deep learning model to achieve monitoring of the future operating status of the ship; Step S300, triggering an early warning mechanism according to the future operating status of the ship.

2. A monitoring method for remote ship management according to claim 1, characterized in that: The optimization weight is calculated based on the initial weight and comprehensive index, which specifically includes the following steps: Step S231, calculating the average value of the comprehensive index of the sample set; Step S232, calculating the optimized weight according to the average value of the comprehensive index, the initial weight and the comprehensive index.

3. A monitoring method for remote ship management according to claim 2, characterized in that: Using the optimized sample set as a training set to train the deep learning model, including updating the weight function; The updated weight function includes an initial updated weight term and a parameter combination term; The updated weight function is: ； Where W represents the update weight function, represents the initial update weight term, Represents the combination of parameters Input the neural network function to generate the adjustment factor, represents a parameter combination, X represents the operating parameters in the parameter combination, and n represents the maximum number of operating parameters in the parameter combination.

4. A monitoring method for remote ship management according to claim 3, characterized in that: The calculation formula of the health index is: ； ； In the formula, represents the health index of the i-th initial parameter in the sample set, a represents the lower bound of the health threshold, b represents the upper bound of the health threshold, represents the i-th initial parameter in the sample set, p represents the adjustment variable, represents the health index of the dth sample set, R represents the maximum number of initial parameters in the sample set, Represents the initial weight of the i-th initial parameter.

5. A monitoring method for remote ship management according to claim 4, characterized in that: The calculation formula for the optimization weight is: ； In the formula, represents the optimization weight of the i-th initial parameter, represents the initial weight of the i-th initial parameter, Represents the average value of the comprehensive index, represents the comprehensive index of the d-th sample set, Represents the adjustment factor.

6. A monitoring method for remote ship management according to claim 5, characterized in that: The calculation formula of the comprehensive index is: ； In the formula, is the adjustment coefficient, and e represents the base of the natural logarithm.

7. A monitoring system for remote ship management, used to execute the monitoring method for remote ship management according to any one of claims 1 to 6, characterized in that: Includes the following modules: Operation parameter collection module: used to collect the operation parameters of the ship; Monitoring module: connected to the operation parameter collection module, used to analyze the operation parameters and monitor the operation status of the ship; Early warning module: connected to the monitoring module, used to trigger the early warning mechanism according to the operating status of the ship.

Images