A Fault Warning Method and System for a Combined Fleet Based on Intelligent Monitoring

Abstract

The present invention provides a method and system for fault warning of a combined fleet based on intelligent monitoring, which relates to the technical field of data processing. The method includes: collecting the power data of the main propulsion ship, as well as the course data, navigation data and connection device data of the fleet to obtain a fleet data set. By analyzing the fleet data set, propulsion power parameters, course change parameters, navigation synchronization parameters and connection stress parameters are obtained, the state relationship between ships is determined, a fleet operation state evaluation matrix is obtained, and abnormal detection is performed on the propulsion power parameters, course change parameters, navigation synchronization parameters and connection stress parameters according to it to determine whether there are abnormal parameters exceeding the preset parameter group, obtaining abnormal parameter data. According to the abnormal parameter data, the influence degree of the abnormal parameters on the fleet is analyzed to obtain the fault influence range, and the warning level is set for the fault according to it, and a warning message is generated. The present invention identifies and warns fleet faults through intelligent monitoring.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a combined fleet fault warning method and system based on intelligent monitoring. Background Art

[0002] Currently, ship fault warning mainly relies on single-ship monitoring systems. Single-ship monitoring systems usually use sensors to collect key parameters such as engine, power system, and cargo hold status, and then analyze them through on-board computers. When an anomaly is detected, the system triggers an alarm and conducts inspections. For conventional ships, this method can effectively reduce sudden failures and improve maintenance efficiency. However, in the application scenario of combined fleets, this single-ship monitoring mode has limitations and may not be able to meet the complex requirements of multi-ship collaborative operations.

[0003] During the operation of a combined fleet, the ships form an integrated whole through mechanical-hydraulic connection devices. The power systems, load distributions, and navigation states of each ship affect each other. When a fault occurs in a ship in the combined fleet, its influence range is not limited to a single ship and may cause a chain reaction to the stability and safety of the entire fleet. For example, when the power system of the main propulsion ship is abnormal, the existing system can give an early warning in time, but it cannot detect the impact of this fault on key factors such as the navigation trajectory of the barge and the force on the connection device, which may lead to uneven distribution of pushing and pulling forces, resulting in ship yaw or damage to the connection device. Summary of the Invention

[0004] The purpose of the present invention is to provide a combined fleet fault warning method and system based on intelligent monitoring, aiming to solve the problems mentioned in the background art.

[0005] To solve the above technical problems, the technical solution of the present invention is as follows:

[0006] In a first aspect, a combined fleet fault warning method based on intelligent monitoring, the method includes:

[0007] Collect the power data of the main propulsion ship, as well as the course data, navigation data, and connection device data of the fleet, and preprocess them to remove redundant data and unify the dimension units to obtain a fleet data set;

[0008] By performing trend analysis on the power data in the fleet data set, calculate the power change rate and torque stability of the main propulsion ship to obtain propulsion power parameters;

[0009] By performing segmented analysis on the course data in the fleet data set, determine the course consistency between the main propulsion ship and the barge, and calculate the course offset angle to obtain course change parameters;

[0010] By performing synchronous analysis on the navigation data in the fleet dataset, calculating the speed difference between the main propulsion ship and the barge and the route difference of the fleet, the navigation synchronization parameters are obtained;

[0011] By performing a force analysis on the connection device data in the fleet dataset, determining the force impact on the connection device during fleet navigation, the connection force parameters are obtained;

[0012] According to the propulsion power parameters, heading change parameters, navigation synchronization parameters and connection force parameters, the state relationship between ships is determined, and the fleet operation state evaluation matrix is obtained;

[0013] According to the fleet operation state evaluation matrix, perform anomaly detection on the propulsion power parameters, heading change parameters, navigation synchronization parameters and connection force parameters, determine whether there are abnormal parameters exceeding the preset parameter group, and obtain the abnormal parameter data;

[0014] According to the abnormal parameter data, analyze the influence degree of the abnormal parameters on the fleet, obtain the fault influence range, and set the warning level for the fault according to it, and generate a warning message.

[0015] Furthermore, by performing trend analysis on the power data in the fleet navigation dataset, calculating the power change rate and torque stability of the main propulsion ship, the propulsion power parameters are obtained, including:

[0016] According to the power data, extract the data related to the power system of the main propulsion ship, and obtain the output power, torque value, timestamp and propeller speed;

[0017] According to the timestamp, set a time window;

[0018] According to the time window, calculate the change rate of the output power within the time window, and obtain the power change rate;

[0019] According to the torque value and the time window, calculate the torque mean value and torque standard deviation within the time window;

[0020] According to the torque standard deviation, combined with the propeller speed, calculate the torque stability.

[0021] Furthermore, it is characterized in that by performing segmented analysis on the heading data in the fleet navigation dataset, determining the heading consistency between the main propulsion ship and the barge, and calculating the heading offset angle, the heading change parameters are obtained, including:

[0022] According to the navigation data, extract the heading angles of the main propulsion ship and the barge respectively, and obtain the main heading angle and the barge heading angle;

[0023] Arrange the main heading angle and the barge heading angle in chronological order, and split them according to the preset time period to obtain the heading segment dataset;

[0024] According to the course segment dataset, calculate the course change rate of the main propulsion vessel in adjacent time periods, analyze the course change amplitude of the fleet during navigation, and obtain the course change dataset;

[0025] According to the course change dataset, identify the consistency of the course angles of the main propulsion vessel and the barges in different time periods, and obtain the navigation consistency;

[0026] According to the navigation consistency, calculate the deviation of the course angles of the main propulsion vessel and the barges in different time periods, and obtain the course offset angle;

[0027] According to the course offset angle, calculate the mean course offset and the standard deviation of the course offset between the main propulsion vessel and the barges during navigation.

[0028] Furthermore, by synchronously analyzing the navigation data in the fleet dataset, calculate the speed difference between the main propulsion vessel and the barges and the route difference of the fleet, and obtain the navigation synchronization parameters, including:

[0029] According to the navigation data, extract the speeds, longitude and latitude coordinates of the main propulsion vessel and the barges, and obtain the navigation status dataset;

[0030] According to the navigation status dataset, calculate the speed change rates of the main propulsion vessel and the barges within the time window respectively, and obtain the main speed change rate and the barge speed change rate;

[0031] According to the navigation status dataset, calculate the average speeds of the main propulsion vessel and the barges within the time window respectively, and obtain the main speed mean and the barge speed mean;

[0032] Calculate the speed difference according to the main speed mean and the barge speed mean;

[0033] According to the navigation status dataset, calculate the predicted positions of the main propulsion vessel and the barges after a preset time length, and calculate the navigation difference of the fleet according to their positions and the preset route.

[0034] Furthermore, by analyzing the forces on the connection device data in the fleet navigation dataset, determine the force influence on the connection device during fleet navigation, and obtain the connection force parameters, including:

[0035] According to the connection device data, extract the tension, force direction of the connection device and the relative distance between the main propulsion vessel and the barges, and obtain the force dataset;

[0036] According to the force dataset, calculate the tension change rate of the connection device within the time window;

[0037] According to the force dataset, calculate the maximum tension and the minimum tension of the connection device, and obtain the force range of the connection device;

[0038] Calculate the mean and standard deviation of the tension of the connecting device based on the force dataset, and judge the tension stability of the connecting device according to them;

[0039] Determine the lateral offset between the main propulsion ship and the barge according to the relative distance between the main propulsion ship and the barge, and calculate the shear force borne by the connecting device according to it;

[0040] Calculate the angular change rate of the connecting device per unit time according to the force direction.

[0041] Furthermore, according to the propulsion power parameters, course change parameters, navigation synchronization parameters and connection force parameters, determine the state relationship between the ships, and obtain the fleet operation state evaluation matrix, including:

[0042] Calculate the correlation between the power change and the course deviation according to the propulsion power parameters and the course change parameters, and obtain the power-course correlation degree;

[0043] Calculate the synchronization between the main propulsion ship and the barge according to the navigation synchronization parameters, and obtain the speed synchronization degree;

[0044] Calculate the standard deviation of the force on the connecting device within the time window according to the connection force parameters, and obtain the force fluctuation degree;

[0045] Calculate the correlation degree between different ships according to the power-course correlation degree, speed synchronization degree and force fluctuation degree, and obtain the ship correlation dataset;

[0046] Determine the size of the matrix according to the number of ships in the fleet, and determine the value of each element in the matrix according to the ship correlation dataset, and obtain the fleet operation state evaluation matrix.

[0047] Furthermore, analyze the influence degree of the abnormal parameters on the fleet according to the abnormal parameter data, obtain the fault influence range, and set the early warning level for the fault according to it, and generate early warning information, including:

[0048] Take the main propulsion ship, barge and connecting device as nodes, and interact the corresponding nodes according to the actual connection situation of the connecting device to obtain edges;

[0049] Obtain the fleet correlation network according to the nodes and edges;

[0050] Calculate the absolute difference of the power change rate between two nodes and the first absolute difference of the course angle according to the fleet correlation network; according to the absolute difference of the power change rate and the absolute difference of the course angle, obtain the first non-linear change value;

[0051] Calculate the absolute difference in the sailing speeds of two nodes and the absolute value of the cosine of the difference in the angular change rate of the connecting device; calculate the second absolute difference in the force values of the connecting devices of the two nodes; based on the absolute value and the second absolute difference, obtain the second non-linear change value;

[0052] Based on the first non-linear change value and the second non-linear change value, obtain the fault impact weight of the edge between the two nodes;

[0053] Determine the fault starting point according to the abnormal parameter data;

[0054] Based on the fault starting point and the fault impact weight, determine the fault nodes affected by the fault starting point to obtain the fault propagation path;

[0055] Analyze the influence degree of the fault starting point according to the fault propagation path to obtain the fault influence range.

[0056] In a second aspect, a fault warning system for a combined fleet based on intelligent monitoring, the system includes:

[0057] A data acquisition module, configured to collect the power data, heading data, navigation data, and connecting device data of the main propulsion ship, and perform preprocessing on them to remove redundant data and unify the dimension units to obtain a fleet data set;

[0058] A propulsion power module, configured to calculate the power change rate and torque stability of the main propulsion ship by performing trend analysis on the power data in the fleet data set to obtain propulsion power parameters;

[0059] A heading change module, configured to determine the heading consistency between the main propulsion ship and the barge by performing segmented analysis on the heading data in the fleet data set, and calculate the heading offset angle to obtain heading change parameters;

[0060] A navigation synchronization module, configured to calculate the speed difference between the main propulsion ship and the barge and the route difference of the fleet by performing synchronization analysis on the navigation data in the fleet data set to obtain navigation synchronization parameters;

[0061] A connection force module, configured to determine the force influence on the connecting device during the fleet navigation by performing force analysis on the connecting device data in the fleet data set to obtain connection force parameters;

[0062] An evaluation matrix module, configured to determine the state relationship between ships according to the propulsion power parameters, heading change parameters, navigation synchronization parameters, and connection force parameters to obtain a fleet operation state evaluation matrix;

[0063] Anomaly detection module, which is used to perform anomaly detection on propulsion power parameters, heading change parameters, navigation synchronization parameters, and connection force parameters according to the fleet operation status evaluation matrix, determine whether there are abnormal parameters exceeding the preset parameter group, and obtain abnormal parameter data;

[0064] Fault warning module, which is used to analyze the influence degree of abnormal parameters on the fleet according to the abnormal parameter data, obtain the fault influence range, and set the warning level for the fault according to it, and generate warning information.

[0065] The above solution of the present invention has at least the following beneficial effects:

[0066] By collecting power data, heading data, navigation data, and connection device data and performing unified preprocessing, the present invention ensures data standardization, improves the comparability between different data sources, and thus avoids calculation errors caused by inconsistent data formats. In addition, through the comprehensive monitoring of multiple key data dimensions of the fleet, this method can comprehensively reflect the operation status of the combined fleet. Especially during the collaborative operation of the fleet, it can effectively detect the mutual influence between ships, avoid the limitations of the single-ship monitoring mode, and accurately identify this potential influence through comprehensive analysis of different data sources, improving the accuracy and integrity of monitoring.

[0067] By processing the power data of the main propulsion ship, the present invention calculates its power change rate and torque stability, so as to be able to detect potential fault hazards in the power system in advance. Compared with the traditional alarm mechanism after a fault occurs, this method can provide an early warning before a fault occurs by analyzing the long-term change trend of the power system. When it is detected that the power change rate of the main propulsion ship shows abnormal fluctuations and the torque stability decreases, it indicates that there may be potential risks in the power system. Based on these parameter changes, an early warning is set before a fault occurs to avoid the suspension of the fleet or serious accidents caused by sudden power failures.

[0068] By performing segmented analysis on the heading data of the fleet, the present invention can identify the heading consistency between the main propulsion ship and the barge and calculate the heading offset angle. This feature can effectively avoid the problem of fleet deviation caused by inconsistent headings. During actual navigation, if the heading of the main propulsion ship is adjusted quickly, but the barge fails to synchronously adjust in time, it may lead to the overall deviation of the fleet and even cause a navigation safety accident. This function can timely identify the inconsistent heading situation by calculating the heading change parameters and provide adjustment suggestions, enabling the fleet to maintain a stable heading, reducing the risk of deviation, and improving navigation safety.

[0069] Through synchronous analysis of navigation data, the present invention calculates the speed difference and fleet route difference between the main propulsion ship and the barge, ensuring a high degree of coordination during the fleet's voyage. The traditional single-ship monitoring method cannot effectively evaluate the collaborative state between different ships, while this method can calculate the speed changes of each ship in real time and determine its deviation from the preset route. When it is found that the speed of the barge lags significantly behind that of the main propulsion ship, the system can automatically adjust the navigation parameters or provide adjustment suggestions to ensure that the entire fleet sails synchronously and avoid the fleet structure becoming loose or abnormal forces on the connecting devices due to speed differences.

[0070] Through force analysis of the connecting device data, the present invention determines the force changes during the fleet's voyage, effectively avoiding equipment damage or safety accidents caused by abnormal forces on the connecting devices. During the fleet's progress, if the thrust of the main propulsion ship changes due to fluctuations in the power system and the barge fails to adjust in time, it may cause the connecting device to bear abnormal shear or tensile forces, thereby increasing the risk of damage. This function calculates the tension change rate, force range, and tension stability of the connecting device, discovers abnormal force conditions in a timely manner, and takes warning measures to ensure the stability and durability of the connecting device and improve the overall navigation safety. Brief Description of the Drawings

[0071] Figure 1 is a flowchart of a fault warning method for a combined fleet based on intelligent monitoring provided by an embodiment of the present invention. Detailed Embodiments

[0072] Hereinafter, exemplary embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present disclosure can be more thoroughly understood and the scope of the present disclosure can be completely conveyed to those skilled in the art.

[0073] As Figure 1 shown, an embodiment of the present invention proposes a fault warning method for a combined fleet based on intelligent monitoring, and the method includes:

[0074] Step S100, collect the power data of the main propulsion ship, the heading data, navigation data, and connecting device data of the fleet, and preprocess them to remove redundant data and unify the dimension units to obtain a fleet data set;

[0075] Step S200, through trend analysis of the power data in the fleet data set, calculate the power change rate and torque stability of the main propulsion ship to obtain propulsion power parameters;

[0076] Step S300: By performing segmented analysis on the heading data in the fleet dataset, determine the heading consistency between the main propulsion ship and the barges, calculate the heading offset angle, and obtain the heading change parameter;

[0077] Step S400: By performing synchronous analysis on the navigation data in the fleet dataset, calculate the speed difference between the main propulsion ship and the barges and the route difference of the fleet, and obtain the navigation synchronization parameter;

[0078] Step S500: By performing force analysis on the connection device data in the fleet dataset, determine the force influence on the connection device during the fleet's navigation, and obtain the connection force parameter;

[0079] Step S600: According to the propulsion power parameter, heading change parameter, navigation synchronization parameter, and connection force parameter, determine the state relationship between the ships, and obtain the fleet operation state evaluation matrix;

[0080] Step S700: According to the fleet operation state evaluation matrix, perform anomaly detection on the propulsion power parameter, heading change parameter, navigation synchronization parameter, and connection force parameter, determine whether there are abnormal parameters exceeding the preset parameter group, and obtain the abnormal parameter data;

[0081] Step S800: According to the abnormal parameter data, analyze the influence degree of the abnormal parameter on the fleet, obtain the fault influence range, and set the warning level for the fault according to it, and generate a warning message.

[0082] In the embodiment of the present invention, the power data of the main propulsion ship and the heading data, navigation data, and connection device data of the fleet are collected and preprocessed to remove redundant data and unify the dimension units, obtaining the fleet dataset, ensuring the consistency and comparability of data input, and improving the accuracy and stability of subsequent data analysis; by performing trend analysis on the power data in the fleet dataset, calculating the power change rate and torque stability of the main propulsion ship, obtaining the propulsion power parameter, effectively identifying the operation state of the propulsion system, especially when the engine load changes, being able to detect the smoothness of power output; by performing segmented analysis on the heading data in the fleet dataset, determining the heading consistency between the main propulsion ship and the barges, calculating the heading offset angle, obtaining the heading change parameter, and detecting whether there is a situation of inconsistent headings during the fleet's navigation.

[0083] By synchronously analyzing the navigation data in the fleet dataset, calculating the speed difference between the main propulsion ship and the barge and the route difference of the fleet, obtaining the navigation synchronization parameters, and real-time monitoring the speed synchronization of the main propulsion ship and the barge, it is possible to avoid uneven internal forces within the fleet caused by speed asynchronization; by analyzing the force on the connecting device data in the fleet dataset, determining the force impact on the connecting device during fleet navigation, obtaining the connection force parameters, effectively evaluating the operating state of the connecting device, and preventing damage or fracture of the connecting device caused by abnormal force.

[0084] According to the propulsion power parameters, heading change parameters, navigation synchronization parameters, and connection force parameters, determine the state relationship between ships, obtain the fleet operation state evaluation matrix, establish the connection between various factors within the fleet, and form a quantifiable state evaluation index to provide a decision-making basis for subsequent anomaly detection; according to the fleet operation state evaluation matrix, perform anomaly detection on the propulsion power parameters, heading change parameters, navigation synchronization parameters, and connection force parameters, determine whether there are abnormal parameters exceeding the preset parameter group, obtain the abnormal parameter data, and be able to provide early warning information before the occurrence of abnormal situations, avoiding serious impacts on the entire fleet caused by sudden failures; according to the abnormal parameter data, analyze the influence degree of the abnormal parameters on the fleet, obtain the fault influence range, and set the early warning level for the fault according to it, generate early warning information, judge that the fleet has a relatively high risk, and provide real-time early warning to improve the safety and reliability of fleet navigation.

[0085] Among them, collect the power data of the main propulsion ship, as well as the heading data, navigation data, and connecting device data of the fleet, and perform preprocessing on them, remove redundant data, and unify the dimension units to obtain the fleet dataset, specifically including:

[0086] The system collects power data in real time through on-board sensors:

[0087] Engine power: Collect the output power of the current engine through the engine control unit;

[0088] Torque: Measure the actual torque output by the engine with a torque sensor;

[0089] Propeller speed: Monitor the current speed of the propeller through a speed sensor;

[0090] All data are collected at fixed time intervals, such as 1 second or 5 seconds, and the timestamp is recorded.

[0091] The system collects heading data through attitude sensors installed on the main propulsion ship and the barge:

[0092] Heading angle of the main propulsion ship: Record the azimuth angle of the main propulsion ship relative to the geographic north pole;

[0093] Heading angle of the barge: Record the azimuth angle of each barge relative to the geographic north pole respectively.

[0094] The system collects navigation data through GPS installed on the main propulsion vessel and barges:

[0095] Speed of the main propulsion vessel: Measure the speed of the main propulsion vessel through GPS;

[0096] Speed of the barge: Measure the speed of each barge through GPS;

[0097] Latitude and longitude coordinates: Use GPS to obtain the ship's position in real time;

[0098] Route trajectory: Draw the fleet's travel trajectory based on latitude and longitude data.

[0099] The system collects connection device data through sensors:

[0100] Tension: Measure the force on the connection device through a tension sensor;

[0101] Direction of force: Calculate the direction of the force on the connection device through a strain gauge sensor;

[0102] Relative distance: Measure the change in distance between the main propulsion vessel and the barge using a laser rangefinder.

[0103] After the collection is completed, the original data may have problems such as inconsistent formats, data redundancy, or missing data, so preprocess it, including:

[0104] Remove invalid data and interpolate to fill in missing data, for example, use linear interpolation to fill in missing time point data;

[0105] Attach timestamps to all data and unify the sampling frequency to ensure that the data is analyzed on the same time axis;

[0106] Since the units of different data are different, normalization processing is required, such as Min-Max normalization, to convert all data into the same numerical range for subsequent calculations.

[0107] Among them, according to the fleet operation status evaluation matrix, perform anomaly detection on the propulsion power parameters, heading change parameters, navigation synchronization parameters, and connection force parameters to determine whether there are abnormal parameters exceeding the preset parameter group, and obtain abnormal parameter data, specifically including:

[0108] Based on the fleet operation status evaluation matrix, the system detects whether there are abnormal situations exceeding the preset parameter range. Anomaly detection mainly uses the method of setting thresholds:

[0109] Preset parameter group, such as:

[0110] The speed difference is less than 0.5 knots, otherwise it may indicate that the fleet is out of sync;

[0111] The course deviation angle is less than 5°, otherwise it may indicate that the fleet is off course;

[0112] The rate of change of the tension of the connecting device is less than 10%, otherwise it may indicate abnormal force on the connecting device;

[0113] When a certain parameter exceeds the threshold, it is recorded as an abnormal parameter.

[0114] In a preferred embodiment of the present invention, by performing trend analysis on the power data in the fleet navigation dataset, calculating the power change rate and torque stability of the main propulsion ship, the propulsion power parameters are obtained, including:

[0115] According to the power data, extract the data related to the power system of the main propulsion ship to obtain the output power, torque value, timestamp, and propeller speed;

[0116] Set a time window according to the timestamp;

[0117] According to the time window, calculate the rate of change of the output power within the time window to obtain the power change rate;

[0118] According to the torque value and the time window, calculate the torque mean and torque standard deviation within the time window;

[0119] Calculate the torque stability according to the torque standard deviation and in combination with the propeller speed.

[0120] In the embodiment of the present invention, according to the power data, extract the data related to the power system of the main propulsion ship to obtain the output power, torque value, timestamp, and propeller speed, providing a basis for subsequent trend analysis by accurately extracting key power data; setting a time window according to the timestamp helps to smooth short-term fluctuations and improve the stability of trend analysis; calculating the rate of change of the output power within the time window according to the time window to obtain the power change rate, monitoring the thrust change of the main propulsion ship in real time and providing power output trend information; calculating the torque mean and torque standard deviation within the time window according to the torque value and the time window, effectively evaluating the load stability of the main propulsion ship; calculating the torque stability according to the torque standard deviation and in combination with the propeller speed, comprehensively considering the relationship between torque volatility and propeller speed, and improving the ability to identify abnormalities in the power system.

[0121] Among them, calculating the torque stability according to the torque standard deviation and in combination with the propeller speed specifically includes:

[0122] ,

[0123] When the torque stability exceeds the preset torque stability, it indicates that the torque fluctuation is large, and there may be abnormalities in the power system. For example, under normal operating conditions, the torque fluctuation should change with the change of the propeller speed. When the torque stability is much higher than the normal level for a certain period of time, it may be caused by problems such as uneven propeller load and unstable fuel supply.

[0124] In a preferred embodiment of the present invention, by performing segmented analysis on the course data in the fleet navigation data set, the course consistency between the main propulsion ship and the barge is determined, and the course deviation angle is calculated to obtain the course change parameter, including:

[0125] According to the navigation data, the course angles of the main propulsion ship and the barge are respectively extracted to obtain the main course angle and the barge course angle;

[0126] The main course angle and the barge course angle are arranged in chronological order and split according to the preset time period to obtain the course segment data set;

[0127] According to the course segment data set, the course change rate of the main propulsion ship in adjacent time periods is calculated, and the course change amplitude of the fleet during navigation is analyzed to obtain the course change data set;

[0128] According to the course change data set, the consistency of the course angles of the main propulsion ship and the barge in different time periods is identified to obtain the navigation consistency;

[0129] According to the navigation consistency, the deviation of the course angles of the main propulsion ship and the barge in different time periods is calculated to obtain the course deviation angle;

[0130] According to the course deviation angle, the mean course deviation and the standard deviation of the course deviation between the main propulsion ship and the barge during navigation are calculated.

[0131] In the embodiment of the present invention, according to the navigation data, the course angles of the main propulsion ship and the barge are respectively extracted to obtain the main course angle and the barge course angle, ensuring the accuracy and integrity of the course data and providing basic data support for subsequent analysis; the main course angle and the barge course angle are arranged in chronological order and split according to the preset time period to obtain the course segment data set, splitting the complex course data during long-term navigation into shorter-term course segments with more analytical value, making the course change trend clearer; according to the course segment data set, the course change rate of the main propulsion ship in adjacent time periods is calculated, and the course change amplitude of the fleet during navigation is analyzed to obtain the course change data set. By calculating the course change rate, the course adjustment situation of the fleet in different time periods can be evaluated, and whether there is an obvious inconsistency in the course adjustment between the main propulsion ship and the barge can be identified.

[0132] Based on the course change dataset, identify the consistency of the course angles of the main propulsion vessel and the barge in different time periods to obtain the navigation consistency, quantitatively analyze the course consistency of the fleet, and provide data support for subsequent deviation calculations; according to the navigation consistency, calculate the deviation of the course angles of the main propulsion vessel and the barge in different time periods to obtain the course deviation angle. By calculating the course deviation angle, the course deviation situation within the fleet can be accurately measured; according to the course deviation angle, calculate the mean value and standard deviation of the course deviation between the main propulsion vessel and the barge during navigation to evaluate the overall trend of the course deviation.

[0133] Among them, based on the course change dataset, identify the consistency of the course angles of the main propulsion vessel and the barge in different time periods to obtain the navigation consistency, which specifically includes:

[0134] On the basis of calculating the course change rate, further analyze the course consistency of the main propulsion vessel and the barge in different time periods:

[0135] Calculate the difference in course changes of the main propulsion vessel and the barge in each time period;

[0136] Set a course consistency threshold. For example, when the course difference is less than a certain set value, it is considered that the courses of the two are consistent in this time period;

[0137] Statistically analyze the proportion of time periods with consistent courses to evaluate the overall course consistency.

[0138] In a preferred embodiment of the present invention, by synchronously analyzing the navigation data in the fleet dataset, calculate the speed difference between the main propulsion vessel and the barge and the route difference of the fleet to obtain navigation synchronization parameters, including:

[0139] According to the navigation data, extract the speeds, longitude and latitude coordinates of the main propulsion vessel and the barge to obtain a navigation status dataset;

[0140] According to the navigation status dataset, calculate the speed change rates of the main propulsion vessel and the barge within the time window respectively to obtain the main speed change rate and the barge speed change rate;

[0141] According to the navigation status dataset, calculate the average values of the speeds of the main propulsion vessel and the barge within the time window respectively to obtain the main speed average value and the barge speed average value;

[0142] Calculate the speed difference according to the main speed average value and the barge speed average value;

[0143] According to the navigation status dataset, calculate the predicted positions of the main propulsion vessel and the barge after a preset time length, and calculate the navigation difference of the fleet according to their positions and the preset route.

[0144] In the embodiments of the present invention, according to the navigation data, the speeds, longitude and latitude coordinates of the main propulsion ship and the barge are extracted to obtain a navigation state data set, ensuring the integrity, accuracy and consistency of the navigation data and providing a reliable data basis for subsequent analysis; according to the navigation state data set, the speed change rates of the main propulsion ship and the barge within the time window are calculated respectively to obtain the main speed change rate and the barge speed change rate, which can dynamically monitor the speed change trends of each ship and identify acceleration or deceleration situations within a short time; according to the navigation state data set, the average speeds of the main propulsion ship and the barge within the time window are calculated respectively to obtain the main speed average value and the barge speed average value, providing data support for subsequent navigation synchronization analysis; according to the main speed average value and the barge speed average value, the speed difference is calculated, which can quantify the speed difference between the main propulsion ship and the barge in real time; according to the navigation state data set, the predicted positions of the main propulsion ship and the barge after a preset time length are calculated, and according to their positions and the preset route, the navigation difference of the fleet is calculated. By calculating the route deviation, the system can determine whether the ship deviates from the set channel.

[0145] Among them, according to the navigation state data set, calculating the predicted positions of the main propulsion ship and the barge after a preset time length, and calculating the navigation difference of the fleet according to their positions and the preset route specifically includes:

[0146] Set a long time window, such as 60 seconds, and obtain the historical longitude and latitude data of the main propulsion ship and the barge within this long time window;

[0147] Calculate their respective navigation trajectories, and establish a route model by the curve fitting method;

[0148] Set the target route of the fleet, and calculate the deviations of the main propulsion ship and the barge relative to the target route:

[0149] ,

[0150] wherein, ( is the longitude and latitude coordinate of the current ship, ( is the nearest matching point on the preset route.

[0151] In a preferred embodiment of the present invention, by analyzing the force on the connecting device data in the fleet navigation data set, the force influence on the connecting device during the fleet navigation is determined to obtain the connecting force parameters, including:

[0152] According to the connecting device data, the tension, force direction of the connecting device and the relative distance between the main propulsion ship and the barge are extracted to obtain a force data set;

[0153] According to the force data set, the tension change rate of the connecting device within the time window is calculated;

[0154] Calculate the maximum and minimum tensions of the connecting device based on the force dataset to obtain the force range of the connecting device;

[0155] Calculate the mean tension and tension standard deviation of the connecting device based on the force dataset, and judge the tension stability of the connecting device according to them;

[0156] Determine the lateral offset between the main propulsion vessel and the barge according to the relative distance between the main propulsion vessel and the barge, and calculate the shear force borne by the connecting device according to it;

[0157] Calculate the angular change rate of the connecting device per unit time according to the force direction.

[0158] In the embodiment of the present invention, based on the connecting device data, the tension, force direction and relative distance between the main propulsion vessel and the barge of the connecting device are extracted to obtain the force dataset, ensuring the integrity and accuracy of the force data and laying a foundation for subsequent analysis; according to the force dataset, calculating the tension change rate of the connecting device within the time window can identify the force change trend of the connecting device; according to the force dataset, calculating the maximum and minimum tensions of the connecting device to obtain the force range of the connecting device helps to judge whether the connecting device is in an overloaded or low-load state for a long time.

[0159] Calculate the mean tension and tension standard deviation of the connecting device according to the force dataset, and judge the tension stability of the connecting device according to them. The mean tension can be used to judge the long-term force level of the connecting device, while the tension standard deviation reflects the force fluctuation; determine the lateral offset between the main propulsion vessel and the barge according to the relative distance between the main propulsion vessel and the barge, and calculate the shear force borne by the connecting device according to it to evaluate the force condition of the connecting device in a complex environment; calculate the angular change rate of the connecting device per unit time according to the force direction to identify abnormal motion patterns during the operation of the fleet.

[0160] Among them, calculating the mean tension and tension standard deviation of the connecting device according to the force dataset, and judging the tension stability of the connecting device according to them specifically includes:

[0161] The judgment criteria for tension stability are as follows:

[0162] When the tension standard deviation < 5N, it indicates that the tension fluctuation is small and the connecting device is in a stable state;

[0163] When 5N ≤ tension standard deviation ≤ 20N, the force of the connecting device is basically stable, but it may be affected by small-range fluctuations;

[0164] When the tension standard deviation > 20N, it indicates that the force of the connecting device changes greatly and may be affected by external forces, such as sea condition changes or improper operations.

[0165] Among them, according to the relative distance between the main propulsion ship and the barge, the lateral offset between the main propulsion ship and the barge is determined, and the shear force borne by the connecting device is calculated based on it, specifically including:

[0166] Calculate the lateral offset according to the GPS coordinate data of the main propulsion ship and the barge;

[0167] The shear force is the lateral force generated by the lateral offset, and the calculation formula is as follows:

[0168] Shear force = lateral offset , is the force direction angle of the connecting device.

[0169] In a preferred embodiment of the present invention, according to the propulsion power parameter, the course change parameter, the navigation synchronization parameter and the connection force parameter, the state relationship between the ships is determined, and the fleet operation state evaluation matrix is obtained, including:

[0170] Calculate the correlation between the power change and the course deviation according to the propulsion power parameter and the course change parameter to obtain the power-course correlation degree;

[0171] Calculate the synchronization between the main propulsion ship and the barge according to the navigation synchronization parameter to obtain the speed synchronization degree;

[0172] Calculate the stress standard deviation of the connecting device within the time window according to the connection force parameter to obtain the stress fluctuation degree;

[0173] Calculate the correlation degree between different ships according to the power-course correlation degree, the speed synchronization degree and the stress fluctuation degree to obtain the ship correlation data set;

[0174] Determine the size of the matrix according to the number of ships in the fleet, and determine the value of each element in the matrix according to the ship correlation data set to obtain the fleet operation state evaluation matrix.

[0175] In the embodiments of the present invention, according to the propulsion power parameters and the course change parameters, the correlation between the power change and the course deviation is calculated to obtain the power-course correlation degree, so as to identify whether the change in the propulsion power of the fleet will cause a course deviation; according to the navigation synchronization parameters, the synchronization between the main propulsion ship and the barges is calculated to obtain the speed synchronization degree, so as to ensure that the ships in the fleet maintain a consistent navigation speed and prevent abnormal towing force or pushing and pulling force caused by speed mismatch; according to the connection force parameters, the standard deviation of the force on the connection device within the time window is calculated to obtain the force fluctuation degree, so as to avoid mechanical damage caused by violent force changes and improve the service life of the connection device; according to the power-course correlation degree, the speed synchronization degree and the force fluctuation degree, the correlation degree between different ships is calculated to obtain the ship correlation data set, which improves the adaptability of the system to complex navigation environments; according to the number of ships in the fleet, the size of the matrix is determined, and according to the ship correlation data set, the value of each element in the matrix is determined to obtain the fleet operation state evaluation matrix, which quantifies the mutual relationship between the ships in the fleet and provides data support for further intelligent analysis.

[0176] Among them, calculating the correlation between the power change and the course deviation according to the propulsion power parameters and the course change parameters to obtain the power-course correlation degree specifically includes:

[0177] Extract the power change rate and torque stability of the main propulsion ship from the propulsion power parameters, and at the same time extract the course offset angle data from the course change parameters;

[0178] Divide the time axis into fixed windows, and calculate the mean values of the power change rate and the course offset angle within each time window;

[0179] Calculate the correlation between the power change rate and the course offset angle through the Pearson correlation coefficient formula.

[0180] Among them, calculating the synchronization between the main propulsion ship and the barges according to the navigation synchronization parameters to obtain the speed synchronization degree specifically includes:

[0181] Extract the average speed, speed difference and route difference between the main propulsion ship and the barges from the navigation synchronization parameters;

[0182] Calculate the speed synchronization degree between the main propulsion ship and the barges through the standard deviation calculation formula;

[0183] When the speed synchronization degree is lower than the preset threshold, the priority of navigation adjustment is increased, and it is recommended to adjust the thrust of the main propulsion ship or the navigation attitude of the barges.

[0184] Among them, calculating the correlation degree between different ships according to the power-course correlation degree, the speed synchronization degree and the force fluctuation degree to obtain the ship correlation data set specifically includes:

[0185] Combine the dynamic course correlation, speed synchronization degree, and force fluctuation degree into a multi-dimensional feature space;

[0186] Comprehensively evaluate the correlation between different ships through a weighted calculation method:

[0187] ,

[0188] wherein, is the correlation between ship and ship, is the dynamic course correlation between ship and ship, is the speed synchronization degree between ship and ship, is the force fluctuation degree between ship and ship, is a coefficient.

[0189] In a preferred embodiment of the present invention, according to the abnormal parameter data, analyze the influence degree of the abnormal parameters on the fleet, obtain the fault influence range, and set the early warning level for the fault according to it, and generate early warning information, including:

[0190] Take the main propulsion ship, barge, and connecting device as nodes, and according to the actual connection situation of the connecting device, interact the corresponding nodes to obtain edges;

[0191] Obtain the fleet correlation network according to the nodes and edges;

[0192] Calculate the fault influence weight of each edge according to the fleet correlation network, and the calculation formula of the fault influence weight is:

[0193] ,

[0194] wherein, is the fault influence weight of the edge between node and node , and are the indexes of the nodes, and are respectively the power change rates of node and node , is the maximum power of the fleet, and are respectively the course angles of node and node , is the maximum course deviation allowed by the fleet. and are respectively the sailing speeds of node and node . is the maximum sailing speed of the fleet, and are respectively the angular change rates of the connecting devices of node and node . and are respectively the force values of the connecting devices of node and node . is the maximum force value of the connecting device, and are coefficients;

[0195] Determine the fault starting point according to the abnormal parameter data;

[0196] Determine the fault nodes affected by the fault starting point according to the fault starting point and the fault impact weight, and obtain the fault propagation path;

[0197] Analyze the influence degree of the fault starting point according to the fault propagation path, and obtain the fault influence range.

[0198] In the embodiment of the present invention, the main propulsion ship, the barge and the connecting device are used as nodes, and according to the actual connection situation of the connecting device, the corresponding nodes are interacted to obtain edges, and a structured representation inside the fleet is established, so that subsequent fault propagation analysis can be calculated based on clear interaction relationships; according to the nodes and edges, a fleet association network is obtained, and the fault influence weight of each edge is calculated according to it, quantifying the influence of different factors on fault propagation and improving the prediction accuracy; according to the abnormal parameter data, the fault starting point is determined, accurately positioning the fault starting point, and targeted measures can be taken quickly; according to the fault starting point and the fault influence weight, the fault nodes affected by the fault starting point are determined, the fault propagation path is obtained, and the fault influence range is dynamically calculated, avoiding the problem that the traditional method only focuses on local faults and ignores the chain effect; according to the fault propagation path, the influence degree of the fault starting point is analyzed, the fault influence range is obtained, and the accurate analysis of the influence range makes the warning information more detailed and specific.

[0199] Among them, analyzing the influence degree of the fault starting point according to the fault propagation path and obtaining the fault influence range specifically includes:

[0200] After determining the fault propagation path, evaluate the influence degree of each affected node. The calculation of the fault influence range mainly considers the following factors:

[0201] Influence duration: Calculate the time when the abnormal parameter continuously exceeds the preset range to judge the persistence of the fault influence;

[0202] Influence intensity: Based on the fault influence weight, determine the degree to which each node is affected;

[0203] Influence type: Combining the functions of each node, such as power, navigation, and connecting devices, analyze the specific problems that may be caused by faults, such as the yaw of the fleet, the imbalance of pushing and pulling forces, and the fracture of the connecting device.

[0204] Among them, when the node is the main propulsion ship, then is the power change rate of the node , when the node is a barge, then is the change rate of work done by the force on the node , and the same applies to the node .

[0205] An embodiment of the present invention also provides a combined fleet fault warning system based on intelligent monitoring. The system includes:

[0206] A data acquisition module, which is used to collect the power data of the main propulsion ship and the heading data, navigation data, and connecting device data of the fleet, and preprocess them to remove redundant data and unify the dimension units to obtain a fleet data set;

[0207] A propulsion power module, which is used to perform trend analysis on the power data in the fleet data set, calculate the power change rate and torque stability of the main propulsion ship, and obtain propulsion power parameters;

[0208] A heading change module, which is used to perform segmented analysis on the heading data in the fleet data set, determine the heading consistency between the main propulsion ship and the barge, and calculate the heading deviation angle to obtain heading change parameters;

[0209] A navigation synchronization module, which is used to perform synchronization analysis on the navigation data in the fleet data set, calculate the speed difference between the main propulsion ship and the barge and the route difference of the fleet, and obtain navigation synchronization parameters;

[0210] A connecting force module, which is used to perform force analysis on the connecting device data in the fleet data set, determine the force influence on the connecting device during the fleet's navigation, and obtain connecting force parameters;

[0211] An evaluation matrix module, which is used to determine the state relationship between ships according to the propulsion power parameters, heading change parameters, navigation synchronization parameters, and connecting force parameters, and obtain a fleet operation state evaluation matrix;

[0212] Anomaly detection module, which is used to perform anomaly detection on propulsion power parameters, course change parameters, navigation synchronization parameters, and connection force parameters according to the fleet operation status evaluation matrix, determine whether there are abnormal parameters exceeding the preset parameter group, and obtain abnormal parameter data;

[0213] Fault warning module, which is used to analyze the influence degree of abnormal parameters on the fleet according to the abnormal parameter data, obtain the fault influence range, and set a warning level for the fault according to it, and generate a warning message.

[0214] It should be noted that this system corresponds to the above method, and all implementation manners in the above method embodiments are applicable to this embodiment and can also achieve the same technical effects.

[0215] An embodiment of the present invention also provides a computing device, including: a processor and a memory storing a computer program. When the computer program is run by the processor, it executes the method as described above. All implementation manners in the above method embodiments are applicable to this embodiment and can also achieve the same technical effects.

[0216] An embodiment of the present invention also provides a computer-readable storage medium storing instructions. When the instructions are run on a computer, the computer is made to execute the method as described above. All implementation manners in the above method embodiments are applicable to this embodiment and can also achieve the same technical effects.

[0217] The above are the preferred embodiments of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention.

Claims

1. A combined fleet fault warning method based on intelligent monitoring, characterized in that The method includes: Collect the power data of the main propulsion ship and the course data, navigation data, and connection device data of the fleet, and preprocess them to remove redundant data and unify the dimension units to obtain the fleet dataset; Through trend analysis of the power data in the fleet dataset, calculate the power change rate and torque stability of the main propulsion ship to obtain the propulsion power parameters; Through segmented analysis of the course data in the fleet dataset, determine the course consistency between the main propulsion ship and the barge, and calculate the course offset angle to obtain the course change parameters; Through synchronous analysis of the navigation data in the fleet dataset, calculate the speed difference between the main propulsion ship and the barge and the route difference of the fleet to obtain the navigation synchronization parameters; Through force analysis of the connection device data in the fleet dataset, determine the force impact on the connection device during fleet navigation to obtain the connection force parameters; Based on the propulsion power parameters, course change parameters, navigation synchronization parameters, and connection force parameters, determine the state relationship between ships to obtain the fleet operation state evaluation matrix; According to the fleet operation state evaluation matrix, perform anomaly detection on the propulsion power parameters, course change parameters, navigation synchronization parameters, and connection force parameters to determine whether there are abnormal parameters exceeding the preset parameter group to obtain the abnormal parameter data; According to the abnormal parameter data, analyze the influence degree of the abnormal parameters on the fleet to obtain the fault influence range, and set the warning level for the fault according to it to generate a warning message; According to the abnormal parameter data, analyze the influence degree of the abnormal parameters on the fleet to obtain the fault influence range, and set the warning level for the fault according to it to generate a warning message, including: Take the main propulsion ship, barge, and connection device as nodes, and according to the actual connection situation of the connection device, interact the corresponding nodes to obtain edges; According to the nodes and edges, obtain the fleet association network; Calculate the absolute difference in the power change rate of two nodes and the first absolute difference in the course angle according to the fleet association network; according to the absolute difference in the power change rate and the absolute difference in the course angle, obtain the first non-linear change value; Calculate the absolute difference in the speeds of two nodes and the absolute value of the cosine of the difference in the angle change rate of the connection device; calculate the second absolute difference in the connection device force values of two nodes; according to the absolute value and the second absolute difference, obtain the second non-linear change value; According to the first non-linear change value and the second non-linear change value, obtain the fault influence weight of the edge between two nodes; According to the abnormal parameter data, determine the fault starting point; According to the fault starting point and the fault influence weight, determine the fault nodes affected by the fault starting point to obtain the fault propagation path; According to the fault propagation path, analyze the influence degree of the fault starting point to obtain the fault influence range.

2. The combined fleet fault warning method based on intelligent monitoring according to claim 1, wherein, Through trend analysis of the power data in the fleet navigation dataset, calculate the power change rate and torque stability of the main propulsion ship to obtain the propulsion power parameters, including: According to the power data, extract the data related to the power system of the main propulsion ship to obtain the output power, torque value, timestamp, and propeller speed; Set a time window according to the timestamp; Calculate the change rate of the output power within the time window according to the time window to obtain the power change rate; Calculate the torque mean value and torque standard deviation within the time window according to the torque value and the time window; Calculate the torque stability according to the torque standard deviation in combination with the thruster speed; 3. The method for fault warning of a combined fleet based on intelligent monitoring according to claim 2, characterized in that By performing segmented analysis on the heading data in the fleet navigation dataset, determine the heading consistency between the main propulsion ship and the barge, calculate the heading offset angle, and obtain the heading change parameters, including: Extract the heading angles of the main propulsion ship and the barge respectively according to the navigation data to obtain the main heading angle and the barge heading angle; Arrange the main heading angle and the barge heading angle in chronological order and split them according to the preset time period to obtain the heading segment dataset; Calculate the heading change rate of the main propulsion ship in adjacent time periods according to the heading segment dataset, analyze the heading change amplitude of the fleet during navigation, and obtain the heading change dataset; Identify the consistency of the heading angles between the main propulsion ship and the barge in different time periods according to the heading change dataset to obtain the navigation consistency; Calculate the deviation of the heading angles between the main propulsion ship and the barge in different time periods according to the navigation consistency to obtain the heading offset angle; Calculate the mean value of the heading offset and the standard deviation of the heading offset between the main propulsion ship and the barge during navigation according to the heading offset angle; 4. The method for fault early warning of a combined fleet based on intelligent monitoring according to claim 3, wherein By performing synchronous analysis on the navigation data in the fleet dataset, calculate the speed difference between the main propulsion ship and the barge and the route difference of the fleet to obtain the navigation synchronization parameters, including: Extract the speeds, longitude and latitude coordinates of the main propulsion ship and the barge according to the navigation data to obtain the navigation state dataset; Calculate the speed change rates of the main propulsion ship and the barge within the time window respectively according to the navigation state dataset to obtain the main speed change rate and the barge speed change rate; Calculate the average values of the speeds of the main propulsion ship and the barge within the time window respectively according to the navigation state dataset to obtain the main speed mean value and the barge speed mean value; Calculate the speed difference according to the main speed mean value and the barge speed mean value; Calculate the predicted positions of the main propulsion ship and the barge after a preset time length according to the navigation state dataset, and calculate the navigation difference of the fleet according to its relationship with the preset route; 5. The method for fault early warning of a combined fleet based on intelligent monitoring according to claim 4, characterized in that, By performing force analysis on the connecting device data in the fleet navigation dataset, determine the force influence on the connecting device during fleet navigation to obtain the connecting force parameters, including: Extract the tension, force direction of the connecting device and the relative distance between the main propulsion ship and the barge according to the connecting device data to obtain the force dataset; Calculate the tension change rate of the connecting device within the time window according to the force dataset; Calculate the maximum tension and minimum tension of the connecting device according to the force dataset to obtain the force range of the connecting device; Calculate the mean value and standard deviation of the tension of the connecting device according to the force dataset, and judge the tension stability of the connecting device according to them; Determine the lateral offset between the main propulsion ship and the barge according to the relative distance between the main propulsion ship and the barge, and calculate the shear force borne by the connecting device according to it; Calculate the angular change rate of the connecting device per unit time according to the force direction.

6. The method for fault early warning of a combined fleet based on intelligent monitoring according to claim 5, characterized in that, Determine the state relationship between ships according to the propulsion power parameters, course change parameters, navigation synchronization parameters, and connection force parameters, and obtain the fleet operation state evaluation matrix, including: Calculate the correlation between power change and course deviation according to the propulsion power parameters and course change parameters to obtain the power-course correlation degree; Calculate the synchronization between the main propulsion ship and the barge according to the navigation synchronization parameters to obtain the speed synchronization degree; Calculate the stress standard deviation of the connection device within the time window according to the connection force parameters to obtain the stress fluctuation degree; Calculate the correlation degree between different ships according to the power-course correlation degree, speed synchronization degree, and stress fluctuation degree to obtain the ship correlation data set; Determine the size of the matrix according to the number of ships in the fleet, and determine the value of each element in the matrix according to the ship correlation data set to obtain the fleet operation state evaluation matrix.

7. A combined fleet fault warning system based on intelligent monitoring, characterized in that, The system is used to execute the method described in any one of claims 1 to 6, and the system includes: A data acquisition module for acquiring the power data of the main propulsion ship, the course data, navigation data, and connection device data of the fleet, and preprocessing them to remove redundant data and unify the dimension units to obtain the fleet data set; A propulsion power module for calculating the power change rate and torque stability of the main propulsion ship by performing trend analysis on the power data in the fleet data set to obtain the propulsion power parameters; A course change module for determining the course consistency between the main propulsion ship and the barge by performing segmented analysis on the course data in the fleet data set, and calculating the course offset angle to obtain the course change parameters; A navigation synchronization module for calculating the speed difference between the main propulsion ship and the barge and the route difference of the fleet by performing synchronization analysis on the navigation data in the fleet data set to obtain the navigation synchronization parameters; A connection force module for determining the force impact on the connection device during the fleet navigation by performing force analysis on the connection device data in the fleet data set to obtain the connection force parameters; An evaluation matrix module for determining the state relationship between ships according to the propulsion power parameters, course change parameters, navigation synchronization parameters, and connection force parameters to obtain the fleet operation state evaluation matrix; An anomaly detection module for performing anomaly detection on the propulsion power parameters, course change parameters, navigation synchronization parameters, and connection force parameters according to the fleet operation state evaluation matrix to determine whether there are abnormal parameters exceeding the preset parameter group, and obtaining the abnormal parameter data; A fault warning module for analyzing the influence degree of the abnormal parameters on the fleet according to the abnormal parameter data to obtain the fault influence range, and setting a warning level for the fault according to it to generate a warning message.

8. A computing device, characterized in that, Including: One or more processors; A storage device for storing one or more programs, which when executed by the one or more processors cause the one or more processors to implement the method described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, A program is stored in the computer-readable storage medium, and when the program is executed by a processor, the method described in any one of claims 1 to 6 is implemented.

Images