Large-scale ocean data buoy safety monitoring system and method based on multi-source fusion

Abstract

The invention discloses a large-scale ocean data buoy safety monitoring system and method based on multi-source fusion, and relates to the technical field of buoy monitoring. Buoy equipment operation parameters, ocean environment data and surrounding ship dynamic information are synchronously acquired through a buoy body sensor group, an environment monitoring unit and a ship identification module; time-frequency domain feature extraction and anomaly detection are carried out on the collected data, and a collision risk dynamic evaluation model is constructed in combination with ship trajectory prediction; establishing an equipment health, environment interference and ship threat fusion evaluation system, and performing risk grade division in combination with real-time monitoring data and a historical database; and generating early warning information based on the risk level, and automatically triggering an equipment maintenance instruction and a ship collision avoidance alarm. The method adapts to ship variable-speed steering scenes, threshold values are dynamically adjusted, and adaptability and analysis accuracy of the system are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of buoy monitoring, and in particular to a large-scale ocean data buoy safety monitoring system and method based on multi-source fusion. Background Art

[0002] The ocean buoy online monitoring system utilizes advanced IoT and wireless sensing technologies to monitor water quality, currents, waves, weather, and other parameters online, providing comprehensive data support for marine ecological research. The buoy serves as the observation platform. In addition to surface-based instrumentation, some equipment can also be moved vertically via an automatic lifting system, enabling the collection of stratified data.

[0003] In existing technologies, ocean buoys typically issue warnings for ship collision risks based on fixed distance thresholds, failing to account for real-time changes in threats due to ship speed and course adjustments. In severe sea conditions, these warnings can be triggered by wave-induced drift of the buoy's position. Furthermore, equipment health assessments rely on manual experience to set alarm thresholds, making it difficult to capture early degradation characteristics such as abnormal vibration patterns and gradual changes in power consumption. Furthermore, it's impossible to establish a nonlinear correlation between equipment performance degradation and multi-source monitoring data, leading to delayed fault warnings. Traditional environmental impact analysis methods also rely on determining if a single parameter has exceeded its limit, weakening their adaptability to complex environments.

[0004] Therefore, the present invention discloses a large-scale ocean data buoy safety monitoring system and method based on multi-source fusion to solve the above problems. Summary of the Invention

[0005] The purpose of the present invention is to provide a large-scale ocean data buoy safety monitoring system and method based on multi-source fusion to solve the problems raised in the prior art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a large-scale ocean data buoy safety monitoring method based on multi-source fusion, the method comprising the following steps:

[0007] S1: The buoy's sensor group, environmental monitoring unit, and ship identification module are used to synchronously collect buoy equipment operating parameters, marine environmental data, and surrounding ship dynamic information;

[0008] S2: Extract time-frequency domain features and detect anomalies from the collected data, and build a dynamic collision risk assessment model based on ship trajectory prediction;

[0009] S3: Establish an integrated assessment system for equipment health, environmental interference, and ship threats, and classify risk levels based on real-time monitoring data and historical databases;

[0010] S4: Generates early warning information based on risk levels, automatically triggering equipment maintenance instructions and ship collision avoidance alarms.

[0011] According to the above scheme, S1 includes the following contents:

[0012] S101: Acquire monitoring data of the buoy body, wherein the monitoring data of the buoy body includes collecting three-axis vibration acceleration a through a vibration sensor x , a y , a z ; Obtain the buoy power consumption sequence P(t) through the current sensor, where t represents the time; Record the buoy position drift △L through the GPS module; Obtain environmental monitoring data, which includes wave height Hs and wave period TP obtained through wave radar; Collect water temperature Tw, salinity S and water depth D through the temperature-salinity-depth sensor; Obtain ship data, which includes parsing AIS signals to obtain ship position, ship speed vs and ship heading αs; Extract ship draft ds through visual recognition;

[0013] S102: Time synchronization alignment of heterogeneous data; establish a spatial grid mapping model to convert the ship position into polar coordinates (rs, θs) relative to the buoy; generate a fused dataset D with a timestamp = {D b ,D e ,D v}, where D b is the buoy body data, D e is the environmental data, D v For ship data.

[0014] This application collects combined monitoring data of vibration, power consumption, and position drift parameters to accurately capture early signs of mechanical failure of equipment, and uses time synchronization to resolve the phase difference problem between waves, ship motion, and equipment status. Polar coordinate mapping converts the ship position into a buoy relative motion model to simplify the collision prediction calculation dimension. The fused data set with timestamps provides standardized input for subsequent time-frequency analysis to avoid conflicts in multi-source data formats.

[0015] According to the above scheme, S2 includes the following contents:

[0016] S201: Extract the buoy power consumption fragment sequence based on the preset window length, calculate the total vibration acceleration of each sampling point, and record the total vibration acceleration of the i-th sampling point as a i , a i =(a x 2 +a y 2 +a z 2 ) 1 / 2 ; Analyze the vibration energy index EV of the buoy body based on the total vibration acceleration of each sampling point:

[0017]

[0018] Where I represents the total number of sampling points in the preset window length; i∈[1,I], i is a positive integer;

[0019] Analyze the abnormality of buoy power consumption AP based on the historical mean and standard deviation of buoy power consumption t :AP t =|P(t)-μ p | / σ p ; where μ p represents the historical mean of buoy power consumption, σ p represents the standard deviation of the buoy power consumption;

[0020] S202: Analyze the radial closing speed rs'=vs×cos(αs-θs) based on the ship's speed, ship's heading, and the polar coordinates of the ship's position relative to the buoy; analyze the collision risk index PC based on the radial closing speed, PC=1 / (1+exp(-K1×RC-K2×ds / D)); wherein K1 and K2 represent sensitivity coefficients, which are system preset constants; exp() represents an exponential function with a natural number as the base; RC represents the ship's closing rate, which is equal to the radial closing speed divided by the distance between the ship and the buoy. The collision risk index threshold is recorded as PC th ; PC th =PC0×exp(-K3×Hs); wherein PC0 represents the threshold base value, K3 represents the threshold coefficient, and the threshold base value and the threshold coefficient are preset constants.

[0021] This application uses triaxial acceleration synthesis calculations to effectively distinguish between normal wave impacts and abnormal vibration modes such as structural resonance; adaptively identify battery aging, sensor short circuits, and power system failures; radial approach speed calculations avoid the limitations of traditional fixed safety distance methods and adapt to ship speed and steering scenarios; convert nonlinear risks into normalized probability values, and dynamically adjust thresholds with wave height to avoid false triggering caused by wind and wave interference;

[0022] According to the above solution, S3 contains the following:

[0023] S301: Constructing an environmental impact factor EB = β1 × |Tw-Tref| + β2 × S / S0; where β1 and β2 represent preset factor coefficients; Tref represents the rated operating temperature of the buoy; and S0 represents the reference salinity.

[0024] Extract the vibration energy index, power consumption abnormality and health degradation index of the faulty buoy at the last operating moment. The health degradation index is set by the administrator to generate a data point set {(EV1, AP1, HD1), (EV2, AP2, HD2), ..., (EV j, AP j , HD j ),…,(EV J , AP J , HD J )}, where EV j Represents the vibration energy index of the jth data point, AP j Indicates the power consumption abnormality of the jth data point, HD j represents the health degradation index of the jth data point, j∈[1,J], j is a positive integer, and J represents the total number of data points; after performing nonlinear fitting on the data points, a health degradation model is established: y=ω1×x1+ω2×x2+ω3, where x1 represents the independent variable corresponding to the vibration energy index divided by the maximum value of the vibration energy index, x2 represents the independent variable corresponding to the power consumption abnormality divided by the maximum value of the power consumption abnormality, y represents the dependent variable of the health degradation index, and ω1, ω2, and ω3 are all fitting coefficients;

[0025] A risk value model is constructed based on the health degradation index, collision risk index, and environmental impact factors: R = γ1 × HD + γ2 × PC + γ3 × EB; where γ1, γ2, and γ3 represent risk coefficients, which are preset constants;

[0026] S302: If the risk value is greater than or equal to the first risk value threshold or the health degradation index is greater than the health degradation index threshold and the environmental impact factor is greater than the environmental impact factor threshold, the risk level is level one; otherwise, the risk value is greater than or equal to the second risk value threshold, the risk level is level two; otherwise, the risk value is greater than or equal to the third risk value threshold, the risk level is level three; otherwise, it is normal.

[0027] This application reflects the accelerating effect of seawater corrosiveness on equipment life through the influence of salinity (S / S0); temperature deviation (|Tw-Tref|) is associated with the structural stress caused by thermal expansion of the sealed cabin; the nonlinear relationship between vibration, power consumption and equipment health is fitted through historical failure data, breaking through the mechanical judgment of traditional threshold alarms; the first-level risk adopts "or" logic to ensure that extreme situations (such as equipment is about to fail and the environment is harsh) are handled first; graded thresholds avoid system overreaction caused by sudden changes in a single indicator.

[0028] According to the above scheme, S4 includes the following contents:

[0029] If the risk level is level one, send the device sleep command and activate the backup power supply; if the risk level is level two, generate the ship collision avoidance path Path = {Δα = arcsin (d safe / rs),Δv=vs-v safe}; where Δα represents the ship’s collision avoidance deflection angle, d saferepresents the preset safety distance, Δv represents the ship's collision avoidance adjustment speed, v safe Indicates the preset safe ship speed; if the risk level is level 3, the satellite emergency communication link is activated and a distress message is broadcast;

[0030] When the false alarm rate of the early warning is greater than the preset threshold, the data point set is expanded and the fitting coefficient is recalibrated.

[0031] This application triggers model parameter recalibration based on false alarm rate monitoring and continuously optimizes evaluation accuracy through incremental learning.

[0032] Another aspect of the present application provides a large-scale ocean data buoy safety monitoring system based on multi-source fusion, which is applied to the above-mentioned large-scale ocean data buoy safety monitoring method based on multi-source fusion. The system includes a buoy data acquisition module, an abnormal risk analysis module, a safety risk assessment module, and an early warning and disposal module.

[0033] The buoy data acquisition module is used to synchronously collect buoy equipment operating parameters, marine environmental data and surrounding ship dynamic information through the buoy body sensor group, environmental monitoring unit and ship identification module;

[0034] The abnormal risk analysis module is used to extract time-frequency domain features and detect anomalies on the collected data, and to build a dynamic collision risk assessment model in combination with ship trajectory prediction;

[0035] The safety risk assessment module is used to establish a fusion assessment system for equipment health, environmental interference and ship threats, and to classify risk levels by combining real-time monitoring data and historical databases;

[0036] The early warning and disposal module is used to generate early warning information based on the risk level and automatically trigger equipment maintenance instructions and ship collision avoidance alarms.

[0037] According to the above solution, the buoy data acquisition module includes a basic data acquisition unit and a data fusion unit;

[0038] The basic data acquisition unit is used to obtain buoy body monitoring data, environmental monitoring data and ship data;

[0039] The data fusion unit is used to perform time synchronization alignment on heterogeneous data; establish a spatial grid mapping model to convert the ship position into polar coordinates relative to the buoy; and generate a fused data set with a time stamp.

[0040] According to the above solution, the abnormal risk analysis module includes a power consumption abnormality analysis unit and a collision risk analysis unit;

[0041] The power consumption anomaly analysis unit is used to extract a buoy power consumption fragment sequence based on a preset window length, calculate the total vibration acceleration of each sampling point, analyze the vibration energy index of the buoy body based on the total vibration acceleration of each sampling point; and analyze the power consumption anomaly of the buoy based on the historical mean and standard deviation of the buoy power consumption;

[0042] The collision risk analysis unit is used to analyze the radial closing speed according to the ship speed, the ship heading and the polar coordinates of the ship position relative to the buoy; and analyze the collision risk index based on the radial closing speed.

[0043] According to the above solution, the security risk assessment module includes a risk value model construction unit and a risk level classification unit;

[0044] The risk value model construction unit is used to construct an environmental impact factor, extract the vibration energy index, power consumption abnormality and health degradation index of the faulty buoy at the last operating moment, and generate a data point set; establish a health degradation model after performing nonlinear fitting on the data points; and construct a risk value model based on the health degradation index, collision risk index and environmental impact factor;

[0045] If the risk value is greater than or equal to the first threshold of the risk value or the health degradation index is greater than the health degradation index threshold and the environmental impact factor is greater than the environmental impact factor threshold, the risk level is level one; otherwise, the risk value is greater than or equal to the second threshold of the risk value, the risk level is level two; otherwise, the risk value is greater than or equal to the third threshold of the risk value, the risk level is level three; otherwise, it is normal.

[0046] According to the above scheme, the early warning and disposal module is used to send a device sleep command and activate the backup power supply if the risk level is level one; generate a ship collision avoidance path if the risk level is level two; and start the satellite emergency communication link and broadcast a distress message if the risk level is level three.

[0047] Compared with the existing technology, the beneficial effects of the present invention are as follows: the present application collects vibration, power consumption, position drift parameter combination monitoring, accurately captures the early signs of mechanical failure of equipment, and time synchronization solves the phase difference problem between waves, ship motion and equipment status; polar coordinate mapping converts the ship position into a buoy relative motion model, simplifying the collision prediction calculation dimension; the fused data set with timestamp provides standardized input for subsequent time-frequency analysis, avoiding multi-source data format conflicts; the present application effectively distinguishes between normal wave impact and abnormal vibration modes such as structural resonance through three-axis acceleration synthesis calculation; adaptively identifies battery aging, sensor short circuit and power system failure Obstacles; radial approach speed calculation circumvents the limitations of traditional fixed safety distance methods and adapts to ship speed changes and steering scenarios; nonlinear risks are converted into normalized probability values, and the threshold is dynamically adjusted with wave height to avoid false triggering caused by wind and wave interference; this application uses salinity to reflect the accelerated effect of seawater corrosiveness on equipment life; temperature deviations are associated with structural stress caused by thermal expansion of sealed cabins; historical fault data is used to fit the nonlinear relationship between vibration, power consumption, and equipment health, breaking through the mechanical judgment of traditional threshold alarms; "OR" logic is used for level 1 risks to ensure priority handling of extreme situations; graded thresholds avoid system overreactions caused by sudden changes in a single indicator. This application monitors the trigger model parameters based on false alarm rates and continuously optimizes assessment accuracy through incremental learning. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0049] Figure 1 Schematic diagram of the flow of the large-scale ocean data buoy safety monitoring method based on multi-source fusion of the present invention;

[0050] Figure 2 This is a structural diagram of the large-scale ocean data buoy safety monitoring system based on multi-source fusion of the present invention. DETAILED DESCRIPTION

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only 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 making creative efforts are within the scope of protection of the present invention.

[0052] See also Figure 1 The present invention provides a technical solution: a large-scale ocean data buoy safety monitoring method based on multi-source fusion, which includes the following steps:

[0053] S1: The buoy's sensor group, environmental monitoring unit, and ship identification module are used to synchronously collect buoy equipment operating parameters, marine environmental data, and surrounding ship dynamic information;

[0054] In S1, the following are included:

[0055] S101: Acquire the monitoring data of the buoy body, which includes collecting the three-axis vibration acceleration a through the vibration sensor x , a y , a z ; Obtain the buoy power consumption sequence P(t) through the current sensor, where t represents the time; record the buoy position drift △L through the GPS module; obtain environmental monitoring data, which includes wave height Hs and wave period TP obtained through wave radar; collect water temperature Tw, salinity S and water depth D through the temperature-salinity-depth sensor; obtain ship data, which includes parsing AIS signals to obtain ship position, ship speed vs and ship heading αs; extract ship draft ds through visual recognition;.

[0056] S102: Time synchronization alignment of heterogeneous data; establish a spatial grid mapping model to convert the ship position into polar coordinates (rs, θs) relative to the buoy; generate a fused dataset D with a timestamp = {D b ,D e ,D v}, where D b is the buoy body data, D e is the environmental data, D v For ship data.

[0057] S2: Extract time-frequency domain features and detect anomalies from the collected data, and build a dynamic collision risk assessment model based on ship trajectory prediction;

[0058] S2 contains the following:

[0059] S201: Extract the buoy power consumption fragment sequence based on the preset window length, calculate the total vibration acceleration of each sampling point, and record the total vibration acceleration of the i-th sampling point as a i , a i =(a x 2 +a y 2 +a z 2 ) 1 / 2 ; Analyze the vibration energy index EV of the buoy body based on the total vibration acceleration of each sampling point:

[0060]

[0061] Where I represents the total number of sampling points in the preset window length; i∈[1,I], i is a positive integer;

[0062] Analyze the abnormality of buoy power consumption AP based on the historical mean and standard deviation of buoy power consumption t :AP t =|P(t)-μ p | / σ p ; where μ p represents the historical mean of buoy power consumption, σ p represents the standard deviation of the buoy power consumption;

[0063] S202: Analyze the radial closing velocity rs'=vs×cos(αs-θs) based on the ship's speed, ship's heading, and the polar coordinates of the ship's position relative to the buoy; analyze the collision risk index PC based on the radial closing velocity, PC=1 / (1+exp(-K1×RC-K2×ds / D)); where K1 and K2 represent sensitivity coefficients, which are system preset constants; RC represents the ship's closing rate, which is equal to the radial closing velocity divided by the distance between the ship and the buoy. The collision risk index threshold is recorded as PC th ; PC th =PC0×exp(-K3×Hs); wherein PC0 represents the threshold base value, K3 represents the threshold coefficient, and the threshold base value and the threshold coefficient are preset constants.

[0064] S3: Establish an integrated assessment system for equipment health, environmental interference, and ship threats, and classify risk levels based on real-time monitoring data and historical databases;

[0065] In S3, it contains the following:

[0066] S301: Constructing an environmental impact factor EB = β1 × |Tw-Tref| + β2 × S / S0; where β1 and β2 represent preset factor coefficients; Tref represents the rated operating temperature of the buoy; and S0 represents the reference salinity.

[0067] Extract the vibration energy index, power consumption abnormality and health degradation index of the faulty buoy at the last operating moment. The health degradation index is set by the administrator to generate a data point set {(EV1, AP1, HD1), (EV2, AP2, HD2), …, (EV j , AP j , HD j ),…,(EV J , AP J , HD J )}, where EV j Represents the vibration energy index of the jth data point, AP j Indicates the power consumption abnormality of the jth data point, HDj represents the health degradation index of the jth data point, j∈[1,J], j is a positive integer, and J represents the total number of data points; after performing nonlinear fitting on the data points, a health degradation model is established: y=ω1×x1+ω2×x2+ω3, where x1 represents the independent variable corresponding to the vibration energy index divided by the maximum value of the vibration energy index, x2 represents the independent variable corresponding to the power consumption abnormality divided by the maximum value of the power consumption abnormality, y represents the dependent variable of the health degradation index, and ω1, ω2, and ω3 are all fitting coefficients;

[0068] A risk value model is constructed based on the health degradation index, collision risk index, and environmental impact factors: R = γ1 × HD + γ2 × PC + γ3 × EB; where γ1, γ2, and γ3 represent risk coefficients, and the risk coefficient is a preset constant.

[0069] S302: If the risk value is greater than or equal to the first risk value threshold or the health degradation index is greater than the health degradation index threshold and the environmental impact factor is greater than the environmental impact factor threshold, the risk level is level one; otherwise, the risk value is greater than or equal to the second risk value threshold, the risk level is level two; otherwise, the risk value is greater than or equal to the third risk value threshold, the risk level is level three; otherwise, it is normal.

[0070] Example 1: In this example, HD = 0.82, PC = 0.3, EB = 0.4; γ1 = 0.6, γ2 = 0.2, γ3 = 0.2;

[0071] Solid R = 0.6 × 0.82 + 0.2 × 0.3 + 0.2 × 0.4 = 0.62;

[0072] In this embodiment, the first threshold of the risk value is 0.8, and the threshold of the health deterioration index is 0.75; although R=0.62<0.8, Hd>0.75, triggering a level I warning (equipment failure first).

[0073] S4: Generates early warning information based on risk levels, automatically triggering equipment maintenance instructions and ship collision avoidance alarms.

[0074] In S4, the following contents are included:

[0075] If the risk level is level one, send the device sleep command and activate the backup power supply; if the risk level is level two, generate the ship collision avoidance path Path = {Δα = arcsin (d safe / rs),Δv=vs-v safe}; where Δα represents the ship’s collision avoidance deflection angle, d safe represents the preset safety distance, Δv represents the ship's collision avoidance adjustment speed, v safe Indicates the preset safe ship speed; if the risk level is level 3, the satellite emergency communication link is activated and a distress message is broadcast;

[0076] When the false alarm rate of the early warning is greater than the preset threshold, the data point set is expanded and the fitting coefficient is recalibrated.

[0077] See also Figure 2 , the present invention provides a technical solution: a large-scale ocean data buoy safety monitoring system based on multi-source fusion, the system includes a buoy data acquisition module, an abnormal risk analysis module, a safety risk assessment module and an early warning and disposal module;

[0078] The buoy data acquisition module is used to synchronously collect buoy equipment operating parameters, marine environmental data and surrounding ship dynamic information through the buoy body sensor group, environmental monitoring unit and ship identification module;

[0079] The abnormal risk analysis module is used to extract time-frequency domain features and detect anomalies from the collected data, and to build a dynamic collision risk assessment model based on ship trajectory prediction;

[0080] The safety risk assessment module is used to establish an integrated assessment system for equipment health, environmental interference, and ship threats, and to classify risk levels based on real-time monitoring data and historical databases;

[0081] The early warning and disposal module is used to generate early warning information based on risk levels, automatically triggering equipment maintenance instructions and ship collision avoidance alarms.

[0082] The buoy data acquisition module includes a basic data acquisition unit and a data fusion unit;

[0083] The basic data acquisition unit is used to obtain buoy body monitoring data, environmental monitoring data and ship data;

[0084] The data fusion unit is used to synchronize the time of heterogeneous data; establish a spatial grid mapping model to convert the ship position into polar coordinates relative to the buoy; and generate a fused dataset with a timestamp.

[0085] The abnormal risk analysis module includes a power consumption abnormality analysis unit and a collision risk analysis unit;

[0086] The power consumption anomaly analysis unit is used to extract the buoy power consumption fragment sequence based on a preset window length, calculate the total vibration acceleration of each sampling point, and analyze the vibration energy index of the buoy body based on the total vibration acceleration of each sampling point; and analyze the power consumption anomaly of the buoy based on the historical mean and standard deviation of the buoy power consumption;

[0087] The collision risk analysis unit is used to analyze the radial closing speed according to the ship speed, the ship heading and the polar coordinates of the ship position relative to the buoy; and analyze the collision risk index based on the radial closing speed.

[0088] The safety risk assessment module includes a risk value model building unit and a risk level classification unit;

[0089] The risk value model construction unit is used to construct environmental impact factors, extract the vibration energy index, power consumption abnormality, and health degradation index of the faulty buoy at the last moment of operation, and generate a data point set; establish a health degradation model after performing nonlinear fitting on the data points; and construct a risk value model based on the health degradation index, collision risk index, and environmental impact factors.

[0090] If the risk value of the risk level division unit is greater than or equal to the first threshold of the risk value or the health deterioration index is greater than the health deterioration index threshold and the environmental impact factor is greater than the environmental impact factor threshold, the risk level is level one; otherwise, the risk value is greater than or equal to the second threshold of the risk value, the risk level is level two; otherwise, the risk value is greater than or equal to the third threshold of the risk value, the risk level is level three; otherwise, it is normal.

[0091] The early warning and disposal module is used to send a sleep command to the equipment and activate the backup power supply if the risk level is level one; generate a ship collision avoidance path if the risk level is level two; and activate the satellite emergency communication link and broadcast a distress message if the risk level is level three.

[0092] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0093] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A large-scale ocean data buoy safety monitoring method based on multi-source fusion is characterized by: The method comprises the following steps: S1: The buoy's sensor group, environmental monitoring unit, and ship identification module are used to synchronously collect buoy equipment operating parameters, marine environmental data, and surrounding ship dynamic information; S2: Extract time-frequency domain features and detect anomalies from the collected data, and build a dynamic collision risk assessment model based on ship trajectory prediction; S3: Establish an integrated assessment system for equipment health, environmental interference, and ship threats, and classify risk levels based on real-time monitoring data and historical databases; S4: Generates early warning information based on risk levels, automatically triggering equipment maintenance instructions and ship collision avoidance alarms.

2. The large-scale ocean data buoy safety monitoring method based on multi-source fusion according to claim 1 is characterized by: In S1, the following are included: S101: Acquire monitoring data of the buoy body, wherein the monitoring data of the buoy body includes collecting three-axis vibration acceleration a through a vibration sensor x , a y , a z ; obtain the buoy power consumption sequence P(t) through the current sensor, where t represents the time; record the buoy position drift ΔL through the GPS module; obtain environmental monitoring data, which includes wave height Hs and wave period TP obtained through wave radar; collect water temperature Tw, salinity S and water depth D through the temperature, salinity and depth sensor; obtain ship data, which includes analyzing AIS signals to obtain ship position, ship speed vs and ship heading αs; Extract the ship's draft ds through visual recognition;. S102: Time synchronization alignment of heterogeneous data; establish a spatial grid mapping model to convert the ship position into polar coordinates (rs, θs) relative to the buoy; generate a fused dataset D with a timestamp = {D b ,D e ,D v }, where D b is the buoy body data, D e is the environmental data, D v For ship data.

3. The large-scale ocean data buoy safety monitoring method based on multi-source fusion according to claim 2 is characterized by: S2 contains the following: S201: Extract the buoy power consumption fragment sequence based on the preset window length, calculate the total vibration acceleration of each sampling point, and record the total vibration acceleration of the i-th sampling point as a i , a i =(a x 2 +a y 2 +a z 2 ) 1 / 2 ; Analyze the vibration energy index EV of the buoy body based on the total vibration acceleration of each sampling point; Analyze the abnormality of buoy power consumption AP based on the historical mean and standard deviation of buoy power consumption t :AP t =|P(t)-μ p | / σ p ; Among them, μ p represents the historical mean of buoy power consumption, σ p represents the standard deviation of the buoy power consumption; S202: Analyze the radial closing speed rs'=vs×cos(αs-θs) based on the ship's speed, ship's heading, and the polar coordinates of the ship's position relative to the buoy; analyze the collision risk index PC based on the radial closing speed, PC=1 / (1+exp(-K1×RC-K2×ds / D)); wherein K1 and K2 represent sensitivity coefficients, which are system preset constants, and exp() represents an exponential function with a natural number as the base; RC represents the ship's closing rate, which is equal to the radial closing speed divided by the distance between the ship and the buoy. The collision risk index threshold is recorded as PC th ; PC th =PC0×exp(-K3×Hs); wherein PC0 represents the threshold base value, K3 represents the threshold coefficient, and the threshold base value and the threshold coefficient are preset constants.

4. The large-scale ocean data buoy safety monitoring method based on multi-source fusion according to claim 3 is characterized by: In S3, it contains the following: S301: Constructing an environmental impact factor EB = β1 × |Tw-Tref| + β2 × S / S0; where β1 and β2 represent preset factor coefficients; Tref represents the rated operating temperature of the buoy; and S0 represents the reference salinity. Extract the vibration energy index, power consumption abnormality and health degradation index of the faulty buoy at the last operating moment. The health degradation index is set by the administrator to generate a data point set {(EV1, AP1, HD1), (EV2, AP2, HD2), ..., (EV j , AP j , HD j ),…,(EV J , AP J , HD J )}, where EV j Represents the vibration energy index of the jth data point, AP j Indicates the power consumption abnormality of the jth data point, HD j represents the health degradation index of the jth data point, j∈[1,J], j is a positive integer, and J represents the total number of data points; after performing nonlinear fitting on the data points, a health degradation model is established: y=ω1×x1+ω2×x2+ω3, where x1 represents the independent variable corresponding to the vibration energy index divided by the maximum value of the vibration energy index, x2 represents the independent variable corresponding to the power consumption abnormality divided by the maximum value of the power consumption abnormality, y represents the dependent variable of the health degradation index, and ω1, ω2, and ω3 are all fitting coefficients; Construct a risk value model based on the health degradation index, collision risk index and environmental impact factors: R = γ1 × HD + γ2 × PC + γ3 × EB; where γ1, γ2, and γ3 represent risk coefficients, which are preset constants; S302: If the risk value is greater than or equal to the first risk value threshold or the health degradation index is greater than the health degradation index threshold and the environmental impact factor is greater than the environmental impact factor threshold, the risk level is level one; otherwise, the risk value is greater than or equal to the second risk value threshold, the risk level is level two; otherwise, the risk value is greater than or equal to the third risk value threshold, the risk level is level three; otherwise, it is normal.

5. The large-scale ocean data buoy safety monitoring method based on multi-source fusion according to claim 4 is characterized by: In S4, the following contents are included: If the risk level is level one, send the device sleep command and activate the backup power supply; if the risk level is level two, generate the ship collision avoidance path Path = {Δα = arcsin (d safe / rs),Δv=vs-v safe }; where Δα represents the ship’s collision avoidance deflection angle, d safe represents the preset safety distance, Δv represents the ship's collision avoidance adjustment speed, v safe Indicates the preset safe ship speed; if the risk level is level 3, the satellite emergency communication link is activated and a distress message is broadcast; When the false alarm rate of the early warning is greater than the preset threshold, the data point set is expanded and the fitting coefficient is recalibrated.

6. A large-scale ocean data buoy safety monitoring system based on multi-source fusion, wherein the system is applied to the large-scale ocean data buoy safety monitoring method based on multi-source fusion according to any one of claims 1 to 5, and is characterized in that: The system includes a buoy data acquisition module, an abnormal risk analysis module, a safety risk assessment module, and an early warning and disposal module; The buoy data acquisition module is used to synchronously collect buoy equipment operating parameters, marine environmental data and surrounding ship dynamic information through the buoy body sensor group, environmental monitoring unit and ship identification module; The abnormal risk analysis module is used to extract time-frequency domain features and detect anomalies on the collected data, and to build a dynamic collision risk assessment model in combination with ship trajectory prediction; The safety risk assessment module is used to establish a fusion assessment system for equipment health, environmental interference and ship threats, and to classify risk levels by combining real-time monitoring data and historical databases; The early warning and disposal module is used to generate early warning information based on the risk level and automatically trigger equipment maintenance instructions and ship collision avoidance alarms.

7. The large-scale ocean data buoy safety monitoring system based on multi-source fusion according to claim 6 is characterized by: The buoy data acquisition module includes a basic data acquisition unit and a data fusion unit; The basic data acquisition unit is used to obtain buoy body monitoring data, environmental monitoring data and ship data; The data fusion unit is used to perform time synchronization alignment on heterogeneous data; A spatial grid mapping model is established to convert the ship position into polar coordinates relative to the buoy; a fused dataset with a timestamp is generated.

8. The large-scale ocean data buoy safety monitoring system based on multi-source fusion according to claim 6 is characterized by: The abnormal risk analysis module includes a power consumption abnormality analysis unit and a collision risk analysis unit; The power consumption anomaly analysis unit is used to extract a buoy power consumption fragment sequence based on a preset window length, calculate the total vibration acceleration of each sampling point, analyze the vibration energy index of the buoy body based on the total vibration acceleration of each sampling point; and analyze the power consumption anomaly of the buoy based on the historical mean and standard deviation of the buoy power consumption; The collision risk analysis unit is used to analyze the radial closing speed based on the ship's speed, the ship's heading, and the polar coordinates of the ship's position relative to the buoy; Analyze collision risk indicators based on radial closing speed.

9. The large-scale ocean data buoy safety monitoring system based on multi-source fusion according to claim 6 is characterized by: The safety risk assessment module includes a risk value model building unit and a risk level classification unit; The risk value model construction unit is used to construct environmental impact factors, extract the vibration energy index, power consumption abnormality and health degradation index of the faulty buoy at the last operating moment, generate a data point set; and establish a health degradation model after performing nonlinear fitting on the data points; Construct a risk value model based on the health degradation index, collision risk index and environmental impact factors; The risk level classification unit determines that if the risk value is greater than or equal to the first risk value threshold or the health deterioration index is greater than the health deterioration index threshold and the environmental impact factor is greater than the environmental impact factor threshold, the risk level is level one; Otherwise, the risk value is greater than or equal to the second risk value threshold, and the risk level is level two; otherwise, the risk value is greater than or equal to the third risk value threshold, and the risk level is level three; otherwise, it is normal.

10. The large-scale ocean data buoy safety monitoring system based on multi-source fusion according to claim 6 is characterized by: The early warning and handling module is used to send a device sleep command and activate the backup power supply if the risk level is level one; generate a ship collision avoidance path if the risk level is level two; and activate a satellite emergency communication link and broadcast a distress message if the risk level is level three.

Images