A wireless monitoring and alarm system and method applied to amphibious ships

Abstract

The present invention relates to the technical field of ship monitoring and alarm, and particularly to a wireless monitoring and alarm system and method applied to amphibious ships. The method includes the following steps: building a ship status monitoring and alarm device on the amphibious ship; monitoring the hull status of the amphibious ship through the ship status monitoring and alarm device to obtain real-time hull inclination values; performing motion inclination compensation on the real-time hull inclination values to generate compensated inclination estimation values; performing fuzzy inference on the compensated inclination estimation values for the ship alarm threshold and performing scene-based dynamic adjustment to obtain a dynamic alarm threshold; using the dynamic alarm threshold to perform intelligent alarm judgment on the compensated inclination estimation values to generate a final ship alarm signal. The present invention can accurately identify the inclination changes of the ship under different environmental conditions, and realizes precise monitoring, intelligent analysis and timely early warning of the ship inclination status.

Description

Technical Field

[0001] The present invention relates to the technical field of ship monitoring and alarm technology, and in particular to a wireless monitoring and alarm system and method applied to amphibious ships. Background Art

[0002] As a special ship that can operate in both water and land environments, amphibious ships have higher requirements for tilt stability due to the complexity and particularity of their operating environment. Amphibious ships need to sail and operate in both water and land environments. When sailing on water, they will be affected by factors such as wind, waves, and water currents. When sailing on land, they will be affected by factors such as ground undulations and load changes, all of which will cause the ship to tilt. Excessive tilt angles will not only affect the navigation performance and operating efficiency of the ship, but in severe cases may even cause the ship to capsize, causing casualties and property losses. Environmental factors such as waves and water currents will interfere with the inclination sensor. When a ship sails in waves, the hull will continue to shake with the ups and downs of the waves. This shaking will affect the measurement results of the inclination sensor and cause deviations in the measurement data. In addition, the water flow will also exert force on the hull, affecting the hull's posture, and thus affecting the measurement accuracy of the inclination sensor. The movement of the ship itself will also affect the inclination measurement. For example, when a ship turns, centrifugal force will be generated, causing the hull to tilt outward. This tilt is part of the normal movement of the ship, but traditional tilt sensors often cannot distinguish between this motion tilt and tilt caused by external factors, resulting in errors in the measurement results. However, traditional amphibious ship tilt monitoring usually simply uses sensor monitoring data for monitoring, and often cannot distinguish between motion tilt and tilt caused by external factors, resulting in errors in the measurement results and frequent false alarms, which ultimately affects the safe navigation of the ship. Summary of the invention

[0003] Based on this, the present invention provides a wireless monitoring alarm system and method applied to amphibious ships to solve at least one of the above technical problems.

[0004] To achieve the above object, a wireless monitoring and alarm method applied to an amphibious ship comprises the following steps:

[0005] Step S1: Building a ship status monitoring and alarm device on an amphibious ship; monitoring the hull status of the amphibious ship through the ship status monitoring and alarm device, and generating calibration ship status monitoring data;

[0006] Step S2: estimating the inclination observation value according to the calibrated ship state monitoring data to obtain the real-time hull inclination value; processing the ship motion parameters according to the calibrated ship state monitoring data to obtain the ship motion turning centrifugal force data; performing motion inclination compensation on the real-time hull inclination value through the ship motion turning centrifugal force data to generate a compensated inclination estimation value;

[0007] Step S3: Obtain real-time water condition and meteorological data; perform fuzzy inference on the ship alarm threshold based on the real-time water condition and meteorological data and the estimated value of the compensation inclination angle to obtain the roll angle alarm threshold and the pitch angle alarm threshold respectively; perform scenario-based dynamic adjustment on the roll angle alarm threshold and the pitch angle alarm threshold to obtain the dynamic alarm threshold;

[0008] Step S4: Use the dynamic alarm threshold to perform intelligent alarm judgment on the estimated value of the compensation inclination angle to generate the final ship alarm signal;

[0009] Step S5: Send the final ship alarm signal to the crew's mobile devices or the shore-based monitoring center through the LoRaWAN wireless communication module to obtain wireless alarm monitoring information.

[0010] By building a ship condition monitoring and alarm device, the present invention can comprehensively monitor the hull condition of the amphibious ship. At the same time, through the processing of the ship's motion parameters, the system can accurately calculate the influence of the centrifugal force when the ship turns, and perform motion inclination compensation in combination with the real-time hull inclination value. This compensation mechanism can effectively distinguish the normal motion inclination of the ship from the inclination caused by the external environment, reduce the monitoring error caused by motion factors, and significantly improve the reliability of the data. Combining real-time water conditions and meteorological data, perform fuzzy inference processing on the hull inclination alarm threshold, and dynamically adjust the alarm threshold according to the operation scenario of the ship. This dynamic adjustment mechanism avoids the limitations of the traditional fixed threshold setting, enables the system to flexibly set reasonable alarm thresholds according to the actual environmental conditions, reduces the false alarm phenomenon under complex water conditions or extreme meteorological conditions, and can timely capture real dangerous inclination changes, providing more accurate early warning support for the safe operation of the ship, realizing independent adjustment of the roll angle and pitch angle alarm thresholds, and being able to perform differential processing according to the risk characteristics of different inclination directions, further improving the accuracy of the alarm. Through the intelligent alarm judgment mechanism, comprehensively analyze the estimated value of the compensated inclination angle to generate the final ship alarm signal, ensuring the credibility and practicality of the alarm signal. This intelligent judgment ability effectively avoids the false alarm phenomenon caused by a single data anomaly, making the alarm system more stable and reliable. Finally, through the LoRaWAN wireless communication module, the alarm signal is transmitted in real time to the crew's mobile devices or the shore-based monitoring center. The system can not only achieve the real-time nature of remote alarms, but also ensure that important information is quickly transmitted to relevant personnel in case of emergencies, facilitating the crew and shore-based management personnel to take countermeasures in a timely manner, thereby greatly improving the efficiency of ship safety management and the emergency handling ability. Therefore, an application of the present invention to an amphibious ship's wireless monitoring and alarm method addresses the problems of false alarms, missed alarms, and poor adaptability existing in the traditional amphibious ship inclination monitoring, realizes precise monitoring, intelligent analysis, and timely early warning of the ship's inclination state, and significantly improves the navigation safety of amphibious ships in complex environments.

[0011] Preferably, step S1 includes the following steps:

[0012] Step S11: Install multiple triaxial accelerometers, triaxial gyroscopes and GPS modules at the bow, stern and middle part of the hull of the amphibious ship, and perform initialization calibration to build a ship status monitoring and alarm device;

[0013] Step S12: Set the sampling frequency according to the ship status monitoring and alarm device, and monitor the hull status of the amphibious ship to generate raw ship status monitoring data;

[0014] Step S13: Transmit the raw ship status monitoring data to the on-board data processing center through the LoRaWAN wireless communication module, and perform multi-source data parsing to generate ship status monitoring metadata;

[0015] Step S14: Perform noise filtering processing on the ship status monitoring metadata to obtain noise-reduced ship status monitoring data;

[0016] Step S15: Perform timestamp synchronization processing on the noise-reduced ship status monitoring data, and perform time correction based on the time signal in the GPS module to generate calibrated ship status monitoring data.

[0017] Through the installation of multiple triaxial accelerometers, triaxial gyroscopes and GPS modules at the bow, stern and middle part of the hull of the amphibious ship and the initialization calibration, the present invention can realize the all-round and multi-angle status monitoring of the ship, effectively improving the comprehensiveness and accuracy of data collection. Through the reasonable setting of the sampling frequency, the system can adapt to the requirements of different navigation and operation scenarios, ensuring the real-time and effectiveness of the monitoring data. Using the LoRaWAN wireless communication module to transmit the collected raw data to the on-board data processing center can reduce the risk of data transmission delay and loss, ensuring the efficiency and reliability of data transmission. Through the multi-source data parsing technology, the data collected by different sensors are fused to generate structured ship status monitoring metadata, effectively improving the usability and consistency of the data. At the same time, through the noise filtering processing technology, the system can significantly reduce the environmental noise interference in the collected data, improving the accuracy and stability of the monitoring data. Further adopting the timestamp synchronization processing technology and performing time correction based on the time signal of the GPS module can ensure the time consistency of the monitoring data.

[0018] Preferably, step S2 includes the following steps:

[0019] Step S21: Extract real-time measurement data according to the calibrated ship status monitoring data to obtain real-time GPS positioning data, real-time accelerometer measurement data and real-time gyroscope measurement data respectively;

[0020] Step S22: Estimate the Kalman tilt observation value based on the real-time accelerometer measurement data and the real-time gyroscope measurement data to obtain the real-time hull tilt value;

[0021] Step S23: Extract the ship's longitude and latitude coordinates through the real-time GPS positioning data to obtain the ship's longitude and latitude coordinate data;

[0022] Step S24: Process the ship's motion parameters according to the ship's longitude and latitude coordinate data to obtain the ship's motion turning centrifugal force data;

[0023] Step S25: Use the ship's motion turning centrifugal force data as the tilt compensation amount to perform motion tilt compensation on the real-time hull tilt value to generate a compensated tilt estimation value.

[0024] Through the extraction and processing of real-time measurement data from the calibrated ship condition monitoring data, the present invention can comprehensively obtain the real-time GPS positioning data, accelerometer measurement data, and gyroscope measurement data of the ship, providing high-precision and multi-dimensional basic data support for subsequent tilt calculation and compensation. Using the Kalman filtering algorithm to fuse and process the data of the accelerometer and gyroscope can effectively reduce the noise and deviation in the data of a single sensor, improving the calculation accuracy and stability of the real-time hull tilt value. At the same time, by extracting the ship's longitude and latitude coordinates through the GPS positioning data, the spatial position and motion trajectory of the ship can be accurately determined, providing an important basis for the calculation of the ship's dynamic motion parameters. Processing the ship's motion parameters based on the longitude and latitude coordinates, calculating the centrifugal force data generated by the ship during turning, and further combining these data to perform motion tilt compensation on the real-time hull tilt value can effectively distinguish the normal motion tilt from the tilt deviation caused by external environmental interference, thereby generating a more accurate compensated tilt estimation value.

[0025] Preferably, step S22 includes the following steps:

[0026] Step S221: Decompose the three-axis measurement values according to the real-time accelerometer measurement data and the real-time gyroscope measurement data, and define the measurement variables to obtain the hull monitoring variable data;

[0027] Step S222: Construct a Kalman measurement tilt calculation model according to the hull monitoring variable data;

[0028] Step S223: Calculate the components of the gravitational acceleration in the three axes using the real-time accelerometer measurement data to obtain the gravitational acceleration components;

[0029] Step S224: Estimate the current tilt observation value according to the gravitational acceleration components to obtain the real-time hull tilt observation estimation value;

[0030] Step S225: Perform real-time measurement noise processing on the real-time accelerometer measurement data and the real-time gyroscope measurement data, and calculate the predicted value of the inclination angle using the Kalman measurement inclination angle calculation model to obtain the predicted value of the hull inclination angle;

[0031] Step S226: Calculate the difference between the predicted value of the hull inclination angle and the estimated value of the real-time hull inclination angle, and perform Kalman gain weighted update to generate the real-time hull inclination angle value.

[0032] Through the three-axis decomposition and variable definition of the real-time accelerometer measurement data and the real-time gyroscope measurement data, the present invention can accurately extract the monitoring variable data of the hull attitude, providing a clear physical basis for the inclination angle calculation. Based on these monitoring variable data, a Kalman measurement inclination angle calculation model is constructed, making the inclination angle estimation and prediction have higher mathematical accuracy and dynamic adaptability. By calculating the components of the gravitational acceleration in each axis and estimating the observed value of the inclination angle accordingly, the system can quickly obtain the estimated value of the real-time hull inclination angle. At the same time, the noise in the measurement data is processed in real time, effectively reducing the influence of external interference on the inclination angle calculation and ensuring the stability and reliability of the data. Using the Kalman filter algorithm to calculate the predicted value of the hull inclination angle, and combining the estimated value of the real-time inclination angle for difference calculation and Kalman gain weighted update, can dynamically correct the inclination angle prediction error and generate a more accurate real-time hull inclination angle value. This joint observation and prediction processing mechanism not only improves the accuracy of the inclination angle calculation, but also enhances the system's response ability to the rapid motion state of the hull, especially effectively reducing the cumulative error and transient error in the inclination angle calculation in a complex environment.

[0033] Preferably, step S222 includes the following steps:

[0034] Define the hull state variables of the amphibious ship to obtain the hull state variable data; wherein, the hull state variable data includes the roll angle, pitch angle, roll angle rate, and pitch angle rate;

[0035] Construct a Kalman filter calculation equation based on the hull monitoring variable data and the hull state variable data to obtain the initial Kalman measurement inclination angle calculation model;

[0036] Obtain the historical navigation data of the amphibious ship;

[0037] Use the historical navigation data of the amphibious ship to perform initial state statistics on the hull state variable data to generate the initial value data of the ship state vector;

[0038] Conduct measurement error analysis based on the accelerometer and gyroscope, and set the initial covariance matrix of the state vector to obtain the initial covariance matrix; wherein, the diagonal elements in the initial covariance matrix represent the initial uncertainties of each state variable, and the non-diagonal elements represent the correlations between state variables;

[0039] The initial covariance matrix and the initial value data of the ship state vector are combined with Kalman parameters, and the parameters of the initial Kalman measurement tilt angle calculation model are adjusted to obtain the Kalman measurement tilt angle calculation model.

[0040] In the present invention, by defining the hull state variables of the amphibious ship, the key monitoring variables including the roll angle, pitch angle, roll angle rate, and pitch angle rate are clarified, providing a comprehensive state description basis for tilt angle calculation. Combining the hull monitoring variable data and state variable data, an initial Kalman filter calculation equation is constructed, enabling the model to accurately reflect the change characteristics of the ship's dynamic state. By using the historical navigation data of the amphibious ship to conduct initial state statistics on the state variables and generating the initial value data of the ship state vector, the historical characteristics and dynamic laws of the ship's operation can be fully considered in the model initialization stage, thereby improving the applicability of the model and the accuracy of the initial calculation. In addition, by analyzing the measurement errors of the accelerometer and gyroscope and combining the setting of the initial covariance matrix of the state vector, the system can effectively quantify the uncertainty of each state variable and its mutual correlation. The setting of the covariance matrix ensures that the Kalman filter can balance the weights between the observed value and the predicted value during the dynamic calculation process, reducing the cumulative effect of model errors. Finally, the initial covariance matrix and the initial value of the ship state vector are combined with parameters, and the parameters of the initial Kalman measurement tilt angle calculation model are adjusted to make the model more conform to the dynamic operation characteristics and external environment interference characteristics of the ship.

[0041] Preferably, step S24 includes the following steps:

[0042] Step S241: Calculate the real-time heading angle based on the ship's longitude and latitude coordinate data to generate real-time heading angle data;

[0043] Step S242: Calculate the real-time speed based on the ship's longitude and latitude coordinate data to generate real-time navigation speed data;

[0044] Step S243: Calculate the rate of change of the heading angle for the real-time heading angle data, and determine whether the change in the real-time heading angle exceeds the heading angle change threshold through a preset heading angle change threshold to obtain heading angle change judgment data;

[0045] Step S244: When the heading angle change judgment data is true, it is determined that the ship is turning to obtain ship turning judgment data;

[0046] Step S245: Based on the ship turning judgment data, calculate the centrifugal force during ship turning through the real-time navigation speed data to obtain ship motion turning centrifugal force data.

[0047] Through the processing of the ship's latitude and longitude coordinate data, the present invention can calculate the heading angle and sailing speed of the ship in real time, provide accurate motion state data, and lay a foundation for the determination of the ship's dynamic behavior. The calculation of the real-time heading angle change rate and the judgment of the heading angle change threshold help to quickly identify whether the ship is in a turning state, avoiding the lag and inaccuracy in the dynamic identification of ship turning in the traditional method. When it is determined that the ship is turning, the system calculates the centrifugal force data during the ship's turning in combination with the real-time sailing speed data, providing key motion parameter support for subsequent inclination compensation. Through this centrifugal force calculation process, the system can accurately quantify the influence of the dynamic external force generated during the ship's turning process and separate it from the actual inclination data, avoiding misjudging the inclination caused by the centrifugal force as external environmental interference, thus significantly improving the accuracy of inclination monitoring.

[0048] Preferably, step S3 includes the following steps:

[0049] Step S31: Set the fuzzy logic input variables according to the type of amphibious ship to obtain the fuzzy logic input variables;

[0050] Step S32: Set the fuzzy logic output variables according to the fuzzy logic input variables to generate the fuzzy logic output variables;

[0051] Step S33: Define the fuzzy sets according to the fuzzy logic input variables and the fuzzy logic output variables, thereby establishing a fuzzy logic inference model;

[0052] Step S34: Calculate the change rates of the roll angle and pitch angle according to the estimated value of the compensated inclination angle to obtain the inclination angle change rate data;

[0053] Step S35: Obtain the real-time water condition and meteorological data; rate the water wave height according to the real-time water condition and meteorological data to obtain the real-time water wave height data;

[0054] Step S36: Input the inclination angle change rate data and the real-time water wave height data into the fuzzy logic inference model and perform fuzzy inference to obtain the roll angle alarm threshold and the pitch angle alarm threshold respectively;

[0055] Step S37: Perform scene-based dynamic adjustment on the roll angle alarm threshold and the pitch angle alarm threshold to obtain the dynamic alarm threshold.

[0056] By setting fuzzy logic input variables according to the type of amphibious ship and generating fuzzy logic output variables, the present invention can perform personalized configuration for the operating characteristics and safety requirements of different types of ships, ensuring the applicability and accuracy of the system. By defining fuzzy sets and establishing a fuzzy logic inference model, the system can effectively handle the non-linear relationships of multiple factors in a complex environment. Especially under dynamically changing water conditions and meteorological conditions, it can flexibly adjust the alarm threshold, avoiding the limitations of traditional fixed threshold settings. By combining the compensated tilt angle estimation value to calculate the roll angle and pitch angle change rates of the ship, the dynamic change characteristics of the ship's tilt state are further quantified, providing real-time and accurate tilt angle change data support for the setting of the alarm threshold. At the same time, by obtaining real-time water condition and meteorological data and rating the water wave height, the system can fully consider the impact of the external environment on the safe operation of the ship, combine the water wave height data with the tilt angle change rate data and input them into the fuzzy logic inference model to comprehensively judge the tilt risk of the ship. Finally, through fuzzy inference, the alarm thresholds of the roll angle and pitch angle are generated and dynamically adjusted according to the real-time operation scenario to generate dynamic alarm thresholds that are more in line with the current environment and ship state.

[0057] Preferably, step S37 includes the following steps:

[0058] Step S371: Obtain the real-time operation application scenario of the amphibious ship;

[0059] Step S372: Match the safety margin coefficient according to the real-time operation application scenario of the amphibious ship to obtain the safety margin coefficient of the operation scenario;

[0060] Step S373: Calculate the scenario adjustment coefficients for the roll angle alarm threshold and the pitch angle alarm threshold respectively through the safety margin coefficient of the operation scenario to obtain the roll angle alarm threshold adjustment coefficient and the pitch angle alarm threshold adjustment coefficient respectively;

[0061] Step S374: Dynamically adjust the corresponding thresholds of the roll angle alarm threshold and the pitch angle alarm threshold based on the roll angle alarm threshold adjustment coefficient and the pitch angle alarm threshold adjustment coefficient to generate dynamic alarm thresholds.

[0062] By obtaining the real-time operation application scenarios of amphibious ships, the present invention can accurately identify the current operating environment and working conditions of the ships, providing a scenario-based basis for the dynamic adjustment of alarm thresholds. By matching the safety margin coefficients according to different operation scenarios, the system can reasonably consider the differences in the safety requirements of ships under various scenarios. For example, in scenarios with heavy operation loads or complex environmental conditions, the system can match a higher safety margin coefficient, thereby making a more conservative adjustment to the alarm threshold to ensure the operational safety of the ships. By calculating the scenario adjustment coefficients of the roll angle and pitch angle alarm thresholds, the system can make differential adjustments to the roll angle and pitch angle alarm thresholds respectively according to the specific requirements of the application scenario, and then generate dynamic alarm thresholds. This scenario-based adjustment method can significantly enhance the system's adaptability to different operating environments, achieving refined management and dynamic optimization of alarm thresholds. The finally generated dynamic alarm thresholds can better fit the actual operating state of the ship in the current operation scenario, not only effectively reducing the false alarms and missed alarms caused by too high or too low thresholds, but also improving the accuracy and reliability of alarms.

[0063] Preferably, step S4 includes the following steps:

[0064] Step S41: Compare the compensated tilt angle estimated value with the dynamic alarm threshold to determine whether it exceeds the threshold, and obtain an alarm trigger flag;

[0065] Step S42: Calculate the degree of tilt angle exceeding the threshold according to the alarm trigger flag, and generate tilt angle overrun degree data;

[0066] Step S43: Divide the tilt angle overrun degree data into the current alarm level through a preset alarm level division standard to obtain preliminary alarm level data;

[0067] Step S44: Evaluate the alarm credibility according to the preliminary alarm level data to generate alarm credibility evaluation data;

[0068] Step S45: Calculate the historical tilt angle change rate of the compensated tilt angle estimated value, compare it with a preset tilt angle change rate threshold, and determine whether the tilt angle change is abnormal to obtain a tilt angle change abnormality flag;

[0069] Step S46: When both the alarm trigger flag and the tilt angle change abnormality flag are true, and the alarm credibility evaluation data is higher than the preset threshold, trigger an alarm to generate a final ship alarm signal; otherwise, it is determined as a false alarm and the alarm is filtered.

[0070] By comparing the compensated inclination angle estimation value with a dynamic alarm threshold, the present invention can quickly determine whether the current inclination angle exceeds the safe range, thereby generating an alarm trigger flag, providing the first layer of screening for potential inclination risks. Further, by calculating the degree of inclination angle exceeding the threshold and generating inclination angle overrun degree data, the system can quantify the specific amplitude of the inclination angle overrun, providing a scientific basis for alarm classification. According to the preset alarm level division standard, the system can classify different degrees of inclination angle overruns, making the response to alarm signals more accurate and targeted. At the same time, by evaluating the credibility of the preliminary alarm level data, false alarm phenomena caused by data noise or short-term anomalies can be effectively identified, generating alarm signals with high credibility, thereby improving the reliability of the system. In addition, by calculating the historical inclination angle change rate, the system can dynamically monitor the inclination angle change trend and, by comparing it with the preset change rate threshold, determine whether the inclination angle change is abnormal. This trend monitoring mechanism can further enhance the accuracy of alarm signals and capture potential dangerous inclination angle dynamics. Finally, when the alarm trigger flag and the inclination angle change anomaly flag are both true, and the alarm credibility evaluation data is higher than the preset threshold, the system will trigger the final ship alarm signal; otherwise, it will be determined as a false alarm and filtered. This multi-level alarm determination and filtering mechanism can significantly reduce the occurrence of false alarms, avoid interfering with the crew's judgment due to false alarms, and ensure that real inclination angle anomalies can be captured in a timely manner and reliable alarm signals can be issued.

[0071] Preferably, the present invention further provides a wireless monitoring and alarm system for an amphibious ship, which executes the wireless monitoring and alarm method for an amphibious ship as described above. The wireless monitoring and alarm system for an amphibious ship includes:

[0072] A hull state monitoring module, which is used to build a ship state monitoring and alarm device on the amphibious ship; monitor the hull state of the amphibious ship through the ship state monitoring and alarm device, and generate calibrated ship state monitoring data;

[0073] An inclination angle compensation calculation module, which is used to estimate the inclination angle observation value based on the calibrated ship state monitoring data to obtain the real-time hull inclination angle value; process the ship motion parameters according to the calibrated ship state monitoring data to obtain the ship motion turning centrifugal force data; perform motion inclination angle compensation on the real-time hull inclination angle value through the ship motion turning centrifugal force data to generate a compensated inclination angle estimation value;

[0074] A threshold dynamic adjustment module, which is used to obtain real-time water condition and meteorological data; perform fuzzy reasoning on the ship alarm threshold based on the real-time water condition and meteorological data and the compensated inclination angle estimation value to respectively obtain the roll angle alarm threshold and the pitch angle alarm threshold; perform scenario-based dynamic adjustment on the roll angle alarm threshold and the pitch angle alarm threshold to obtain a dynamic alarm threshold;

[0075] An intelligent alarm judgment module is used to make an intelligent alarm judgment on the compensated tilt angle estimation value by using a dynamic alarm threshold, and generate a final ship alarm signal;

[0076] A wireless signal transmission module is used to send the final ship alarm signal to the crew's mobile devices or the shore-based monitoring center through the LoRaWAN wireless communication module, and obtain wireless alarm monitoring information. Description of the Drawings

[0077] Figure 1 It is a schematic flow chart of the steps of the wireless monitoring and alarm method of the present invention applied to an amphibious ship;

[0078] Figure 2 is Figure 1 a detailed implementation step flow chart of step S1 in

[0079] Figure 3 is Figure 1 a detailed implementation step flow chart of step S4 in

[0080] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the drawings. Detailed Embodiments

[0081] The technical method of the present invention will be clearly and completely described below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0082] In addition, the drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0083] It should be understood that although the terms "first", "second", etc. may be used here to describe each unit, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be called the second unit, and similarly the second unit may be called the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed related items.

[0084] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides a wireless monitoring and alarm method for an amphibious ship, including the following steps:

[0085] Step S1: Build a ship status monitoring and alarm device on the amphibious ship; monitor the hull status of the amphibious ship through the ship status monitoring and alarm device to generate calibrated ship status monitoring data;

[0086] Step S2: Estimate the inclination observation value according to the calibrated ship status monitoring data to obtain the real-time hull inclination value; process the ship motion parameters according to the calibrated ship status monitoring data to obtain the ship motion turning centrifugal force data; compensate the motion inclination of the real-time hull inclination value through the ship motion turning centrifugal force data to generate a compensated inclination estimation value;

[0087] Step S3: Obtain the real-time water condition and meteorological data; perform fuzzy inference on the ship alarm threshold according to the real-time water condition and meteorological data and the compensated inclination estimation value to obtain the roll angle alarm threshold and the pitch angle alarm threshold respectively; perform scene-based dynamic adjustment on the roll angle alarm threshold and the pitch angle alarm threshold to obtain the dynamic alarm threshold;

[0088] Step S4: Use the dynamic alarm threshold to perform intelligent alarm judgment on the compensated inclination estimation value to generate the final ship alarm signal;

[0089] Step S5: Send the final ship alarm signal to the crew's mobile device or the shore-based monitoring center through the LoRaWAN wireless communication module to obtain the wireless alarm monitoring information.

[0090] In the embodiment of the present invention, the wireless monitoring and alarm method for an amphibious ship includes the following steps:

[0091] Step S1: Build a ship status monitoring and alarm device on the amphibious ship; monitor the hull status of the amphibious ship through the ship status monitoring and alarm device to generate calibrated ship status monitoring data;

[0092] In the embodiments of the present invention, integrated sensing units are installed at key positions of the bow, stern and middle part of the hull of the amphibious ship. Each unit includes an MPU6050 sensor (configured with a sampling rate of 100 Hz) for measuring three-axis acceleration and three-axis angular velocity, and an NEO-6M GPS module (configured with a sampling rate of 1 Hz) for obtaining geographical location information. The raw data collected by each sensing unit is stably transmitted to the on-board data processing center based on the STM32F407 microcontroller through the RS485 bus. The on-board center is responsible for performing preliminary data processing, specifically including: zero-bias calibration and scale factor calibration of the raw output of the MPU6050 sensor to correct the inherent errors of the sensor; at the same time, satellite signal acquisition and positioning solution are performed on the raw signal of the NEO-6M GPS module to extract preliminary latitude and longitude, speed and heading information. The data after preliminary processing is wirelessly transmitted to the (shore-based or remote) data processing center by using the LoRaWAN module (adopting the SX1278 chip, operating in the 433 MHz frequency band, and the transmit power is 10 dBm). After receiving the data packet, the data processing center parses it and assigns accurate timestamp metadata to it. To further improve the data quality, the center uses a Butterworth low-pass filter with a cut-off frequency of 10 Hz to filter the received three-axis acceleration and three-axis angular velocity data (which has been calibrated on board) to remove high-frequency noise. Finally, in order to unify the time reference of the sensor data with different sampling rates, with the accurate timestamp provided by the GPS module as a reference, all the processed sensor data is time-synchronized through the linear interpolation algorithm to generate calibrated ship status monitoring data including timestamp, three-axis acceleration, three-axis angular velocity, latitude and longitude, speed (ground speed) and heading (ground heading).

[0093] Step S2: Estimate the tilt observation value according to the calibrated ship status monitoring data to obtain the real-time hull tilt value; process the ship motion parameters according to the calibrated ship status monitoring data to obtain the ship motion turning centrifugal force data; perform motion tilt compensation on the real-time hull tilt value through the ship motion turning centrifugal force data to generate a compensated tilt estimation value;

[0094] In the embodiment of the present invention, GPS data (latitude and longitude, speed over ground, and course over ground) at 1 Hz and IMU data (acceleration and angular velocity) at 10 Hz are extracted from the calibration data. The IMU data is fused using the Kalman filter algorithm, with the state vector being [roll angle, pitch angle, roll angle rate, pitch angle rate], and the observation vector being [estimated roll angle from accelerometer, estimated pitch angle from accelerometer, roll angle rate from gyroscope, pitch angle rate from gyroscope]. The state transition matrix is based on a uniform motion model, and the observation matrix is an identity matrix. The initial state vector and covariance matrix are obtained through statistics of historical navigation data, and the process noise and measurement noise covariance matrices are adjusted according to the sensor noise characteristics. The Kalman filter outputs real-time hull inclination values (roll angle and pitch angle). The course change rate and haversine distance are calculated based on adjacent GPS data, and the turning radius and centripetal acceleration are calculated in combination with the speed over ground. Assuming the ship mass is 1000 kg, the centrifugal force is calculated and decomposed into the hull coordinate system, and the inclination offset is calculated and subtracted from the real-time inclination value to obtain the compensated inclination estimate value.

[0095] Step S3: Obtain real-time water condition and meteorological data; perform fuzzy inference on the ship alarm threshold based on the real-time water condition and meteorological data and the compensated inclination estimate value to obtain the roll angle alarm threshold and the pitch angle alarm threshold respectively; perform scenario-based dynamic adjustment on the roll angle alarm threshold and the pitch angle alarm threshold to obtain the dynamic alarm threshold.

[0096] In the embodiment of the present invention, data such as wind speed, wind direction, wave height, and wave period are obtained through on-board meteorological sensors. The water wave height level is divided according to the wave height (for example: low, medium, high). The change rate of the compensated inclination estimate value is calculated. The wind speed, wave height level, and inclination change rate are used as fuzzy logic input variables, and the roll angle alarm threshold and the pitch angle alarm threshold are used as output variables. Fuzzy sets and membership functions (such as triangular or trapezoidal) are defined, and a fuzzy rule base is established (for example: IF wind speed is high AND wave height is high THEN roll angle alarm threshold is large). Fuzzy inference and defuzzification are performed to obtain the roll angle alarm threshold and the pitch angle alarm threshold. According to the real-time operation scenario of the ship (for example: normal navigation, landing / offshore), a preset safety margin coefficient is matched (for example: 1.0, 1.2), and the adjustment coefficient is calculated and used to adjust the alarm threshold to obtain the dynamic alarm threshold.

[0097] Step S4: Use the dynamic alarm threshold to perform intelligent alarm judgment on the compensated inclination estimate value to generate the final ship alarm signal.

[0098] In the embodiment of the present invention, the compensated tilt estimation value is compared with the dynamic alarm threshold, and an alarm trigger flag is set. The degree of tilt exceeding the limit is calculated. According to the preset alarm level classification standard (for example: exceeding the limit by 1 - 5 degrees is a first-level alarm), the preliminary alarm level is obtained. The alarm credibility is evaluated by combining the preliminary alarm level, historical alarm data, and environmental factors to generate a credibility value between 0 and 1. The historical change rate of the compensated tilt estimation value is calculated and compared with the preset threshold to determine whether the tilt change is abnormal. When both the alarm trigger flag and the tilt change abnormality flag are true, and the alarm credibility is higher than the preset threshold (for example, 0.8), an alarm is triggered to generate a final ship alarm signal including the alarm type, level, and time. Otherwise, the alarm is filtered.

[0099] Step S5: Send the final ship alarm signal to the crew's mobile device or the shore-based monitoring center through the LoRaWAN wireless communication module to obtain wireless alarm monitoring information.

[0100] In the embodiment of the present invention, it is sent to the crew's mobile device or the shore-based monitoring center through the LoRaWAN wireless communication module (model: SX1278, operating frequency: 433 MHz). Each IMU and GPS module is equipped with a LoRaWAN module, which is connected to the sensor through the UART interface. The LoRaWAN module accesses the LoRaWAN network in the OTAA (Over-The-Air Activation) mode. The alarm signal is encapsulated into a LoRaWAN data packet, and the payload of the data packet includes the alarm type, alarm level, alarm time, compensated tilt estimation value, dynamic alarm threshold, and ship position information. The header of the data packet contains the target device address (the server of the crew's mobile device or the shore-based monitoring center). The LoRaWAN module sends the data packet to the nearby LoRaWAN gateway through the ISM frequency band. The gateway forwards the data packet to the LoRaWAN network server. The network server decrypts and authenticates the data packet and sends the payload to the server of the crew's mobile device or the shore-based monitoring center. After receiving the alarm information, the server of the crew's mobile device or the shore-based monitoring center gives a prompt in a graphical interface or voice. For example, the alarm information is displayed on the crew's mobile device and an alarm sound is emitted to prompt the crew to pay attention to the tilt state of the ship.

[0101] As an example of the present invention, refer to Figure 2 shown as Figure 1 the detailed implementation step flow diagram of step S1 in

[0102] Step S11: Install multiple three-axis accelerometers, three-axis gyroscopes, and GPS modules at the bow, stern, and middle of the hull of the amphibious ship and perform initialization calibration to build a ship status monitoring and alarm device;

[0103] In an embodiment of the present invention, an integrated unit is installed at each of the bow, stern, and middle part of the hull of the amphibious ship. Each integrated unit includes a three-axis accelerometer and a three-axis gyroscope of model MPU6050, and a GPS module of model NEO-6M. Each integrated unit is connected to the on-board data processing center through the RS485 bus. After installation, each MPU6050 is initialized and calibrated, including zero-offset calibration and scale factor calibration. Zero-offset calibration is performed by collecting data for a certain period of time under static conditions and calculating the average value as the zero-offset value. Scale factor calibration is performed by placing the sensor in an environment with known acceleration and angular velocity and calculating the ratio between the actual value and the measured value. The initialization and calibration of the GPS module include acquiring satellite signals and performing positioning and resolution calculations.

[0104] Step S12: Set the sampling frequency according to the ship status monitoring and alarm device, and monitor the hull status of the amphibious ship to generate the original ship status monitoring data;

[0105] In an embodiment of the present invention, the sampling frequencies of the three-axis accelerometer and the three-axis gyroscope are set to 100 Hz, and the sampling frequency of the GPS module is set to 1 Hz. The data acquisition module in each integrated unit acquires sensor data at the set sampling frequency. The data of the three-axis accelerometer and the three-axis gyroscope include the three-axis acceleration values and the three-axis angular velocity values, with the units of g and ° / s respectively. The data of the GPS module includes information such as longitude, latitude, altitude, speed, heading, and timestamp. The acquired original data is stored in the buffer area inside the integrated unit.

[0106] Step S13: Transmit the original ship status monitoring data to the on-board data processing center through the LoRaWAN wireless communication module, and perform multi-source data parsing to generate the meta ship status monitoring data;

[0107] In an embodiment of the present invention, each integrated unit sends the acquired original data to the on-board data processing center through the LoRaWAN wireless communication module. The LoRaWAN wireless communication module uses the SX1278 chip, with a working frequency of 433 MHz and a transmission power of 10 dBm. The on-board data processing center is based on the STM32F407 microcontroller and receives data from each integrated unit. The data processing center parses the received data packets, extracts the data of each sensor, and classifies them according to the data source and type to generate the meta ship status monitoring data. The meta data includes the data from different sensors and the corresponding timestamp information.

[0108] Step S14: Perform noise filtering processing on the meta ship status monitoring data to obtain the noise-reduced ship status monitoring data;

[0109] In the embodiment of the present invention, noise filtering processing is performed on the acceleration and angular velocity data in the ship state monitoring metadata. A Butterworth low-pass filter with a cut-off frequency of 10 Hz is used to filter out high-frequency noise. Since the GPS data has a relatively low sampling frequency, no filtering processing is performed.

[0110] Step S15: Perform timestamp synchronization processing on the noise-reduced ship state monitoring data, and use the time signal in the GPS module as a reference for time correction to generate calibrated ship state monitoring data.

[0111] In the embodiment of the present invention, due to the time delay in data acquisition and transmission of each sensor, it is necessary to perform timestamp synchronization processing on the noise-reduced ship state monitoring data. Taking the time signal provided by the GPS module as the reference time, perform time correction on the data of the accelerometer and gyroscope. Using the linear interpolation method, align the acceleration and angular velocity data with the GPS time. The data after time synchronization and correction is the calibrated ship state monitoring data, which includes information such as timestamps, three-axis acceleration, three-axis angular velocity, longitude and latitude, speed, and heading.

[0112] Preferably, step S2 includes the following steps:

[0113] Step S21: Extract real-time measurement data according to the calibrated ship state monitoring data to obtain real-time GPS positioning data, real-time accelerometer measurement data, and real-time gyroscope measurement data respectively;

[0114] Step S22: Estimate the Kalman tilt observation value according to the real-time accelerometer measurement data and the real-time gyroscope measurement data to obtain the real-time hull tilt value;

[0115] Step S23: Extract the ship's longitude and latitude coordinates through the real-time GPS positioning data to obtain the ship's longitude and latitude coordinate data;

[0116] Step S24: Process the ship's motion parameters according to the ship's longitude and latitude coordinate data to obtain the ship's motion turning centrifugal force data;

[0117] Step S25: Use the ship's motion turning centrifugal force data as the tilt compensation amount to perform motion tilt compensation on the real-time hull tilt value to generate a compensated tilt estimation value.

[0118] In the embodiments of the present invention, real-time GPS positioning data including longitude, latitude, speed, and heading are extracted from the calibrated ship status monitoring data, and the data update frequency is 1 Hz. At the same time, real-time accelerometer measurement data including three-axis acceleration values (ax, ay, az) with the unit of g are extracted, and the data update frequency is 10 Hz. In addition, real-time gyroscope measurement data including three-axis angular velocity values (gx, gy, gz) with the unit of ° / s are extracted, and the data update frequency is 10 Hz. The real-time accelerometer measurement data and the real-time gyroscope measurement data are fused using the Kalman filtering algorithm to obtain a more accurate hull inclination value. The state variables of the Kalman filter include the hull inclination and angular velocity, and the observed variables are the measurement values of the accelerometer and gyroscope. Through the prediction and update steps, the Kalman filter continuously corrects the estimated values of the state variables, and finally obtains the real-time hull inclination value including the roll angle and pitch angle. The units of the roll angle and pitch angle are degrees. The longitude and latitude coordinate data of the ship are extracted from the real-time GPS positioning data in degrees, and these data are used to calculate the motion parameters of the ship, such as the speed and heading change rate. According to the longitude and latitude coordinate data at two adjacent times, the heading change rate and displacement of the ship are calculated. Combining the speed information in the real-time GPS positioning data, the turning radius of the ship is calculated. The turning radius is calculated using the formula R = d / (2 sin(Δθ / 2)), where d is the distance between two points and Δθ is the heading change. Then, the centripetal acceleration of the ship is calculated using the formula a = v^2 / R, where v is the speed of the ship. Finally, according to Newton's second law F = ma, the turning centrifugal force of the ship's motion is calculated, where m is the mass of the ship, which is set as a fixed value. The turning centrifugal force of the ship's motion calculated in step S24 is decomposed into the x-axis and y-axis directions of the hull coordinate system to obtain Fx and Fy. According to Fx and Fy, the inclination offset caused by the centrifugal force is calculated: Δθx = arctan(Fx / (mg)), Δθy = arctan(Fy / (mg)), where g is the acceleration due to gravity. The real-time hull inclination value obtained in step S22 is subtracted by the corresponding inclination offset to obtain the compensated inclination estimated value: compensated roll angle = roll angle - Δθy, compensated pitch angle = pitch angle - Δθx.

[0119] Preferably, step S22 includes the following steps:

[0120] Step S221: Decompose the three-axis measurement values according to the real-time accelerometer measurement data and the real-time gyroscope measurement data, and define the measurement variables to obtain the hull monitoring variable data;

[0121] Step S222: Construct a Kalman measurement inclination calculation model according to the hull monitoring variable data;

[0122] Step S223: Calculate the components of the gravitational acceleration in three axial directions using the real-time accelerometer measurement data to obtain the gravitational acceleration components;

[0123] Step S224: Estimate the current tilt angle observation value based on the gravitational acceleration components to obtain the real-time hull tilt angle observation and estimation value;

[0124] Step S225: Perform real-time measurement noise processing on the real-time accelerometer measurement data and the real-time gyroscope measurement data, and calculate the predicted tilt angle value using the Kalman measurement tilt angle calculation model to obtain the hull tilt angle prediction value;

[0125] Step S226: Calculate the difference between the hull tilt angle prediction value and the real-time hull tilt angle observation and estimation value, and perform Kalman gain weighted update to generate the real-time hull tilt angle value.

[0126] In the embodiments of the present invention, the real-time accelerometer measurement data is decomposed into acceleration components in three axial directions, denoted as ax, ay, and az respectively, with the unit of g. The real-time gyroscope measurement data is decomposed into angular velocity components in three axial directions, denoted as gx, gy, and gz respectively, with the unit of ° / s. Define the hull monitoring variable data, including the roll angle φ, the pitch angle θ, and the angular velocities gx, gy, and gz. Construct a Kalman filter model for estimating the hull inclination. The state vector X is defined as [φ, θ, gx, gy, gz]T, representing the roll angle, the pitch angle, and the three-axis angular velocities respectively. The state transition matrix F is determined according to the hull kinematic model. The observation vector Z is defined as [φ_meas, θ_meas, gx_meas, gy_meas, gz_meas]T, where gx_meas is the measured value of the angular velocity on the x-axis, gy_meas is the measured value of the angular velocity on the y-axis, gz_meas is the measured value of the angular velocity on the z-axis, and T is the matrix transpose symbol. Respectively represent the roll angle, the pitch angle, and the three-axis angular velocities measured by the accelerometer and the gyroscope. The observation matrix H maps the state vector to the observation vector. The process noise covariance matrix Q and the measurement noise covariance matrix R are determined according to the sensor noise characteristics. According to the real-time accelerometer measurement data ax, ay, and az, calculate the components of the gravitational acceleration in the three axial directions. Assume that when the hull coordinate system is aligned with the direction of gravity, the components of the gravitational acceleration are [0, 0, g]T, where g is the gravitational acceleration constant with a value of 9.8 m / s². Through coordinate transformation, the components of the gravitational acceleration are transformed into the components in the current attitude of the hull, denoted as gx_acc, gy_acc, and gz_acc. Use the gravitational acceleration components gx_acc, gy_acc, and gz_acc to estimate the current observed value of the hull inclination. The calculation formula is: φ_meas = arctan(gy_acc / gz_acc); θ_meas = arctan(gx_acc / sqrt(gy_acc² + gz_acc²)). The obtained φ_meas and θ_meas are the estimated values of the real-time hull inclination, with the unit of degrees. Perform noise processing on the real-time accelerometer measurement data and the real-time gyroscope measurement data, such as using a low-pass filter to remove high-frequency noise. Use the Kalman filter model constructed in step S222 to calculate the predicted value of the inclination. According to the state estimate value at the previous moment and the state transition matrix F, predict the state vector X_pred at the current moment. Calculate the difference between the estimated value of the real-time hull inclination and the predicted value of the hull inclination, that is, the measurement residual. Calculate the Kalman gain K for fusing the predicted value and the observed value. Use the Kalman gain to update the state predicted value to obtain the state estimate value X_est at the current moment, which includes the real-time hull inclination values φ and θ, with the unit of degrees. X_est = X_pred + K (Z - H X_pred). The updated state estimate is used as the prediction input for the next moment, and the Kalman filtering calculation is performed iteratively.

[0127] Preferably, step S222 includes the following steps:

[0128] Define the hull state variables of the amphibious ship to obtain the hull state variable data; wherein, the hull state variable data includes roll angle, pitch angle, roll angle rate, and pitch angle rate.

[0129] Construct a Kalman filter calculation equation based on the hull monitoring variable data and the hull state variable data to obtain an initial Kalman measurement inclination calculation model.

[0130] Obtain the historical navigation data of the amphibious ship.

[0131] Use the historical navigation data of the amphibious ship to perform initial state statistics on the hull state variable data to generate the initial value data of the ship state vector.

[0132] Perform measurement error analysis based on the accelerometer and gyroscope, and set the initial covariance matrix of the state vector to obtain the initial covariance matrix; wherein, the diagonal elements in the initial covariance matrix represent the initial uncertainties of the respective state variables, and the non-diagonal elements represent the correlations between the state variables.

[0133] Perform Kalman parameter combination on the initial covariance matrix and the initial value data of the ship state vector, and adjust the parameters of the initial Kalman measurement inclination calculation model to obtain the Kalman measurement inclination calculation model.

[0134] In the embodiment of the present invention, the hull state variables are defined to describe the attitude and motion state of the hull. The hull state variable data includes roll angle (roll, φ), pitch angle (pitch, θ), roll angle rate (rollrate, φ̇), and pitch angle rate (pitchrate, θ̇). The units of the roll angle and pitch angle are radians, and the units of the roll angle rate and pitch angle rate are radians / second. Based on the hull state variables and the hull monitoring variables (accelerometer and gyroscope data), a Kalman filter calculation equation is constructed. The state vector X is defined as . The state transition matrix F describes the variation relationship of the hull state variables over time. The initial Kalman measurement inclination calculation model includes the state transition matrix F, the observation matrix H, and the process noise covariance matrix Q and the measurement noise covariance matrix R that have not been initialized. Collect the historical navigation data of the amphibious ship under different sea conditions and working conditions, including accelerometer, gyroscope, and GPS data. Analyze the historical navigation data, and statistically calculate the average values of the roll angle, pitch angle, roll angle rate, and pitch angle rate of the ship in the stationary state as the initial value data of the ship state vector. For example, data for 10 seconds in a stationary state can be averaged. Analyze the measurement errors of the accelerometer and gyroscope, for example, by calculating the standard deviation of the sensor output to quantify the measurement noise. Based on the results of the measurement error analysis, set the initial covariance matrix P0 of the state vector. P0 is a 4x4 matrix, where the diagonal elements represent the initial uncertainties of the respective state variables, and the off-diagonal elements represent the correlations between the state variables. For example, if it is assumed that there is no correlation between the state variables, then P0 can be set as a diagonal matrix, and the diagonal elements are the squares of the initial uncertainties of the respective state variables. Substitute the initial covariance matrix P0 and the initial value data X0 of the ship state vector into the initial Kalman measurement inclination calculation model. Adjust the process noise covariance matrix Q and the measurement noise covariance matrix R according to the historical navigation data and the actual application scenario to obtain the best filtering effect. Finally, obtain the Kalman measurement inclination calculation model, including the state transition matrix F, the observation matrix H, the process noise covariance matrix Q, the measurement noise covariance matrix R, the initial state vector X0, and the initial covariance matrix P0.

[0135] Preferably, step S24 includes the following steps:

[0136] Step S241: Calculate the real-time heading angle based on the ship's latitude and longitude coordinate data to generate real-time heading angle data;

[0137] Step S242: Calculate the real-time speed based on the ship's latitude and longitude coordinate data to generate real-time navigation speed data;

[0138] Step S243: Calculate the rate of change of the heading angle for the real-time heading angle data, and determine whether the change in the real-time heading angle exceeds the heading angle change threshold through a preset heading angle change threshold to obtain heading angle change judgment data;

[0139] Step S244: When the heading angle change judgment data is true, it is determined that the ship is turning to obtain ship turning determination data;

[0140] Step S245: Calculate the centrifugal force when the ship is turning based on the real-time navigation speed data based on the ship turning determination data to obtain ship motion turning centrifugal force data.

[0141] In an embodiment of the present invention, the real-time heading angle is calculated using the ship's latitude and longitude coordinate data (latitude1, longitude1) and (latitude2, longitude2) at two adjacent times. First, the latitude and longitude coordinates are converted into coordinates in the Cartesian coordinate system using the WGS84 ellipsoid model for conversion. Then, the arctangent function is used to calculate the angle of the line connecting the two coordinate points, that is, the heading angle. The calculation formula is: heading = atan2(longitude2 - longitude1, latitude2 - latitude1). The calculated heading angle is converted into degrees and limited between 0 and 360 degrees. Using the ship's latitude and longitude coordinate data and timestamps at two adjacent times, the real-time sailing speed is calculated. First, the distance between the two coordinate points is calculated, and the spherical distance is calculated using the Haversine formula. Then, the distance is divided by the time difference to obtain the real-time sailing speed in meters per second. The difference between the real-time heading angle data at two adjacent times is calculated to obtain the change in the heading angle. The change in the heading angle is divided by the time difference to obtain the rate of change of the heading angle in degrees per second. A preset threshold for the change in the heading angle is set, for example, 5 degrees per second. The absolute value of the rate of change of the heading angle is compared with the preset threshold. If the absolute value of the rate of change of the heading angle is greater than the threshold, the data for judging the change in the heading angle is true; otherwise, it is false. According to the data for judging the change in the heading angle obtained in step S243, it is judged whether the ship is turning. If the data for judging the change in the heading angle is true, the data for judging the ship's turning is true, indicating that the ship is turning; otherwise, the data for judging the ship's turning is false, indicating that the ship is not turning or is in a straight sailing state. When the data for judging the ship's turning is true, the centrifugal force during the ship's turning is calculated based on the real-time sailing speed data and the rate of change of the heading angle. First, the turning radius is calculated according to the rate of change of the heading angle and the real-time sailing speed. The formula is: radius = velocity / (angular_velocity pi / 180), where velocity is the real-time sailing speed and angular_velocity is the rate of change of the heading angle. Then, the centrifugal force is calculated according to the turning radius and the real-time sailing speed. The formula is: centrifugal_force = mass velocity^2 / radius, where mass is the ship's mass, which is set to a fixed value, for example, 1000 kg. The data for the centrifugal force during the ship's turning motion is obtained in newtons. If the data for judging the ship's turning is false, the data for the centrifugal force during the ship's turning motion is set to 0.

[0142] Preferably, step S3 includes the following steps:

[0143] Step S31: Set the fuzzy logic input variables according to the type of amphibious ship to obtain the fuzzy logic input variables;

[0144] Step S32: Set the fuzzy logic output variables according to the fuzzy logic input variables to generate fuzzy logic output variables;

[0145] Step S33: Define the fuzzy sets according to the fuzzy logic input variables and the fuzzy logic output variables, thereby establishing a fuzzy logic inference model;

[0146] Step S34: Calculate the roll angle and pitch angle change rates based on the estimated compensation inclination angle to obtain inclination angle change rate data;

[0147] Step S35: Obtain real-time water condition and meteorological data; rate the water wave height according to the real-time water condition and meteorological data to obtain real-time water wave height data;

[0148] Step S36: Input the inclination angle change rate data and the real-time water wave height data into the fuzzy logic inference model and perform fuzzy inference to obtain the roll angle alarm threshold and the pitch angle alarm threshold respectively;

[0149] Step S37: Perform scene-based dynamic adjustment on the roll angle alarm threshold and the pitch angle alarm threshold to obtain dynamic alarm thresholds.

[0150] In the embodiments of the present invention, according to the type and operating characteristics of the amphibious ship, fuzzy logic input variables are set. The input variables include real-time water condition and meteorological data and inclination rate of change data. The real-time water condition and meteorological data include parameters such as wind speed, wind direction, wave height, and wave period. The inclination rate of change data includes the roll angle rate of change and the pitch angle rate of change. For example, for a certain type of amphibious ship, the wind speed, wave height, roll angle rate of change, and pitch angle rate of change are set as fuzzy logic input variables. According to a predetermined alarm strategy, fuzzy logic output variables are set. The output variables are the roll angle alarm threshold and the pitch angle alarm threshold. These two thresholds are used to determine whether the ship's inclination degree reaches the alarm level. Fuzzy sets are defined for each fuzzy logic input variable and output variable. For example, the wind speed is divided into three fuzzy sets: "low", "medium", and "high", and each set corresponds to a membership function, such as a triangular membership function or a trapezoidal membership function. Similarly, the wave height, roll angle rate of change, pitch angle rate of change, roll angle alarm threshold, and pitch angle alarm threshold are also divided into corresponding fuzzy sets, and the corresponding membership functions are defined. According to the pre-set rules, a fuzzy logic inference model is established. The fuzzy rule base contains a series of IF-THEN rules, such as: IF the wind speed is "high" AND the wave height is "high" THEN the roll angle alarm threshold is "large"; IF the wind speed is "low" AND the wave height is "low" THEN the roll angle alarm threshold is "small". According to the estimated values of the compensated inclination angles at two adjacent moments, the roll angle rate of change and the pitch angle rate of change are calculated. The calculation formula is: rate of change = (current value - previous moment value) / time interval. Real-time water condition and meteorological data, including wind speed, wind direction, wave height, and wave period, are obtained through on-board meteorological sensors. According to the numerical range of the wave height, it is divided into different levels, such as three levels: "low", "medium", and "high", corresponding to different wave height ranges. For example, the wave height less than 1 meter is "low", 1 to 2 meters is "medium", and greater than 2 meters is "high". The wave height level is used as the real-time water wave height data. The inclination rate of change data obtained in step S34 and the real-time water wave height data obtained in step S35 are input into the fuzzy logic inference model established in step S33. According to the fuzzy rule base and the membership function, fuzzy inference is performed to calculate the fuzzy values of the output variables. Then, the fuzzy values of the output variables are defuzzified to obtain the clear roll angle alarm threshold and pitch angle alarm threshold. According to the current operating scenario of the amphibious ship, the roll angle alarm threshold and pitch angle alarm threshold obtained in step S36 are dynamically adjusted. For example, during landing / offshore operations, since the hull attitude changes greatly, the alarm threshold can be appropriately relaxed. During normal navigation, the standard alarm threshold is adopted. The adjusted threshold is the dynamic alarm threshold.

[0151] Preferably, step S37 includes the following steps:

[0152] Step S371: Obtain the real-time operation application scenario of the amphibious ship;

[0153] Step S372: Match the safety margin coefficient according to the real-time operation application scenario of the amphibious ship to obtain the safety margin coefficient of the operation scenario;

[0154] Step S373: Calculate the scenario adjustment coefficients for the roll angle alarm threshold and the pitch angle alarm threshold respectively through the safety margin coefficient of the operation scenario, and obtain the roll angle alarm threshold adjustment coefficient and the pitch angle alarm threshold adjustment coefficient respectively;

[0155] Step S374: Dynamically adjust the corresponding thresholds of the roll angle alarm threshold and the pitch angle alarm threshold based on the roll angle alarm threshold adjustment coefficient and the pitch angle alarm threshold adjustment coefficient to generate a dynamic alarm threshold.

[0156] In the embodiment of the present invention, the real-time operation application scenario information of the amphibious ship is obtained through the sensors and control systems on the ship. The real-time operation application scenario information includes the current state of the ship, such as: normal navigation, landing / offshore, loading / unloading goods, berthing, etc. The real-time operation application scenario of the ship can be judged through information such as GPS data, speed, course, and the ship's own state sensors. For example, by analyzing the GPS data and speed, it can be judged whether the ship is approaching the shore, so as to judge whether the ship is in the landing / offshore state. The safety margin coefficients corresponding to different operation application scenarios are preset in advance. The safety margin coefficient is a numerical value used to adjust the alarm threshold to meet the safety requirements in different scenarios. For example, in the normal navigation state, the safety margin coefficient is set to 1.0; in the landing / offshore state, since the ship's attitude changes greatly, the safety margin coefficient is set to 1.2; in the loading / unloading goods state, since the ship's stability requirements are higher, the safety margin coefficient is set to 0.8; in the berthing state, the safety margin coefficient is set to 1.5. According to the real-time operation application scenario obtained in step S371, the corresponding safety margin coefficient is matched. According to the safety margin coefficient of the operation scenario obtained in step S372, the roll angle alarm threshold adjustment coefficient and the pitch angle alarm threshold adjustment coefficient are calculated. The calculation formula is: adjustment coefficient = safety margin coefficient. For example, if the safety margin coefficient of the operation scenario is 1.2, then both the roll angle alarm threshold adjustment coefficient and the pitch angle alarm threshold adjustment coefficient are 1.2. Multiply the roll angle alarm threshold and the pitch angle alarm threshold obtained in step S36 by the corresponding adjustment coefficients respectively to obtain the dynamic alarm threshold. The calculation formula is: dynamic alarm threshold = original alarm threshold × adjustment coefficient. For example, if the original roll angle alarm threshold is 15 degrees and the roll angle alarm threshold adjustment coefficient is 1.2, then the dynamic roll angle alarm threshold is 15 × 1.2 = 18 degrees. Similarly, the dynamic pitch angle alarm threshold is calculated. The finally generated dynamic alarm threshold will be used for the alarm judgment in step S4.

[0157] As an example of the present invention, refer to Figure 3 shown in Figure 1 the detailed implementation step flow diagram of step S4 in

[0158] Step S41: Compare the compensated tilt angle estimate with the dynamic alarm threshold to determine whether it exceeds the threshold, and obtain an alarm trigger flag;

[0159] In the embodiment of the present invention, the compensated roll angle estimate is compared with the dynamic roll angle alarm threshold, and the compensated pitch angle estimate is compared with the dynamic pitch angle alarm threshold respectively. If the absolute value of the compensated roll angle estimate is greater than the dynamic roll angle alarm threshold, the roll angle alarm trigger flag is set to true; otherwise, the roll angle alarm trigger flag is set to false. Similarly, if the absolute value of the compensated pitch angle estimate is greater than the dynamic pitch angle alarm threshold, the pitch angle alarm trigger flag is set to true; otherwise, the pitch angle alarm trigger flag is set to false. If the roll angle alarm trigger flag or the pitch angle alarm trigger flag is true, the total alarm trigger flag is true, indicating that at least one tilt angle exceeds the corresponding dynamic alarm threshold; otherwise, the total alarm trigger flag is false.

[0160] Step S42: Calculate the degree of tilt angle exceeding the threshold according to the alarm trigger flag, and generate tilt angle overrun degree data;

[0161] In the embodiment of the present invention, if the alarm trigger flag is true, the degree of tilt angle exceeding the threshold is calculated. For the roll angle, the calculation formula is: roll angle overrun degree = abs(compensated roll angle estimate) - dynamic roll angle alarm threshold. For the pitch angle, the calculation formula is: pitch angle overrun degree = abs(compensated pitch angle estimate) - dynamic pitch angle alarm threshold. The calculated roll angle overrun degree and pitch angle overrun degree are respectively stored as tilt angle overrun degree data. If the alarm trigger flag is false, the tilt angle overrun degree data is set to 0.

[0162] Step S43: Divide the tilt angle overrun degree data according to the preset alarm level division standard to obtain preliminary alarm level data;

[0163] In the embodiment of the present invention, the alarm level division standard is preset, for example: Level 1 alarm: The tilt angle exceeds the threshold by 1 - 5 degrees; Level 2 alarm: The tilt angle exceeds the threshold by 5 - 10 degrees; Level 3 alarm: The tilt angle exceeds the threshold by more than 10 degrees. According to the tilt angle overrun degree data and the preset alarm level division standard, the current alarm level is divided. For example, if the roll angle overrun degree is 3 degrees, the preliminary roll angle alarm level data is a Level 1 alarm; if the pitch angle overrun degree is 7 degrees, the preliminary pitch angle alarm level data is a Level 2 alarm.

[0164] Step S44: Perform an alarm credibility assessment based on the preliminary alarm level data to generate alarm credibility assessment data;

[0165] In the embodiment of the present invention, an alarm credibility assessment is performed based on information such as the preliminary alarm level data, historical alarm data, and current environmental factors (such as wind speed, wave height). For example, the Bayesian method or the fuzzy logic method can be used for the alarm credibility assessment. The evaluation result is quantified as a value between 0 and 1, indicating the credibility of the alarm, and alarm credibility assessment data is generated. The larger the value, the higher the credibility.

[0166] Step S45: Calculate the historical inclination change rate of the estimated compensation inclination angle, compare it with a preset inclination change rate threshold, and determine whether the inclination change is abnormal to obtain an inclination change abnormality flag;

[0167] In the embodiment of the present invention, the historical change rate of the estimated compensation inclination angle is calculated, for example, the average change rate over a past period of time (such as 5 seconds). A preset inclination change rate threshold is set, for example, 10 degrees / second. The calculated inclination change rate is compared with the preset threshold. If the absolute value of the inclination change rate is greater than the preset threshold, the inclination change abnormality flag is true, indicating that the inclination change is abnormal; otherwise, the inclination change abnormality flag is false.

[0168] Step S46: When both the alarm trigger flag and the inclination change abnormality flag are true, and the alarm credibility assessment data is higher than the preset threshold, trigger an alarm to generate a final ship alarm signal; otherwise, it is determined as a false alarm and the alarm is filtered.

[0169] In the embodiment of the present invention, if both the alarm trigger flag and the inclination change abnormality flag are true, and the alarm credibility assessment data is higher than the preset threshold (such as 0.8), then an alarm is triggered to generate a final ship alarm signal. The final ship alarm signal includes information such as the alarm type (rolling angle or pitch angle), alarm level, and alarm time. If the above conditions are not met, it is determined as a false alarm, the alarm is filtered, and no alarm signal is generated.

[0170] Preferably, the present invention also provides a wireless monitoring and alarm system applied to an amphibious ship, which executes the wireless monitoring and alarm method applied to an amphibious ship as described above. The wireless monitoring and alarm system applied to an amphibious ship includes:

[0171] A hull state monitoring module for setting up a ship state monitoring and alarm device on the amphibious ship; monitoring the hull state of the amphibious ship through the ship state monitoring and alarm device to generate calibrated ship state monitoring data;

[0172] The inclination compensation calculation module is used to estimate the observed inclination value according to the calibrated ship status monitoring data to obtain the real-time hull inclination value; process the ship motion parameters according to the calibrated ship status monitoring data to obtain the ship motion turning centrifugal force data; perform motion inclination compensation on the real-time hull inclination value through the ship motion turning centrifugal force data to generate a compensated inclination estimation value.

[0173] The threshold dynamic adjustment module is used to obtain the real-time water condition and meteorological data; perform fuzzy inference on the ship alarm threshold according to the real-time water condition and meteorological data and the compensated inclination estimation value to obtain the roll angle alarm threshold and the pitch angle alarm threshold respectively; perform scenario-based dynamic adjustment on the roll angle alarm threshold and the pitch angle alarm threshold to obtain the dynamic alarm threshold.

[0174] The intelligent alarm judgment module is used to perform intelligent alarm judgment on the compensated inclination estimation value by using the dynamic alarm threshold to generate the final ship alarm signal.

[0175] The wireless signal transmission module is used to send the final ship alarm signal to the crew's mobile devices or the shore-based monitoring center through the LoRaWAN wireless communication module to obtain the wireless alarm monitoring information.

[0176] The present application lies in that by building a ship status monitoring and alarm device on an amphibious ship, the hull status can be comprehensively and real-time monitored. The construction of this device not only improves the comprehensiveness and accuracy of data collection, but also ensures the time consistency and availability of data through multi-source data analysis and timestamp synchronization processing, effectively reducing the risk of data transmission delay and loss, and ensuring the efficiency and reliability of data transmission. Through further processing of the calibrated ship status monitoring data, the real-time hull inclination value can be accurately estimated, and motion inclination compensation can be performed in combination with ship motion parameters, which not only effectively distinguishes the normal motion inclination of the ship from the inclination caused by the external environment, reduces the monitoring error caused by motion factors, but also improves the accuracy and stability of inclination calculation through the fusion processing of the Kalman filter algorithm. Also, through the acquisition of real-time water condition and meteorological data, fuzzy inference and scenario-based dynamic adjustment of the ship alarm threshold are performed in combination with the compensated inclination estimation value to generate the dynamic alarm threshold. This mechanism avoids the limitations of traditional fixed threshold settings, enables the system to flexibly set reasonable alarm thresholds according to actual environmental conditions, reduces false alarm phenomena under complex water conditions or extreme meteorological conditions, and can timely capture real dangerous inclination changes, providing more accurate early warning support for the safe operation of the ship.

[0177] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to cover all changes falling within the meaning and scope of the equivalent elements of the application documents within the present invention.

[0178] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A wireless monitoring and alarm method applied to amphibious ships, characterized in that, It includes the following steps: Step S1: Install a ship status monitoring and alarm device on the amphibious ship; monitor the hull status of the amphibious ship through the ship status monitoring and alarm device to generate calibrated ship status monitoring data; specifically, step S1 is as follows: Step S11: Install multiple triaxial accelerometers, triaxial gyroscopes and GPS modules at the bow, stern and middle of the hull of the amphibious ship, and perform initial calibration to install the ship status monitoring and alarm device; Step S12: Set the sampling frequency according to the ship status monitoring and alarm device, and monitor the hull status of the amphibious ship to generate raw ship status monitoring data; Step S13: Transmit the raw ship status monitoring data to the on-board data processing center through the LoRaWAN wireless communication module, and perform multi-source data analysis to generate ship status monitoring metadata; Step S14: Perform noise filtering on the ship status monitoring metadata to obtain noise-reduced ship status monitoring data; Step S15: Perform timestamp synchronization on the noise-reduced ship status monitoring data, and perform time correction based on the time signal in the GPS module to generate calibrated ship status monitoring data; Step S2: Estimate the inclination observation value according to the calibrated ship status monitoring data to obtain the real-time hull inclination value; process the ship motion parameters according to the calibrated ship status monitoring data to obtain the ship motion turning centrifugal force data; compensate the real-time hull inclination value with the ship motion turning centrifugal force data to generate a compensated inclination estimation value; Step S3: Obtain real-time water condition and meteorological data; perform fuzzy inference on the ship alarm threshold according to the real-time water condition and meteorological data and the compensated inclination estimation value to obtain the roll angle alarm threshold and the pitch angle alarm threshold respectively; perform scene-based dynamic adjustment on the roll angle alarm threshold and the pitch angle alarm threshold to obtain the dynamic alarm threshold; Step S4: Use the dynamic alarm threshold to perform intelligent alarm judgment on the compensated inclination estimation value to generate the final ship alarm signal; Step S5: Send the final ship alarm signal to the crew's mobile device or the shore-based monitoring center through the LoRaWAN wireless communication module to obtain wireless alarm monitoring information.

2. The wireless monitoring and alarming method applied to an amphibious ship according to claim 1, characterized in that, Step S2 includes the following steps: Step S21: Extract real-time measurement data according to the calibrated ship status monitoring data to obtain real-time GPS positioning data, real-time accelerometer measurement data and real-time gyroscope measurement data respectively; Step S22: Estimate the Kalman inclination observation value according to the real-time accelerometer measurement data and the real-time gyroscope measurement data to obtain the real-time hull inclination value; Step S23: Extract the ship's longitude and latitude coordinates through the real-time GPS positioning data to obtain the ship's longitude and latitude coordinate data; Step S24: Process the ship motion parameters according to the ship's longitude and latitude coordinate data to obtain the ship motion turning centrifugal force data; Step S25: Use the ship motion turning centrifugal force data as the inclination compensation amount to compensate the real-time hull inclination value to generate a compensated inclination estimation value.

3. The wireless monitoring and alarming method applied to amphibious ships according to claim 2, characterized in that, Step S22 includes the following steps: Step S221: Decompose the three-axis measurement values based on the real-time accelerometer measurement data and the real-time gyroscope measurement data, and define the measurement variables to obtain the hull monitoring variable data; Step S222: Construct a Kalman measurement inclination calculation model based on the hull monitoring variable data; Step S223: Calculate the components of the gravitational acceleration in the three axes using the real-time accelerometer measurement data to obtain the gravitational acceleration components; Step S224: Estimate the current inclination observation value based on the gravitational acceleration components to obtain the real-time hull inclination observation and estimation value; Step S225: Perform real-time measurement noise processing on the real-time accelerometer measurement data and the real-time gyroscope measurement data, and calculate the inclination prediction value using the Kalman measurement inclination calculation model to obtain the hull inclination prediction value; Step S226: Calculate the difference between the real-time hull inclination observation and estimation value and the hull inclination prediction value, and perform Kalman gain weighted update to generate the real-time hull inclination value.

4. The wireless monitoring and alarming method applied to an amphibious ship according to claim 3, characterized in that Step S222 includes the following steps: Define the hull state variables of the amphibious ship to obtain the hull state variable data; wherein, the hull state variable data includes the roll angle, pitch angle, roll angle rate, and pitch angle rate; Construct a Kalman filter calculation equation based on the hull monitoring variable data and the hull state variable data to obtain the initial Kalman measurement inclination calculation model; Obtain the historical navigation data of the amphibious ship; Perform initial state statistics on the hull state variable data using the historical navigation data of the amphibious ship to generate the initial value data of the ship state vector; Conduct measurement error analysis based on the accelerometer and gyroscope, and set the initial covariance matrix of the state vector to obtain the initial covariance matrix; wherein, the diagonal elements in the initial covariance matrix represent the initial uncertainties of the respective state variables, and the non-diagonal elements represent the correlations between the state variables; Perform Kalman parameter combination on the initial covariance matrix and the initial value data of the ship state vector, and adjust the parameters of the initial Kalman measurement inclination calculation model to obtain the Kalman measurement inclination calculation model.

5. The wireless monitoring and alarming method applied to an amphibious ship according to claim 2, characterized in that, Step S24 includes the following steps: Step S241: Calculate the real-time heading angle based on the ship's latitude and longitude coordinate data to generate the real-time heading angle data; Step S242: Calculate the real-time speed based on the ship's latitude and longitude coordinate data to generate the real-time navigation speed data; Step S243: Calculate the rate of change of the heading angle for the real-time heading angle data, and determine whether the change in the real-time heading angle exceeds the heading angle change threshold through a preset heading angle change threshold to obtain the heading angle change judgment data; Step S244: When the heading angle change judgment data is true, it is determined that the ship is turning to obtain the ship turning judgment data; Step S245: Calculate the centrifugal force during ship turning based on the ship turning judgment data through the real-time navigation speed data to obtain the ship motion turning centrifugal force data.

6. The wireless monitoring and alarming method applied to an amphibious ship according to claim 1, characterized in that Step S3 includes the following steps: Step S31: Set the fuzzy logic input variables according to the type of amphibious ship to obtain the fuzzy logic input variables; Step S32: Set the fuzzy logic output variables according to the fuzzy logic input variables to generate fuzzy logic output variables; Step S33: Define the fuzzy sets based on the fuzzy logic input variables and the fuzzy logic output variables, thereby establishing a fuzzy logic inference model; Step S34: Calculate the roll angle and pitch angle change rates based on the compensated tilt angle estimate to obtain the tilt angle change rate data; Step S35: Obtain the real-time water condition and meteorological data; rate the water wave height according to the real-time water condition and meteorological data to obtain the real-time water wave height data; Step S36: Input the tilt angle change rate data and the real-time water wave height data into the fuzzy logic inference model and perform fuzzy inference to obtain the roll angle alarm threshold and the pitch angle alarm threshold respectively; Step S37: Perform a scenario-based dynamic adjustment on the roll angle alarm threshold and the pitch angle alarm threshold to obtain the dynamic alarm threshold.

7. The wireless monitoring and alarming method applied to an amphibious ship according to claim 6, characterized in that, Step S37 includes the following steps: Step S371: Obtain the real-time operation application scenario of the amphibious ship; Step S372: Match the safety margin coefficient according to the real-time operation application scenario of the amphibious ship to obtain the operation scenario safety margin coefficient; Step S373: Calculate the scenario adjustment coefficients for the roll angle alarm threshold and the pitch angle alarm threshold respectively through the operation scenario safety margin coefficient to obtain the roll angle alarm threshold adjustment coefficient and the pitch angle alarm threshold adjustment coefficient; Step S374: Perform a dynamic corresponding threshold adjustment on the roll angle alarm threshold and the pitch angle alarm threshold based on the roll angle alarm threshold adjustment coefficient and the pitch angle alarm threshold adjustment coefficient to generate the dynamic alarm threshold.

8. The wireless monitoring and alarm method applied to an amphibious ship according to claim 1, wherein Step S4 includes the following steps: Step S41: Compare the compensated tilt angle estimate with the dynamic alarm threshold to determine whether it exceeds the threshold, and obtain the alarm trigger flag; Step S42: Calculate the degree of tilt angle exceeding the threshold according to the alarm trigger flag to generate the tilt angle overrun degree data; Step S43: Divide the tilt angle overrun degree data according to the preset alarm level division standard to obtain the preliminary alarm level data; Step S44: Evaluate the alarm credibility according to the preliminary alarm level data to generate the alarm credibility evaluation data; Step S45: Calculate the historical tilt angle change rate of the compensated tilt angle estimate and compare it with the preset tilt angle change rate threshold to determine whether the tilt angle change is abnormal, and obtain the tilt angle change abnormality flag; Step S46: When both the alarm trigger flag and the tilt angle change abnormality flag are true, and the alarm credibility evaluation data is higher than the preset threshold, trigger an alarm to generate the final ship alarm signal, otherwise it is determined as a false alarm and the alarm is filtered.

9. A wireless monitoring and alarm system applied to amphibious ships, characterized in that, For implementing the wireless monitoring and alarm method for amphibious ships as described in claim 1, the wireless monitoring and alarm system for amphibious ships includes: A hull state monitoring module, which is used to build a ship state monitoring and alarm device on the amphibious ship; monitor the hull state of the amphibious ship through the ship state monitoring and alarm device to generate calibrated ship state monitoring data; The inclination angle compensation calculation module is used to estimate the observed inclination angle value according to the calibrated ship status monitoring data to obtain the real-time hull inclination angle value; process the ship motion parameters according to the calibrated ship status monitoring data to obtain the ship motion turning centrifugal force data; perform motion inclination angle compensation on the real-time hull inclination angle value through the ship motion turning centrifugal force data to generate a compensated inclination angle estimation value; The threshold dynamic adjustment module is used to obtain the real-time water condition and meteorological data; perform fuzzy inference on the ship alarm threshold according to the real-time water condition and meteorological data and the compensated inclination angle estimation value to obtain the roll angle alarm threshold and the pitch angle alarm threshold respectively; perform scenario-based dynamic adjustment on the roll angle alarm threshold and the pitch angle alarm threshold to obtain the dynamic alarm threshold; The intelligent alarm judgment module is used to perform intelligent alarm judgment on the compensated inclination angle estimation value by using the dynamic alarm threshold to generate the final ship alarm signal; The wireless signal transmission module is used to send the final ship alarm signal to the crew's mobile device or the shore-based monitoring center through the LoRaWAN wireless communication module to obtain the wireless alarm monitoring information.

Images