Dual-mode satellite communication position indication and warning device and method based on sea state and attitude perception

Abstract

The application discloses a dual-mode satellite communication position indication and warning device and method based on sea state and attitude sensing, and relates to the technical fields of satellite communication and distress rescue. The device comprises an inertial measurement module for collecting real-time attitude data of the device; a Beidou satellite communication module for reporting first position data through a Beidou satellite link; a low-orbit satellite communication module for reporting second position data through a low-orbit satellite link; and a main control board for evaluating a current sea state level according to the attitude data. The application can sense the sea state in real time and adaptively switch the communication mode, enters the Beidou single-mode energy-saving mode in a low sea state, and automatically wakes up the low-orbit satellite communication module to realize redundant parallel communication of the Beidou and the low-orbit satellite in a high sea state, so that the continuous and reliable reporting of the position data is ensured under the whole sea state condition, the communication success rate in the high sea state is improved, and the overall power consumption is reduced.

Description

Technical Field

[0001] This application relates to the fields of satellite communication and distress rescue technology, specifically to a dual-mode satellite communication positioning and warning device and method based on maritime attitude perception. Background Technology

[0002] When an amphibious vehicle or vessel falls into the water at sea, the vehicle-mounted or ship-mounted positioning and warning equipment must automatically report the coordinates of the fall to the command center via satellite link after surfacing, providing crucial positioning support for search and rescue operations.

[0003] Currently, such equipment generally uses a single BeiDou satellite communication system. BeiDou-3 geostationary orbit satellites are located in a high orbit above the equator, and their communication antennas need to maintain a certain elevation angle to ensure effective signal delivery to the satellite. However, in high sea state environments (e.g., wave height ≥ 1.5m), the equipment will sway violently with the waves, causing frequent limitations on the antenna's elevation angle. This significantly reduces the success rate of BeiDou short message transmission. In high sea state environments, the success rate may be drastically lower than in static environments, posing a significant risk of losing critical rescue coordinates.

[0004] While the concept of multi-mode satellite communication has emerged in existing technologies, it still suffers from the following shortcomings: First, it lacks real-time perception and adaptive capabilities regarding current sea conditions. After power-on, each communication module typically operates in a fixed mode, unable to dynamically adjust communication strategies based on wave intensity. In low sea conditions, all modules operate at full speed, resulting in unnecessary power consumption waste; in high sea conditions, there is a lack of effective redundancy compensation methods. Second, in high sea conditions, the communication link is singular and lacks redundancy guarantees. Existing solutions mostly rely on BeiDou single-mode communication or simple primary / backup switching, unable to provide multi-link parallel redundancy when the equipment experiences severe swaying, making it difficult to guarantee communication success rates in high sea conditions. Summary of the Invention

[0005] In view of the above-mentioned deficiencies or defects in the existing technology, the purpose of this application is to provide a dual-mode satellite communication positioning and warning device and method based on sea state attitude perception. It can perceive sea state in real time and adaptively switch communication modes. When the sea state is low, it enters the Beidou single-mode energy-saving mode. When the sea state is high, it automatically wakes up the low-orbit satellite communication module to realize Beidou and low-orbit dual-mode redundant parallel communication, thereby ensuring continuous and reliable reporting of position data under all sea state conditions, improving the communication success rate under high sea state and reducing overall power consumption.

[0006] To achieve the above objectives, this application provides the following solution: Firstly, this application provides a dual-mode satellite communication positioning and warning device based on maritime attitude awareness, comprising: An inertial measurement module is used to collect real-time attitude data of the device; The BeiDou satellite communication module is used to acquire initial location data and report it via the BeiDou satellite link; The low-Earth orbit satellite communication module is used to acquire second location data and report it via the low-Earth orbit satellite link; The main control board is connected to the inertial measurement module, the Beidou satellite communication module, and the low-orbit satellite communication module, respectively. The main control board is used to assess the current sea state level based on the attitude data. When the sea state level is low, the low-orbit satellite communication module is controlled to enter a sleep state or power-off state, and the Beidou satellite communication module reports the first location data. When the sea state is high, the low-Earth orbit satellite communication module is activated or enabled, so that the Beidou satellite communication module and the low-Earth orbit satellite communication module work in parallel and report their respective position data in a dual-mode redundancy manner.

[0007] Optionally, the main control board is used to calculate a statistical value representing the severity of the equipment's swaying based on the angular velocity data or acceleration data in the attitude data, and compare the statistical value with a preset threshold to assess the current sea state level.

[0008] Optionally, the main control board is used to switch sea state levels using a hysteresis mechanism, wherein the threshold for switching from low sea state to high sea state is greater than the threshold for recovering from high sea state to low sea state.

[0009] Optionally, the main control board is used to predict the attitude data collected by the inertial measurement module using a pre-trained deep neural network model in the high sea state mode, obtain the probability that the antenna elevation angle will reach a local maximum value within a future preset time window, and control the Beidou satellite communication module to send short messages when the probability exceeds a preset threshold.

[0010] Optionally, the deep neural network model is a lightweight fully connected network, whose input is the angular velocity time series data of the most recent sampling periods, and whose output is the probability of the antenna elevation angle reaching its peak within a future time window.

[0011] Optionally, the main control board is used to acquire the first position data output by the Beidou satellite communication module and the second position data output by the low-orbit satellite communication module in the dual-mode redundancy mode, calculate the deviation between the two, and take the arithmetic mean of the two as the fused position data when the deviation is less than or equal to a preset deviation threshold, and select the position data with better data quality when the deviation is greater than the preset deviation threshold.

[0012] Secondly, this application provides a dual-mode satellite communication positioning and warning method based on maritime attitude awareness, comprising the following steps: The device's real-time attitude data is acquired through an inertial measurement module; Assess the current sea state level based on the attitude data; When the sea state level is low, the control low-orbit satellite communication module enters a sleep state or power-off state, and the Beidou satellite communication module reports the first position data. When the sea state is high, the low-Earth orbit satellite communication module is activated or enabled, so that the Beidou satellite communication module and the low-Earth orbit satellite communication module work in parallel and report their respective position data in a dual-mode redundancy manner.

[0013] Optionally, it also includes: periodically performing system verification, forcibly waking up the low-orbit satellite communication module, verifying the integrity of the dual links, and reassessing the sea state level; when the sea state level is low and both links are normal, re-controlling the low-orbit satellite communication module to enter a sleep state or a power-off state.

[0014] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the dual-mode satellite communication positioning and warning method based on maritime attitude awareness as described above.

[0015] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the dual-mode satellite communication positioning and warning method based on maritime attitude awareness as described above.

[0016] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application provides a dual-mode satellite communication positioning and warning device and method based on sea state attitude perception. The device collects real-time attitude data through an inertial measurement module, and the main control board assesses the current sea state level based on this attitude data. Since the degree of device swaying is directly reflected in changes in real-time attitude data, the main control board can quantitatively distinguish between relatively stable low sea states and violently swaying high sea states by analyzing the intensity of these fluctuations. This solves the problem of existing technologies being unable to perceive sea states in real time and quantify the distinction between high and low sea states, achieving real-time perception of the marine environment and providing a reliable basis for subsequent adaptive communication strategies. When the sea state level is low, the low-Earth orbit (LEO) satellite communication module is put into sleep or powered off state, and the BeiDou satellite communication module reports the first position data. When the sea state level is high, the LEO satellite communication module is woken up or enabled, allowing the BeiDou and LEO satellite communication modules to work in parallel, reporting their respective position data in a dual-mode redundancy manner. In low sea states, the device sway is slight, and the communication success rate of a single BeiDou satellite link is high, which can meet the basic reporting requirements; if the LEO satellite communication module continues to work, it will only result in wasted power consumption. Disabling or putting the low-Earth orbit (LEO) satellite communication module into sleep mode reduces overall power consumption, solving the problem of wasted power caused by multiple modules operating at full speed in low sea states. This achieves a low-sea-state energy-saving mode and extends the equipment's endurance. In high sea states, the equipment sways violently, frequently limiting the BeiDou antenna's elevation angle and significantly reducing the success rate of a single BeiDou satellite link, making it difficult to meet reliable communication requirements in rescue scenarios. In this case, actively waking up the LEO satellite communication module allows it to work simultaneously with the BeiDou satellite communication module. Because the two links have different satellite orbits, communication frequency bands, and signal propagation characteristics, their performance differs when facing wave obstruction, providing redundancy. Even if one link fails due to obstruction, the other link may still successfully report data. If either link succeeds, reporting is completed, thus solving the problem of a sharp drop in single-link communication success rate in high sea states. This achieves dual-link redundancy and parallel operation in high sea states, significantly improving communication success rate. In summary, this application, through the above synergistic effect, achieves a comprehensive technical effect of environmental adaptation, significantly reduced power consumption in low sea states, and significantly improved communication success rate in high sea states, all under all sea states. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating a dual-mode satellite communication positioning and warning method based on maritime attitude awareness, provided as an embodiment of this application; Figure 2 A schematic diagram of the structure of a dual-mode satellite communication positioning and warning device based on maritime attitude perception, provided for another embodiment of this application; Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] The dual-mode satellite communication positioning and warning device and method based on sea state and attitude perception provided in this application can be applied to maritime distress positioning scenarios. The positioning and warning device automatically floats to the surface after falling into the water, senses its real-time attitude through an inertial measurement module, assesses the sea state level through a main control board, and adaptively controls the BeiDou satellite communication module and / or the low-Earth orbit satellite communication module to report location data based on the sea state level. The reported location data is transmitted to the user command center via a BeiDou satellite link or a low-Earth orbit satellite link. The user command center is equipped with a BeiDou-3 user command terminal and a low-Earth orbit satellite user command terminal, which are used to receive location data from the two links respectively, enabling real-time monitoring and search and rescue scheduling of the water-fall location.

[0022] In some embodiments, the device can independently complete the entire attitude perception, sea condition assessment, communication switching, and data reporting process without relying on an external server or network. In other embodiments, the device can also transmit the raw attitude data or intermediate processing results back to the user command center via at least one of the BeiDou satellite communication module or the low-Earth orbit satellite communication module, for auxiliary analysis or backup by the user command center.

[0023] In one exemplary embodiment, a dual-mode satellite communication positioning and warning device based on sea state attitude awareness is provided. This embodiment illustrates the example of the positioning and warning device independently completing the entire attitude awareness, sea state assessment, communication switching, and data reporting process without relying on an external server or network. The device includes an inertial measurement module, a BeiDou satellite communication module, a low-Earth orbit satellite communication module, and a main control board, wherein: An inertial measurement module is used to collect real-time attitude data of the device; The BeiDou satellite communication module is used to acquire initial location data and report it via the BeiDou satellite link; The low-Earth orbit satellite communication module is used to acquire second location data and report it via the low-Earth orbit satellite link; The main control board is connected to the inertial measurement module, the Beidou satellite communication module, and the low-orbit satellite communication module, respectively. The main control board is used to assess the current sea state level based on the attitude data. When the sea state level is low, the low-orbit satellite communication module is controlled to enter a sleep state or power-off state, and the Beidou satellite communication module reports the first location data. When the sea state is high, the low-Earth orbit satellite communication module is activated or enabled, so that the Beidou satellite communication module and the low-Earth orbit satellite communication module work in parallel and report their respective position data in a dual-mode redundancy manner.

[0024] This application implements a dual-mode satellite communication positioning and warning device based on sea state attitude perception. The device's attitude data, swaying with the waves, is collected in real time via an inertial measurement module. The main control board then assesses the current sea state level (low or high) based on this data, adaptively controlling the sleep / wake-up state of the low-Earth orbit (LEO) satellite communication module and determining whether to use BeiDou single-mode or BeiDou + LEO dual-mode redundancy for reporting position data. Because the inertial measurement module continuously senses the device's real-time attitude data, the main control board can quantitatively distinguish between low sea state (wave height < 1.5m, slight swaying) and high sea state (wave height ≥ 1.5m, severe swaying) by analyzing the intensity of attitude data fluctuations (e.g., root mean square angular velocity). This solves the problem of existing technologies being unable to perceive sea state in real time and dynamically adjust communication strategies based on sea state, achieving real-time, quantitative perception of the marine environment and providing a reliable basis for subsequent adaptive switching.

[0025] When the sea state is assessed as low, the main control board actively controls the low-Earth orbit satellite communication module to enter a sleep or power-off state, with only the BeiDou satellite communication module reporting the first position data. Since the BeiDou satellite link itself has a high success rate in low sea states, shutting down the low-Earth orbit satellite communication module avoids unnecessary power consumption, thus solving the problem of power waste caused by multiple modules operating at full speed in low sea states. This achieves a low-sea-state energy-saving mode, significantly extending the equipment's battery life.

[0026] When the sea state is assessed as high, the main control board immediately wakes up or enables the low-Earth orbit (LEO) satellite communication module, allowing it to work in parallel with the BeiDou satellite communication module, reporting their respective position data in a dual-mode redundancy manner. Because the severe swaying of equipment under high sea state conditions frequently limits the elevation angle of the BeiDou antenna, the success rate of a single BeiDou satellite link communication decreases significantly. In contrast, the LEO satellite has a low orbit and a large variation in its elevation angle during transit, and is less affected by sea wave obstruction. The two links complement each other and are redundant; success of either link is sufficient to complete the reporting, thus solving the problems of low single-link communication success rate and easy loss of position data under high sea state conditions, achieving a significant improvement in communication success rate under high sea state conditions.

[0027] In summary, through the synergistic effect of the aforementioned technical features, this application achieves the dual benefits of low power consumption in low sea state and high reliability in high sea state under all sea state conditions.

[0028] Furthermore, this application can also introduce deep neural networks (DNN) into the transmission timing prediction in high sea state mode, further concentrating short messages into the peak window of the largest antenna elevation angle, thereby reducing the number of invalid transmissions and improving communication efficiency; it can also perform deviation comparison and weighted fusion on the position data output by dual links to output highly reliable fused position data, further improving the accuracy of reported information.

[0029] In one exemplary embodiment, this implementation provides a dual-mode satellite communication positioning and warning device based on sea attitude perception, including a buoyancy-sealed cabin and a mounting base. The buoyancy-sealed cabin integrates a main control board, an inertial measurement module, a BeiDou satellite communication module, and a low-Earth orbit satellite communication module.

[0030] As an optional implementation, the Inertial Measurement Unit (IMU) uses the MIMU-330 six-axis IMU manufactured by the 13th Research Institute of China Electronics Technology Group Corporation (CETC). It integrates a 3D accelerometer (range ±2g) and a 3D gyroscope (range ±125dps), consuming only 0.75mA and operating at a temperature of -40℃ to +85℃. This module connects to the main control board via an SPI interface, outputting three-axis acceleration data at a 1Hz sampling rate. ) and triaxial angular velocity ( (This is used to collect real-time attitude data of the equipment as it sways with the waves).

[0031] As an optional implementation, the BeiDou satellite communication module uses the C500 terminal and the BeiDou stacked antenna used in conjunction with the C500 terminal. The C500 terminal supports two-way communication on BeiDou-3 RDSS (Radio Determination Satellite Service) frequencies and positioning on BeiDou-3 RNSS (Radio Navigation Satellite Service) frequencies. The BeiDou-3 RDSS operates in the S-band (2491.75±8.16MHz) and L-band (1615.68±4.08MHz), with a maximum short message length of 1000 Chinese characters. The communication success rate in space tests is ≥98%, the transmit EIRP is 3-13dBW, and the receive sensitivity is: for an 8kbps information frame, when the signal level is ≤-130.0dBm, the bit error rate is ≤1×10⁻⁶. -5 The power supply voltage is a wide 9-36V input. The BeiDou-3 RNSS frequency is B1 / L1, with a horizontal accuracy ≤10m (horizontal accuracy factor HDOP≤4) and an elevation accuracy ≤5m (vertical accuracy factor VDOP≤4), and is compatible with BeiDou-2. The BeiDou stacked antenna adopts a multi-frequency stacked design, supporting multiple BeiDou-3 frequencies (B1I, B1C, L1, S2C, Lf1, Lf2). It can receive BeiDou satellite positioning signals (RNSS) and transmit short message signals (RDSS). It is usually installed on the top or side of the floating sealed cabin to maintain a good field of view. This antenna and the low-orbit tape measure antenna of the low-orbit satellite communication module are two independent antennas, and they must maintain a physical isolation distance of ≥10cm to avoid radio frequency interference. This module connects to the main control board via the USART1 interface (115200bps baud rate, 8N1 format), with a standby power consumption of approximately 1.09W and a transmission instantaneous power consumption of ≤25W. It is used to report location data via the BeiDou satellite link.

[0032] As an optional implementation, the low-Earth orbit (LEO) satellite communication module uses the Tianqi constellation TQZD-08 terminal, supporting UHF band data transmission and GNSS (Global Navigation Satellite System) positioning (horizontal accuracy <2.5m), with a receiving sensitivity ≤-132dBm. This module connects to the main control board via a USART2 interface (115200bps baud rate, 8N1 format), with a transmit power consumption of 9.6W and standby power consumption ≤0.04W. The module is equipped with an integrated LEO measuring antenna and a terminal motherboard. The terminal motherboard measures 92mm × 66mm × 9.5mm and weighs 0.2kg. The LEO measuring antenna is physically isolated from the BeiDou stacked antenna by ≥10cm, and the RF link is independently shielded with an isolation of ≥40dB, used for reporting position data via the LEO satellite link.

[0033] As an optional implementation, the main control board uses the GigaDevice GD32H759IMK6 chip, a Cortex-M7 core with a clock speed of 600MHz, 1MB RAM, 3840KB FLASH, and integrates a DSP hardware accelerator, a double-precision FPU, a hardware trigonometric function accelerator (TMU), and a filtering algorithm accelerator (FAC). It achieves a performance of 1552 DMIPS and supports 5 UART channels, multiple PWM channels, and a 14-bit ADC (configured with a sampling rate of 2kHz). The main control board runs the FreeRTOS real-time operating system and connects to the inertial measurement module, the BeiDou satellite communication module, and the low-Earth orbit satellite communication module.

[0034] The main control board is configured to perform the following operations: A1) Sea condition rating assessment The main control board is configured to calculate a statistical value representing the severity of the equipment's swaying based on the attitude data collected by the inertial measurement module, and compare the statistical value with a preset threshold to assess the current sea state level.

[0035] As one specific implementation, the statistical value can be the root mean square value of angular velocity or acceleration data. For example: taking the angular velocity about the X-axis. and angular velocity around the Y-axis The larger value in the range is used as the characteristic angular velocity of the current sampling point. , For angular velocity over a continuous 30 minutes Calculate the root mean square value of the sequence , root mean square value With a preset threshold (e.g.) Compare them. When When the sea condition is determined to be high (corresponding to wave height ≥ 1.5m, sea condition 4-5); when The sea condition was determined to be low (corresponding to wave height <1.5m, sea condition 1-3).

[0036] To prevent frequent changes in sea state level near the threshold, a hysteresis mechanism can be adopted: the rising threshold (e.g., 22° / s) for switching from low to high sea state is greater than the falling threshold (e.g., 18° / s) for recovering from high to low sea state, and the switching can only be triggered if the condition is met for several consecutive sampling periods (e.g., 3 seconds).

[0037] A2) Dual-mode adaptive switching When the sea state is low, the main control board pulls down the power enable signal of the low-orbit satellite communication module through the GPIO pin, causing it to enter a sleep state or power-off state, and the Beidou satellite communication module reports the first position data.

[0038] When the sea state is high, the main control board pulls the power enable of the low-Earth orbit satellite communication module high through the GPIO pin, wakes up the module, and enables the Beidou satellite communication module and the low-Earth orbit satellite communication module to work in parallel and report their respective position data in a dual-mode redundancy manner.

[0039] A3) DNN launch timing prediction In this embodiment, the main control board, in high sea state mode, is also used to optimize launch timing. The main control board loads a pre-trained lightweight deep neural network model. This model is a 3-layer fully connected network: 20 nodes in the input layer, 32 nodes in the hidden layer (ReLU activation), 16 nodes in the hidden layer (ReLU activation), and 1 node in the output layer (Sigmoid activation). The model has approximately 1.2K parameters, and the inference time is ≤1ms (utilizing the GD32H759IMK6 DSP hardware accelerator and TMU hardware trigonometric function accelerator). For example, the model input is the angular velocity time series data corresponding to the most recent 10 seconds (sampling rate 1Hz, 10 sampling points, taking X-axis and Y-axis angular velocities, hence the input dimension is 20-dimensional), and the model output is the probability P that the antenna elevation angle will reach a local maximum within the next 2 seconds. When P≥0.7, the main control board immediately sends an "immediate launch" command to the BeiDou satellite communication module, ensuring the short message is sent within the optimal window.

[0040] It is understood that the structure of the deep neural network model described above is not limited to this. Any lightweight network model that can predict the future antenna attitude based on time-series attitude data, such as a recurrent neural network (RNN) or its variants, can be applied to this application.

[0041] A4) Dual-link location data fusion In this embodiment, the main control board, in dual-mode redundancy, is also used to perform location data fusion. The main control board acquires the first location data output by the BeiDou satellite communication module and the second location data (both latitude and longitude) output by the low-Earth orbit satellite communication module. The Haversine formula is used to calculate the geographical distance deviation between the two. .when When the preset deviation threshold is reached, the arithmetic mean of the two sets of location data is taken as the fused location data; when... When selecting location data with better data quality, the data quality is determined based on the horizontal accuracy factor output by the BeiDou satellite communication module or the signal-to-noise ratio output by the low-orbit satellite communication module (for example, comparing the BeiDou horizontal accuracy factor HDOP (the smaller the value, the better) with the low-orbit signal-to-noise ratio C / N0 (the larger the value, the better)), and abnormal events are recorded in the fault log.

[0042] It should be noted that the specific hardware models (such as MIMU-330, C500, TQZD-08, GD32H759IMK6, etc.), parameter values ​​(such as sampling rate of 1Hz, threshold of 20° / s, etc.), and specific algorithms (such as root mean square value calculation, DNN structure, etc.) listed above are merely illustrative examples and should not be construed as limiting the scope of protection of this application. Those skilled in the art can utilize other equivalent hardware, parameters, or algorithms to achieve the same functionality based on the concept of this application.

[0043] This application also provides an application scenario in which the above-mentioned equipment is used in amphibious vehicle maritime training or combat missions. When the vehicle accidentally falls into the water, the equipment sinks with the vehicle body. The 4mm thick PVA water-soluble sheet in the unlocking mechanism on the mounting base dissolves within a few seconds (e.g., within 3-10 seconds) upon contact with water, triggering the linkage of springs A and B, causing the buoyancy chamber to separate from the mounting base and float to the sea surface. During the separation process, the distance between the Hall switch (HX6383) at the bottom of the buoyancy chamber and the permanent magnet of the mounting base increases from ≤5mm to >20mm, the magnetic saturation is released, and the Hall switch output changes from low level to high level. After filtering and shaping, it drives the power supply module (TPP60506) to supply power to the entire system.

[0044] Assuming the current sea state is Class 4, with a significant wave height of approximately 1.8m and wave heights ranging from 1.5m to 4m, this is considered a high sea state. The equipment sways violently with the waves, with peak roll angles reaching approximately ±45°, frequently limiting the antenna's elevation angle. In this scenario, the success rate of single BeiDou satellite link communication drops significantly (measured at approximately 58%), requiring the equipment to immediately activate dual-mode redundant communication to ensure continuous location data reporting.

[0045] In this scenario, the measured success rate of a single BeiDou satellite link communication is only about 58%. With the solution proposed in this application, the main control board senses high sea state through the IMU and immediately wakes up the low-Earth orbit (LEO) satellite communication module. The BeiDou and LEO dual links operate in parallel. Due to the large variation in the elevation angle of the LEO satellite's passage, it is less affected by sea wave obstruction, and its link can serve as effective redundancy. Actual measurements show that the success rate of dual-mode redundancy reporting is improved to over 96%. Simultaneously, in low sea state (wave height 0.5m, root mean square angular velocity 8° / s), shutting down the LEO satellite communication module reduces overall power consumption and extends battery life. DNN launch timing prediction further significantly reduces invalid launches. Therefore, this application, through the synergistic effect of sea state awareness and dual-mode adaptation, achieves the dual benefits of low power consumption in low sea state and high reliability in high sea state under all sea state conditions.

[0046] Based on the same inventive concept, this application also provides a method for implementing the above-mentioned dual-mode satellite communication positioning and warning device based on sea state and attitude awareness. The solution provided by this method is similar to the implementation described in the above method. Therefore, the specific limitations in one or more embodiments of the dual-mode satellite communication positioning and warning method based on sea state and attitude awareness provided below can be found in the limitations of the dual-mode satellite communication positioning and warning device based on sea state and attitude awareness described above, and will not be repeated here.

[0047] In yet another exemplary embodiment, such as Figure 1 As shown, a dual-mode satellite communication positioning and warning method based on maritime attitude awareness is provided. The method includes the following steps S01 to S03: Step S01: Acquire real-time attitude data The device's real-time attitude data is collected through an inertial measurement module.

[0048] Step S02: Assess the current sea state level Based on the angular velocity or acceleration data in the attitude data, a statistical value characterizing the severity of the device's swaying is calculated, and the statistical value is compared with a preset threshold: If the statistical value is greater than or equal to the preset threshold, it is determined to be a high sea state; otherwise, it is a low sea state.

[0049] Optionally, a hysteresis mechanism (e.g., an upward threshold of 22° / s and a downward threshold of 18° / s, lasting for 3 seconds) can be used for smooth switching.

[0050] Step S03: Adaptively switch communication modes If the sea state is low: control the low-orbit satellite communication module to enter a sleep state or power-off state, and only the Beidou satellite communication module will report the first position data; If it is a high-altitude sea condition: wake up or enable the low-orbit satellite communication module, so that the Beidou satellite communication module and the low-orbit satellite communication module can work in parallel and report their respective position data in a dual-mode redundancy mode.

[0051] As an optional implementation method, the dual-mode satellite communication positioning and warning method based on maritime attitude awareness in this application further includes step S04: periodically performing system verification. The low-orbit satellite communication module is forcibly woken up to verify the integrity of the dual links, reassess the sea state level, and update the communication mode accordingly. When the sea state level is low and both links are normal, the low-orbit satellite communication module is put back into hibernation or power-off mode to restore the energy-saving mode.

[0052] As an optional implementation method, the dual-mode satellite communication positioning and warning method based on sea state attitude perception in this application further includes step S05: DNN transmission timing optimization: In high sea state mode, a pre-trained deep neural network model is used to predict the angular velocity time series data of the most recent 10 seconds to obtain the probability that the antenna elevation angle will reach a local maximum value within a future preset time window, and when the probability exceeds a preset threshold, the Beidou satellite communication module is controlled to send a short message so that the message is sent within the optimal window.

[0053] As an optional implementation method, the dual-mode satellite communication positioning and warning method based on maritime attitude perception in this application further includes step S06: dual-link data fusion: in dual-mode redundancy mode, the deviation between Beidou and low-orbit position data is calculated. If the deviation is less than or equal to a preset deviation threshold, the arithmetic mean of the two is taken as the fused position data. When the deviation is greater than the preset deviation threshold, the position data with better data quality is selected.

[0054] As an optional implementation, step S07 is also included: checking the battery power (State of Charge, SOC): when SOC < 20%, the low-Earth orbit satellite communication module and the high-brightness warning light are turned off; when SOC < 10%, the device is shut down in an emergency and the last location data is saved.

[0055] This application also provides an application scenario in which the aforementioned dual-mode satellite communication positioning and warning method based on sea state and attitude perception is applied to an amphibious vehicle distress positioning scenario. Assume that an amphibious vehicle accidentally falls into the water while performing a training mission in sea state 4 (significant wave height approximately 1.8m, wave height between 1.5m and 4m), and the vehicle sinks, with the onboard positioning and warning equipment sinking underwater along with the vehicle.

[0056] like Figure 2 As shown, the entire device consists of two main parts: the buoyancy sealing chamber and the mounting base. The buoyancy sealing chamber is a sealed cavity, internally integrating: The main control board uses the GigaDevice GD32H759IMK6 chip (Cortex-M7 core, 600MHz, built-in 1MB RAM, 3840KB FLASH, integrated DSP hardware accelerator, TMU trigonometric function accelerator and FAC filtering algorithm accelerator).

[0057] The inertial measurement module adopts the MIMU-330 six-axis IMU (integrated with a 3D accelerometer ±2g and a 3D gyroscope ±125dps, with a power consumption of 0.75mA) from the 13th Research Institute of China Electronics Technology Group Corporation.

[0058] The BeiDou satellite communication module uses the C500 terminal and a matching BeiDou stacked antenna, supporting BeiDou-3 RDSS short message and RNSS positioning.

[0059] The low-orbit satellite communication module uses the Tianqi constellation TQZD-08 terminal and a low-orbit measuring tape antenna, supporting UHF band data transmission and GNSS positioning.

[0060] The power supply module uses Zhizi New Energy SX-CB1250BA lithium battery pack (12V / 50Ah / 600Wh) to power the entire system.

[0061] Warning light module: Includes light-emitting light group and light distribution lens. The main control board (detected by MT3200 brightness sensor) controls the normal brightness or high brightness mode according to the ambient brightness to emit light warning signals.

[0062] The mounting base includes a base housing, a shock absorber, a reel module, and a unlocking mechanism. The shock absorber absorbs the impact force when the vehicle falls into water; the reel module contains a reel shaft, winding mechanism, and adjustment mechanism for winding and unwinding the connecting cable; the unlocking mechanism contains a water-soluble sheet (PVA water-soluble sheet, 4mm thick), pins A and B, and springs A and B. Upon contact with water, the water-soluble sheet dissolves, triggering the springs to separate the floating sealed compartment from the base. The user command center is equipped with a BeiDou-3 user command terminal and a low-orbit satellite user terminal, which respectively receive location data reported by the equipment through the BeiDou satellite link and the low-orbit satellite link to realize real-time monitoring and search and rescue scheduling of the location where the object fell into the water.

[0063] The following combination Figure 1 The above-mentioned hardware, and a detailed explanation of the equipment's workflow.

[0064] Step S1: Immersion Trigger and Initialization After the vehicle falls into the water, the equipment sinks with the vehicle. The 4mm thick PVA water-soluble sheet in the unlocking mechanism on the mounting base dissolves within 3-10 seconds upon contact with water, triggering the dual-spring two-stage linkage mechanism to complete the mechanical unlocking. The floating sealed compartment separates from the mounting base and automatically floats to the sea surface.

[0065] During the separation process, the distance between the Hall switch (Wuxi Huaxin HX6383 Hall element) fixed at the bottom of the sealed chamber and the permanent magnet fixed on the mounting base increases from the initial ≤5mm to >20mm, the magnetic saturation state is released, and the Hall switch output changes from low level to high level. After the signal is filtered by an RC filter circuit (R=10kΩ, C=100nF, time constant 1ms) to remove high-frequency noise, it is sent to a 74HC14 Schmitt trigger to be shaped into a standard square wave, driving the P-channel MOSFET (SI7478DP) to conduct, connecting the power supply module (PMU, core chip is Silergy TPP60506), and the lithium battery pack begins to power the entire system.

[0066] After the main control board is powered on, the GD32H759IMK6 main control chip starts the FreeRTOS real-time operating system and performs initialization in the order of "hardware → driver → service → application": configuring USART1 (interfacing with the Beidou satellite communication module, i.e., the C500 terminal, baud rate 115200bps, 8N1 format), USART2 (interfacing with the low-Earth orbit satellite communication module, i.e., the TQZD-08 terminal, baud rate 115200bps, 8N1 format), I2C interface (interfacing with the MT3200 brightness sensor), SPI interface (interfacing with the MIMU-330 IMU), and ADC channel (acquiring battery voltage, voltage divider resistor 100kΩ+10kΩ, 14-bit precision, sampling rate 2kHz); loading DNN model parameters and satellite ephemeris data from the W25Q64JVFlash chip (64Mbit); creating 8 core tasks and allocating stack space. The total initialization time is ≤150ms.

[0067] Step S2: Verify simultaneous power-on of both terminals After initialization, the main control board simultaneously connects the power supply circuits of the two satellite terminals through GPIO pins (GPIOA0 controls the power enable of the Beidou satellite communication module, and GPIOB1 controls the power enable of the low-orbit satellite communication module).

[0068] The BeiDou satellite communication module initiates RNSS positioning (supporting B1I / B1C / L1 frequencies), with a cold start positioning time of ≤40s and a warm start time of ≤3s, while simultaneously activating the RDSS short message function; the low-Earth orbit satellite communication module performs a power-on self-test and initiates GNSS positioning. Both terminals report their initial position data and communication status to the main control board via their respective isolated 485 buses.

[0069] The main control board verifies the validity of the two links: it parses the NMEA GGA / RMC statements output by the BeiDou satellite communication module, checking HDOP≤4, VDOP≤4, and signal-to-noise ratio C / N0≥35dB-Hz; it queries the status register of the low-Earth orbit satellite communication module to confirm that the receiving sensitivity is ≤-132dBm. If both links are normal, it proceeds to step S3; if either link is abnormal, it performs a maximum of 3 soft reboots (sending a reset AT command). If it still fails, the link is marked as faulty, and only the normal link is used.

[0070] Step S3: Continuous acquisition of data from multiple sensor sources After entering steady-state operation, the main control board continuously performs the following data acquisition tasks: S31, IMU Data Acquisition: The MIMU-330 six-axis IMU outputs three-axis acceleration data to the main control board at a frequency of 1Hz via the SPI interface. ) and triaxial angular velocity ( The original data. The main control board uses the built-in filtering algorithm accelerator (FAC) of GD32H759IMK6 to perform sliding window mid-range filtering (window length 5) on the original data to remove the spike noise caused by the impact of the waves and output a smoothed attitude data sequence.

[0071] S32. Illuminance Acquisition: The MT3200 luminance sensor outputs ambient illuminance values ​​(in lux) at a frequency of 1Hz via the I2C interface, with a measurement range of 0.01 lux to 65535 lux and an operating temperature of -40℃ to +85℃.

[0072] S33. Battery Status Acquisition: The battery voltage is sampled by ADC (once per second), the operating current is collected by INA219 current sensor (with a 0.1Ω sampling resistor in series), and the SOC, SOH (State of Health), cell temperature and other data are received from the BMS (Battery Management System, model ZZ-BMS-12S) via CAN2.0B bus (baud rate 250kbps).

[0073] Step S4: Real-time assessment of sea state level The main control board processes the attitude data (e.g., three-axis angular velocity or three-axis acceleration) output by the IMU, calculates statistical values ​​characterizing the severity of the equipment's swaying, and assesses the current sea state level based on a comparison of these statistical values ​​with a preset threshold. The calculation window length and calculation method (e.g., root mean square, standard deviation, moving average, etc.) for the aforementioned statistical values ​​can be configured according to actual power consumption and response speed requirements. The specific algorithm is as follows (taking the root mean square value of angular velocity data as an example): S41, Take the angular velocity around the X-axis and angular velocity around the Y-axis The larger value in the range is used as the characteristic angular velocity of the current sampling point. ; S42, angular velocity over a continuous 30 minutes Sequence, calculate root mean square value As the statistical value; S43, Root mean square value Compare with a preset threshold: when When, it is determined to be a high sea state (corresponding to wave height ≥ 1.5m, sea state 4-5); when At that time, the sea condition was determined to be low (corresponding to wave height <1.5m, sea condition 1-3). S44. To prevent frequent jumps in sea state levels near the threshold, a hysteresis mechanism can be introduced. For example, the threshold for switching from low to high sea state is 22° / s, and the threshold for returning from high to low sea state is 18° / s, and the condition must be met for 3 consecutive seconds before the switch can proceed.

[0074] In this application example, the current sea state is 4, with a significant wave height of approximately 1.8m, and the equipment is swaying violently with the waves. The root mean square value of the angular velocity over 30 consecutive minutes was calculated. The speed is approximately 25° / s, which is greater than the preset threshold of 20° / s, and the condition is met for 3 consecutive seconds. Therefore, the main control board determines that the current sea state is high.

[0075] Step S5: Adaptive switching of dual-mode communication Based on the sea state assessment result in step S4 (currently high sea state), the main control board performs the following communication strategy switch: The main control board wakes up the TQZD-08 terminal by pulling the power enable signal of the low-Earth orbit satellite communication module high via the GPIOB1 pin, enabling it to work in parallel with the C500 terminal. The two terminals synchronously perform first and second position data acquisition and message transmission. BeiDou satellite link: Short messages are reported via RDSS (including device number, latitude and longitude, UTC timestamp, battery SOC, and sea state level code). The duration of a single transmission is ≤5 seconds, the instantaneous power consumption during transmission is ≤25W, and the standby power consumption is approximately 1.09W.

[0076] Low Earth Orbit (LEO) satellite link: Reporting via UHF band (power consumption of 9.6W per transmission, lasting approximately 6 seconds).

[0077] In this mode, the average power consumption of the whole machine is about 8.46W, and the 600Wh battery can support continuous operation for about 71 hours.

[0078] Meanwhile, the main control board also executes emergency switching logic for link failures: if the BeiDou satellite communication module fails to send two short messages consecutively (judged by parsing the RDSS receipt message), the low-orbit satellite communication module is immediately switched to the primary link; the reverse is also true. If both terminals fail, a hard reboot is performed (by pulling the module power low on the GPIO pin for 500ms and then powering it back on).

[0079] Step S6: Optimize DNN launch timing (enabled in high sea state mode) In high seas conditions mode, to further improve the success rate of BeiDou RDSS short message transmission, the main control board uses a pre-trained lightweight DNN model for launch timing prediction. The specific implementation is as follows: S61. Model input: Take the IMU angular velocity time series data of the most recent 10 seconds (10 sampling points × 2 axes = 20-dimensional feature vector).

[0080] S62. Model Structure: A 3-layer fully connected network is used → 20 nodes in the input layer → 32 nodes in the hidden layer (ReLU activation) → 16 nodes in the hidden layer (ReLU activation) → 1 node in the output layer (Sigmoid activation). The total number of model parameters is approximately 1.2K.

[0081] S63. Model Inference: The main control board uses the built-in DSP hardware accelerator and TMU trigonometric function accelerator of GD32H759IMK6 to perform matrix multiplication and activation function calculation. The inference time is ≤1ms. The model output is the probability P of the device antenna elevation angle reaching a local maximum within the next 2 seconds.

[0082] S64. Launch Decision: When P≥0.7, the main control board immediately sends an "immediate launch" command to the Beidou satellite communication module, so that the message can be sent during the period when the antenna alignment is optimal.

[0083] In this example, the DNN model is trained on a PC using a large amount of offline collected marine IMU data (covering sea states 1-5) and corresponding BeiDou communication success / failure labels. After training, the DNN model weights are quantized into INT8 format and burned into the W25Q64JV Flash chip.

[0084] In this example, under sea state 4, the equipment oscillates periodically with the waves. The DNN model predicts that the equipment will reach the wave crest within the next 2 seconds, and the antenna elevation angle will reach its peak (approximately 65°), with a prediction probability P=0.85, which is greater than the preset threshold of 0.7. The main control board immediately triggers the transmission of a BeiDou short message, and the message is successfully sent within the optimal communication window.

[0085] Step S7: Dual-link location data fusion In dual-mode redundancy mode, the main control board simultaneously receives first and second position data (latitude and longitude) from the BeiDou satellite communication module and the low-orbit satellite communication module, and performs the following fusion processing: S71. Use the Haversine formula to calculate the geographical distance deviation ΔD between the two sets of latitude and longitude.

[0086] S72, if The arithmetic mean of the two sets of data is taken as the fusion result.

[0087] S73, if The signal-to-noise ratio (SNR) of the two terminals is compared (HDOP value from GGA statement for BeiDou, C / N0 value from status register for LEO), and the location data with better SNR is selected as the fusion result. At the same time, abnormal deviation events are recorded in the fault log.

[0088] S74. The merged location data is appended with a timestamp, device status code, and CRC16 checksum, and encapsulated into a standard message frame (frame header 0xAA55 + device ID (4 bytes) + longitude (4 bytes) + latitude (4 bytes) + timestamp (4 bytes) + status code (2 bytes) + CRC16 (2 bytes) + frame tail 0xEEFF (2 bytes), total length 22 bytes), and uploaded through the currently available link.

[0089] In this example, the first location data output by the BeiDou satellite communication module is (118.3521°E, 24.8912°N), and the second location data output by the LEO satellite communication module is (118.3523°E, 24.8910°N). Calculated using the Haversine formula, the geographical distance deviation ΔD ≈ 2.1m, which is less than the preset deviation threshold of 3m. The main control board takes the arithmetic mean of the two sets of data to obtain the fused location data (118.3522°E, 24.8911°N), and uploads it simultaneously via both the BeiDou satellite link and the LEO satellite link.

[0090] Step S8: Periodic Verification and Self-Recovery A system-level check is performed every 30 minutes. S81: Forcefully wake up all terminals and send verification messages synchronously on both links to verify the integrity of the link.

[0091] S82. Reassess the sea state level and update the communication mode.

[0092] S83, Check battery SOC: SOC ≥ 20%: Normal operation; 10%≤SOC<20%: Trigger low battery warning, turn off low-orbit satellite communication module and warning light high brightness mode, only retain Beidou single mode + ordinary brightness warning; SOC < 10%: Trigger emergency shutdown, save the last location data to Flash and then shut down all peripherals.

[0093] S84. After verification, if the current sea state is low and the dual links are normal, shut down the low-orbit satellite communication module to restore the energy-saving mode.

[0094] In this example, the system performs its first periodic check one hour after power-on. At this time, the battery SOC is 92%, indicating normal operation. The sea state is reassessed and remains high, therefore the dual-mode redundancy mode is maintained. The main control board simultaneously sends check messages through two links, both of which receive confirmation from the command center, confirming the integrity of the dual links.

[0095] In this example, under sea state 4 (significant wave height approximately 1.8m, wave height between 1.5m and 4m, classified as high sea state), the equipment swayed violently with the waves, with peak roll angles frequently exceeding ±40°. The BeiDou-3 geostationary orbit (GEO) satellite is located approximately 35,786km above the equator, requiring the antenna to maintain an elevation angle ≥20° to ensure effective signal delivery to the satellite. Under high sea state conditions, the antenna's main lobe frequently deviated from the satellite's orientation, causing the BeiDou short message success rate to plummet from over 98% in static sky-alignment tests to approximately 58%. In this scenario, the success rate of a single BeiDou satellite link communication significantly decreased, necessitating the immediate activation of dual-mode redundant communication to ensure continuous reporting of positioning data.

[0096] After adopting the technical solution of this application, the actual measured data are as follows:

[0097] In addition, the dual-link data fusion function improves the positioning accuracy from 10m (HDOP≤4) of single link to within 5m; the DNN model launch timing prediction function increases the proportion of BeiDou short messages launched in the optimal window from about 30% of random launches to more than 85%.

[0098] In summary, this embodiment achieves the predetermined technical objectives of communication success rate ≥95% under all sea conditions, low power consumption, and long battery life, fully verifying the effectiveness and advancement of this application.

[0099] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 3 As shown, the computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores relevant data for a dual-mode satellite communication positioning and warning method based on maritime attitude awareness. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a dual-mode satellite communication positioning and warning method based on maritime attitude awareness.

[0100] Those skilled in the art will understand that Figure 3The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0101] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0102] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0103] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0104] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0105] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0106] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0107] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0108] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A dual-mode satellite communication positioning and warning device based on maritime attitude perception, characterized in that, include: An inertial measurement module is used to collect real-time attitude data of the device; The BeiDou satellite communication module is used to acquire initial location data and report it via the BeiDou satellite link; The low-Earth orbit satellite communication module is used to acquire second location data and report it via the low-Earth orbit satellite link; The main control board is connected to the inertial measurement module, the Beidou satellite communication module, and the low-orbit satellite communication module, respectively. The main control board is used to assess the current sea state level based on the attitude data. When the sea state level is low, the low-orbit satellite communication module is controlled to enter a sleep state or power-off state, and the Beidou satellite communication module reports the first location data. When the sea state is high, the low-Earth orbit satellite communication module is activated or enabled, so that the Beidou satellite communication module and the low-Earth orbit satellite communication module work in parallel and report their respective position data in a dual-mode redundancy manner.

2. The dual-mode satellite communication positioning and warning device based on maritime attitude awareness according to claim 1, characterized in that, The main control board is used to calculate a statistical value representing the severity of the equipment's swaying based on the angular velocity or acceleration data in the attitude data, and compare the statistical value with a preset threshold to assess the current sea state level.

3. The dual-mode satellite communication positioning and warning device based on maritime attitude perception according to claim 2, characterized in that, The main control board is used to switch sea state levels using a hysteresis mechanism, wherein the threshold for switching from low sea state to high sea state is greater than the threshold for switching back from high sea state to low sea state.

4. The dual-mode satellite communication positioning and warning device based on maritime attitude awareness according to claim 1, characterized in that, The main control board is used to predict the attitude data collected by the inertial measurement module using a pre-trained deep neural network model in the high sea state mode, obtain the probability that the antenna elevation angle will reach a local maximum value within a preset time window, and control the Beidou satellite communication module to send short messages when the probability exceeds a preset threshold.

5. The dual-mode satellite communication positioning and warning device based on maritime attitude awareness according to claim 4, characterized in that, The deep neural network model is a lightweight fully connected network. Its input is the angular velocity time series data of the most recent sampling periods, and its output is the probability that the antenna elevation angle will reach its peak within a future time window.

6. The dual-mode satellite communication positioning and warning device based on maritime attitude awareness according to claim 1, characterized in that, The main control board is used to acquire the first position data output by the Beidou satellite communication module and the second position data output by the low-orbit satellite communication module in the dual-mode redundancy mode, calculate the deviation between the two, and take the arithmetic mean of the two as the fused position data when the deviation is less than or equal to a preset deviation threshold. When the deviation is greater than the preset deviation threshold, the position data with better data quality is selected.

7. A dual-mode satellite communication position indication and warning method based on maritime attitude awareness, characterized in that, Includes the following steps: The device's real-time attitude data is acquired through an inertial measurement module; Assess the current sea state level based on the attitude data; When the sea state level is low, the control low-orbit satellite communication module enters a sleep state or power-off state, and the Beidou satellite communication module reports the first position data. When the sea state is high, the low-Earth orbit satellite communication module is activated or enabled, so that the Beidou satellite communication module and the low-Earth orbit satellite communication module work in parallel and report their respective position data in a dual-mode redundancy manner.

8. The dual-mode satellite communication positioning and warning method based on maritime attitude awareness according to claim 7, characterized in that, Also includes: The system periodically performs checks, forcibly wakes up the low-orbit satellite communication module, verifies the integrity of the dual links, and reassesses the sea state level. When the sea state level is low and both links are normal, the system re-controls the low-orbit satellite communication module to enter a sleep state or a power-off state.

9. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the dual-mode satellite communication positioning and warning method based on maritime attitude awareness as described in claim 7 or 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the computer program implements the steps of the dual-mode satellite communication positioning and warning method based on maritime attitude awareness as described in claim 7 or 8.

Images