A method and device for transmitting back polar activity information

Abstract

The present invention provides a method and a device for transmitting polar activity information, relating to the technical field of electrical digital data processing, and particularly to an electrical digital data processing method and a corresponding device for ensuring the effective transmission of signals of scientific research equipment in a special polar environment. The transmission of polar activity information in the present invention specifically includes: collecting polar vehicle working condition information, positioning information, and weather image sequences; predicting a first signal transmission window period based on the current weather image sequences; obtaining connectable communication satellite IDs based on a communication module and predicting a second signal transmission window period; obtaining a transmission window by using the first and second signal transmission window periods, sorting transmission information based on the transmission window, and completing the transmission of the transmission information. Through the above steps, the present invention avoids the waste of energy and communication resources caused by making ineffective communication attempts under adverse conditions, and improves the overall operating efficiency and battery life of the transmission device.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic digital data processing. Specifically, it relates to a method and device for transmitting polar activity information, and in particular, to an electronic digital data processing method and corresponding device that can ensure the effective transmission of signals of scientific research equipment in the special polar environment. Background Art

[0002] With the development of society and the progress of technology, in conventional human activity areas, such as cities, towns or areas covered by communication infrastructure, there are already various mature technical means for positioning and collecting relevant information of activity targets such as personnel, vehicles, and assets. In terms of positioning, in addition to using the global satellite navigation system to obtain basic location information, in an environment with corresponding ground facility support, the base station signals of the ground mobile communication network are often used for positioning, and Wi-Fi network signals or Bluetooth beacons are used for more refined indoor or local area positioning. The effectiveness of these positioning methods often depends on the density and availability of surrounding fixed infrastructure. In terms of information collection and transmission, in the conventional environment, it mainly relies on the widely covered ground communication network. For example, the status or environmental information collected by various sensors is transmitted to a designated server or monitoring platform through the public land mobile network. These technologies developed under the conditions of perfect infrastructure and relatively stable communication environment provide basic support for target tracking, status monitoring and management in daily production and life, and constitute the mainstream technical system for positioning and information interaction in non-extreme environments.

[0003] However, the polar environment is unique and extreme, posing severe challenges to traditional information backhaul methods and devices, making it often difficult for existing technologies to be directly applicable or perform poorly. First, the polar surface environment is mainly composed of vast ice sheets, glaciers, and snow cover. These media have a high reflectivity to radio signals. When communication satellites, especially those at a low elevation angle and close to the horizon, transmit signals to ground receiving devices or receive signals from ground devices, the signals will experience complex surface reflections and scatterings, forming multipath effects. This multipath interference will cause amplitude fading, phase distortion, and delay spread of the received signal, reducing the stability of the communication link and the success rate of data transmission. Especially in the ice margin area with large terrain undulations or areas with ice hummocks and ice crevasses, the multipath effect is more significant, making it extremely difficult to reliably backhaul data via satellites. Second, the weather environment in the polar region is extremely harsh and unpredictable, posing a severe challenge to information backhaul relying on radio waves. The stable and reliable transmission of wireless signals, especially satellite communication links for long-distance data backhaul, often requires relatively good atmospheric window conditions, that is, a smooth and less-interfered signal propagation path. However, the weather in the polar region changes extremely violently, often changing from relatively calm to extremely harsh in a short period. The frequent strong winds and blizzards in this region will form high-density ice crystals and snow particles in the atmosphere. These suspended particles will have a strong absorption and scattering effect on radio wave signals, causing a sharp attenuation of the signal energy during the process of penetrating the atmosphere to reach the satellite or from the satellite to the ground device, a significant decrease in the signal-to-noise ratio, and even complete signal blocking, making it impossible to establish an effective communication connection. This means that traditional positioning information backhaul devices and methods mainly designed for mid- and low-latitude regions fail to fully consider the drastic deterioration and unreliability of the signal propagation path caused by harsh weather in terms of signal processing algorithms and environmental adaptability. As a result, in practical applications, once extreme weather is encountered, there is a risk of complete communication interruption, making it difficult to meet the data backhaul requirements for activities such as polar scientific expeditions.

[0004] In view of the above problems and limitations of the existing technology in the special polar environment, the present invention aims to provide a method and device for backhauling polar activity information. By optimizing the data processing flow and transmission strategy, this method and device can significantly improve the success rate and reliability of positioning information backhaul in the complex polar environment, and are particularly suitable for information backhaul application scenarios of various scientific research equipment or personnel-carrying equipment deployed in the polar region. Summary of the Invention

[0005] The present invention provides a method for backhauling polar activity information, which specifically includes the following steps:

[0006] S1: Collect polar vehicle condition information, positioning information, and weather image sequences;

[0007] S2: Predict the first signal window period for backhaul based on the current weather image sequence;

[0008] S3: Obtain the ID of the connectable communication satellite based on the communication module and predict the second signal window period for backhaul;

[0009] S4: Obtain the backhaul window using the first and second signal window periods for backhaul, sort the backhaul information based on the backhaul window, and complete the sending of the backhaul information.

[0010] The embodiments of this specification also propose a device for backhauling polar activity information, and this device includes:

[0011] Collection module: The collection module collects the working condition information, positioning information, and weather image sequence of the polar vehicle;

[0012] First signal window period determination module: Predict the first signal window period for backhaul based on the current weather image sequence

[0013] Second signal window period determination module: Obtain the ID of the connectable communication satellite based on the communication module and predict the second signal window period for backhaul;

[0014] Sorting module: The sorting module obtains the backhaul window using the first and second signal window periods for backhaul, sorts the backhaul information based on the backhaul window, and completes the sending of the backhaul information.

[0015] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned method for backhauling polar activity information is implemented.

[0016] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned method for backhauling polar activity information is implemented.

[0017] The prior art often uses fixed-period backhaul or only sends based on the current link quality. Such a backhaul method is difficult to cope with the drastic and rapid changes in the polar environment, especially extreme weather such as blizzards. The polar environment changes rapidly, and blizzards may not only completely block the satellite line-of-sight path, but also the large amount of ice crystals and snow particles it contains will cause a certain degree of scattering, attenuation, or signal quality degradation to the satellite signal, resulting in communication interruption or failure.

[0018] The present invention collects sky image sequences in real time and uses a time series prediction model to predict the sky state in the future for a period of time. In particular, the sky field of view is divided into refined grids Gij, and the occlusion probability of each grid is predicted, enabling accurate identification and prediction of local or large-scale blizzard occlusion areas and their spatio-temporal evolution trends. This refined and proactive weather occlusion prediction enables the backhaul device to actively avoid communication link interruptions caused by bad weather, no longer "blindly" transmit, but instead select sky areas and time periods predicted to be "unobstructed" for communication attempts, thereby fundamentally improving the data backhaul success rate under the influence of extreme weather such as blizzards.

[0019] In addition, the vast and flat ice and snow surface in the polar regions is a natural electromagnetic wave reflection surface, resulting in strong multipath effects being extremely likely to occur in domestic medium and low Earth orbit satellite communications, including those of State Grid, Hongyun Project, and Galaxy Space, when the satellite pitch angle is relatively low. The multipath signals interfere with the direct signals, causing signal fading and distortion, seriously affecting the communication quality and the accuracy of positioning information demodulation. By predicting the trajectory of the future available satellite s and mapping it to the sky grid Gij, the present invention not only determines the spatio-temporal position where the satellite is available, but more importantly, can estimate the communication link quality in combination with the predicted pitch angle information. This enables the communication strategy to preferentially select satellite communication opportunities with higher predicted pitch angles for data transmission, thereby actively avoiding or reducing the severe multipath interference caused by low pitch angles, selecting a communication link with a better and more reliable signal propagation path, and ensuring the integrity and accuracy of the backhaul data.

[0020] The present invention integrates two key constraint conditions that independently change, namely weather occlusion prediction and satellite availability and link quality prediction. By calculating the intersection of the two, the final backhaul window is obtained, which precisely indicates which time period in the future, through which area, and using which specific satellite s for communication, and simultaneously meets the weather conditions and satellite geometry and link quality conditions. Based on this spatio-temporal availability map, the present invention can implement an adaptive communication scheduling strategy: for example, arranging the most important and urgent information in the earliest available window with better quality; arranging large-volume and non-urgent information for transmission in a window with a longer predicted duration and a higher satellite elevation angle; or adopting strategies such as data compression and discarding when it is predicted that there will be no available window for a long time. This intelligent scheduling maximally avoids the waste of energy and communication resources caused by ineffective communication attempts under adverse conditions, and improves the overall operating efficiency and battery life of the backhaul device. Brief Description of the Drawings

[0021] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the accompanying drawings required for the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0022] Figure 1 It is a flowchart of the method for transmitting back polar activity information of the present invention. Specific embodiments

[0023] The following will describe the embodiments of the present application in detail with reference to the accompanying drawings.

[0024] The following illustrates the embodiments of the present application through specific examples. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts belong to the scope of protection of the present application.

[0025] It should be noted that the following describes various aspects of the embodiments within the scope of the appended claims. It should be obvious that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is illustrative only. Based on the present application, those skilled in the art should understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number and aspects described herein can be used to implement the device and / or practice the method. In addition, this device and / or this method can be implemented using other structures and / or functions in addition to one or more of the aspects described herein.

[0026] In addition, in the following description, specific details are provided for a thorough understanding of the examples. However, those skilled in the art will understand that the examples can be practiced without these specific details.

[0027] The embodiments of this specification propose a method for transmitting back polar activity information. The method specifically includes the following steps:

[0028] S1: Collect polar vehicle condition information, positioning information, and weather image sequences;

[0029] S2: Predict the first signal feedback window period based on the current weather image sequence;

[0030] S3: Obtain the connectable communication satellite IDs based on the communication module and predict the second signal feedback window period;

[0031] S4: Obtain the feedback window using the first and second signal feedback window periods, sort the feedback information based on the feedback window, and complete the transmission of the feedback information.

[0032] This embodiment provides a method for obtaining polar environment positioning information. The feedback device is deployed on polar exploration vehicles such as all-terrain vehicles. The feedback device includes, but is not limited to, a positioning module. During the process of obtaining positioning information, first, firmly install this feedback device in the all-terrain vehicle cockpit and correctly connect it to the external multi-mode GNSS antenna and vehicle power supply. After the device is started, the positioning module starts to work. The positioning module uses a multi-mode positioning chip that mainly uses the Beidou Navigation Satellite System (BDS), is compatible with the Global Positioning System (GPS) and the Global Navigation Satellite System (GLONASS) as the core component. The positioning module can scan and attempt to lock all visible BDS, GPS, and GLONASS satellite signals in real time. There is a signal priority discrimination and switching strategy preset inside the system. Specifically, the positioning module first evaluates the BDS signal quality. If it can stably track no less than five BDS satellites, and the signal strength of each satellite is higher than the preset threshold, and at the same time the Position Dilution of Precision (PDOP) is less than 3.0, then it is determined that the BDS signal state is good, and the positioning module preferentially uses the pure BDS solution mode to output the vehicle's real-time longitude, latitude, altitude, and time information.

[0033] Considering the complex polar environment, when the vehicle approaches an iceberg or enters a canyon area, it may cause partial BDS satellite signals to be blocked or interfered, resulting in a reduction in the number of available BDS satellites or a deterioration of the geometric configuration. If the positioning module detects that the PDOP value rises and exceeds the preset threshold at this time, the automatic switching mechanism is activated. This mechanism immediately evaluates the quality and quantity of the currently available GPS and GLONASS satellite signals. For example, when at least four GPS satellites and three GLONASS satellites can be stably received, the positioning module judges according to the internal fusion positioning algorithm that if the combined positioning of BDS and GPS can obtain the best positioning accuracy and reliability, and the combined PDOP value is reduced to 3.5, it will automatically switch to the BDS+GPS combined solution mode, use the satellite signals of the two navigation systems for fusion positioning, and output optimized and more reliable position information. In the actual environment, if GPS or GLONASS alone or in combination with other systems can provide better solution results, the positioning module will also automatically switch to the corresponding solution mode. The entire switching process is automatically completed inside the module, ensuring that even in the complex polar environment, the positioning module can continuously and stably obtain and output high-precision and reliable vehicle positioning information.

[0034] In one embodiment, the feedback device includes an image receiving module for receiving a sequence of sky images collected externally. On the top of the polar all-terrain vehicle, an independent image acquisition device is installed. The external image acquisition device has a lens that can be adjusted according to requirements and is adjusted to face the sky vertically when collecting a sequence of sky images, and high-resolution images covering the entire sky range can be obtained. The image acquisition device is connected to a designated external data interface of the feedback device installed in the vehicle cabin through a shielded data cable, and at the same time, the vehicle power supply system provides power supply guarantee for the imager. During the vehicle's mission, the image acquisition device operates automatically according to a preset program. The image acquisition device is set to automatically take a sky image at a preset acquisition cycle, and the image content includes the current date and timestamp information. Whenever the image acquisition device completes the shooting of an image, it immediately transmits the image data file to the feedback device via an Ethernet cable. The data access module of the feedback device is configured to continuously monitor the data stream of the external data interface. When detecting an image data file from the image acquisition device, the data access module immediately identifies, receives, and stores it in the internal buffer or a designated storage area. As the mission progresses, the feedback device can continuously receive and store the sky images taken by the external imager in chronological order, thus forming a time-series sky image sequence inside the device.

[0035] In a specific embodiment of the present invention, the device for transmitting the active positioning information of the polar vehicle further integrates the function of obtaining the real-time working condition information of the vehicle. The CAN controller in the data access module automatically monitors various working condition information broadcasted on the vehicle CAN bus by key components such as the engine control unit and the body control module. The system can actively filter and capture CAN messages containing the preset parameter group number, and these messages carry real-time data related to the vehicle running state. For example, the data access module can continuously receive and parse messages containing fuel level to obtain the current fuel percentage of the vehicle; parse messages containing engine speed to obtain the engine speed per minute; parse messages containing engine coolant temperature to obtain the current engine coolant temperature. In addition, the system can also parse information such as battery voltage, current gear, and activated diagnostic fault codes.

[0036] After the data access module receives the above CAN messages, the internal processor of the transmission device parses them based on the original data, extracts the corresponding original values, and these structured real-time working condition information including at least fuel quantity and engine state are sorted and packaged for integration with other data such as positioning information.

[0037] The first signal transmission window period predicted based on the current weather image sequence includes:

[0038] Based on the current moment t, the sky area that can be covered by the image acquisition device is divided into a fixed virtual grid G, is a specific area block in the sky, and i and j are the interval indexes of the pitch angle and azimuth angle respectively;

[0039] Each frame of the sky image sequence I is processed using a pre-trained image segmentation model , generating an occlusion map corresponding to each frame of the image ,

[0040] Based on the occlusion map Calculate the quantization occlusion state of each sky grid unit at time k ;

[0041] Using a preset time series prediction model, based on the historical state sequence Predict the occlusion state of each sky grid unit after l time periods ;

[0042] Based on the occlusion state of each sky grid unit after l time periods Obtain the first signal transmission window period.

[0043] The pre-trained image segmentation is an improved U-net network, and the improved U-net network consists of an encoder, a decoder, and an attention enhancement module;

[0044] Among them, the encoder uses a lightweight convolutional neural network such as EfficientNet-B0 as the backbone network, and the encoder receives each frame of image , and generates multi-scale feature maps through convolution and downsampling ;

[0045] The decoder includes an upsampling module and a convolutional layer. The decoder uses skip connections to fuse the corresponding feature maps of the encoder with the upsampled feature maps of the decoder at the corresponding spatial resolution, , , and are the feature maps of the q+1 and q layers of the decoding layer before and after fusion respectively. Concat and Up represent feature concatenation and upsampling respectively. The attention module is embedded in each skip connection to enhance the ability to recognize and locate the boundaries of cloud clusters or blizzard regions in the polar sky;

[0046] The output feature map of the last layer of the decoder is mapped to a single-channel segmentation map through 1×1 convolution and an activation function is applied to obtain a pixel occlusion probability map. Based on the segmentation threshold, the corresponding occlusion map is obtained ;

[0047] The quantization occlusion state is specifically expressed as: , where is the grid The total number of pixels contained, The value range of is [0,1], and the larger the value, the more serious the occlusion of the grid area.

[0048] Using a preset time series prediction model, using the historical state sequence Predict the occlusion state of each sky grid cell after l time periods Specifically include:

[0049] Using the historical state sequence Calculate the difference between adjacent state maps to obtain a motion feature sequence , for the first state of the sequence , its corresponding motion feature sequence is a zero tensor; Is spliced according to the grid position at the same moment , N and Δt represent the length of the historical image sequence and the acquisition time interval respectively;

[0050] The state map Is concatenated with its corresponding motion feature map On the channel dimension to form a composite feature map containing the current state and change information , and the input for constructing the preset time series model is finally input into the sequence of the prediction model ;

[0051] ;

[0052] An encoder containing ConvLSTM processes the input sequence in chronological order. The p-th layer of the encoder receives the hidden state sequence from the (p - 1)-th layer,

[0053] The final output of the encoder is the final hidden state and the cell state of the last layer after processing the entire input sequence X and the cell state , the final hidden state and the cell state encapsulate the spatio-temporal information of the historical N frames.

[0054] The internal calculation of the ConvLSTM cell includes:

[0055] ;

[0056] ;

[0057] ;

[0058] ;

[0059] ;

[0060] ;

[0061] where * represents the convolution operation, ⊙ represents the element-wise multiplication, σ is the Sigmoid function, and tanh is the hyperbolic tangent function, both are learnable weights and both are bias terms.

[0062] A decoder containing ConvLSTM processes the final state of the encoder as the initial state of all layers of the decoder for processing;

[0063] The input at the first time step of the decoder is a zero tensor. At the l-th time step of the decoder, l = 1...L, the decoder ConvLSTM network calculates the hidden state of the current step based on the state at the previous moment and the input at the current step, and takes the hidden state of the last layer of the decoder Generate the predicted occlusion probability map at this moment through an output convolutional layer and an activation function. For l < L, use the prediction result of the current step as the input for the next-step decoding. Continue the loop prediction to obtain a sequence containing L-frame prediction results. For the sequence Segment according to the virtual grid G to obtain the occlusion state after l time periods for each sky grid cell. .

[0064] Based on the occlusion state after l time periods for each sky grid cell Obtain the first feedback signal window period using loop judgment: For each grid , set the window start step index , window end step index to -1, and the boolean flag to false;

[0065] Use a loop to traverse the time step l from 1 to L to obtain the current occlusion state , and judge whether . If the current time step satisfies and the boolean flag is false, record the start index , update the boolean flag to True; if the current time step satisfies and the boolean flag is True, continue traversing; if the current time step does not satisfy , and the boolean flag is True, record the end index , and break out of the loop;

[0066] If the loop ends because all L steps have been traversed and the flag is true at the end, set the end index: ;

[0067] When , the first feedback signal window period of grid is determined as the time interval: ;

[0068] When , there is no available first feedback signal window for grid , and the time interval is empty;

[0069] Based on the time interval of each grid obtain the first feedback signal window of the virtual grid G. .

[0070] Before inputting the historical grid occlusion state information into the time series prediction model, the present invention adopts the state graph at the current moment k and its corresponding motion feature map to be concatenated in the channel dimension to form a composite feature map as the actual input of the model at this time step. By providing the time series prediction model with recent information on the trend changes in the occlusion area, rather than just an independent static state snapshot, the ability of the model to capture and understand the dynamic weather process is enhanced. Specifically, for a fast-moving snowstorm front or rapidly accumulating cloud clusters, they will show obvious signals on the map. For example, a positive value indicates an increase in occlusion or moving in, and a negative value indicates a decrease or moving out. This enables the model to more easily and accurately learn key dynamic features such as the moving speed, direction, and intensity change of the occlusion area. Compared with only relying on the recurrent network structure to infer motion information from the sequence, this explicit input of motion features reduces the difficulty for the model to learn dynamic patterns, accelerates the convergence process of the model, and improves the final prediction accuracy. Especially in the polar sky scene where the weather changes violently and there are few obvious texture details, directly using the provided change signals helps the model distinguish between static continuous occlusion and dynamic occlusion changes, so as to make a more accurate and physically consistent prediction of the evolution of the future occlusion state .

[0071] In addition, when analyzing the sky image sequence involved in the present invention, the present invention does not take into account the problem that the image acquisition platform, i.e., the polar vehicle, may be in a small-scale operation state, resulting in the images continuously acquired not strictly coming from the same geographical coordinate point. However, it can be reasonably considered that this offset of the observation position introduced by the small-scale movement of the vehicle has no substantial impact on the accuracy of subsequent weather occlusion prediction based on sky grid division. The target of the prediction of the present invention is weather phenomena that affect satellite communication links, such as moving cloud masses, large-scale blowing snow, or distant blizzard cloud walls. These phenomena are usually at a considerable distance from the ground observation point, and the scale range is often hundreds of meters to several kilometers or more. In comparison, the moving distance of the vehicle in small-scale operations is much smaller than the distance from the vehicle to the observed weather phenomena. Therefore, the parallax effect caused by the vehicle movement is extremely small, that is, for the same distant weather feature in the images continuously captured before and after, its apparent position and apparent shape relative to the camera's field of view will hardly change perceptibly due to this displacement of dozens of meters. Secondly, the defined sky grid Gij is divided based on the pitch angle and azimuth angle of the vehicle's local coordinate system. As long as the vehicle's attitude remains relatively stable during small-scale movement, this relative grid reference system is stable. Combining the characteristic of small parallax effect, this means that if a weather feature occupies grid Gij at time t, at time t+Δt, even if the vehicle's position changes slightly, the weather feature will still mainly occupy the same grid Gij. The subsequent time series prediction model aims to learn and predict the law of the occlusion state evolution over time within each grid cell Gij. This evolution is mainly driven by the macroscopic movement, development, or dissipation of the weather system itself. The tiny apparent position jitter introduced by the small-scale movement of the vehicle is more like weak noise superimposed on the main signal compared to the changes of the weather system itself. The time series prediction model usually has a certain robustness to this kind of noise and can still effectively capture and predict the main dynamic trends of the weather pattern. Therefore, when processing the sky image sequence in the small-scale operation scenario, the present invention approximately regards the observation point as quasi-static, and its impact on the accuracy of the final weather occlusion prediction and communication window planning is within an acceptable range.

[0072] Based on the communication module, obtain the ID of the connectable communication satellite and predict the second backhaul signal window period;

[0073] Among them, obtaining the ID of the connectable communication satellite based on the communication module includes:

[0074] Perform real-time handshake to determine the current available satellite set ;

[0075] Using the positioning information obtained by the backhaul device, the communication module executes a scanning program to attempt to search for and lock the available communication satellite signals within the field of view;

[0076] For satellites whose signal strength reaches a preset threshold, the communication module actively initiates a communication handshake request, records the unique identifier IDs of all satellites that successfully establish connections during this scan and handshake attempt, and forms the current set of available satellites. Record the number of satellites. .

[0077] Predict the future trajectories of the current available satellites.

[0078] For each satellite s in

[0079] , retrieve the corresponding TLE data of the satellite according to its ID; Using the standard orbit propagation SGP4 or SDP4 model, input the TLE data, time t, and positioning information, and calculate the spatial positions of satellite s at the next L discrete time points Retain the predicted position points with the pitch angle greater than or equal to the preset minimum pitch angle threshold.

[0080] An exemplary implementation of predicting position point data is performed by the following pseudocode:

[0081] from skyfield.api import Topos, load, EarthSatellite

[0082] from datetime import datetime, timedelta

[0083] import pytz

[0084] # Example latitude and longitude definition

[0085] observer_latitude_deg = -69.4 # Polar vehicle latitude (degrees)

[0086] observer_longitude_deg = 76.4 # Polar vehicle longitude (degrees)

[0087] observer_elevation_m = 18.0 # Polar vehicle altitude (meters)

[0088] observer = Topos(latitude_degrees=observer_latitude_deg,

[0089] longitude_degrees=observer_longitude_deg,

[0090] elevation_m = observer_elevation_m)

[0091] Taking the TLE of a satellite (IRIDIUM 145 - NORAD ID 42791) as an example, the TLE data is obtained from CelesTrak.org.

[0092] tle_line1 = '1 42791U 17036E 25111.30000000 .00000XXX 00000-0 XXXXX-X0 999X'

[0093] tle_line2 = '2 42791 86.3999 150.0000 000XXXX 80.0000 280.000014.34100000XXXXXX'

[0094] satellite_name = "IRIDIUM 145

[0095] ts = load.timescale()

[0096] try:

[0097] satellite = EarthSatellite(tle_line1, tle_line2, satellite_name,ts)

[0098] except ValueError as e:

[0099] print(f"Error creating satellite object from TLE: {e}")

[0100] satellite = None

[0101] current_time_utc = datetime.now(pytz.utc)

[0102] prediction_offset_minutes = 10

[0103] future_time_utc = current_time_utc + timedelta(minutes = prediction_offset_minutes)

[0104] skyfield_time_now = ts.from_datetime(current_time_utc)

[0105] skyfield_time_future = ts.from_datetime(future_time_utc)

[0106] if satellite:

[0107] try:

[0108] difference = satellite.at(skyfield_time_future) - observer.at(skyfield_time_future)

[0109] elevation, azimuth, distance = difference.altaz()

[0110] print(f"Target satellite: {satellite.name} (NORAD ID:{satellite.model.satnum})")

[0111] print(f"Predicted UTC time (t'): {future_time_utc.strftime('%Y-%m-%d %H:%M:%S')} UTC ({prediction_offset_minutes} minutes after t)")

[0112] print("-" * 100)

[0113] print(f"Predicted satellite position (at t'):")

[0114] print(f" Azimuth (A): {azimuth.degrees:.2f} degrees")

[0115] print(f" Elevation (E): {elevation.degrees:.2f} degrees")

[0116] Check if the elevation angle is higher than the minimum requirement

[0117] E_min_check = 10.0 # Assume the minimum visible elevation angle is 10 degrees

[0118] if elevation.degrees >= E_min_check:

[0119] print(f" The satellite is above the minimum elevation angle threshold ({E_min_check}°).")

[0120] else:

[0121] print(f" The satellite is below the minimum elevation angle threshold ({E_min_check}°).")

[0122] except Exception as e:

[0123] print(f"Error occurred during satellite position calculation: {e}")

[0124] else:

[0125] print("Failed to create a satellite object from the provided TLE data, unable to perform calculations.")

[0126] Map the satellite positions to the grid and record the availability;

[0127] Initialization: GridAvailability = {}, for all valid grid indices (i,j), initialize GridAvailability[(i,j)] = []

[0128] For each , obtain a time series of valid spatial position coordinates , and map them to the grid indices in the virtual grid G to obtain the time series of grid indices for each satellite s;

[0129] Add the information indicating that satellite s is available for the grid at time step l, as a tuple (s, l), to the list of the corresponding grid, GridAvailability[(i_l, j_l)].append((s, l))

[0130] For any grid , the list GridAvailability[(i,j)] contains all the information pairs (s, l) of satellite s that will appear in this grid at some future time step l and come from the set, where l ∈ {1,...,L}.

[0131] For each sky grid , its second downlink signal window period is a set that contains all discrete time step indices l in the grid where there is at least one satellite from available. Also, for each available time step l, it is possible to identify which satellites are available based on their tuples (s, l).

[0132] Traverse the tuples (s, l) in each grid within the second downlink window and check whether its available period overlaps with the available time period of the first downlink signal window to integrate the first downlink signal window and the second downlink signal window period to obtain the final downlink window;

[0133] In a specific embodiment, based on the final downlink window, sort the downlink information. To complete the sending of downlink information, it is necessary to define the priorities of different data types:

[0134] The highest priority is set to emergency status or critical fault information, the higher priority is set to positioning information and key operating condition parameters, and the key operating condition parameters include: fuel percentage, engine speed, coolant temperature, battery voltage. The medium priority includes system logs, and the lower priority includes historical data and ordinary short messages. The system extracts all future available downlink windows, and each window is associated with specific satellites and time periods. Synchronously obtain all current data items to be sent, and send the data in sequence according to the priority.

[0135] A method for downlinking polar activity information, which specifically includes the following steps:

[0136] S1: Collect polar vehicle operating condition information, positioning information, and weather image sequences;

[0137] S2: Predict the first downlink signal window period based on the current weather image sequence;

[0138] S3: Obtain the connectable communication satellite IDs based on the communication module and predict the second downlink signal window period;

[0139] S4: Obtain the downlink window using the first and second downlink signal window periods, sort the downlink information based on the downlink window, and complete the sending of downlink information.

[0140] This embodiment of the specification also proposes a device for downlinking polar activity information, which includes:

[0141] Collection module: The collection module collects polar vehicle operating condition information, positioning information, and weather image sequences;

[0142] First downlink signal window period determination module: Predict the first downlink signal window period based on the current weather image sequence

[0143] Second signal feedback window determination module: Based on the communication module, obtain the ID of the connectable communication satellite and predict the second signal feedback window period;

[0144] Sorting module: The sorting module uses the first and second signal feedback window periods to obtain a feedback window, sorts the feedback information based on the feedback window, and completes the sending of the feedback information.

[0145] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-mentioned method for transmitting polar activity information is implemented.

[0146] A computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the above-mentioned method for transmitting polar activity information is implemented.

[0147] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned method embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above-mentioned method embodiments. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0148] In this specification, the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the embodiments described later, the description is relatively simple, and the relevant parts can be referred to the partial description of the foregoing embodiments.

[0149] As described above, it is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present application should be covered within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for transmitting back polar activity information, characterized in that The method includes: S1: Collect the working condition information, positioning information and weather image sequence of the polar vehicle; S2: Predict the first backhaul signal window period based on the current weather image sequence; S3: Obtain the connectable communication satellite ID based on the communication module and predict the second backhaul signal window period; S4: Obtain the backhaul window using the first and second backhaul signal window periods, sort the backhaul information based on the backhaul window, and complete the sending of the backhaul information; The predicting the first backhaul signal window period based on the current weather image sequence includes: Based on the current moment t, the sky area that can be covered by the image acquisition device is divided into a fixed virtual grid G, where G ij is a specific area block in the sky, and i and j are the interval indices of the pitch angle and the azimuth angle respectively; Process each frame image I corresponding to the sky image sequence I using a pre-trained image segmentation model k , generate an occlusion map O corresponding to each frame image k , Based on the occlusion map O k Calculate the quantized occlusion state S of each sky grid cell at time k ij，k ; Based on the historical state sequence S, using a preset time series prediction model hist Predict the occlusion state of each sky grid cell after l time periods Occlusion state after l time periods for each sky grid cell Obtain the first backhaul signal window period.

2. The method for transmitting back polar activity information according to claim 1, wherein Using a preset time series prediction model, based on the historical state sequence S hist Predict the occlusion state of each sky grid cell after 1 time period Specifically including: Using the historical state sequence S hist = {S k | k = t, t - Δt,..., t - (N - 1)Δt} Calculate the difference between adjacent state diagrams to obtain the motion feature sequence ΔS k = S k - S k-1 , for the first state S t-(N-1)Δt of the sequence, its corresponding motion feature sequence is a zero tensor; S k is concatenated by S ij，k at the same moment according to the grid positions, where N and Δt represent the length of the historical image sequence and the acquisition time interval respectively; The state diagram S k and its corresponding motion feature diagram ΔS k are concatenated in the channel dimension to form a composite feature diagram X containing the current state and change information k , and the input of the preset time series model is constructed and finally input into the sequence X of the prediction model = {X k |k = t, t - Δt, …, t - (N - 1)Δt}.

3. A method for transmitting back polar activity information according to claim 2, characterized in that: Wherein obtaining the connectable communication satellite ID based on the communication module includes: Perform a real-time handshake to determine the current set S of available satellites current_vis , for satellites with signal strength reaching the preset threshold, the communication module actively initiates a communication handshake request, records the unique identifier IDs of all satellites that successfully establish connections during this scan and handshake attempt, and forms the current set S of available satellites current_vis , record the number of satellites N sat .

4. A method for transmitting back polar activity information according to claim 3, characterized in that: Predicting the second downlink signal window period includes: predicting the future trajectories of currently available satellites; mapping satellite positions to a grid and recording availability; for each sky grid G ij , its second downlink signal window period W SatAvail (i, j) is a set that contains all the discrete time step indices l at which at least one satellite from S current_vis is available in the grid. For each available time step l, identify which satellites are available based on their tuples (s, 1).

5. A method for transmitting back polar activity information according to claim 4, characterized in that: Traverse the tuples (s, 1) in each grid in the second backhaul window period, and check whether its available time period coincides with the available time period of the first backhaul signal window, and integrate the first backhaul signal window and the second backhaul signal window period to obtain the final backhaul window.

6. A method for transmitting back polar activity information according to claim 5, characterized in that: Using the standard orbit propagation SGP4 or SDP4 model, inputting the TLE data, the time t, and the positioning information, calculate the spatial position of the satellite s at the future t discrete time points t′ = t + lΔt, and retain the predicted position points where the pitch angle is greater than or equal to the preset minimum pitch angle threshold E min of the predicted position points.

7. A device for transmitting back polar activity information, which is used to execute a method for transmitting back polar activity information according to any one of claims 1-6, characterized in that The device includes: Collection module: The collection module collects the working condition information, positioning information and weather image sequence of the polar vehicle; First backhaul signal window period determination module: Predict the first backhaul signal window period based on the current weather image sequence; Second backhaul signal window period determination module: Obtain the connectable communication satellite ID based on the communication module and predict the second backhaul signal window period; Sorting module: The sorting module obtains the backhaul window using the first and second backhaul signal window periods, sorts the backhaul information based on the backhaul window, and completes the sending of the backhaul information.

8. An electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where when the processor executes the computer program, it implements a method for backhauling polar activity information as described in any one of claims 1-6.

9. A computer-readable storage medium, where the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements a method for backhauling polar activity information as described in any one of claims 1-6.

Images