Airplane multi-network fusion data real-time transmission and distribution system

Abstract

The invention relates to the technical field of digital information transmission, and discloses an aircraft multi-network fusion data real-time transmission and distribution system which comprises a physical layer state monitoring module, a transmission quality deduction engine, a deduction routing engine and a mapping model calibration module. Deducing a transmission quality index based on the transmission layer-physical layer mapping model so as to guide a routing engine to distribute data packets; meanwhile, the calibration module utilizes actual transmission layer feedback of a data packet to dynamically correct the mapping model, active measurement is replaced by passive deduction, information lag and resource occupation are avoided, and the problem of drifting failure of a deduction model in a complex environment is solved by introducing a self-calibration closed loop.

Description

TECHNICAL FIELD

[0001] The application relates to a real-time data transmission and distribution system for aircraft multi-network fusion, and belongs to the technical field of digital information transmission. BACKGROUND

[0002] One of the current core tasks is to plan the optimal transmission path for data packets in a complex network environment. For this purpose, existing network decision systems generally rely on active measurement methods, that is, the system actively sends probe data packets to measure the quality of different transmission links such as time delay, packet loss, etc., and then makes routing or distribution decisions based on these measurement results. However, when this effective decision-making method in ground networks is applied to the specific scenario of aircraft multi-network fusion, it exposes inherent operational constraints in application. The environment in which the aircraft is located combines high-latency satellite links, bandwidth-scarce backup links, and dynamically changing ground cellular networks, making it logically difficult to balance the active measurement behavior: on the one hand, for bandwidth-scarce links, the probe packets themselves will occupy valuable transmission resources, and their measurement behavior itself will interfere with business data; on the other hand, for high-latency links, due to the high mobility of the aircraft, when the system receives the measurement report from the previous time, the aircraft's attitude or position may have already changed, and the real state of the link may not be the same as at that time, resulting in a lag in the decision-making basis.

[0003] For this situation, linear improvements attempted by those skilled in the art, such as adjusting the probe frequency, cannot fundamentally solve this constraint; if the probe frequency is reduced to avoid resource occupation, the link state information on which the decision is based will become even more outdated, and the system will be unable to respond to instantaneous changes in the link; if the probe frequency is increased to pursue real-time performance, it will further exacerbate the occupation of scarce link resources, and even frequent switching based on outdated information may cause routing oscillation, so that the system decision is always limited by the trade-off between information lag and measurement overhead. In addition to the limitations of the above-mentioned active measurement method, there are other schemes in the art that attempt to alleviate network congestion from the application layer, for example, Chinese patent CN116389374A discloses a method for adaptive adjustment of data distribution throughput in a multi-robot system in a SLAM scenario, which attempts to estimate the upper limit of throughput through an online learning algorithm, and to distinguish between data types by discarding image frames with lower utility to adapt to the network. However, the technical basis of this method is to rely on the observation of message time delay to infer the network state. This mechanism that relies on time delay feedback at the transmission layer or application layer has inherent lag when applied to the high-latency, high-dynamic aircraft network environment. When the system makes decisions based on outdated time delay data, the network link state of the aircraft may have already changed. This scheme still does not fundamentally solve the problem of information lag in extreme conditions and cannot meet the demand for real-time and high-fidelity decision-making in the aircraft multi-network fusion scenario.

[0004] Therefore, how to construct a new data transmission decision mechanism, which can obtain the real transmission quality of multiple heterogeneous links without relying on active probing and without occupying the service bandwidth, and distribute the data packets of different service levels in real time and stably based on the transmission quality, becomes a technical problem to be solved by the application. SUMMARY

[0005] The application provides an aircraft multi-network fusion data real-time transmission and distribution system, which mainly aims to solve the problem that the information lag or resource occupation caused by relying on active probing in the prior art cannot realize real-time and efficient distribution of aircraft multi-network data.

[0006] To achieve the above-mentioned purpose, the application provides an aircraft multi-network fusion data real-time transmission and distribution system, which comprises: A physical layer state monitoring module is configured to obtain physical layer statistics from multiple heterogeneous network interfaces carried by the aircraft. A transmission quality deduction engine is configured to deduce the physical layer statistics into transmission quality indexes representing the transmission quality of the multiple heterogeneous network interfaces based on a transmission layer-physical layer mapping model. A deduction routing engine is configured to select a target transmission interface for a data packet to be transmitted based on the transmission quality indexes output by the transmission quality deduction engine, and distribute the data packet via the target transmission interface. A mapping model calibration module is configured to obtain the physical layer statistics, obtain actual transmission layer feedback of the data packet distributed via the target transmission interface, and dynamically correct the transmission layer-physical layer mapping model when there is a preset deviation between the actual transmission layer feedback and the transmission quality indexes deduced by the transmission quality deduction engine based on the physical layer statistics.

[0007] Preferably, the deduction routing engine further comprises a slow passive check loop configured to passively monitor the transmission layer feedback of the data packet distributed via the target transmission interface to generate the actual transmission layer feedback.

[0008] Preferably, the transmission layer-physical layer mapping model is a static transmission quality deduction lookup table, and the mapping model calibration module is configured to dynamically correct the entries in the transmission quality deduction lookup table when the preset deviation exists.

[0009] Preferably, the system further comprises a message service level identification module configured to classify the data packet based on a preset policy rule library to determine the service level of the data packet, and the deduction routing engine is further configured to jointly select the target transmission interface based on the service level of the data packet and the transmission quality indexes.

[0010] Preferably, the physical layer statistics include one or more of signal-to-noise ratio (SNR), bit error rate (BER), and received signal strength indication (RSSI).

[0011] Preferably, the transmission quality indicators include one or more of the following: the estimated packet loss rate or the estimated latency.

[0012] Preferably, the system further includes a downlink quality signaling encapsulation module; the downlink quality signaling encapsulation module is used to obtain the transmission quality indicators that characterize the downlink of the aircraft output by the transmission quality inference engine, generate the transmission quality indicators into status messages, and encapsulate the status messages in data packets distributed by the inference routing engine and sent to the ground station.

[0013] Preferably, the system also includes a communication health trend analysis module; the communication health trend analysis module is used to archive the transmission quality indicators output by the transmission quality inference engine within a historical time period, perform statistical trend analysis on the transmission quality indicators within the historical time period, and generate a communication system maintenance alarm when the result of the statistical trend analysis meets the preset maintenance threshold.

[0014] Preferably, the communication health trend analysis module is used to calculate the slope of the degradation trend when performing statistical trend analysis. : ,in, For transmission quality indicators at the first historical time point The rolling average, For transmission quality indicators at the second historical time point The rolling average value of the communication health trend analysis module in terms of the slope of the degradation trend. When the preset positive slope threshold is exceeded, a communication system maintenance alarm is generated.

[0015] Preferably, the system also includes a network mapping data collection module; the network mapping data collection module is used to obtain non-transmission quality event logs representing the operating status of heterogeneous network interfaces from the physical layer status monitoring module, obtain current geographical location information from the airborne navigation system, generate network mapping data packets based on the event logs and current geographical location information, and submit the network mapping data packets to the inference routing engine for low-priority distribution to the ground network planning server.

[0016] Compared with the prior art, the beneficial effects of the present invention are: 1. The system of the present invention establishes a new data transmission decision-making method. It uses a cross-layer status monitoring module to obtain physical layer statistics, and generates transmission quality indicators that characterize the link status through a quality inference engine. These indicators serve as the basis for the distribution of the inference routing engine. This technical approach replaces the process of actively sending probe packets for link measurement with the passive acquisition of physical layer data. This allows the state perception of low-speed, high-latency channels to no longer come at the cost of occupying channel resources or acquiring outdated information, thus ensuring the real-time performance and effectiveness of data transmission decisions in complex network convergence environments.

[0017] 2、Through the quality deduction engine, transmission quality indicators of each heterogeneous network are obtained, and at the same time, a message service level identification module determines the service level of the data packet to be sent; when making distribution decisions, the deduction routing engine can consider the information of the two dimensions in coordination, guide the data packet of high service level to the deduced low latency link, and distribute the data packet of low service level to the deduced low cost link, realize differentiated and refined routing based on service intention, and avoid blind competition of key data and non-key data for high-quality links.

[0018] 3、Through the communication health trend analysis module, the transmission quality indicators generated by the quality deduction engine in the historical period are archived and statistically analyzed; this mechanism multiplexes the instantaneous deduction data serving real-time routing decisions into the basis for representing the state of hardware health in a non-real-time long period, so that the system can distinguish between the instantaneous fluctuation of the channel and the chronic degradation of the hardware, and provides objective decision support for the predictive maintenance of the communication system, and expands the management and maintenance capability of the data transmission system. BRIEF DESCRIPTION OF DRAWINGS

[0019] Fig. 1 The system architecture diagram of the cross-layer deduction and closed-loop calibration of the application; Fig. 2 The link allocation effect diagram of different service level CoS of the application; Fig. 3 The core mechanism overview diagram for realizing high-reliability data distribution of the application. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical scheme and advantages of the application clearer, the technical scheme of the application will be described in detail below. Obviously, the described embodiments are part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the application.

[0021] The application provides a kind of aircraft multi-network fusion data real-time transmission and distribution system, which is built on the basis of airborne computing platform, and its core purpose is to solve the inherent resource squeeze and information lag problem of traditional active detection mechanism when aircraft is in the interface of multiple heterogeneous networks such as high-orbit satellite, ground 5G, airborne network, etc.The system architecture logically includes a physical layer state monitoring module, a transmission quality deduction engine, a deduction routing engine and a mapping model calibration module, which work together in a zero-overhead cross-layer deduction manner to replace the traditional measurement-action paradigm, realize real-time, efficient and high-reliability distribution of data packets;The physical layer state monitoring module acts as a passive cross-layer information collector in the system, which does not send any active probe data packet, but accesses multiple heterogeneous network interfaces carried by the aircraft through standard management interfaces such as Simple Network Management Protocol (SNMP) or dedicated API at a high frequency and periodically (for example, every 100ms), These interfaces correspond to the bottom Modem, and the physical layer state monitoring module obtains the physical layer statistics measured by these devices to maintain their own link, which provides non-layer raw data input for routing decision, which can include one or more of signal-to-noise ratio (SNR), bit error rate (BER) and received signal strength indication (RSSI);Transmission quality deduction engine is used to convert the physical layer statistics obtained by physical layer state monitoring module into the performance indicators required for routing decision at transmission layer, The input of the engine is the physical layer statistics such as Satcom interface, SNR=7dB, and the transmission layer-physical layer mapping model is built in, In a simple and efficient implementation, the mapping model can be implemented as a static transmission quality deduction lookup table, which is generated by offline laboratory calibration in the development stage, which establishes a deterministic mapping relationship between the indicators and KPIs, Transmission quality deduction engine performs a one-time lookup table operation, and a set of deduced transmission quality indicators can be output, Transmission quality indicators can include deduced packet loss rate or deduced latency, For example, the input of Satcom interface, SNR=7dB, its lookup table output can correspond to Est.Loss=1.5%, Est.Latency=750ms.

[0022] The system can also include a packet service level identification module that classifies the data packet before the routing engine works, which determines the service level of the data packet according to a preset policy rule library based on the header field of the data packet, such as the Differentiated Services Code Point (DSCP) mark, VLAN tag, source / destination IP address, or target port number, for example, identifying the air traffic control (ATC) instruction data packet as CoS-1 level, identifying the airline operation control (AOC) data packet as CoS-2 level, and identifying the passenger Wi-Fi data packet as CoS-3 level; the routing engine is the final decision and distribution execution unit of the data packet, which obtains the CoS level of the data packet from the packet service level identification module at the same time when receiving the data packet, and obtains the real-time transmission quality index of all available network interfaces from the transmission quality inference engine, which selects the target transmission interface based on the service level of the data packet and the transmission quality index. Specifically, the cost function dependent on the service level is executed, for example, the cost function of the CoS-1 level data packet can be defined as only minimizing the inference delay (Cost = Est. Latency); while for the CoS-3 level data packet, the cost function can be defined as minimizing the transmission cost (Cost = Est. Cost_Per_Bit), and the routing engine selects the network interface with the lowest calculation cost as the target transmission interface for the data packet, and sends the data packet out through the target transmission interface; to solve the inference inaccuracy problem caused by the dynamic drift of the transmission layer-physical layer mapping model in the physical environment (such as the appearance of a new interference type), the system also includes a mapping model calibration module for closed-loop adaptive correction of the inference model. To achieve this function, the routing engine can also include a slow passive verification loop, which passively monitors the actual feedback of the transmission layer such as the TCP protocol, the actual retransmission rate or the actual packet loss rate to generate the actual transmission layer feedback. The mapping model calibration module runs in the background at a low priority to obtain physical layer statistics (such as SNR = 10 dB), and obtain the actual transmission layer feedback (such as ActualLoss = 5%) on the same link generated by the verification loop, and obtain the transmission quality index (such as Est. Loss = 1%) inferred based on the SNR = 10 dB from the transmission quality inference engine. When the actual transmission layer feedback (5%) and the inferred transmission quality index (1%) have a preset deviation (such as a deviation lasting more than a threshold), the mapping model calibration module is activated to dynamically correct the transmission layer-physical layer mapping model. In the implementation of the model as a lookup table, the correction action specifically rewrites the corresponding entry in the lookup table, and corrects the Est. Loss value corresponding to SNR = 10 dB from 1% to 5% which is closer to the actual situation.

[0023] To solve the problem of downlink routing failure caused by the asymmetry of uplink and downlink quality, the system can also include a downlink quality signaling packaging module. Since the receiver statistics at the aircraft end, such as the downlink SNR, are also obtained by the physical layer state monitoring module, and the transmission quality indicators of the downlink are deduced by the transmission quality deduction engine, the downlink quality signaling packaging module is used to obtain a set of transmission quality indicators representing the downlink, generate them as compact state messages (such as [Satcom: Loss = 90%], [5G: Loss = 0.1%]), and use signaling piggybacking to package the state messages in the reserved field or payload of any regular uplink data packet (such as AOC report) distributed by the deduced routing engine. After receiving this uplink packet, the ground network device parses the piggybacked information to instantly know the downlink live of the aircraft end, and optimizes its downlink routing decision accordingly to avoid sending critical data to the failed link (such as Satcom). To extend the function of the system from real-time tactical routing to long-period strategic maintenance, the system can also include a communication health trend analysis module. This module is used to start at a non-real-time period (such as after the aircraft lands), archive the transmission quality indicators (such as the deduced packet loss rate) output by the transmission quality deduction engine in a historical time period (such as the past 100 flight hours), and perform statistical trend analysis on the transmission quality indicators in the historical time period. This analysis is used to distinguish between transient fluctuations of the channel and chronic degradation of the hardware. In specific embodiments, the statistical trend analysis is used to calculate the degradation trend slope which can follow the calculation wherein, is the rolling average of the transmission quality indicator at the first historical time point, is the rolling average of the transmission quality indicator at the second historical time point; when the result of the statistical trend analysis (such as ) meets the preset maintenance threshold, for example, the degradation trend slope exceeds the preset positive slope threshold (such as +0.01% Loss / flight hour), it indicates that the / link has chronic performance decline, and the module will generate a communication system maintenance alarm for the maintenance personnel to conduct predictive troubleshooting; in addition, to reuse the byproducts of the physical layer information to provide network planning value, the system can also include a network mapping data collection module. This module obtains the event logs generated by the modem in daily operation, which are not of the transmission quality type, from the physical layer state monitoring module. Such logs, taking signal search / reacquisition events as an example, contain network coverage information. The collection module obtains the current geographic location information from the onboard navigation system at the same time as obtaining such event logs, and generates a network mapping data packet based on the event logs and the current geographic location information. This data packet is marked as the lowest service level, such as CoS-4, and submitted to the deduced routing engine. The deduced routing engine automatically delays this non-emergency data packet to the link with the lowest cost, such as the ground Wi-Fi, and then distributes it to the ground network planning server with low priority.

[0024] Example 1: In a high-speed flight mission, the aircraft simultaneously accesses a high-latency satellite communication interface (Satcom) and a dynamically available ground cellular network interface (5G). When the aircraft is in the en-route cruise phase, the 5G interface is temporarily unavailable, and the only communication outlet for the system is the Satcom interface. At this time, the aircraft encounters a physical layer interference that causes the signal-to-noise ratio (SNR) of the physical layer to be at a medium level, for example, 10 dB, as obtained by the physical layer state monitoring module. However, the actual burst loss rate (Actual Loss) of the transmission layer is abnormally high, reaching 10%. This mapping deviates from the system's initial calibrated transmission layer-physical layer mapping model. In the initial static lookup table, the deduced loss rate Est.Loss corresponding to SNR = 10 dB is only 1%. Under this working condition, when a high-service-level (CoS-1, for example, air traffic control instructions) data packet arrives, the transmission quality deduction engine reports to the deduction routing engine that the deduced loss rate of the Satcom interface is 1% based on its static lookup table. Based on this deduced index, the deduction routing engine distributes the CoS-1 data packet via the Satcom interface, but the data packet encounters a 10% actual loss in the transmission layer, resulting in transmission failure.

[0025] The slow passive check loop built into the deduction routing engine obtains the actual transmission layer feedback of the data packet, Actual Loss = 10%, by monitoring the retransmission or failure feedback of the transmission layer (such as TCP). The mapping model calibration module obtains this actual transmission layer feedback in the background and compares it with the transmission quality index (Est.Loss = 1%) deduced by the transmission quality deduction engine based on the same physical layer statistic (SNR = 10 dB). When the system determines that there is a preset deviation between the actual value and the deduced value, the mapping model calibration module is immediately activated to perform dynamic correction, dynamically correcting the Est.Loss entry corresponding to the SNR = 10 dB interval in the transmission layer-physical layer mapping model (lookup table) from 1% to 10%. Later, when the aircraft approaches the land, the 5G interface becomes available, and the physical layer state monitoring module obtains the physical layer statistics of the 5G interface. The transmission quality deduction engine deduces the transmission quality index (such as Est.Loss = 0.1%, Est.Latency = 50 ms) of the 5G interface. At this time, when another CoS-1 data packet arrives, the link state obtained by the deduction routing engine from the transmission quality deduction engine changes to: Satcom interface (Est.Loss = 10%, after calibration) and 5G interface (Est.Loss = 0.1%). Based on the low-latency, low-loss rate cost function of the CoS-1 data packet, the deduction routing engine instantaneously selects the 5G interface with better transmission quality index as the target transmission interface and distributes the data packet via the 5G interface.

[0026] Embodiment 2: To objectively verify the cross-layer deduction method adopted by the system of the present application, compared with the active measurement method, the response ability to instantaneous link changes in high dynamic aviation scenarios, a network simulation test platform is constructed, which simulates a high-speed aircraft, the interface of which includes: high-latency satellite interface (Satcom), the baseline round-trip time RTT is set to 600 ms, and the baseline packet loss rate is 0.1%; low-latency ground interface (5G), the baseline RTT is 40 ms, and the baseline packet loss rate is 0.01%; the simulation platform can simulate the change of physical layer channel quality and accurately measure the actual delay and packet loss of data packet transmission; set the control group and the sample group of the present application, the control group adopts the active measurement method, the routing decision unit sends the Ping to the Satcom and 5G interface with a fixed period of 1.0 seconds, and updates the routing table according to the returned measurement delay and packet loss rate; the sample group of the present application adopts the cross-layer deduction method, does not send any active probe packet, and the physical layer state monitoring module obtains the physical layer statistics (SNR) from the virtual interface of the simulation platform with a period of 100 ms, the transmission quality deduction engine deduces the transmission quality index according to the transmission layer-physical layer mapping model (static lookup table), and the deduction routing engine distributes accordingly; the test scenario is set as follows: the 5G interface encounters instantaneous physical layer deep fading, at the test time T=0.5s, the SNR from the stable 25.3dB instantaneously drops to 4.1dB (corresponding to the actual packet loss rate >50%), the fading lasts for 800ms, and at T=1.3s, the SNR instantaneously recovers to 26.1dB; the test traffic is continuous and constant-rate CoS-1 level simulation data packet, during the test fading event, the decision behavior of the two groups of systems and the transmission performance of the CoS-1 data packet are recorded in Table 1.

[0027] Table 1: System response comparison table under instantaneous fading scenario

[0028] Referring to Table 1, at T=0.5s, the 5G link SNR instantaneously drops, the physical layer state monitoring module of the inventive sample group obtains the decaying SNR at T=0.6s (lagging 100ms sampling period), the transmission quality deduction engine instantaneously deduces that the 5G link packet loss rate rises to 55.8%, the deduction routing engine immediately switches all CoS-1 data packets to the Satcom interface with better transmission quality index at that time (deduced packet loss rate ≈0.1%), the actual time delay of the data packets rises to about 605ms accordingly, but the actual packet loss rate remains at a low level (0.11%); in contrast, the active probe packet of the control group returns the failure report at T=1.0s, the decision basis lags 500ms, which causes it to continue to send CoS-1 data packets to the 5G interface that has failed in the time window from T=0.5s to T=1.0s, resulting in a 55.8% loss of data packets in this period; further, at T=1.3s, the SNR recovers, the inventive sample group deduces the recovery state at T=1.4s (lagging 100ms) and instantaneously switches back to the high-quality 5G interface, while the control group does not switch back to the 5G interface until the next probe period at T=2.0s, causing the data to unnecessarily stay on the high-latency link for 600ms; the test data shows that when the network physical layer state changes rapidly by milliseconds, the active measurement method has a decision lag due to the measurement period and latency overhead, resulting in loss of critical data or improper routing selection; the cross-layer deduction method adopted by the present application can synchronize the instantaneous changes of the physical layer and convert them into transmission quality indicators by passively obtaining physical layer statistics with zero overhead, avoiding decision lag.

[0029] Embodiment 3: This embodiment combines Figs. 1 to 3 , a description of the aircraft multi-network fusion data real-time transmission and distribution system is as follows, as shown in Fig. 1 , a physical layer state monitoring module for obtaining physical layer statistics SNR, BER, RSSI from heterogeneous network interfaces, 5G, etc., and a message service level identification module for determining the service level CoS of the data packets to be transmitted are shown, the physical layer state monitoring module outputs the physical layer statistics to the transmission quality deduction engine, which deduces the deduced transmission quality indicators packet loss rate, time delay, the indicators and the service level are jointly input into the deduction routing engine, which makes decisions to select the target transmission interface for data packet distribution, at the same time, the actual transmission layer feedback generated by the distribution process is input into the mapping model calibration module together with the physical layer statistics, the calibration module dynamically corrects the mapping model and feeds back the results to the transmission quality deduction engine, forming a self-calibrating closed loop.

[0030] As Fig. 2As shown, the chart shows the distribution of four different service classes of data packets CoS-1 (ATC command), CoS-2 (AOC data), CoS-3 (passenger Wi-Fi), and CoS-4 (network mapping) in two dimensions of satellite link usage and 5G link usage, and the data shows that the high-priority CoS-1 mainly uses 85% of the 5G link usage, while the low-priority CoS-4 mostly uses 90% of the satellite link usage; as Fig. 3 As shown, the chart includes a cross-layer inference mechanism implemented by passively acquiring physical layer statistics and inferring transmission quality indicators, a differentiated service routing implemented by identifying data packet service classes and executing service class-dependent cost functions, a closed-loop adaptive correction implemented by acquiring actual transmission layer feedback and dynamically correcting the mapping model, and a long-term health trend analysis implemented by archiving historical transmission quality indicators and generating communication system maintenance alerts.

[0031] Embodiment 4: This embodiment describes the transmission layer-physical layer mapping model inside the transmission quality inference engine, i.e., the static transmission quality inference lookup table, which is calibrated offline in the development stage to eliminate the problem of unclear model source by standardizing engineering procedures; in the calibration scenario, the enabling environment defined by its initial state includes: a network impairment simulator that can accurately simulate various channel conditions, a specific type of airborne modem to be calibrated, for example, a certain type of SatcomModem, a traffic generator, and a high-precision network analyzer; the problem to be solved in calibration is to establish a reproducible mapping relationship between the physical layer statistics, for example, SNR, and the transmission layer performance indicators, i.e., packet loss rate Loss and latency Latency.

[0032] The calibration process is performed using the parameter scanning method: first, set a specific physical layer signal-to-noise ratio (SNR) value through the network impairment simulator, for example, the scanning interval is -5dB to +25dB, the scanning step can be set to 1dB, and the initial SNR is set to -5dB; second, the traffic generator sends a large sample of data packets to the network analyzer via the Modem interface, for example, N=10000 UDP data packets of 1024 bytes; third, the network analyzer measures and records the actual transmission layer packet loss rate ( = (N-received number) / N) and the average one-way latency ( ) at this SNR point; fourth, repeat steps one to three, increment the SNR value, and complete all scanning points up to +25dB to obtain a set of original (SNR, The original calibration dataset is statistically processed in intervals to generate the lookup table entries after calibration is completed. Taking the <5 dB interval of the Satcom interface as an example, all data points with SNR < 5 dB in the calibration dataset are extracted, and the statistical mean or the 95th percentile of these points is calculated. If the statistical value is 14.8%, 15.0% (with a certain engineering margin) is taken as the derived packet loss rate (Est. Loss) of the interval. Similarly, the statistical mean of the interval is calculated, such as 1180 ms, and the margin value 1200 ms is taken as the derived latency (Est. Latency), thereby generating the determined entry Satcom, <5 dB, >10e-5, 15.0%, 1200 ms in the lookup table. Through this procedure, a static transmission quality derivation lookup table with engineering reproducible basis can be established for different types of network interfaces (such as the 5G interface), which is called by the transmission quality derivation engine in flight.

[0033] Embodiment 5: This embodiment describes the preset policy rule library of the packet service level identification module, which is defined by an engineering-defined reproducible procedure before system deployment. The purpose of the procedure is to ensure that the derivation routing engine can perform differentiated routing decisions on different service data packets. The input of the procedure is the network interface control document (ICD) of the airborne avionics system, which defines the network traffic characteristics of all airborne applications. The procedure steps are as follows: traverse the application list in the ICD, divide the network traffic into service levels according to the service importance, and extract the five-tuple (source IP, destination IP, protocol number, source port, destination port) characteristics of the data packet header as the matching key value. Taking the air traffic control (ATC) data link application as an example, its service importance is the highest, and the ICD defines its target port number as X1. Therefore, the first rule in the policy rule library is generated: IF (destination port = X1) THEN ServiceLevel = CoS-1. The importance of the airline operation control (AOC) application (such as engine state feedback) is second, and the ICD defines its target IP address range as Y1 to Y2. Therefore, the second rule is generated: IF (target IP IN [Y1, Y2]) THEN ServiceLevel = CoS-2. The importance of the in-flight entertainment (IFE) application is the lowest, and the ICD defines its source IP network segment as Z1. Therefore, the default rule is generated: IF (source IP IN Z1) THEN ServiceLevel = CoS-3. The policy rule library output by this procedure is solidified in the packet service level identification module, providing classification basis for its operation.

[0034] This embodiment further elaborates on the standardized offline calibration procedure for the preset maintenance threshold of the communication health trend analysis module in the specific implementation. The purpose of this procedure is to establish a statistically significant alarm baseline to distinguish between normal aging and abnormal chronic degradation of hardware. The input to the procedure is a historical transmission quality index dataset of the healthy fleet. This dataset contains the packet loss rate time series of each Satcom interface archived by the transmission quality inference engine over the past 2000 flight hours, taking 20 aircraft as an example. The calibration steps include: First, performing linear regression analysis on the packet loss rate time series of each interface in the dataset to calculate its degradation trend slope. Second, collect the values ​​of all health interfaces to form a statistical distribution of the normal aging slope, and calculate the mean (e.g., +0.003% Loss / flight hour) and standard deviation (e.g., 0.002% Loss / flight hour) of this distribution; Third, set alarm thresholds based on this statistical distribution, with a 3-sigma control limit (…). For example, the preset maintenance threshold is set to +0.009% Loss / flight hours. This threshold is loaded into the communication health trend analysis module. When the degradation trend slope of any subsequent interface exceeds 0.009%, the system determines that it deviates from the normal aging baseline and generates a maintenance alarm.

[0035] Example 6: This example illustrates a reproducible engineering implementation procedure for obtaining actual transport layer feedback using a slow passive verification ring. This procedure is executed at the operating system kernel level of the airborne computing platform, and its technical path is passively parsing network protocol stack statistics. Taking a Linux-based system as an example, the slow passive verification ring is configured as a low-priority background daemon process, which uses a slow sampling period (e.g., ...). A statistical snapshot operation is performed every 10 seconds; at the sampling point... At that time, the process reads the MIB statistics counter exposed by the kernel network subsystem, specifically the cumulative number of retransmitted packets in the TCP protocol. and the total number of messages sent The check loop then calculates the incremental retransmission rate over the past 10-second period. The calculation formula is as follows: This calculation result That is, it serves as the actual transmission layer feedback output to the image model calibration module.

[0036] The embodiment further illustrates a reproducible engineering implementation procedure for the network mapping data collection module to obtain the non-transmission quality type event log, which is based on the standard Simple Network Management Protocol (SNMP). When the system is deployed, the network mapping data collection module is configured as an SNMP manager and loaded with a private management information base (MIB) provided by a manufacturer of an onboard modem (such as a 5G modem). The MIB defines specific object identifiers (OIDs) for storing the latest status codes of network search events (such as 0x01 representing the start of search and 0x02 representing the successful recapture). The network mapping data collection module sends an SNMP Get request to the modem at a low priority polling rate, such as every 30 seconds, to read the value of the OID (i.e., the event log) and packs it with the geographic location information to generate a network mapping data packet.

[0037] It is apparent for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0038] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application but not limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced equivalently without departing from the spirit and scope of the present application.

Claims

1. An aircraft multi-network converged data real-time transmission and distribution system, characterized in that, The system comprises: a physical layer status monitoring module configured to obtain physical layer statistics from a plurality of heterogeneous network interfaces onboard an aircraft; a transport quality inference engine configured to infer the physical layer statistics into transport quality indicators characterizing the plurality of heterogeneous network interfaces based on a transport layer-physical layer mapping model; an inference routing engine configured to select a target transport interface for a data packet to be transmitted based on the transport quality indicators output by the transport quality inference engine, and to distribute the data packet via the target transport interface; a mapping model calibration module configured to obtain the physical layer statistics, to obtain actual transport layer feedback of the data packet distributed via the target transport interface, and to dynamically correct the transport layer-physical layer mapping model when a preset deviation exists between the actual transport layer feedback and the transport quality indicators inferred by the transport quality inference engine based on the physical layer statistics.

2. The real-time data transmission and distribution system for aircraft multi-network integration according to claim 1, wherein, The inference routing engine further comprises a slow passive check loop configured to passively monitor the transport layer feedback of the data packet distributed via the target transport interface to generate the actual transport layer feedback.

3. The real-time data transmission and distribution system for aircraft multi-network integration according to claim 1, wherein, The transport layer-physical layer mapping model is a static transport quality inference lookup table, and the mapping model calibration module is configured to dynamically correct entries in the transport quality inference lookup table when the preset deviation exists.

4. The real-time data transmission and distribution system for aircraft multi-network integration according to claim 1, wherein, The system further comprises a message service level identification module configured to classify the data packet based on a preset policy rule library to determine a service level of the data packet, and the inference routing engine is further configured to jointly select the target transport interface based on the service level of the data packet and the transport quality indicators.

5. The real-time data transmission and distribution system for aircraft multi-network integration according to claim 1, wherein, The physical layer statistics comprise one or more of a signal-to-noise ratio (SNR), a bit error rate (BER), and a received signal strength indication (RSSI).

6. The real-time data transmission and distribution system of claim 1, wherein, The transport quality indicators comprise one or more of an inferred packet loss rate or an inferred latency.

7. The real-time data transmission and distribution system of claim 1, wherein, The system further comprises a downlink quality signaling encapsulation module configured to obtain the transport quality indicators characterizing a downlink of the aircraft output by the transport quality inference engine, to generate the transport quality indicators into a status message, and to encapsulate the status message into the data packet distributed by the inference routing engine to a ground station.

8. The real-time data transmission and distribution system of claim 1, wherein, The system further comprises a communication health trend analysis module. The communication health trend analysis module is configured to archive the transport quality indicators output by the transport quality inference engine in a historical time period, to perform statistical trend analysis on the transport quality indicators in the historical time period, and to generate a communication system maintenance alarm when a result of the statistical trend analysis satisfies a preset maintenance threshold.

9. The real-time data transmission and distribution system of claim 8, wherein, The communication health trend analysis module is configured to calculate a degradation trend slope when performing statistical trend analysis : wherein is a rolling average of the transmission quality indicator at a first historical time point, is a rolling average of the transmission quality indicator at a second historical time point, is a rolling average of the transmission quality indicator at a second historical time point, The communication health trend analysis module is configured to generate a communication system maintenance alert when the degradation trend slope exceeds a pre-defined positive slope threshold.

10. The real-time data transmission and distribution system for aircraft multi-network fusion according to claim 1, wherein, The system further comprises a network mapping data collection module configured to obtain non-transport quality event logs characterizing running states of the heterogeneous network interfaces from the physical layer status monitoring module, to obtain current geographic location information from an onboard navigation system, to generate a network mapping data packet based on the event logs and the current geographic location information, and to submit the network mapping data packet to the inference routing engine for low-priority distribution to a ground network planning server.

Images