Modular digital audio multi-channel IO control system and method for aeronautical communication

Abstract

The invention belongs to the technical field of data processing, relates to a modular digital audio multi-channel IO control system and method for aviation communication, and aims to solve the problems of poor environmental adaptability, static synchronization parameters, calibration lag and insufficient intelligent fault-tolerant capability of a synchronization technology in the aviation field. The method comprises the steps that a scene sensing module fuses multi-domain data to generate a scene vector, synchronous parameters are generated through a look-ahead control module, clock skew of multiple IO channels is calibrated in combination with a synchronous execution module, and synchronous control is achieved; the health monitoring module quantifies the full-link health degree and dynamically adapts to the self-healing strategy through the self-healing learning module. According to the method, high-precision synchronization and high-robustness fault tolerance are balanced through perspective prediction and response type self-healing closed-loop cooperation, the system is endowed with intelligent self-adaptive evolution ability, and the synchronization performance and task reliability of the aviation audio system in a complex dynamic environment are improved.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of data processing, and particularly relates to a modular digital audio multi-channel IO control system and method for aviation communication. BACKGROUND

[0002] In modern avionics systems, audio input / output systems play a crucial role, carrying key tasks such as cockpit intercom, air-ground communication, and warning prompts. These systems usually contain multiple distributed input / output nodes, which must maintain microsecond-level or even higher precision time synchronization between them to ensure the integrity, real-time performance, and clarity of audio streams.

[0003] Existing synchronization technologies, such as Phase-Locked Loop (PLL), Kalman filtering, or Network Time Protocol (NTP) schemes, can provide good synchronization results under stable and ideal working conditions. However, the aviation environment has its inherent complexity and harshness: Dynamic changes in the environment: changes in flight states (such as takeoff, cruising, and landing) and electromagnetic environments can unpredictably impact the quality of communication links (latency, jitter, and packet loss rate), leading to synchronization parameter mismatch and a sharp decline in performance; Limitations of passive response: traditional methods are mostly "post-error correction" mode, i.e., compensation is performed only after detecting synchronization errors; this passive response mechanism has inherent delays and cannot foresee and avoid synchronization jitter caused by predictable scenario changes (such as entering a strong electromagnetic interference zone); Insufficient fault tolerance: in the face of link interruptions, hardware failures, and other sudden and structural problems, traditional systems rely on preset and fixed redundancy switching logic. This logic lacks intelligence and cannot make optimal recovery decisions based on real-time fault context, resulting in long recovery times and reduced system reliability.

[0004] Therefore, there is an urgent need for a synchronization control technology that can actively perceive complex aviation environments, predictively adjust synchronization strategies, and intelligently and quickly recover from faults, to meet the higher standards of future aviation systems for audio communication. SUMMARY

[0005] To solve the above problems in the prior art and address the poor environmental adaptability, static synchronization parameters, calibration lag, and insufficient intelligent fault tolerance in aviation audio synchronization technology, the present application proposes, in a first aspect, a modular digital audio multi-channel IO control system for aviation communication, which includes: The scene perception module, the forward control module, the synchronous execution module, the health monitoring module and the self-healing learning module are connected through a bus communication to form a closed-loop control architecture. The scene perception module collects multi-domain heterogeneous data and performs dynamic weight fusion processing, and outputs a scene vector representing the current flight scene. The forward control module receives the scene vector as input, and a pre-trained neural network inference model generates core synchronization parameters adapted to the current scene. The synchronous execution module generates a reference clock according to the core synchronization parameters, uses a prediction compensation mechanism to calibrate the clock deviation of the digital audio multi-IO channel, and realizes multi-channel synchronous control. The health monitoring module collects the full-link running state, evaluates the system health degree and outputs the evaluation result. The self-healing learning module dynamically selects a self-healing strategy according to the evaluation result and the scene vector, feeds back the self-healing result to the forward control module, and regenerates adaptive parameters based on the changed state to realize a control strategy closed loop.

[0006] In some preferred embodiments, the scene perception module comprises: An interface adaptation unit is configured with interfaces connected to a flight management system, a traffic warning and collision avoidance system and an engine control system respectively, to collect three-dimensional route data, multi-target threat data and engine real-time state parameters respectively. A dynamic weight fusion unit has an electromagnetic interference detection subunit built in, which adjusts the weight proportion of each domain data according to the electromagnetic interference intensity, specifically: When the electromagnetic interference intensity is higher than -80dBm, the weight proportion of the engine real-time state parameters is increased; when the electromagnetic interference intensity is lower than -100dBm, the weight proportion of the multi-target threat data is increased. A scene vector generation unit is used to quantize the fused data into a four-dimensional scene vector containing flight phase, threat density, engine state and electromagnetic interference intensity.

[0007] In some preferred embodiments, the forward control module comprises: A neural network processing unit is used to receive the four-dimensional parameters of the scene vector using a trained neural network inference model, extract scene depth features through a ReLU activation function, and output core synchronization parameters from the output layer. A parameter cache unit is used to store the generated core synchronization parameters, which include synchronization accuracy threshold, sampling rate and PI controller adjustment coefficient, and the parameter update delay is ≤2ms. A parameter feedback adjustment unit, in communication connection with the self-healing learning module, is configured to receive optimization instructions and dynamically correct output parameters of the neural network inference model.

[0008] In some preferred embodiments, the synchronous execution module comprises: A reference clock generation unit configured to generate a reference clock signal according to a sampling rate in the core synchronization parameters; A prediction compensation calibration unit comprising a bias prediction subunit and a compensation execution subunit, configured to analyze historical clock bias data by the bias prediction subunit to calculate a bias change trend, and to generate a compensation amount according to the predicted bias by the compensation execution subunit to realize the clock bias advanced calibration; A calibration period adjustment unit configured to dynamically adjust the calibration period according to the scenario vector, with the calibration period being one fifth of the regular period in the emergency scenario and twice the regular period in the cruising scenario.

[0009] In some preferred embodiments, the clock bias advanced calibration is realized by the following method: Timestamps of local clocks of each IO channel are collected, and the current clock bias of each channel is calculated with reference to the reference timestamp corresponding to the reference clock signal; The historical bias data of each channel is analyzed by the sliding window method, and the current bias change rate is calculated in combination with the sampling period; A compensation value is generated in combination with the current clock bias, the bias change rate of each channel, and the prediction coefficient corresponding to the scenario; the prediction coefficient is dynamically adjusted according to the flight phase; The compensation value is written into the clock controller of each IO channel through software interruption, the local clock frequency is adjusted respectively, and the calibration is completed; the calibration period is consistent with the sampling period, and the clock bias after calibration does not exceed the synchronization accuracy threshold.

[0010] In some preferred embodiments, the synchronous execution module further comprises a link dynamic configuration unit in communication connection with the forward-looking control module, which dynamically adjusts the link working mode according to the synchronization accuracy threshold in the core synchronization parameters by the following method: When the synchronization accuracy threshold is lower than the preset accuracy threshold, the low-latency mode is enabled, the link cache depth is reduced, and the CPU resource allocation proportion is increased; When the synchronization accuracy threshold is higher than the preset accuracy threshold, the energy efficiency mode is enabled, the link cache depth is adjusted, and the lightweight transmission coding is adopted; The link dynamic configuration unit comprises a priority determination subunit, which dynamically adjusts the link priority according to the threat collision time in the multi-target threat data, and sets the link priority to the highest level in the emergency scenario.

[0011] In some preferred embodiments, the link dynamic configuration unit further comprises a spatial audio enhancement subunit configured to, when the link is at the highest level, calculate left and right channel gain difference through a head-related transfer function, and add delay compensation according to a threat azimuth to ensure that a pilot's identification error of the threat azimuth is not more than an error threshold.

[0012] In some preferred embodiments, the health monitoring module comprises: a state acquisition unit configured to acquire three types of indexes, i.e., synchronization stability, link smoothness, and data integrity, wherein the synchronization stability is a time proportion of clock deviation meeting a synchronization accuracy threshold, the link smoothness is a time proportion of link delay being less than or equal to a delay threshold, and the data integrity is 1 minus a data packet loss rate; a health degree calculation unit configured to calculate a system health degree through a weighted algorithm based on the synchronization stability, the link smoothness, and the data integrity; a threshold dynamic adjustment unit configured to correct a health degree threshold according to a historical fault number to realize adaptive optimization of a self-healing triggering condition.

[0013] In some preferred embodiments, the self-healing learning module comprises: a self-healing strategy library storing three types of self-healing strategies, i.e., a non-key link sacrifice strategy, an anti-interference coding enhancement strategy, and a minimum feature set start strategy, each self-healing strategy being mapped to a scene vector; a strategy selection unit configured to call an adaptive self-healing strategy according to a health degree evaluation result and a current scene vector, call the anti-interference coding enhancement strategy in a strong electromagnetic interference scene, and call the non-key link release strategy in a multi-threat scene; a Q-learning unit configured to update a mapping relationship between a scene and a strategy according to a self-healing result.

[0014] The second aspect of the application provides a modular digital audio multi-channel IO control method for aviation communication, which comprises the following steps: acquiring and fusing multi-domain heterogeneous data to construct a scene vector for quantifying a real-time aviation scene; the scene vector comprises a flight phase, a threat density, an engine state, and an electromagnetic interference intensity; based on the scene vector, inferring and generating core synchronization parameters matched with a current scene through a pre-trained neural network inference model; the core synchronization parameters at least include a synchronization accuracy threshold for calibrating clock deviation; performing clock calibration and link configuration on a plurality of IO channels of aviation audio according to the core synchronization parameters to realize synchronization control among the channels; monitoring a running state of the synchronization control to evaluate a system health degree, and performing feedback optimization on the neural network inference model based on an evaluation result of the system health degree.

[0015] The beneficial effects of the present application are: 1. Through the dynamic weight fusion of three types of core domain data, the forward control module performs fine prediction optimization, and through the self-healing learning module, the system quickly and stably recovers in abnormal states, realizes the closed-loop cooperation of forward-looking prediction and responsive self-healing, changes passive error correction to active prediction, thereby solving the contradiction between precision and robustness of traditional systems, and endowing the system with intelligent self-healing and adaptive evolution ability, and realizing significant improvement of the synchronization performance and task reliability of the aviation audio system in complex dynamic environments; 2. Using neural networks to deeply understand multi-domain information, the system can predict the potential impact of environmental changes on synchronization performance, adjust the cache strategy in advance, switch the best communication link, and kill the synchronization jitter in the bud, change passive error correction to active prediction, realize more smooth and more forward control than traditional feedback systems, and significantly improve the audio communication quality; 3. When the system is healthy, the forward-looking module is responsible for fine and forward-looking optimization, ensuring that the synchronization accuracy reaches the theoretical limit; when facing serious faults such as link interruption, the self-healing module based on reinforcement learning can break free from the shackles of fixed rules, make dynamic optimal decisions according to real-time fault context, greatly shorten the fault recovery time, improve the task reliability of the system under extreme conditions, and endow the system with fast and intelligent autonomous fault tolerance ability; 4. Through the state information feedback link, the fault handling experience of the self-healing module can make the forward-looking module adapt to the new normal of the system structure; this makes the system have the ability to learn from faults and continuously evolve, and the whole system forms an intelligent closed loop that can learn from faults and adapt to the new normal, making the system more stable and adaptive. BRIEF DESCRIPTION OF DRAWINGS

[0016] Other features, objects, and advantages of the present application will become more apparent from the following detailed description of non-limiting embodiments, made with reference to the following drawings: Figure 1 is a structural diagram of a modular digital audio multi-channel IO control system for aviation communication in an embodiment of the present application; Figure 2 is a flowchart of a modular digital audio multi-channel IO control method for aviation communication in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The present application will be further described in detail below with reference to the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the related application, and not to limit the application. In addition, it should be noted that, in order to facilitate description, only the parts related to the application are shown in the drawings.

[0018] It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other in the case of no conflict. The present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0019] The present application provides a modular digital audio multi-channel IO control system for aviation communication, constructs a multi-modal, predictive response adaptive control architecture, through the closed-loop cooperation of prospective prediction and responsive self-healing, changes passive error correction to active prediction, balances between high-precision synchronization and high-robustness fault tolerance, and endows the system with intelligent self-healing and adaptive evolution ability, and significantly improves the synchronization performance and task reliability of the aviation audio system in a complex dynamic environment.

[0020] In order to more clearly illustrate the present application, a modular digital audio multi-channel IO control module for aviation communication will be described below in combination with Figure 1 The system in the embodiment of the present application will be described in detail, the system comprises a scene perception module, a forward-looking control module, a synchronous execution module, a health monitoring module and a self-healing learning module, each module is connected through bus communication, forming a closed-loop control architecture; The scene perception module collects multi-domain heterogeneous data and performs dynamic weight fusion processing, and outputs a scene vector representing the current flight scene, wherein the dynamic weight is adaptively adjusted according to the electromagnetic interference intensity; The forward-looking control module receives the scene vector as input, and a pre-trained neural network inference model generates core synchronization parameters adapted to the current scene; The synchronous execution module generates a reference clock according to the core synchronization parameters, adopts a prediction compensation mechanism to calibrate the clock deviation of the digital audio multi-IO channel, and realizes multi-channel synchronous control; The health monitoring module collects the running state of the whole link, evaluates the system health degree and outputs the evaluation result; The self-healing learning module dynamically selects a self-healing strategy according to the evaluation result and the scene vector, feeds back the self-healing result to the forward-looking control module, and regenerates adaptive parameters based on the changed state to realize control strategy closed loop.

[0021] Preferably, the scene perception module comprises: An interface adaptation unit is configured with interfaces connected to a flight management system (FMS), a traffic collision avoidance system (TCAS) and an engine control unit (ECU) respectively, to collect three-dimensional route data, multi-target threat data and engine real-time state parameters respectively; The dynamic weighted fusion unit, with a built-in electromagnetic interference detection subunit, adjusts the weight ratio of data in each domain according to the intensity of electromagnetic interference. Specifically: When the electromagnetic interference intensity is higher than -80dBm, increase the weighting of the engine's real-time status parameters; when the electromagnetic interference intensity is lower than -100dBm, increase the weighting of multi-target threat data. The scene vector generation unit is used to quantize the fused data into a four-dimensional scene vector that includes flight phase, threat density, engine status, and electromagnetic interference intensity.

[0022] More preferably, in some embodiments, the interface adapter unit directly collects three types of core data through a dedicated interface: Flight Management System (FMS) data: 3D route data, including longitude, latitude, altitude, and approach speed; using ARINC429 interface, baud rate 1Mbps; Traffic Alert and Collision Avoidance System (TCAS) data: multi-target threat data, including threat location, distance, height difference, alarm level, and collision time (TTC); using ARINC664p7 interface, 100Mbps speed; Engine control system (ECU) data: real-time status parameters, including engine speed, exhaust temperature, vibration value, and engine status code; using a CAN bus interface with a speed of 500kbps; Environmental data: Electromagnetic interference intensity I (collected by the electromagnetic interference detection subunit, sampling frequency 1MHz).

[0023] Specifically, the collected data needs to be preprocessed, and the method is as follows: 1) Outlier removal: using Criteria for data sequences { x 1, x 2,..., x n Calculate the mean μ with standard deviation σ Remove | x ᵢ- μ |>3 σ Data; 2) Timestamp alignment: Based on GPS synchronized clock, the alignment accuracy is ≤1μs; 3) Aviation verification: FMS phase codes must be ∈ {1 (takeoff), 2 (cruise), 3 (approach), 4 (emergency)}, otherwise an interface reconnection will be triggered; TCAS data must satisfy "threat number N≥0 and TTC>0", otherwise it will be marked as invalid data; 4) Obtain preprocessed structured data (e.g., "Flight phase = approach, N = 5, I = -75dBm, TTC = 25s").

[0024] Preferably, the dynamic weight fusion unit adjusts the weight proportion of each domain data according to the electromagnetic interference intensity, and the method is as follows: A multi-domain data confidence calculation model is constructed, and the weight coefficient is dynamically adjusted according to the electromagnetic interference intensity: ; Among them, respectively, the confidence (0~1) of FMS, TCAS, and ECU data; .

[0025] Further preferably, the confidence is inversely deduced from the data error rate, and the specific inverse deduction rule is: confidence S=1-data error rate, data error rate=error code number in data transmission process / total transmission number (such as TCAS data error rate 0.5%, then STCAS=0.995); if the error rate is greater than 20%, the confidence is forced to be 0.1 (marked as low reliable data).

[0026] Further preferably, the output data after fusion is "scene feature data (including flight phase, threat density, and electromagnetic interference intensity)" and "business driven data (including threat coordinates, air route parameters, and ECU alarm)". Double bus parallel transmission is adopted, scene feature data is transmitted to the synchronous scheduling module through ARINC664p7 safety bus, the transmission delay is ≤1ms, and the error code rate is ≤10⁻¹²; business driven data is transmitted to the dynamic link module through PCIe (Peripheral Component Interconnect Express) 4.0 high-speed bus, the bandwidth is ≥8GB / s, and the delay is ≤0.8ms. Bus transmission adopts "frame priority marking", threat alarm data is marked as "emergency frame", and transmission resources are preferentially occupied.

[0027] Further preferably, in the embodiment, the initial value of the weight is: , ; the dynamic adjustment rule is: when the electromagnetic interference intensity I is greater than -80dBm, the weight is increased by 30% (i.e. =0.52), and a is reduced to 0.28, so as to ensure the weight proportion of reliable data (such as ECU) under strong interference.

[0028] Preferably, the scene vector generation unit quantizes the fused data into a four-dimensional scene vector containing flight phase, threat density, engine state, and electromagnetic interference intensity, and the method is as follows: The synchronous scheduling module maps the unstructured data into discrete values according to the preset quantization rule based on the fused scene feature data, and constructs a four-dimensional scene vector: ; Among them, is the flight phase, ∈ {1 (takeoff), 2 (cruise), 3 (approach), 4 (emergency)}, subscript "ph" is the abbreviation of "phase", representing the flight phase; N is the threat density, i.e. the number of threat targets detected by TCAS; is the engine state; I is the electromagnetic interference intensity, with the unit of dBm.

[0029] Further preferably, the quantization rules of each dimension are as follows: N is an integer between 0 and 10, N = 0 when there is no threat, N ≥ 5 when there are multiple threats, and N = 10 when the threat density N ≥ 10 (upper limit protection), N < 0 when taking 0 (lower limit protection); = 0, indicating that the engine is running normally (no alarm or failure); = 1, indicating that the engine enters an alarm state (such as sensor abnormalities, parameter overruns); = 2, indicating that the engine has a serious failure (such as mechanical damage, power loss); In order to ensure the unity of the description, I in the scene vector V adopts the original dBm value of electromagnetic interference intensity (for example, -90), and the continuous value is directly used as the input of the neural network. Table 1 below provides a reference method for mapping the original dBm value to a discrete level, which is used to assist in understanding the interference intensity level, but not as the direct input value of the scene vector.

[0030] In this embodiment, when the electromagnetic interference intensity I < -120 dBm, -120 dBm is taken (lower limit protection), and when I > -60 dBm, -60 dBm is taken (upper limit protection).

[0031] Preferably, the forward control module comprises: a neural network processing unit for receiving four-dimensional parameters of the scene vector by using the trained neural network inference model, extracting scene depth features through a ReLU (Rectified Linear Unit) activation function, and outputting core synchronization parameters from the output layer; a parameter caching unit for storing the generated core synchronization parameters, wherein the core synchronization parameters include a synchronization accuracy threshold, a sampling rate, and a PI controller adjustment coefficient, and the parameter update delay is ≤ 2 ms; a parameter feedback adjustment unit in communication connection with the self-healing learning module, for receiving optimization instructions and dynamically correcting the output parameters of the neural network inference model.

[0032] Further preferably, the forward control module receives the scene vector as input, and the pre-trained neural network inference model generates core synchronization parameters adapted to the current scene, and the method is as follows: Receive the scene vector V, map V to the synchronization parameter through the pre-trained neural network inference model, and output the synchronization execution result / core synchronization parameter , link running state (delay , resource utilization rate R used ).

[0033] Specifically, the core synchronization parameter includes: 1) synchronization accuracy threshold , as the maximum allowed value of multi-channel IO clock deviation, directly determines the audio synchronization effect The smaller, the higher the synchronization accuracy), high accuracy is the key prerequisite to realize high-fidelity three-dimensional space audio warning (so that the driver can intuitively judge the threat direction through hearing); 2) the working sampling frequency f of the software phase-locked loop (SW-PLL), as the "frequency reference" for generating the reference clock signal, directly determines the accuracy of the reference clock and the period of synchronization calibration; the higher the sampling rate, the higher the time resolution of the reference clock, the shorter the period of synchronization calibration (i.e. the time interval between two calibrations), and the faster the response to the change of clock deviation; 3) PI controller coefficients , , used to adjust the locking speed and stability of SW-PLL The larger, the faster the locking, The larger, the stronger the anti-interference).

[0034] In some embodiments, the neural network inference model adopts a neural network structure of "4-input-2-hidden layer-4-output", which establishes a mathematical mapping relationship between the scene vector V and the core synchronization parameter , solidifies expert knowledge into a deterministic model, and ensures the accuracy and real-time performance of parameter prediction; specifically: The input layer includes 4 neurons, which receives the scene vector ; the first hidden layer includes 16 neurons, which extracts low-dimensional features (such as "approach + multiple threats") using ReLU activation function; the second hidden layer includes 16 neurons, which extracts high-dimensional feature mapping (such as "fault + strong interference") using ReLU activation function; the output layer includes 4 neurons, which outputs the synchronization core parameter .

[0035] Preferably, the mapping relationship includes: The synchronization accuracy threshold is negatively correlated with the threat density N (the more threats, the higher the accuracy required), and is negatively correlated with the electromagnetic interference intensity I (the stronger the interference, the higher the accuracy required): ; wherein, is a scene correction coefficient, =1 (takeoff) -> =1.0, =2 (cruise) -> =1.2, =3 (approach) -> =1.0, =4 (emergency) -> =0.9; sampling rate f is positively correlated with electromagnetic interference strength I (stronger interference requires higher sampling rate for anti-interference), and is associated with flight phase (emergency scene requires the highest sampling rate); the sampling rate is adjusted based on the flight phase, and the electromagnetic interference strength is dynamically enhanced as the basis, and the engine state is used as a fault superposition coefficient, through two-level mapping of initial calculation by formula and final optimization by neural network, to realize accurate matching of sampling rate and scene demand, which is specifically expressed as follows: ; wherein, is an ECU state coefficient, =0 -> = 1.0, =1 -> = 1.2, =2 -> = 1.5; is the absolute value of interference strength (dBm), is an emergency compensation term to reduce the sampling rate redundancy of the cruise scene; is associated with the threat density N in the scene vector and the engine state , and the formula is as follows: ; ; wherein, N is the threat density, and the base value 0.3 / 0.05 is the coefficient of the cruise scene without threat (to ensure stability).

[0036] Preferably, in the present embodiment, when the threat density ≥5 is forced to be 0.3 us ; the constant term is 0.3 to achieve the minimum accuracy of the emergency scene to ensure the synchronization of the alarm sound; for every 10dBm increase in interference strength, f 20MHz is increased (range 10MHz~250MHz; ≤60 is taken as 60 (no additional sampling requirement), 80 (upper limit of sampling rate), increase sampling rate in strong interference scenario; emergency scenario = 0.9, = 0.25, cruise scenario = 0.3, = 0.05; N ≥ 3, take 3 (upper limit protection) to avoid overly large to cause oscillation; = 2 (fault) to additionally increase , enhance anti-interference ability.

[0037] Specifically, the pre-training process is: 1) Sample generation: using the neural network inference model, input the scene vector V covering all 7428 scene combinations, generate more than 100,000 groups of high-precision "(input V, output )" training sample pairs. The training data is derived from high-fidelity flight simulators and real flight data records.

[0038] 2) Network training: adopt the neural network structure of "4 input-2 hidden layer-4 output" for training until the model prediction error does not exceed the preset error threshold.

[0039] 3) Model solidification: solidify the trained neural network weight as a deterministic software component and deploy it to the onboard "audio synchronization control module". No online training is performed during flight to meet the deterministic requirements of DO-178C Level A.

[0040] Further preferably, the parameter feedback adjustment unit receives the optimized parameters fed back by the reinforcement learning module, such as the synchronization accuracy threshold obtained after self-healing, and generates adaptive parameters based on the changed state to realize the control strategy closed loop.

[0041] In the embodiments of the present application, a neural network inference model is adopted; however, those skilled in the art can understand that other types of machine learning models can also be adopted, such as gradient boosting decision tree, support vector machine, etc. In an alternative embodiment, the model can not rely on a preset explicit mathematical formula, but directly learn the complex nonlinear mapping relationship from the scene vector to the core synchronization parameter through an end-to-end deep learning method from a large amount of flight simulator or real operation data, to adapt to more complex scenarios.

[0042] Preferably, the synchronization execution module comprises: a reference clock generation unit for generating a reference clock signal according to the sampling rate in the core synchronization parameter; The predictive compensation calibration unit has a built-in deviation prediction subunit and a compensation execution subunit. The deviation prediction subunit analyzes historical clock deviation data to calculate the deviation change trend, and the compensation execution subunit generates the compensation amount based on the predicted deviation to achieve clock deviation advance calibration. The calibration cycle adjustment unit dynamically adjusts the calibration cycle according to the scenario vector. In emergency scenarios, the calibration cycle is one-fifth of the normal cycle, and in cruise scenarios, the calibration cycle is twice the normal cycle.

[0043] More preferably, the method for achieving clock deviation lead calibration is as follows: Collect the timestamp of the local clock of each IO channel, and calculate the current clock deviation of each channel with the reference timestamp corresponding to the reference clock signal as a reference. The historical deviation data of each channel is analyzed using the sliding window method, and the current deviation change rate is calculated in combination with the sampling period. A compensation value is generated by combining the current clock deviation, deviation change rate, and prediction coefficient of each channel with the corresponding scenario; the prediction coefficient is dynamically adjusted according to the flight phase. The compensation value is written to the clock controller of each IO channel via software interrupt, and the local clock frequency is adjusted to complete the calibration. The calibration period is consistent with the sampling period, and the clock deviation after calibration does not exceed the synchronization accuracy threshold.

[0044] In some embodiments, the method for implementing clock skew ahead calibration is as follows: Based on the reference clock signal, the timestamp of the local clock of the acquisition channel is collected. Calculate the first i Current clock skew of each I / O channel : ; The rate of change of deviation was calculated using the sliding window method. : ; Based on the current deviation and rate of change, generate the predicted compensation value: ; in, For channel timestamps, M is the base timestamp; M is the window size. The sampling period is t, where t is the current time. For the Mth sampling period before the first i Clock skew of each I / O channel; k The prediction coefficients are dynamically adjusted based on the scene vector. The dynamic adjustment rule is as follows: in emergency scenarios... k =0.8, in approach / takeoff scenarios k =0.6, under cruise scenariok =0.3; Compensation value is written into channel clock controller through software interruption to adjust local clock frequency and complete calibration.

[0045] Further preferably, the synchronization execution module further comprises a link dynamic configuration unit, which is in communication connection with the look-ahead control module and dynamically adjusts a link working mode according to a synchronization precision threshold in the core synchronization parameter, and the method is as follows: When the synchronization precision threshold is lower than a preset precision threshold, a low-delay mode is enabled, the link cache depth is reduced, and the CPU resource allocation proportion is increased; When the synchronization precision threshold is higher than the preset precision threshold, an energy efficiency mode is enabled, the link cache depth is adjusted, and a lightweight transmission coding is adopted; The link dynamic configuration unit comprises a priority determination subunit, which dynamically adjusts a link priority according to a threat collision time in the multi-target threat data, and sets the link priority to the highest level in an emergency scenario.

[0046] In the embodiment, the precision threshold is preferably 0.5 μs: When ≤0.5 μs (high synchronization demand, such as a multi-threat scenario): a “low-delay mode” is enabled, the link cache depth is ≤32 bytes, the CPU resource is preferentially allocated (the proportion is ≥70%), and unnecessary data compression is disabled; When >0.5 μs (normal synchronization demand, such as a cruise scenario): an “energy efficiency mode” is enabled, and the link cache depth is dynamically adjusted: The specific adjustment rule is: cache depth D=ceil(data amount x 1.2) (ceil is the ceiling function), and 64≤D≤256; data amount≤53 bytes / ms→D=64 bytes; 54 bytes / ms

[0047] Preferably, the transmission coding mode comprises Turbo coding, CRC check, or no coding.

[0048] In the embodiment, based on the threat collision time TTC and the engine state , the link priority P is divided into 0-2 levels (0 level is the highest): ; A link configuration table (including unit connection order, parameter value, and validity period) is automatically generated, the configuration validity period is ≤3 minutes, and no code modification is required.

[0049] ​In some embodiments, the link dynamic configuration unit further comprises a spatial audio enhancement sub-unit, configured to, when the link is the highest level, calculate left and right channel gain difference through head-related transfer function, and add delay compensation according to threat azimuth to ensure that the pilot's identification error of the threat azimuth is not more than the error threshold.

[0050] Specifically, the link configuration of the spatial audio enhancement sub-unit is adjusted through head-related transfer function (HRTF), including the following contents: Azimuth mapping: threat azimuth (-180°~180°) corresponds to left and right channel gain difference: ; Left channel gain: (when <0, left threat); right channel gain: (when >0, right threat); Delay compensation: different azimuths correspond to different propagation delays, and compensation values need to be added in the link: ; for example: =30° (right threat), right channel delay is reduced by 0.03ms to ensure binaural synchronization.

[0051] For example, when the left threat azimuth is 90°, the left channel gain is +3dB and the right channel gain is -3dB to ensure that the pilot's azimuth identification error is less than or equal to the error threshold, and the error threshold of the embodiment is preferably .

[0052] Further preferably, based on the link priority P and the scene vector V, a multi-dimensional resource allocation model is constructed to ensure that the core link resource is given priority, and the resource scheduler allocates CPU and bandwidth resources according to the balance model and the priority. The specific method is: 1) Allocate CPU resources: ; Wherein, is the CPU resource of the current link priority, is the CPU priority coefficient of the current link priority (link priority P=0→ =0.7, P=1→ =0.2, P=2→ =0.1); is the scene emergency coefficient ( =4→ =1.2, other scenes→ =1.0); When When the sum of the calculated values is greater than 100%, reduce according to the priority ladder: P=0 level link keeps the calculated value unchanged, P=1 level link is allocated at 80% of the calculated value, and P=2 level link is allocated at 50% of the calculated value; if it is still greater than 100%, then suspend the P=2 level link; 2) Allocate bus bandwidth: ; Wherein, is the bandwidth resource of the current link priority, is the bandwidth priority weight of the current link priority (link priority P=0→ =5, P=1→ =3, P=2→ =2), satisfying ; 3) Allocate memory: ; The memory of the current link priority is linearly related to the cache depth D and the number of links.

[0053] In this embodiment, for example: 0 level link: CPU occupancy ≥70%, bandwidth occupancy ≥50%, transmission delay ≤1.5ms; 1 level link: CPU occupancy 20%~30%, bandwidth occupancy 30%~40%; 2 level link: CPU occupancy ≤10%, bandwidth occupancy ≤20%; Further preferably, 20% of redundant space is reserved to avoid memory overflow; the resource allocation adjustment delay is ≤1ms to avoid link lag caused by resource contention.

[0054] Preferably, the health monitoring module comprises: A state acquisition unit is configured to acquire three types of indexes, including synchronization stability, link smoothness, and data integrity, wherein the synchronization stability is the time proportion of clock deviation meeting the synchronization accuracy threshold, the link smoothness is the time proportion of link delay being less than or equal to the delay threshold, and the data integrity is 1 minus the data packet loss rate. A health degree calculation unit is configured to calculate the system health degree by a weighting algorithm based on the synchronization stability, the link smoothness, and the data integrity. A threshold dynamic adjustment unit is configured to correct the health degree threshold according to the historical fault times, so as to realize adaptive optimization of the self-healing triggering condition.

[0055] Further preferably, the state acquisition unit is deployed in the cross-domain fusion, synchronization scheduling, and dynamic link layer to monitor points and acquire indexes: ​Synchronization scheduling layer: SW-PLL lock status, IO channel synchronization deviation compliance rate; Cross-domain fusion layer: data packet loss rate (≤0.1%), fusion model confidence (≥0.8); Dynamic link layer: total link delay (≤3ms), unit fault identifier.

[0056] More preferably, the system health is calculated using a weighted algorithm, the method of which is as follows: H = 0.4 × Synchronization Stability + 0.3 × Link Smoothness + 0.3 × Data Integrity; Among them, synchronization stability is the percentage of time when the clock deviation meets the synchronization accuracy threshold, link smoothness is the percentage of time when the link delay is less than or equal to the delay threshold, and data integrity is 1 minus the data packet loss rate.

[0057] In this embodiment, the synchronization stability statistics window is 1 second, that is, within 1 second The sampling frequency is 1kHz, and the total sampling frequency is 1000. The link smoothness statistics window is 10 seconds. In this embodiment, the latency threshold is preferably 3ms, that is, the number of transmission frames with Tlink ≤ 3ms within 10 seconds / the total transmission frames × 100%.

[0058] More preferably, the unit fault identifier is obtained based on the fault code mapping, and the fault code mapping relationship is shown in Table 2.

[0059] In this embodiment, the health level H (e.g., H=0.55, which is lower than the threshold of 0.6) and the fault type F (e.g., F=0) are used to make a judgment. When H≤0.6, an interrupt signal is triggered, and [V,F,H,KPI] are packaged and sent to the reinforcement learning module with a response delay of ≤1ms.

[0060] Furthermore, to address the potential unintended behavior of the intelligent model and meet the stringent requirements of Level A, this invention designs an independent security monitoring and degradation mechanism: Output boundary monitoring: The hardware monitoring unit within the FPGA continuously verifies whether the synchronization parameters (δ,f,Kp,Ki) output by the BP neural network are within the preset safety boundaries (e.g., ); Heartbeat and Timeout Monitoring: Monitors the running status of the intelligent algorithm module. If there is no response or calculation timeout, it is determined to be a module failure.

[0061] Degradation mode trigger: Once the model output is detected to be out of bounds or the module is faulty, the system will immediately trigger the degradation mode to bypass the intelligent decision-making module; Deterministic strategy takeover: In degraded mode, the system will load a pre-set, phase-based, simple but absolutely reliable table of fixed synchronization parameters (e.g., fixed for cruise phases). =1.5μs, fixed during emergency phase =0.5μs), ensuring that the most critical audio alarm function is not interrupted.

[0062] Preferably, the self-healing learning module includes: The self-healing strategy library stores three types of self-healing strategies: non-critical link sacrifice strategy, anti-interference coding enhancement strategy, and minimum function set startup strategy. Each self-healing strategy establishes a mapping relationship with the scene vector. The strategy selection unit is used to call the appropriate self-healing strategy based on the health assessment results and the current scenario vector. In the case of strong electromagnetic interference, the anti-interference coding enhancement strategy is called, and in the case of multiple threats, the non-critical link release strategy is called. Q-learning units are used to update the mapping relationship between scenarios and policies based on the self-healing results.

[0063] More preferably, the method for achieving a closed-loop control strategy is as follows: 1) Dynamically select a self-healing strategy based on the evaluation results and scene vectors: Based on multi-dimensional scene vectors Add two key system state indicators, F and H, to form a complete state vector S; Define the action space: Action A1: Non-critical link sacrifice strategy; Triggering conditions: Threat density ≥ 3 (multi-threat scenario), fault type is excessive link latency; Operation steps: Immediately disconnect priority level 2 links (such as normal navigation tones) to release CPU / bandwidth resources; prioritize repairing level 0 / 1 links (TCAS alarms, approach commands) and restart link drivers; record information of sacrificed links, which will be automatically restored after the fault is resolved.

[0064] Action A2: Anti-interference enhancement strategy; Triggering conditions: Electromagnetic interference intensity > -70dBm (strong interference scenario), fault type is excessive data packet loss rate; Operation steps: Enable Turbo encoding (increase the code rate from 1 / 3 to 1 / 2) to enhance data anti-interference capability; switch to a backup transmission link (e.g., switch from the PCIe bus to the ARINC664p7 bus); increase the SW-PLL sampling rate by 20MHz to enhance clock synchronization stability.

[0065] Action A3: Minimal Feature Set Startup Strategy Triggering conditions: Engine status = fault (emergency scenario), health level H ≤ 0.6; Operation content: only keep the core links of fire warning and TCAS threat warning 2, suspend other links; load light software image (remove unnecessary functions, start time ≤8ms); lock synchronization parameters (fixed ), avoid introducing risks by dynamic adjustment.

[0066] Design reward function: ; Wherein, is the scene emergency coefficient, when the emergency scene (flight phase=4) or engine failure (state=2) =2, the reward is doubled, and =1 in other scenarios; is the fault recovery time, is the self-healing success rate (value range is 0~1, 1 represents complete success, 0 represents complete failure); is the number of fault recurrence within 2 minutes, fault recurrence=the same link appears the same type of fault again within 2 minutes (such as P=0 level link t=0 F=0, t=50 seconds F=0 again, then it is recorded as 1 recurrence); different links or different types of faults are not counted as recurrence; Adopt ε-greedy strategy to select self-healing strategy from action space A={A1,A2,A3}, Q value update: ; Wherein, =0.1 is the learning rate, which controls the update amplitude to avoid large fluctuations; =0.9 is the discount factor; is the previous state, is the new state after executing action ; After multiple iterations, the optimal self-healing strategy (such as A1) is obtained, and the optimized synchronization / link parameters are obtained.

[0067] Total state number=4(flight phase)×11(threat density)×3(engine state)×7(interference intensity)×3(fault type)×3(health)=4×11×3×7×3×3=7428 kinds, covering all typical scenarios and fault combinations.

[0068] Preferably, the number of iterations is the number of self-healing operations (i.e. after each trigger H≤0.6 and execute self-healing action, it is recorded as 1 iteration); in this embodiment, the initial =0.3, every 100 iterations decreases by 0.05, the minimum is 0.1.

[0069] 2) Execute the self-healing strategy according to the scene vector and obtain the self-healing result, for example as follows: Threat density >= 3 (multi-threat scene): execute the "quick sacrifice non-critical link" strategy, prioritize repairing 0 / 1 level links, temporarily cut off 2 level links (such as normal navigation sound), self-healing time <= 15ms; Electromagnetic interference strength > -70dBm (strong interference scene): automatically enable Turbo anti-interference coding (code rate 1 / 2), while restarting the data transmission link affected by interference, self-healing time <= 20ms; Engine state = failure (emergency scene): trigger "minimum feature set", only keep fire warning, TCAS warning link, other links are suspended, self-healing time <= 8ms.

[0070] 3) Feedback the self-healing result to the forward control module, use the Q-learning reinforcement learning model, take the self-healing result (recovery time, link stability) as a reward signal, update the scene-self-healing strategy mapping relationship, and regenerate the adaptive parameters based on the changed state: State space: discretized value of scene vector V; Action space: 3 types of self-healing strategies (sacrifice non-critical link, anti-interference coding, minimum feature set); Reward function: R = 100 - 5 x recovery time - 10 x failure recurrence number.

[0071] Wherein, the model training and deployment are completed offline, the initial Q table of the Q-learning model is generated by large-scale simulation training on the ground, covering all typical fault scenes; the mature Q table is solidified and deployed to the airborne system. Learning update in flight is only performed during non-critical flight phase and when system resources are sufficient, or learning logs are recorded for iterative optimization of the ground model.

[0072] It should be noted that the above embodiment provides a modular digital audio multi-channel IO control system for aviation communication, which is only exemplified by the division of the above functional modules. In actual application, the above functions can be completed by different functional modules according to needs, that is, the modules or steps in the embodiment of the application are further decomposed or combined, for example, the modules of the above embodiment can be combined into one module, or can be further split into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the application are only for distinguishing the modules and steps, and should not be considered as an improper limitation of the application.

[0073] The second embodiment of the application provides a modular digital audio multi-channel IO control method for aviation communication, which comprises: S1, acquire and fuse multi-domain heterogeneous data to construct a scene vector for quantifying a real-time aviation scene; the scene vector includes a flight phase, a threat density, an engine state, and an electromagnetic interference intensity; S2, based on the scene vector, infer and generate core synchronization parameters matched with the current scene through a pre-trained neural network inference model; the core synchronization parameters at least include a synchronization accuracy threshold for calibrating clock bias; S3, according to the core synchronization parameters, perform clock calibration and link configuration on multiple IO channels of aviation audio to realize synchronization control between channels; S4, monitor the running state of the synchronization control to evaluate system health, and perform feedback optimization on the neural network inference model based on the evaluation result of the system health.

[0074] Although the above embodiments are described in the above order, those skilled in the art can understand that, in order to achieve the effect of the embodiments, the different steps do not have to be executed in such an order, and can be executed simultaneously (in parallel) or in a reversed order, and these simple changes are within the protection scope of the present application.

[0075] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related description of the above-described method can refer to the corresponding process in the foregoing system embodiments, which will not be repeated here.

[0076] The electronic device of the third embodiment of the present application comprises: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to realize the above-described modular digital audio multi-channel IO control method for aviation communication.

[0077] The computer readable storage medium of the fourth embodiment of the present application stores computer instructions, and the computer instructions are used to be executed by a computer to realize the above-described modular digital audio multi-channel IO control method for aviation communication.

[0078] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process and related description of the above-described electronic device and computer readable storage medium can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0079] Those skilled in the art will appreciate that the modules, methods steps of the examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or combinations of both. The program of the software modules, method steps are stored in a random access memory (RAM), a memory, a read only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and design constraints imposed on the overall system. Skilled persons can implement the described functionality in varying ways for each particular application, but such implementation should not be construed as beyond the scope of the present application.

[0080] Computer program code for carrying out operations of the present application can be written in one or more programming languages or combinations of languages including an object oriented programming language such as Java, Smalltalk, C++ or the like and conventional procedural programming languages such as C or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0081] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flow diagrams or block diagrams can represent a module, a procedure, or a portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or the blocks may

[0082] The terms "first", "second", etc. are used to distinguish similar objects, rather than to describe or indicate a particular order or sequence.

[0083] The term "comprising" or any other similar term is intended to encompass the inclusion of non-exclusive inclusion, so that the process, method, article or equipment / device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or also includes elements inherent to the process, method, article or equipment / device.

[0084] So far, the technical solutions of the present application have been described in combination with the preferred embodiments shown in the drawings, but it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to the related technical features without departing from the principles of the present application, and the technical solutions after these changes or replacements will all fall within the protection scope of the present application.

Claims

1. A modular digital audio multi-channel IO control system for avionics communications, characterized in that, The system comprises: A scene perception module, a forward control module, a synchronous execution module, a health monitoring module and a self-healing learning module, each module being connected by a bus communication to form a closed-loop control architecture; The scene perception module collects multi-domain heterogeneous data and performs dynamic weight fusion processing, and outputs a scene vector representing the current flight scene, wherein the dynamic weight is adaptively adjusted according to the electromagnetic interference intensity; The forward control module receives the scene vector as input, and a pre-trained neural network inference model generates core synchronization parameters adapted to the current scene; The synchronous execution module generates a reference clock according to the core synchronization parameters, uses a prediction compensation mechanism to calibrate the clock deviation of the digital audio multi-IO channel, and realizes multi-channel synchronous control; The health monitoring module collects the whole link running state, evaluates the system health degree and outputs the evaluation result; The self-healing learning module dynamically selects a self-healing strategy according to the evaluation result and the scene vector, feeds back the self-healing result to the forward control module, and regenerates the adaptive parameters based on the changed state to realize the control strategy closed loop.

2. The modular digital audio multi-channel IO control system for aeronautical communications of claim 1, wherein, The scene perception module comprises: An interface adaptation unit configured with interfaces connected to a flight management system, a traffic warning and collision avoidance system and an engine control system respectively to collect three-dimensional route data, multi-target threat data and engine real-time state parameters respectively; A dynamic weight fusion unit with an electromagnetic interference detection subunit, which adjusts the weight proportion of each domain data according to the electromagnetic interference intensity, specifically: When the electromagnetic interference intensity is higher than -80dBm, the weight proportion of the engine real-time state parameters is increased; when the electromagnetic interference intensity is lower than -100dBm, the weight proportion of the multi-target threat data is increased; A scene vector generation unit for quantizing the fused data into a four-dimensional scene vector containing flight phase, threat density, engine state and electromagnetic interference intensity.

3. The modular digital audio multi-channel IO control system for aeronautical communications of claim 1, wherein, The forward control module comprises: A neural network processing unit for receiving the four-dimensional parameters of the scene vector, extracting scene depth features through a ReLU activation function, and outputting core synchronization parameters from the output layer using a trained neural network inference model; A parameter cache unit for storing the generated core synchronization parameters, wherein the core synchronization parameters include a synchronization accuracy threshold, a sampling rate and a PI controller adjustment coefficient, and the parameter update delay is ≤2ms; A parameter feedback adjustment unit in communication connection with the self-healing learning module for receiving optimization instructions and dynamically correcting the output parameters of the neural network inference model.

4. The modular digital audio multi-channel IO control system for aeronautical communications of claim 3, wherein, The synchronous execution module comprises: A reference clock generation unit for generating a reference clock signal according to the sampling rate in the core synchronization parameters; A prediction compensation calibration unit with a deviation prediction subunit and a compensation execution subunit for analyzing historical clock deviation data to calculate the deviation trend through the deviation prediction subunit, and generating a compensation amount according to the predicted deviation through the compensation execution subunit to realize the advance calibration of the clock deviation; A calibration cycle adjustment unit for dynamically adjusting the calibration cycle according to the scene vector, wherein the calibration cycle in an emergency scene is one fifth of the regular cycle, and the calibration cycle in a cruising scene is twice the regular cycle.

5. The modular digital audio multi-channel IO control system for aeronautical communications of claim 4, wherein, The method for realizing the advance calibration of the clock deviation is: Collect the time stamp of the local clock of each IO channel, and calculate the current clock deviation of each channel with reference to the reference time stamp corresponding to the reference clock signal; Analyze the historical deviation data of each channel by using the sliding window method, and calculate the current deviation change rate combined with the sampling period; Combine the current clock deviation, deviation change rate of each channel, and the prediction coefficient corresponding to the scene to generate a compensation value; the prediction coefficient is dynamically adjusted according to the flight phase; Write the compensation value into the clock controller of each IO channel through software interruption, respectively adjust the local clock frequency, and complete the calibration; wherein the calibration period is consistent with the sampling period, and the clock deviation after calibration does not exceed the synchronization accuracy threshold.

6. The modular digital audio multi-channel IO control system for aeronautical communications of claim 4, wherein, The synchronization execution module further includes a link dynamic configuration unit, which is in communication connection with the forward-looking control module, dynamically adjusts the link working mode according to the synchronization accuracy threshold in the core synchronization parameter, and the method is as follows: When the synchronization accuracy threshold is lower than the preset accuracy threshold, a low-delay mode is enabled, the link cache depth is reduced, and the CPU resource allocation ratio is increased; When the synchronization accuracy threshold is higher than the preset accuracy threshold, an energy efficiency mode is enabled, the link cache depth is adjusted, and a lightweight transmission coding is used; The link dynamic configuration unit includes a priority determination subunit, which dynamically adjusts the link priority according to the threat collision time in the multi-target threat data, and sets the link priority to the highest level in an emergency scene.

7. The modular digital audio multi-channel IO control system for aeronautical communications of claim 6, wherein, The link dynamic configuration unit further includes a spatial audio enhancement subunit, which is used to calculate the left and right channel gain difference through the head-related transfer function when the link is at the highest level, and adds delay compensation according to the threat azimuth angle.

8. The modular digital audio multi-channel IO control system for aeronautical communications of claim 5, wherein, The health monitoring module includes: A state acquisition unit is configured to acquire three types of indexes, including synchronization stability, link smoothness and data integrity, wherein the synchronization stability is the time proportion of the clock deviation meeting the synchronization accuracy threshold, the link smoothness is the time proportion of the link delay being less than or equal to the delay threshold, and the data integrity is 1 minus the data packet loss rate; A health degree calculation unit is configured to calculate the system health degree by using a weighted algorithm based on the synchronization stability, the link smoothness and the data integrity; A threshold dynamic adjustment unit is configured to correct the health degree threshold according to the historical fault number, so as to realize adaptive optimization of the self-healing triggering condition.

9. The modular digital audio multi-channel IO control system for aeronautical communications of claim 1, wherein, The self-healing learning module includes: A self-healing strategy library stores three types of self-healing strategies, including a non-key link sacrifice strategy, an anti-interference coding enhancement strategy and a minimum feature set starting strategy, and each self-healing strategy is mapped to a scene vector; A strategy selection unit is configured to call the adaptive self-healing strategy according to the health degree evaluation result and the current scene vector, and call the anti-interference coding enhancement strategy in a strong electromagnetic interference scene and call the non-key link release strategy in a multi-threat scene; A Q learning unit is configured to update the mapping relationship between the scene and the strategy according to the self-healing result.

10. A modular digital audio multi-channel IO control method for aeronautical communications, characterized by, The method includes the following steps: Obtain and fuse multi-domain heterogeneous data to construct a scene vector for quantifying real-time aviation scenes; the scene vector includes a flight phase, a threat density, an engine state and an electromagnetic interference intensity; Based on the scene vector, a pre-trained neural network inference model is used to infer and generate core synchronization parameters matched with the current scene; the core synchronization parameters at least include a synchronization accuracy threshold for calibrating clock bias; According to the core synchronization parameters, clock calibration and link configuration are performed on multiple IO channels of the aviation audio to realize synchronization control between channels; The running state of the synchronization control is monitored to evaluate the system health, and the neural network inference model is optimized based on the evaluation result of the system health.

Images