Aircraft avionics management method and system based on centralized power supply and signal hub

Abstract

This invention belongs to the field of artificial intelligence and intelligent control system technology, and discloses an aircraft avionics management method and system based on a centralized power supply and signal hub. The method includes: performing power supply channel status analysis and energy consumption analysis on the overall aircraft power supply and distribution data to obtain overall aircraft power supply and distribution analysis results; performing protocol analysis and topology connectivity judgment on the overall aircraft signal data to obtain overall aircraft signal link analysis results; using flight control status data as status anchors and mission phase data as semantic context to construct an overall aircraft energy information status fusion map; extracting a multi-dimensional coupling feature set of the overall aircraft avionics; and combining pre-set avionics control rules to achieve centralized management of aircraft avionics energy flow and data flow. This invention lays a solid foundation for achieving predictive maintenance, energy efficiency optimization, and adaptive mission configuration.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence and intelligent control system technology, and in particular to an aircraft avionics management method and system based on a centralized power supply and signal hub. Background Technology

[0002] Currently, with the widespread application of advanced configuration aircraft such as vertical takeoff and landing (VTOL) UAVs and compound-wing UAVs, their avionics systems are becoming increasingly complex, integrating multiple power systems, servo mechanisms, various mission payloads, and various navigation sensors. Traditional avionics systems generally adopt a distributed or regional convergence architecture in terms of physical integration and electrical interconnection. A typical approach involves distributing power management and signal processing functions across flight control computers, power supply boxes, power distribution boards, and various independent interface modules, then connecting these units to terminal equipment (such as motors, servos, sensors, and payloads) throughout the fuselage via numerous, lengthy cables. This architecture results in a complex internal cabling network, a significant increase in overall weight, and numerous connection points and wiring harness branches. These nodes are highly susceptible to failure under harsh environments such as vibration and extreme temperatures, making it difficult to improve the overall reliability of the system. Furthermore, power lines and signal lines often inevitably run parallel or cross over long distances, leading to significant electromagnetic interference problems and threatening sensitive signal acquisition and control loops. At the maintenance and upgrade level, replacing or adding any equipment has far-reaching consequences, requiring the redesign or modification of numerous cable connections. This process is cumbersome and prone to errors, severely impacting the mission adaptability and rapid deployment capabilities of the aircraft platform. Existing integration solutions, even those using multi-core aviation connectors for partial integration, merely reduce some external cables. They do not fundamentally restructure and centrally manage the energy and data flow of the entire aircraft from the top system level, failing to meet the urgent needs of next-generation UAVs for high reliability, high maintainability, and agile configuration.

[0003] Therefore, how to provide an aircraft avionics management method and system based on a centralized power supply and signal hub is an urgent problem to be solved. Summary of the Invention

[0004] The present invention provides an aircraft avionics management method and system based on a centralized power supply and signal hub to solve the above-mentioned technical problems in the prior art.

[0005] According to a first aspect of the present invention, an aircraft avionics management method based on a centralized power supply and signal hub is provided.

[0006] In one embodiment, the aircraft avionics management method based on a centralized power supply and signal hub includes: Acquire the power supply and distribution data and signal data of the whole machine, perform power supply channel status analysis and energy consumption analysis on the power supply and distribution data of the whole machine to obtain the power supply and distribution analysis results of the whole machine, and perform protocol analysis and topology connectivity judgment on the signal data of the whole machine to obtain the signal link analysis results of the whole machine. Using flight control status data as status anchors and mission phase data as semantic context, and combining the results of the whole aircraft power supply and distribution analysis and the whole aircraft signal link analysis, a whole aircraft energy information status fusion map is constructed. Based on the energy information status fusion map of the whole aircraft, the coupling correlation and dynamic change characteristics of energy flow, data flow and flight status and mission phase in the map are extracted to obtain the multi-dimensional coupling feature set of the whole aircraft avionics; The system performs feature decoupling analysis and operating condition strategy matching on the multi-dimensional coupling feature set of the entire aircraft's avionics system, and generates power supply and distribution control commands and signal link configuration commands in combination with preset avionics control rules, thereby realizing centralized management of the aircraft's avionics energy flow and data flow.

[0007] In one embodiment, power supply channel status analysis and energy consumption analysis are performed on the overall power supply and distribution data to obtain the overall power supply and distribution analysis results. Furthermore, protocol parsing and topology connectivity determination are performed on the overall signal data to obtain the overall signal link analysis results, including: The power supply and distribution data of the whole machine is analyzed for parameters of each power supply channel, and the state is determined in combination with the preset channel rated threshold. The state is quantified according to the determination result to obtain the power supply channel state vector. An energy consumption distribution matrix is ​​constructed based on the power supply channel state vector. Abnormal power consumption patterns are identified on the energy consumption distribution matrix to obtain a star-shaped energy consumption distribution map of the entire machine and generate the power supply and distribution analysis results of the entire machine. The system analyzes the signal data of the whole machine according to the port identification signal protocol type to obtain the parsed device signal data, and determines the link connectivity and communication quality level according to the preset mapping table and the continuous frame reception status. A star topology connectivity graph is constructed based on link connectivity and communication quality level. Signal link health diagnosis and resource optimization are performed on the star topology connectivity graph to generate full-machine signal link analysis results.

[0008] In one embodiment, an energy consumption distribution matrix is ​​constructed based on the power supply channel state vector. Abnormal power consumption patterns are identified on the energy consumption distribution matrix to obtain a star-shaped energy consumption distribution map of the entire machine. The resulting power supply and distribution analysis of the entire machine includes: Energy consumption is assessed based on the power supply channel state vector to obtain load energy consumption assessment results. The load energy consumption assessment results are then categorized according to equipment function categories to obtain energy consumption classification results. The energy consumption classification results are combined with the task phase data to perform energy consumption feature weight labeling, and the weighted energy consumption classification results are filled into the matrix cells to obtain the energy consumption distribution matrix. A power consumption baseline is constructed based on historical normal operating condition data. Deviation detection and abnormal load labeling are performed on the energy consumption distribution matrix and the corresponding power consumption baseline to obtain an abnormal load labeled energy consumption matrix. The abnormal load marker energy consumption matrix is ​​mapped to a star topology centered on the whole machine power supply and distribution hub to generate a star distribution map of the whole machine's energy consumption; The energy consumption star distribution diagram of the whole machine is extracted and quantified to obtain the quantitative statistical results of the load energy consumption of each node. The energy consumption matching degree of the power supply channel under the star topology is analyzed to obtain the power supply and distribution analysis results of the whole machine.

[0009] In one embodiment, a star topology connectivity graph is constructed based on link connectivity and communication quality level. Signal link health diagnosis and resource optimization are then performed on the star topology connectivity graph to generate full-machine signal link analysis results, including: Based on the link connectivity determination results, connected edges are constructed, and weight labels are set according to the communication quality level to construct a star topology connectivity graph. The star topology connectivity graph is combined with preset communication quality thresholds and continuous frame reception status to determine the status, and link faults are identified based on the determination results to obtain link fault diagnosis results. Based on the link fault diagnosis results, the parameters of the star topology connectivity diagram are adjusted to generate the optimal signal connectivity diagram. Then, the link redundancy of the optimal signal connectivity diagram is quantitatively calculated to obtain the overall signal link analysis results.

[0010] In one embodiment, a fusion map of the entire aircraft's energy information status is constructed by using flight control status data as the status anchor, mission phase data as the semantic context, and combining the results of the overall aircraft power supply and distribution analysis with the results of the overall aircraft signal link analysis. Using the sampling period of flight control status data as the primary time reference and the aircraft's centroid coordinate system as the spatial reference, the spatiotemporal synchronization mapping and multidimensional feature alignment of the whole aircraft power supply and distribution analysis results and the whole aircraft signal link analysis results are performed to generate physically aligned multimodal spatiotemporal tensors. Using task phase data as domain labels, the adversarial domain adaptation mechanism is used to decouple the multimodal spatiotemporal tensor to obtain energy domain and data domain features. The energy domain and data domain features are then fused according to task semantic weights to obtain a semantic feature embedding set and a domain confidence matrix. Using semantic feature embedding sets as node attributes and domain confidence matrices as edge dynamic adjustment factors, and constructing a heterogeneous graph structure with power supply and distribution hubs and signal hubs as dual cores, a model of the heterogeneous graph structure is obtained to obtain a fusion map of the energy information status of the entire machine.

[0011] In one embodiment, based on the whole-aircraft energy information state fusion map, the coupling correlation patterns and dynamic change characteristics of energy flow, data flow, flight status, and mission phase in the map are extracted to obtain the whole-aircraft avionics multi-dimensional coupling feature set, including: Based on the energy information state fusion graph of the whole machine, source nodes and target nodes are set, and energy edges and data edges in the energy information state fusion graph of the whole machine are sampled to obtain several meta-paths. Path association coupling is performed on each meta-path to obtain a set of coupled paths and a path-level coupling coefficient matrix. Based on the set of coupling paths and the path-level coupling coefficient matrix, the snapshot sequence of the whole machine energy information state fusion map within a continuous time window is slicing to obtain the slicing result. Dynamic coupling pattern recognition is performed on the sliding slice results to obtain a co-evolution feature set. The co-evolution feature set is then mapped and encapsulated according to four dimensions: energy flow, data flow, flight status, and mission phase, to obtain a multi-dimensional coupling feature set of the entire aircraft's avionics.

[0012] In one embodiment, source nodes and target nodes are set according to the overall energy information state fusion graph, and energy edges and data edges in the overall energy information state fusion graph are sampled to obtain several meta-paths. Path association coupling is performed on each meta-path to obtain a set of coupled paths and a path-level coupling coefficient matrix, including: Using the power supply and distribution hub and signal hub in the whole aircraft energy information state fusion graph as source nodes, and the flight control state and mission phase as target nodes, the energy edge and data edge in the whole aircraft energy information state fusion graph are jointly sampled based on meta-path to obtain the causal transmission meta-path of energy flow to flight state and the response feedback meta-path of data flow to mission phase. The coupling strength coefficient between the source node and the target node under each meta-path is calculated by using the path accumulation attention mechanism, resulting in a set of coupled paths with correlation strength weights and a path-level coupling coefficient matrix.

[0013] In one embodiment, dynamic coupling pattern recognition is performed on the sliding slice results to obtain a co-evolution feature set. This co-evolution feature set is then mapped and encapsulated along four dimensions: energy flow, data flow, flight state, and mission phase, resulting in a multi-dimensional coupling feature set for the entire aircraft's avionics system, including: A temporal graph convolutional network is used to jointly extract spatial neighborhood features and temporal evolution trends from the sliding slice results to obtain energy flow and data flow feature time-series curves. Cross covariance is used to perform dynamic coupling pattern recognition on the energy flow and data flow feature time-series curves to obtain a co-evolution feature set. The co-evolutionary feature set is mapped to fields according to four dimensions: energy flow, data flow, flight status, and mission phase, resulting in an evolutionary feature grouping table. The features in each group of the evolution feature grouping table are standardized in terms of dimensions to obtain a standard multidimensional coupling feature set. The standard multidimensional coupling feature set is then hierarchically organized according to a preset feature sorting architecture. The organized coupling feature set is then encapsulated with structured vectors to obtain the full-aircraft avionics multidimensional coupling feature set.

[0014] In one embodiment, feature decoupling analysis and operational condition strategy matching are performed on the multi-dimensional coupling feature set of the entire aircraft's avionics system. Combined with pre-set avionics control rules, power supply and distribution control commands and signal link configuration commands are generated to achieve centralized management of the aircraft's avionics energy flow and data flow. The multi-dimensional coupling feature set of the whole aircraft avionics is decoupled according to four dimensions: energy flow, data flow, flight status and mission phase, to obtain energy information decoupling sub-features; The energy information decoupled sub-features are matched with a pre-set operating condition feature template library for similarity, and the operating condition label of the current aircraft is identified based on the similarity matching results. Based on the operating condition label, the corresponding control strategy is retrieved from the pre-set avionics control rule library, and combined with the power coupling strength, command response correlation and energy constraint coefficient in the energy information decoupling sub-feature, the power supply priority, communication bandwidth allocation and load energy consumption limit parameters are dynamically adapted. The power supply priority, communication bandwidth allocation, and load energy consumption limit parameters are converted into power supply channel switching timing, voltage regulation commands, and overload protection thresholds that can be executed by the whole machine power supply and distribution hub, as well as protocol configuration, redundant link switching, and bandwidth scheduling commands that can be executed by the whole machine signal hub. These commands are then sent to the whole machine power supply and distribution hub and the whole machine signal hub for coordinated execution, thereby achieving centralized management of energy flow and data flow.

[0015] According to a second aspect of the present invention, an aircraft avionics management system based on a centralized power supply and signal hub is provided.

[0016] In one embodiment, the aircraft avionics management system based on a centralized power supply and signaling hub includes: The whole machine data analysis module is used to acquire the whole machine power supply and distribution data and the whole machine signal data. It performs power supply channel status analysis and energy consumption analysis on the whole machine power supply and distribution data to obtain the whole machine power supply and distribution analysis results. It also performs protocol analysis and topology connectivity judgment on the whole machine signal data to obtain the whole machine signal link analysis results. The map construction module is used to construct a fusion map of the energy information status of the entire aircraft by using flight control status data as status anchors, mission phase data as semantic context, and combining the analysis results of the power supply and distribution of the entire aircraft and the analysis results of the signal link of the entire aircraft. The feature coupling module is used to extract the coupling correlation and dynamic change characteristics of energy flow, data flow and flight status and mission phase in the energy information status fusion map of the whole aircraft, and obtain the multi-dimensional coupling feature set of the whole aircraft avionics. The operating condition strategy matching module is used to perform feature decoupling analysis and operating condition strategy matching on the multi-dimensional coupling feature set of the entire aircraft's avionics system. It also generates power supply and distribution control commands and signal link configuration commands in combination with preset avionics control rules, thereby realizing centralized management of the aircraft's avionics energy flow and data flow.

[0017] According to a third aspect of the present invention, a computer device is provided.

[0018] In some embodiments, the computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the above-described aircraft avionics management method based on a centralized power supply and signal hub.

[0019] According to a fourth aspect of the present invention, a computer-readable storage medium is provided.

[0020] In one embodiment, a computer program is stored on a computer-readable storage medium, which, when executed by a processor, implements the steps of the above-described aircraft avionics management method based on a centralized power supply and signal hub.

[0021] The technical solutions provided by the embodiments of the present invention may include the following beneficial effects: 1. This invention fundamentally reconstructs the energy flow and data flow management of aircraft. By integrating the power supply and distribution and signal links of the entire aircraft into a spatiotemporally aligned energy, information, and status fusion map for collaborative perception and intelligent decision-making, it achieves dynamic optimization configuration of power supply channels and communication links, rapid fault isolation, and adaptive load balancing. This not only significantly reduces the number of internal cables and connection nodes, but also significantly reduces system weight and failure rate, and improves electromagnetic compatibility and operational reliability.

[0022] 2. This invention transforms the traditional complex and intertwined cable network into a clear star-shaped structure radiating outwards from two central hubs. This significantly reduces the total cable length, weight, and number of connection points, lowering manufacturing costs and parasitic losses. Furthermore, it fundamentally reduces the probability of failures caused by cable and connector issues, resulting in a qualitative improvement in system physical reliability. In terms of electrical performance, the centralized isolation of high-voltage and low-voltage signals at the hub level, coupled with internal filtering and shielding design, greatly improves the system's electromagnetic compatibility, significantly enhancing the integrity and stability of signal transmission. Its advantages are particularly prominent in terms of system maintainability and scalability. The installation, replacement, or upgrade of any terminal device only requires operating on the single connection between that device and the corresponding hub, much like plugging and unplugging modules on a "hub." It supports rapid connection and even hot-swapping, making field maintenance, load switching, or system reconfiguration exceptionally convenient and efficient. Meanwhile, this centralized architecture enables global status monitoring and intelligent management. The power supply hub can monitor the energy consumption and health status of each load in real time, and the signal hub can monitor the connectivity and quality of each data link. This information is aggregated to the flight control system, laying a solid foundation for predictive maintenance, energy efficiency optimization, and adaptive mission configuration. Furthermore, this architecture has high platform adaptability and standardization potential. By defining and solidifying the external interface standards of the hub module, it can become a universal core avionics component, quickly adaptable to various UAV platforms of different sizes and purposes.

[0023] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0024] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0025] Figure 1 This is a flowchart illustrating an aircraft avionics management method based on a centralized power supply and signal hub, according to an exemplary embodiment. Figure 2 This is a schematic diagram illustrating the structure of an aircraft avionics management system based on a centralized power supply and signal hub, according to an exemplary embodiment. Figure 3 This is a schematic diagram of the structure of a computer device according to an exemplary embodiment; Figure 4 This is a power supply connection diagram of the entire machine according to an exemplary embodiment; Figure 5 This is a signal connection diagram of the entire machine according to an exemplary embodiment; Figure 6This is a diagram illustrating the connection of an avionics box according to an exemplary embodiment.

[0026] Figure label: 201. Whole machine data analysis module; 202. Map construction module; 203. Feature coupling module; 204. Operating condition strategy matching module. Detailed Implementation

[0027] The following description and accompanying drawings fully illustrate specific embodiments described herein to enable those skilled in the art to practice them. Some portions and features of certain embodiments may be included in or replace portions and features of other embodiments. The scope of the embodiments herein includes the entire scope of the claims and all available equivalents thereof. The various embodiments described herein are presented in a progressive manner, with each embodiment focusing on its differences from other embodiments; similar or identical parts between embodiments can be referred to interchangeably.

[0028] The various modules in the apparatus or system of the present invention can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device in hardware form, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0029] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0030] Figure 1 An embodiment of the aircraft avionics management method based on a centralized power supply and signal hub of the present invention is shown.

[0031] In this optional embodiment, the aircraft avionics management method based on a centralized power supply and signal hub includes: Step S101: Obtain the power supply and distribution data and signal data of the whole machine; perform power supply channel status analysis and energy consumption analysis on the power supply and distribution data of the whole machine to obtain the power supply and distribution analysis results of the whole machine; and perform protocol analysis and topology connectivity judgment on the signal data of the whole machine to obtain the signal link analysis results of the whole machine. Step S102: Using flight control status data as the status anchor point and mission phase data as the semantic context, and combining the whole aircraft power supply and distribution analysis results and the whole aircraft signal link analysis results, construct a whole aircraft energy information status fusion map. Step S103: Based on the full-aircraft energy information status fusion map, extract the coupling correlation rules and dynamic change characteristics of energy flow, data flow and flight status and mission phase in the map to obtain the full-aircraft avionics multi-dimensional coupling feature set; Step S104 involves performing feature decoupling analysis and operating condition strategy matching on the multi-dimensional coupling feature set of the entire aircraft's avionics system, and generating power supply and distribution control commands and signal link configuration commands in conjunction with preset avionics control rules, thereby realizing centralized management of the aircraft's avionics energy flow and data flow.

[0032] In this optional embodiment, the power supply channel status is analyzed and energy consumption is analyzed on the overall power supply and distribution data to obtain the overall power supply and distribution analysis results. Furthermore, the overall signal data is parsed and topology connectivity is determined to obtain the overall signal link analysis results, including: The power supply and distribution data of the whole machine is analyzed for parameters of each power supply channel, and the state is determined in combination with the preset channel rated threshold. The state is quantified according to the determination result to obtain the power supply channel state vector. An energy consumption distribution matrix is ​​constructed based on the power supply channel state vector. Abnormal power consumption patterns are identified on the energy consumption distribution matrix to obtain a star-shaped energy consumption distribution map of the entire machine and generate the power supply and distribution analysis results of the entire machine. The system analyzes the signal data of the whole machine according to the port identification signal protocol type to obtain the parsed device signal data, and determines the link connectivity and communication quality level according to the preset mapping table and the continuous frame reception status. A star topology connectivity graph is constructed based on link connectivity and communication quality level. Signal link health diagnosis and resource optimization are performed on the star topology connectivity graph to generate full-machine signal link analysis results.

[0033] In this optional embodiment, an energy consumption distribution matrix is ​​constructed based on the power supply channel state vector. Abnormal power consumption patterns are identified on the energy consumption distribution matrix to obtain a star-shaped energy consumption distribution map of the entire machine. The resulting power supply and distribution analysis of the entire machine includes: Energy consumption is assessed based on the power supply channel state vector to obtain load energy consumption assessment results. The load energy consumption assessment results are then categorized according to equipment function categories to obtain energy consumption classification results. The energy consumption classification results are combined with the task phase data to perform energy consumption feature weight labeling, and the weighted energy consumption classification results are filled into the matrix cells to obtain the energy consumption distribution matrix. A power consumption baseline is constructed based on historical normal operating condition data. Deviation detection and abnormal load labeling are performed on the energy consumption distribution matrix and the corresponding power consumption baseline to obtain an abnormal load labeled energy consumption matrix. The abnormal load marker energy consumption matrix is ​​mapped to a star topology centered on the whole machine power supply and distribution hub to generate a star distribution map of the whole machine's energy consumption; The energy consumption star distribution diagram of the whole machine is extracted and quantified to obtain the quantitative statistical results of the load energy consumption of each node. The energy consumption matching degree of the power supply channel under the star topology is analyzed to obtain the power supply and distribution analysis results of the whole machine.

[0034] In this optional embodiment, a star topology connectivity graph is constructed based on link connectivity and communication quality level. Signal link health diagnosis and resource optimization are performed on the star topology connectivity graph to generate full-machine signal link analysis results, including: Based on the link connectivity determination results, connected edges are constructed, and weight labels are set according to the communication quality level to construct a star topology connectivity graph. The star topology connectivity graph is combined with preset communication quality thresholds and continuous frame reception status to determine the status, and link faults are identified based on the determination results to obtain link fault diagnosis results. Based on the link fault diagnosis results, the parameters of the star topology connectivity diagram are adjusted to generate the optimal signal connectivity diagram. Then, the link redundancy of the optimal signal connectivity diagram is quantitatively calculated to obtain the overall signal link analysis results.

[0035] In this optional embodiment, using flight control status data as the status anchor point and mission phase data as the semantic context, and combining the results of the overall aircraft power supply and distribution analysis and the overall aircraft signal link analysis to construct an overall aircraft energy information status fusion map includes: Using the sampling period of flight control status data as the primary time reference and the aircraft's centroid coordinate system as the spatial reference, the spatiotemporal synchronization mapping and multidimensional feature alignment of the whole aircraft power supply and distribution analysis results and the whole aircraft signal link analysis results are performed to generate physically aligned multimodal spatiotemporal tensors. Using task phase data as domain labels, the adversarial domain adaptation mechanism is used to decouple the multimodal spatiotemporal tensor to obtain energy domain and data domain features. The energy domain and data domain features are then fused according to task semantic weights to obtain a semantic feature embedding set and a domain confidence matrix. Using semantic feature embedding sets as node attributes and domain confidence matrices as edge dynamic adjustment factors, and constructing a heterogeneous graph structure with power supply and distribution hubs and signal hubs as dual cores, a model of the heterogeneous graph structure is obtained to obtain a fusion map of the energy information status of the entire machine.

[0036] In this optional embodiment, based on the whole-aircraft energy information state fusion map, the coupling correlation patterns and dynamic change characteristics of energy flow, data flow, flight status, and mission phase in the map are extracted to obtain the whole-aircraft avionics multi-dimensional coupling feature set, including: Based on the energy information state fusion graph of the whole machine, source nodes and target nodes are set, and energy edges and data edges in the energy information state fusion graph of the whole machine are sampled to obtain several meta-paths. Path association coupling is performed on each meta-path to obtain a set of coupled paths and a path-level coupling coefficient matrix. Based on the set of coupling paths and the path-level coupling coefficient matrix, the snapshot sequence of the whole machine energy information state fusion map within a continuous time window is slicing to obtain the slicing result. Dynamic coupling pattern recognition is performed on the sliding slice results to obtain a co-evolution feature set. The co-evolution feature set is then mapped and encapsulated according to four dimensions: energy flow, data flow, flight status, and mission phase, to obtain a multi-dimensional coupling feature set of the entire aircraft's avionics.

[0037] In this optional embodiment, source nodes and target nodes are set according to the overall energy information state fusion graph, and energy edges and data edges in the overall energy information state fusion graph are sampled to obtain several meta-paths. Path association coupling is performed on each meta-path to obtain a set of coupled paths and a path-level coupling coefficient matrix, including: Using the power supply and distribution hub and signal hub in the whole aircraft energy information state fusion graph as source nodes, and the flight control state and mission phase as target nodes, the energy edge and data edge in the whole aircraft energy information state fusion graph are jointly sampled based on meta-path to obtain the causal transmission meta-path of energy flow to flight state and the response feedback meta-path of data flow to mission phase. The coupling strength coefficient between the source node and the target node under each meta-path is calculated by using the path accumulation attention mechanism, resulting in a set of coupled paths with correlation strength weights and a path-level coupling coefficient matrix.

[0038] In this optional embodiment, dynamic coupling pattern recognition is performed on the sliding slice results to obtain a co-evolution feature set. This co-evolution feature set is then mapped and encapsulated according to four dimensions: energy flow, data flow, flight status, and mission phase, resulting in a multi-dimensional coupling feature set for the entire aircraft's avionics system, including: A temporal graph convolutional network is used to jointly extract spatial neighborhood features and temporal evolution trends from the sliding slice results to obtain energy flow and data flow feature time-series curves. Cross covariance is used to perform dynamic coupling pattern recognition on the energy flow and data flow feature time-series curves to obtain a co-evolution feature set. The co-evolutionary feature set is mapped to fields according to four dimensions: energy flow, data flow, flight status, and mission phase, resulting in an evolutionary feature grouping table. The features in each group of the evolution feature grouping table are standardized in terms of dimensions to obtain a standard multidimensional coupling feature set. The standard multidimensional coupling feature set is then hierarchically organized according to a preset feature sorting architecture. The organized coupling feature set is then encapsulated with structured vectors to obtain the full-aircraft avionics multidimensional coupling feature set.

[0039] In this optional embodiment, feature decoupling analysis and operating condition strategy matching are performed on the multi-dimensional coupling feature set of the entire aircraft's avionics system. Combined with pre-set avionics control rules, power supply and distribution control commands and signal link configuration commands are generated to achieve centralized management of the aircraft's avionics energy flow and data flow, including: The multi-dimensional coupling feature set of the whole aircraft avionics is decoupled according to four dimensions: energy flow, data flow, flight status and mission phase, to obtain energy information decoupling sub-features; The energy information decoupled sub-features are matched with a pre-set operating condition feature template library for similarity, and the operating condition label of the current aircraft is identified based on the similarity matching results. Based on the operating condition label, the corresponding control strategy is retrieved from the pre-set avionics control rule library, and combined with the power coupling strength, command response correlation and energy constraint coefficient in the energy information decoupling sub-feature, the power supply priority, communication bandwidth allocation and load energy consumption limit parameters are dynamically adapted. The power supply priority, communication bandwidth allocation, and load energy consumption limit parameters are converted into power supply channel switching timing, voltage regulation commands, and overload protection thresholds that can be executed by the whole machine power supply and distribution hub, as well as protocol configuration, redundant link switching, and bandwidth scheduling commands that can be executed by the whole machine signal hub. These commands are then sent to the whole machine power supply and distribution hub and the whole machine signal hub for coordinated execution, thereby achieving centralized management of energy flow and data flow.

[0040] Figure 2 An embodiment of the aircraft avionics management system based on a centralized power supply and signaling hub of the present invention is shown.

[0041] In this optional embodiment, the aircraft avionics management system based on a centralized power supply and signal hub includes: The whole machine data analysis module 201 is used to acquire whole machine power supply and distribution data and whole machine signal data, perform power supply channel status analysis and energy consumption analysis on the whole machine power supply and distribution data to obtain the whole machine power supply and distribution analysis results, and perform protocol analysis and topology connectivity judgment on the whole machine signal data to obtain the whole machine signal link analysis results. The map construction module 202 is used to construct a fusion map of the energy information status of the whole aircraft by using flight control status data as status anchors, mission phase data as semantic context, and combining the analysis results of the whole aircraft power supply and distribution and the analysis results of the whole aircraft signal links. The feature coupling module 203 is used to extract the coupling correlation rules and dynamic change features of energy flow, data flow and flight status and mission phase in the energy information status fusion map of the whole aircraft, and obtain the multi-dimensional coupling feature set of the whole aircraft avionics. The operating condition strategy matching module 204 is used to perform feature decoupling analysis and operating condition strategy matching on the multi-dimensional coupling feature set of the entire aircraft's avionics, and generate power supply and distribution control instructions and signal link configuration instructions in combination with preset avionics control rules, so as to realize centralized management of the aircraft's avionics energy flow and data flow.

[0042] To facilitate understanding of the above technical solutions of the present invention, the following further explains the above technical solutions of the present invention from the perspective of architecture and principle, as follows: It should be further explained that the power supply and distribution data of the whole machine is obtained, and the voltage, current, power, temperature and switch status parameters of each power supply channel are analyzed. In addition, the overcurrent, overvoltage, undervoltage and overtemperature status are judged in combination with the preset channel rated threshold. Based on the judgment results, the power supply channel status is quantified to obtain the power supply channel status vector with health label.

[0043] Based on the preset device and port mapping table, the parsed device signal data is used to identify the device and verify its status. The link connectivity and communication quality level are determined by combining the continuous frame reception status.

[0044] The instantaneous power and cumulative energy consumption of each electrical device are calculated based on the power supply channel state vector to obtain the device-level load energy consumption assessment results. These results are then categorized according to device function to obtain the function-level energy consumption classification results. The function-level energy consumption classification results are combined with task phase data to weight the typical energy consumption characteristics of each task phase. Using task phases as rows and device categories as columns, the weighted function-level energy consumption classification results are filled into matrix cells to obtain an energy consumption distribution matrix reflecting the overall energy allocation under different task phases. Based on historical normal operating data, power consumption baselines and confidence intervals for each device category in different task phases are constructed. Each cell value in the energy consumption distribution matrix is ​​then compared with its corresponding power consumption baseline. Deviation detection is performed, and abnormal load labels are marked on the energy consumption distribution matrix based on the deviation detection results to obtain an abnormal load-labeled energy consumption matrix. The abnormal load-labeled energy consumption matrix is ​​mapped to a star topology structure centered on the whole machine power supply and distribution hub, and the abnormal load labels are associated with the corresponding radial branches according to the physical connection relationship of the equipment to generate a whole machine energy consumption star distribution map with abnormal load labels. The load energy consumption values, proportions and changing trends of each radial node in the whole machine energy consumption star distribution map are extracted and quantified to obtain the load energy consumption quantification statistics of each node. The energy consumption matching degree of the power supply channel under the star topology is analyzed by comparing the rated load threshold of each power supply channel with the energy consumption benchmark range to obtain the whole machine power supply and distribution analysis results.

[0045] Based on the link connectivity determination results, with the overall signal hub as the central node and each terminal device as the peripheral node, a star topology is constructed to connect the central node and each peripheral node. Each connecting edge is assigned a corresponding weight label according to the communication quality level, thus constructing a star topology connectivity graph. The star topology connectivity graph is then combined with preset communication quality thresholds and continuous frame reception status to compare and determine the status of each connecting edge between the central node and each peripheral node. Link faults are identified based on the comparison and determination results, yielding link fault diagnosis results. Based on the link fault diagnosis results, bandwidth resources are reallocated and weight parameters are adaptively adjusted in the star topology connectivity graph to generate an optimal signal connectivity graph. Finally, link redundancy is quantitatively calculated on the optimal signal connectivity graph to obtain the overall signal link analysis results.

[0046] Using task stage data as domain labels, an adversarial training framework is constructed, consisting of a feature extractor, an energy domain discriminator, a data domain discriminator, and a domain classifier. The feature extractor first maps the multimodal spatiotemporal tensor to a shared latent space representation. The domain classifier, connected by a gradient inversion layer (GRL), predicts the task stage to which the current sample belongs. The feature extractor minimizes the domain classification accuracy through adversarial training, forcing the extracted features to remain unchanged for the task stage (i.e., the domain). Based on this, two parallel sub-networks are introduced to reconstruct power supply and distribution-related features, such as voltage and current timing, and signal link-related features, such as communication delay and packet loss rate, from the dedomainized features. The semantic fidelity is constrained by the reconstruction loss, and the decoupled energy domain features and data domain features are output. The two features are statistically insensitive to the task stage but retain the physical semantic information of their respective modalities.

[0047] In practical applications, the voltage, current, and power parameters of each power supply channel in the overall aircraft power supply and distribution analysis results are aligned with the communication quality and message throughput parameters of each data link in the overall aircraft signal link analysis results. The time axis is aligned using the sampling period of the flight control status data as the time reference, and a spatial grid is mapped using the aircraft's centroid coordinate system as the spatial reference. This constructs a multimodal feature table with equipment nodes as rows and energy and signal characteristics as columns. Based on the stage labels (takeoff, cruise, hovering, landing, etc.) in the mission stage data, the system searches for the relevant equipment nodes under the current mission stage from a pre-set mission stage semantic weight table. The energy feature weight coefficients and signal feature weight coefficients of the backup nodes are multiplied by the corresponding weight coefficients of the energy feature column and the corresponding weight coefficients of the signal feature column of each device node in the multimodal feature table, and then the elements are summed in a weighted manner to generate the semantic feature vector of each device node. The set of semantic feature vectors of all nodes constitutes the semantic feature embedding set. At the same time, based on the statistical frequency of each device node appearing at the same time as each mission stage in historical flight data, the empirical probability of each device node belonging to each mission stage is calculated to form a domain confidence matrix with device nodes as rows and mission stages as columns.

[0048] In practical applications, a heterogeneous graph structure is constructed with power supply and distribution hubs and signal hubs as dual core nodes and various airborne equipment as peripheral nodes. Semantic feature embedding sets are used as attribute vectors for each node. The confidence values ​​in the domain confidence matrix are multiplied by the physical impedance values ​​of the power supply and distribution channels and the communication delay values ​​of the signal links, and then normalized to obtain the weight values ​​for each edge. Continuous time windows are divided according to mission phases such as takeoff, cruise, hovering, and landing. Within each time window, the mean and variance of each node's attributes, the fluctuation range and rate of change of each edge's weights are statistically analyzed. This is achieved by comparing adjacent time windows. The magnitude of node attribute changes and edge weight drift are used to identify the moments when node states undergo significant jumps and the trend of continuous edge weight drift. The node attribute statistics, edge weight statistics, and change characteristics between windows for each time window are filled into the evolution feature table in chronological order. The change patterns in the feature table are manually summarized and classified according to the preset evolution law matching template. The evolution stage label corresponding to each time window is marked. The node attributes, edge weights, evolution stage labels, and time window index are organized together into a whole-machine energy information state fusion map containing dynamic evolution information.

[0049] The standard multidimensional coupling feature set is hierarchically organized according to the three-layer logical structure of energy / data physical layer, flight status state layer, and mission phase semantic layer, and encapsulated in structured vector or JSON format to form a clear and hierarchical multidimensional coupling feature set of the whole aircraft avionics.

[0050] Joint walk sampling involves pre-defining two semantically clear meta-path templates based on the physical connections and functional logic of the aircraft's avionics system. One type is the path from the power supply and distribution hub to the electrical equipment, then to the signal hub, and finally to the flight control status, used to capture the causal transmission relationship of how energy supply affects flight status. The other type is the path from the signal hub to the communication equipment, then to the power supply and distribution hub, and finally to the mission phase, used to characterize the logic of how data interaction feeds back and affects mission execution. Starting from either the power supply and distribution hub or the signal hub, a restricted random walk is performed in the graph, strictly following the node and edge types specified in the meta-path templates. Each step moves only along actual connections in the graph, ensuring that the types of nodes and edges traversed are consistent with the template. During the walk, relevant attributes of energy edges along the path are simultaneously collected, such as channel load rate and energy consumption matching degree, as well as relevant attributes of data edges, such as communication quality level and link redundancy. The node and edge features along the entire path are then sequentially combined into a complete path sample. By repeatedly executing the above process, a large number of path instances that conform to the preset semantic logic are generated, forming a set of joint roaming paths that cover the coupling relationship between key energy flows and data flows.

[0051] The map is divided into time-series slices according to mission phases such as takeoff, cruise, hovering, and landing. The energy flow characteristic parameters and data flow characteristic parameters in each slice are averaged and extreme values ​​are calculated within the phase. By comparing the change amplitude of characteristic parameters between adjacent phase slices, the jump nodes of energy flow before and after phase switching and the gradual change trend of data flow with the phase advancement are identified. The change direction of characteristic parameters on each associated path is summarized and classified, and the synchronous coupling mode of energy flow fluctuating synchronously with flight status, the lag coupling mode of data flow responding to mission phase switching with delay, and the interactive coupling mode of energy flow and data flow exhibiting mutual constraints in specific phases are summarized. The output is an evolutionary feature set including the phase change amplitude, jump node position, and coupling mode classification.

[0052] It should be further explained that the pre-built avionics control rule base is a structured set of strategies pre-built by domain experts based on the aircraft system architecture, mission profile, and safe operation specifications. Each rule is organized in the form of operating condition tags and control actions, specifying the specific control measures to be taken for the power supply and signaling systems during specific flight phases, such as takeoff, cruise, reconnaissance, return to base, emergency landing, and abnormal states, such as low battery, communication interruption, and overload. For example, when the operating condition tag is emergency return to base, priority is given to ensuring power supply to flight control, navigation, and data transmission equipment, power channels for non-critical payloads are shut down, and the image transmission link is switched to a high-priority CAN redundant channel. This rule base is stored in the non-volatile memory of the flight control core module, supports rapid retrieval by operating condition tag, and can be dynamically adapted in combination with real-time characteristic parameters. It is the core decision-making basis for realizing centralized intelligent management of energy flow and data flow.

[0053] It should be further explained that the core of the aircraft's avionics system integrated architecture lies in completely abandoning the traditional mesh interconnection model and instead constructing a centralized star topology structure with the whole aircraft's power supply and distribution hub and the whole aircraft's signal hub as dual cores. This architecture uses the flight control computer as the top-level decision-making and computing center and establishes two core hub modules that are physically and functionally independent yet collaborative. The first is the whole aircraft's power supply and distribution hub module, which serves as the aircraft's sole global energy scheduling and distribution center. It is directly connected to the main battery and integrates an intelligent power distribution management unit. It has multiple independently controllable power supply channels with complete protection circuits, such as overcurrent, overvoltage, and short-circuit protection. It provides precise, stable, and monitorable power to all airborne electrical equipment, including the flight control system itself, the ESCs of each power motor, servos, communication equipment, and mission payloads, in a star-shaped radial configuration. The second is the overall signal hub module, which serves as the central hub for global data aggregation, exchange, and routing. It integrates hardware interfaces and level conversion circuits for various commonly used avionics communication protocols such as CAN, UART, PWM, I2C, and SPI. All units on the aircraft that need to exchange information with the flight control system, such as inertial navigation sensors, satellite receivers, remote control receivers, servo feedback devices, payload controllers, and various discrete sensors, directly connect their signal lines to the standardized ports of this signal hub. The signal hub is responsible for converting between different interface protocols and encapsulating data, and for efficient and orderly data exchange with the flight control computer through a high-bandwidth, highly reliable backbone communication bus, such as CAN FD. These two hubs are closely related in their internal layout, usually integrated in the same reinforced shielded chassis, but they achieve complete isolation between high-voltage and low-voltage electricity through internal physical partitions. The power supply hub provides the signal hub and all low-power devices connected to it with clean power that has undergone deep filtering, suppressing interference at the source. At the same time, the signal hub can feed back the status and load information of each device to the flight control and power supply hubs, supporting the implementation of intelligent power distribution strategies based on system status, such as priority power-on, fault isolation and energy consumption management, thereby achieving deep integration and integrated intelligent control of energy flow and information flow at the architecture level.

[0054] The flight control core module serves as the system's computing and control center, integrating at least a flight management unit, a navigation calculation unit, and a Controller Area Network (CAN) bus controller. The overall power supply hub module, as the sole primary power distribution center for the entire aircraft, connects directly to the aircraft's main power source, such as the battery pack. This module integrates an intelligent power distribution unit containing multiple independently controllable power supply channels. Each channel features overcurrent, overvoltage, and undervoltage protection, as well as switching control functions. The outputs of each power supply channel are directly connected to all electrical equipment on the aircraft via standardized power interfaces in a star topology, including: the flight control core module itself; electronic speed controllers (ESCs) for each power motor; servos; mission payloads such as gimbals and cameras; communication equipment such as image and data transmission systems; and lighting equipment. This module also integrates a power status monitoring unit, capable of collecting real-time voltage, current, and temperature parameters from each power supply channel and reporting them to the flight control core module via the communication interface.

[0055] like Figure 4 As shown, the overall power supply hub module is a separate metal box with a built-in intelligent power distribution board. The input terminals are connected to the 6S lithium polymer battery pack in the fuselage via high-current wires. The front panel of the box has 12 standardized power output sockets, such as XT30 / XT60, each corresponding to an independent controllable channel. The overall signal hub module is an integrated circuit board mounted near the flight controller. The board integrates interface chips and protection circuits for 2 CAN FDs, 8 UARTs (compatible with RS-232 / 422 / 485), 16 PWM capture / outputs, 4 I2Cs, 4 SPIs, multiple ADCs, and discrete I / O. This board is connected to the flight controller core module via a 4-core shielded cable (containing dual CAN, power, and ground lines).

[0056] like Figure 5 As shown, power cables are directly led out from the output sockets of the overall power supply hub module and connected to: 4 lift rotor motor ESCs, 1 propulsion motor ESC, 5 servos (aileron, elevator, rudder, and V-tail hybrid), 1 electro-optical pod, 1 image transmitter, and 1 data radio. All power cables are cut to the required length for the shortest possible path. All sensor and actuator signal lines are connected to the nearest signal hub module: IMU and GNSS antenna: directly connected to the dedicated UART / SPI interface of the signal hub. Remote control receiver: SBUS signal connected to the UART port of the signal hub. 5 servos: PWM control lines connected to the PWM output port of the signal hub. Electro-optical pod (gimbal control): its serial control line connected to another UART port of the signal hub. Motor ESC (speed feedback / control): connected via the CAN bus interface of the signal hub (the ESC must support the CAN protocol). Landing gear retraction switch, mission buttons, etc.: connected to the discrete input ports of the signal hub.

[0057] The overall signal hub module, serving as the central hub for data communication and exchange, is physically a highly integrated circuit board or independent unit. Its core is a multi-protocol switching and routing core, integrating hardware controllers and level conversion circuits for common communication protocols such as CAN bus transceivers, Universal Asynchronous Receivers (UART), Serial Peripheral Interface (SPI), and Integrated Circuit Bus (I2C). This module provides a unified, multi-channel standardized signal interface. All devices requiring data exchange with the flight control core are directly connected to this hub, including: Inertial Measurement Unit (IMU), Global Navigation Satellite System (GNSS) receivers, remote control receivers, feedback interfaces for various servos, mission payload control interfaces, and various discrete / analog sensors. The signal hub internally performs necessary conversions and data routing between different interface protocols, such as converting PWM servo signals into CAN bus standard messages or packaging UART sensor data into specific CAN frames. All processed data interacts with the flight control core module via a high-speed backbone communication link, such as a highly reliable CAN FD bus. The overall power supply hub module and the overall signal hub module are physically and electrically coordinated. Physical Coordination: The two hub modules can be integrated into the same sealed enclosure, but high-voltage (power supply) and low-voltage (signal) circuits are physically isolated through internal shielding partitions. Electrical Coordination: The power supply hub provides filtered and regulated clean power to the signal hub and all devices connected to it, reducing common-mode interference at the source. Simultaneously, the load status information reported by the signal hub assists the power supply hub in making intelligent power distribution decisions, such as sequentially powering on non-critical equipment and isolating faulty pathways.

[0058] With its powerful standalone AI capabilities, multiple UAVs equipped with the avionics management system of this invention can form a UAV swarm, enabling autonomous swarm control, efficient collaborative flight, and rapid completion of various high-intensity tasks. For swarm applications, this invention integrates the aforementioned overall power supply and distribution hub module, overall signal hub module, and swarm-specific onboard high-performance computing module and swarm data link communication module into a single package. The latter two are integrated into a robust, standardized avionics sealed box with electromagnetic shielding and excellent heat dissipation design. This avionics box becomes the single, unified intelligent avionics core of the UAV platform. Its most critical external feature is that it provides only one high-density, multi-functional, single external electrical interface, such as using aviation-grade connectors like the J30J series. This interface manages all energy output and signal interaction to the aircraft platform itself, including: power supply to the propulsion motor ESC, propulsion motor ESC, servos, etc., through high-current pins in the interface; and platform sensor signals, such as the RTK navigation antenna (ANT1, ANT2), backup attitude reference system, and remote control receiver signal lines, which are introduced into the box. Mission payload interface: Provides control (e.g., UART) and data (e.g., Ethernet or USB 3.0 channels) for mission equipment such as electro-optical pods and delivery systems. Platform power input: Receives electrical energy from the spacecraft platform's main battery and connects to the internal power distribution hub.

[0059] like Figure 6As shown, the system integrates two core cluster modules: a cluster intelligent computing module, which utilizes high-performance embedded computing units such as NVIDIA Jetson Orin NX. This module is directly connected to the overall signal hub module and flight control core via a high-speed bus, such as PCIe or Gigabit Ethernet, and is responsible for running cluster collaborative algorithms, such as formation keeping, conflict resolution, and task allocation; and real-time environmental perception processing, such as fusing LiDAR, visual data, and local autonomous decision-making. Its power supply is provided by a dedicated power distribution hub, and it connects to possible extended sensors or storage devices via internal USB 3.0, Ethernet, and other interfaces. The cluster data link communication module integrates a high-bandwidth, low-latency radio with self-organizing (mesh) capabilities, such as a custom radio based on Wi-Fi 6 or a proprietary protocol. This module acts as a neural link between cluster nodes, and its antenna interface, for example, is reserved for external connection to the optimized fuselage position shown in the diagram. The communication module connects to the signal hub and intelligent computing module via Ethernet or a high-speed serial port, enabling real-time sharing and collaboration of status information, control commands, and perception data within the cluster. In cluster missions, each UAV's avionics box operates as an independent cluster node. Internal Control: The flight control core continuously manages the flight status, sensor data, and equipment health of the drone through the signal hub. The power supply hub provides stable power to all internal modules and external devices of this node and monitors energy consumption. External Collaboration: Based on the drone's status provided by the flight control system and the status of friendly drones received via data link, as well as global mission information, the onboard intelligent computing module calculates in real time the formation position, flight path, or collaborative action commands that the drone should execute and sends them to the flight control core for execution. Mission Execution: When the cluster needs to collaboratively execute tasks such as reconnaissance, strike, or network communication, mission commands are distributed via data link or decided by the lead drone. After being parsed by the intelligent computing module, the relevant commands are converted into specific equipment control commands through the signal hub, such as controlling the pod to point to a specific area or triggering electronic jamming payloads, and the power supply hub ensures reliable power supply to the mission payloads. Rapid Deployment and Reconfiguration: Because all complex hardware and software related to the cluster are integrated into a standard avionics box and connected to a relatively simple flight platform—airframe, power system, and basic servo system—through a single interface, the production, maintenance, and mission reconfiguration of the clustered drones become extremely efficient. Replacing or upgrading the cluster algorithm and communication protocol mainly involves replacing or updating the internal modules of the avionics box, without requiring any changes to the flight platform itself.

[0060] Furthermore, based on the star topology, this avionics system undergoes deep intelligent and adaptive reconfiguration, leading to a composite avionics integrated system based on dynamic topology configuration and adaptive load management. Its core lies in breaking through the static structure of the traditional star topology by introducing a programmable power supply and signal routing matrix. Combined with the real-time decision-making capabilities of the flight control system, it achieves virtualized reuse of physical interfaces and dynamic optimization of the system topology. Specifically, in the overall power supply and distribution hub, the traditional multiple independent fixed output channels are replaced by a central power routing matrix and several sets of programmable multi-channel intelligent switches. The matrix input is connected to the main power supply, and its output is not directly connected to fixed physical interfaces, but rather to a set of output nodes with programmable connectivity. Simultaneously, in the overall signal hub, programmable logic devices or switching matrices are introduced to replace fixed multi-protocol hardware interface combinations. A system resource management and topology control unit is added to the flight control core module. This unit acquires the type and status of all equipment on the aircraft in real time, such as standby, operation, and fault status; power consumption requirements; and mission phase information. During system power-on initialization or mission switching, this unit dynamically plans the optimal power and signal paths based on preset rules and real-time load. Through software commands, it controls the power routing matrix in the power distribution hub and the switching logic in the signal hub, dynamically allocating a limited number of physical interfaces to currently active devices on demand, thus effectively reducing the number of physical interfaces. For example, during cruise, power and signal links to some mission payloads and sensors can be shut down, reserving the freed-up interface resources for devices to be activated in the next phase. When a device fails, the system can automatically isolate its link and dynamically switch the connection of the backup device to the corresponding physical interface. This not only statically reduces the number of required high-reliability avionics interfaces, lowering cost, weight, and complexity, but also dynamically enables on-demand allocation of system resources and autonomous reconfiguration in case of failure, improving system reliability, mission adaptability, and survivability. This software-defined physical topology transforms the avionics system from a rigid, fixed-connection architecture into a self-configuring and self-optimizing intelligent organism.

[0061] In terms of the power supply hub's form, it can be designed as a composite structure conformal to the main aircraft structure, such as the center wing rib or equipment bay bulkhead. Power distribution lines and protection devices can be directly printed or embedded into the load-bearing structure, achieving structural and power supply integration, further reducing weight and improving space utilization. For small or low-cost UAV platforms, the functional parts of the overall signal hub can be integrated onto the flight control computer's mainboard, forming an integrated core board for flight control and signal processing, while the power supply hub remains an independent unit. This reduces the number of independent modules, lowers costs, and is suitable for applications with low scalability requirements.

[0062] Regarding the selection of the communication backbone, in addition to the preferred high-reliability CAN FD bus, for systems with ultra-high-speed data transmission requirements, such as multiple high-definition video streams, Ethernet based on Time-Sensitive Networking (TSN) can be considered as the backbone between the flight control and signal hubs. Simultaneously, more powerful network switching and protocol processing chips can be integrated within the signal hubs to adapt to future more complex data fusion and real-time computing needs. To further enhance safety, a dual-redundancy design can be adopted, i.e., setting up two sets of power supply and signal hubs that serve as backups for each other. These two sets are synchronized and failover is achieved through a cross-channel, forming a highly secure, fault-tolerant avionics system to meet the needs of special or high-reliability mission scenarios.

[0063] The core of this invention lies in proposing a novel pair of avionics architecture concepts: a power distribution hub and a signal hub. Through their collaborative design, a fundamental shift from decentralized management to centralized scheduling of the aircraft's energy and data links is achieved. Its core lies in the reconstruction of the top-level design, rather than improvements to local connections. Based on this, the overall system architecture comprises an integrated system consisting of a flight control computer, a power distribution hub module, a signal hub module, and all airborne terminal equipment directly connected to these two hubs in a star topology. The specific technical features of the power distribution hub module include its status as the sole primary power distribution center for the entire aircraft, its internally integrated multiple independent and controllable intelligent power distribution channels, circuit protection functions for each channel, and a direct star-shaped power supply connection for all electrical equipment. The technical features of the signal hub module include its hardware design integrating multiple protocol interfaces, its functional positioning as the data exchange center for the entire aircraft, its mechanism for unified access and protocol conversion and routing of signals from heterogeneous devices, and its interaction with the flight control system via a single backbone communication link. The collaborative relationship between the two hub modules includes their physical integration and isolation arrangement, the electrical connection of the power supply hub to provide filtered power to the signal hub and its downstream equipment, and the control method for achieving coordinated intelligent management between the two through information interaction.

[0064] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 3As shown, the computer device includes a processor, memory, and network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database stores static and dynamic information data. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements the steps described in the embodiment of the aircraft avionics management method based on a centralized power supply and signal hub.

[0065] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present invention and does not constitute a limitation on the computer device to which the present invention is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0066] In addition, the present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above embodiments of the aircraft avionics management method based on a centralized power supply and signal hub.

[0067] In addition, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the above embodiments of the aircraft avionics management method based on a centralized power supply and signal hub.

[0068] Those skilled in the art will understand that implementing all or part of the processes in the above-described embodiments of the aircraft avionics management method based on a centralized power supply and signal hub can be accomplished by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above-described aircraft avionics management method based on a centralized power supply and signal hub. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include at least non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0069] This invention is not limited to the structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this invention is limited only by the appended claims.

Claims

1. An aircraft avionics management method based on a centralized power supply and signal hub, characterized in that, include: Acquire the power supply and distribution data and signal data of the whole machine, perform power supply channel status analysis and energy consumption analysis on the power supply and distribution data of the whole machine to obtain the power supply and distribution analysis results of the whole machine, and perform protocol analysis and topology connectivity judgment on the signal data of the whole machine to obtain the signal link analysis results of the whole machine. Using flight control status data as status anchors and mission phase data as semantic context, and combining the results of the whole aircraft power supply and distribution analysis and the whole aircraft signal link analysis, a whole aircraft energy information status fusion map is constructed. Based on the energy information status fusion map of the whole aircraft, the coupling correlation and dynamic change characteristics of energy flow, data flow and flight status and mission phase in the map are extracted to obtain the multi-dimensional coupling feature set of the whole aircraft avionics; The system performs feature decoupling analysis and operating condition strategy matching on the multi-dimensional coupling feature set of the entire aircraft's avionics system, and generates power supply and distribution control commands and signal link configuration commands in combination with preset avionics control rules, thereby realizing centralized management of the aircraft's avionics energy flow and data flow.

2. The aircraft avionics management method based on a centralized power supply and signal hub according to claim 1, characterized in that, The process of analyzing the power supply channel status and energy consumption of the overall power supply and distribution data to obtain the overall power supply and distribution analysis results, and performing protocol parsing and topology connectivity judgment on the overall signal data to obtain the overall signal link analysis results, includes: The power supply and distribution data of the whole machine is analyzed for parameters of each power supply channel, and the state is determined in combination with the preset channel rated threshold. The state is quantified according to the determination result to obtain the power supply channel state vector. An energy consumption distribution matrix is ​​constructed based on the power supply channel state vector. Abnormal power consumption patterns are identified on the energy consumption distribution matrix to obtain a star-shaped energy consumption distribution map of the entire machine and generate the power supply and distribution analysis results of the entire machine. The system analyzes the signal data of the whole machine according to the port identification signal protocol type to obtain the parsed device signal data, and determines the link connectivity and communication quality level according to the preset mapping table and the continuous frame reception status. A star topology connectivity graph is constructed based on link connectivity and communication quality level. Signal link health diagnosis and resource optimization are performed on the star topology connectivity graph to generate full-machine signal link analysis results.

3. The aircraft avionics management method based on a centralized power supply and signal hub according to claim 2, characterized in that, The process of constructing an energy consumption distribution matrix based on the power supply channel state vector, identifying abnormal power consumption patterns on the energy consumption distribution matrix, obtaining a star-shaped energy consumption distribution map of the entire machine, and generating power supply and distribution analysis results for the entire machine includes: Energy consumption is assessed based on the power supply channel state vector to obtain load energy consumption assessment results. The load energy consumption assessment results are then categorized according to equipment function categories to obtain energy consumption classification results. The energy consumption classification results are combined with the task phase data to perform energy consumption feature weight labeling, and the weighted energy consumption classification results are filled into the matrix cells to obtain the energy consumption distribution matrix. A power consumption baseline is constructed based on historical normal operating condition data. Deviation detection and abnormal load labeling are performed on the energy consumption distribution matrix and the corresponding power consumption baseline to obtain an abnormal load labeled energy consumption matrix. The abnormal load marker energy consumption matrix is ​​mapped to a star topology centered on the whole machine power supply and distribution hub to generate a star distribution map of the whole machine's energy consumption; The energy consumption star distribution diagram of the whole machine is extracted and quantified to obtain the quantitative statistical results of the load energy consumption of each node. The energy consumption matching degree of the power supply channel under the star topology is analyzed to obtain the power supply and distribution analysis results of the whole machine.

4. The aircraft avionics management method based on a centralized power supply and signal hub according to claim 2, characterized in that, The process of constructing a star topology connectivity graph based on link connectivity and communication quality level, performing signal link health diagnosis and resource optimization on the star topology connectivity graph, and generating full-machine signal link analysis results includes: Based on the link connectivity determination results, connected edges are constructed, and weight labels are set according to the communication quality level to construct a star topology connectivity graph. The star topology connectivity graph is combined with preset communication quality thresholds and continuous frame reception status to determine the status, and link faults are identified based on the determination results to obtain link fault diagnosis results. Based on the link fault diagnosis results, the parameters of the star topology connectivity diagram are adjusted to generate the optimal signal connectivity diagram. Then, the link redundancy of the optimal signal connectivity diagram is quantitatively calculated to obtain the overall signal link analysis results.

5. The aircraft avionics management method based on a centralized power supply and signal hub according to claim 1, characterized in that, The construction of a fusion map of the aircraft's energy information status, using flight control status data as the status anchor, mission phase data as the semantic context, and combining the results of the overall aircraft power supply and distribution analysis and the overall aircraft signal link analysis, includes: Using the sampling period of flight control status data as the primary time reference and the aircraft's centroid coordinate system as the spatial reference, the spatiotemporal synchronization mapping and multidimensional feature alignment of the whole aircraft power supply and distribution analysis results and the whole aircraft signal link analysis results are performed to generate physically aligned multimodal spatiotemporal tensors. Using task phase data as domain labels, the adversarial domain adaptation mechanism is used to decouple the multimodal spatiotemporal tensor to obtain energy domain and data domain features. The energy domain and data domain features are then fused according to task semantic weights to obtain a semantic feature embedding set and a domain confidence matrix. Using semantic feature embedding sets as node attributes and domain confidence matrices as edge dynamic adjustment factors, and constructing a heterogeneous graph structure with power supply and distribution hubs and signal hubs as dual cores, a model of the heterogeneous graph structure is obtained to obtain a fusion map of the energy information status of the entire machine.

6. The aircraft avionics management method based on a centralized power supply and signal hub according to claim 1, characterized in that, The method of extracting the coupling correlation patterns and dynamic change characteristics of energy flow, data flow, flight status, and mission phase from the energy information state fusion map of the whole aircraft yields a multi-dimensional coupling feature set of the whole aircraft avionics, including: Based on the energy information state fusion graph of the whole machine, source nodes and target nodes are set, and energy edges and data edges in the energy information state fusion graph of the whole machine are sampled to obtain several meta-paths. Path association coupling is performed on each meta-path to obtain a set of coupled paths and a path-level coupling coefficient matrix. Based on the set of coupling paths and the path-level coupling coefficient matrix, the snapshot sequence of the whole machine energy information state fusion map within a continuous time window is slicing to obtain the slicing result. Dynamic coupling pattern recognition is performed on the sliding slice results to obtain a co-evolution feature set. The co-evolution feature set is then mapped and encapsulated according to four dimensions: energy flow, data flow, flight status, and mission phase, to obtain a multi-dimensional coupling feature set of the entire aircraft's avionics.

7. The aircraft avionics management method based on a centralized power supply and signal hub according to claim 6, characterized in that, The process involves setting source and target nodes based on the overall energy information state fusion graph, sampling energy edges and data edges in the graph to obtain several meta-paths, and performing path association coupling on each meta-path to obtain a set of coupled paths and a path-level coupling coefficient matrix, including: Using the power supply and distribution hub and signal hub in the whole aircraft energy information state fusion graph as source nodes, and the flight control state and mission phase as target nodes, the energy edge and data edge in the whole aircraft energy information state fusion graph are jointly sampled based on meta-path to obtain the causal transmission meta-path of energy flow to flight state and the response feedback meta-path of data flow to mission phase. The coupling strength coefficient between the source node and the target node under each meta-path is calculated by using the path accumulation attention mechanism, resulting in a set of coupled paths with correlation strength weights and a path-level coupling coefficient matrix.

8. The aircraft avionics management method based on a centralized power supply and signal hub according to claim 6, characterized in that, The dynamic coupling pattern recognition of the sliding slice results yields a co-evolution feature set, which is then mapped and encapsulated along four dimensions: energy flow, data flow, flight status, and mission phase, resulting in a multi-dimensional coupling feature set for the entire aircraft's avionics system, including: A temporal graph convolutional network is used to jointly extract spatial neighborhood features and temporal evolution trends from the sliding slice results to obtain energy flow and data flow feature time-series curves. Cross covariance is used to perform dynamic coupling pattern recognition on the energy flow and data flow feature time-series curves to obtain a co-evolution feature set. The co-evolutionary feature set is mapped to fields according to four dimensions: energy flow, data flow, flight status, and mission phase, resulting in an evolutionary feature grouping table. The features in each group of the evolution feature grouping table are standardized in terms of dimensions to obtain a standard multidimensional coupling feature set. The standard multidimensional coupling feature set is then hierarchically organized according to a preset feature sorting architecture. The organized coupling feature set is then encapsulated with structured vectors to obtain the full-aircraft avionics multidimensional coupling feature set.

9. The aircraft avionics management method based on a centralized power supply and signal hub according to claim 1, characterized in that, The process of performing feature decoupling analysis and operational condition strategy matching on the multi-dimensional coupling feature set of the entire aircraft's avionics system, and generating power supply and distribution control commands and signal link configuration commands in conjunction with pre-set avionics control rules, to achieve centralized management of the aircraft's avionics energy flow and data flow includes: The multi-dimensional coupling feature set of the whole aircraft avionics is decoupled according to four dimensions: energy flow, data flow, flight status and mission phase, to obtain energy information decoupling sub-features; The energy information decoupled sub-features are matched with a pre-set operating condition feature template library for similarity, and the operating condition label of the current aircraft is identified based on the similarity matching results. Based on the operating condition label, the corresponding control strategy is retrieved from the pre-set avionics control rule library, and combined with the power coupling strength, command response correlation and energy constraint coefficient in the energy information decoupling sub-feature, the power supply priority, communication bandwidth allocation and load energy consumption limit parameters are dynamically adapted. The power supply priority, communication bandwidth allocation, and load energy consumption limit parameters are converted into power supply channel switching timing, voltage regulation commands, and overload protection thresholds that can be executed by the whole machine power supply and distribution hub, as well as protocol configuration, redundant link switching, and bandwidth scheduling commands that can be executed by the whole machine signal hub. These commands are then sent to the whole machine power supply and distribution hub and the whole machine signal hub for coordinated execution, thereby achieving centralized management of energy flow and data flow.

10. An aircraft avionics management system based on a centralized power supply and signal hub, characterized in that: The system includes: The whole machine data analysis module is used to acquire the whole machine power supply and distribution data and the whole machine signal data. It performs power supply channel status analysis and energy consumption analysis on the whole machine power supply and distribution data to obtain the whole machine power supply and distribution analysis results. It also performs protocol analysis and topology connectivity judgment on the whole machine signal data to obtain the whole machine signal link analysis results. The map construction module is used to construct a fusion map of the energy information status of the entire aircraft by using flight control status data as status anchors, mission phase data as semantic context, and combining the analysis results of the power supply and distribution of the entire aircraft and the analysis results of the signal link of the entire aircraft. The feature coupling module is used to extract the coupling correlation and dynamic change characteristics of energy flow, data flow and flight status and mission phase in the energy information status fusion map of the whole aircraft, and obtain the multi-dimensional coupling feature set of the whole aircraft avionics. The operating condition strategy matching module is used to perform feature decoupling analysis and operating condition strategy matching on the multi-dimensional coupling feature set of the entire aircraft's avionics system. It also generates power supply and distribution control commands and signal link configuration commands in combination with preset avionics control rules, thereby realizing centralized management of the aircraft's avionics energy flow and data flow.

Images