A method for resolving conflicts in fault diagnosis of an aircraft power distribution system

Abstract

The application provides a kind of aircraft power distribution system fault diagnosis conflict resolution method, belong to the technical field of aviation equipment support.The method comprises: real-time acquisition and pre-set fault mode associated key parameters;For each fault mode, according to the inherent hazard degree setting basic weight;Through the analysis of the real-time change trend of key parameters, the trend weight is calculated;According to historical fault statistical data, the frequency weight is calculated;The dynamic comprehensive weight is obtained by fusing the basic weight, the trend weight and the frequency weight;When multiple fault modes are diagnosed, according to the dynamic comprehensive weight sequence, the fault mode with the highest weight value is selected as the diagnosis result output.The application fuses the inherent hazard of fault, real-time evolution trend and historical statistical law, provides reliable resolution basis for multiple diagnosis evidence conflict scene, significantly improves the accuracy, robustness and adaptability of diagnosis, and can improve the operation safety and intelligent maintenance level of aircraft power distribution system.

Description

Technical Field

[0001] This invention belongs to the field of aviation equipment support technology, and more specifically relates to a method for fault diagnosis and conflict resolution in aircraft power distribution systems. Background Technology

[0002] As the core of the aircraft's energy distribution, the reliability of the aircraft's power distribution system is directly related to flight safety. With the development of "more electric aircraft" technology, modern aircraft power distribution systems integrate a variety of intelligent modules such as generators, intelligent power distribution units (IPDUs), remote terminals, and load managers. The system topology exhibits complex network characteristics of multiple branches and strong coupling. This complexity leads to the diversity and concealment of fault propagation paths. A single fault point may trigger multiple sensors to alarm simultaneously, resulting in contradictory or even conflicting fault diagnosis evidence.

[0003] To improve the automation and accuracy of fault diagnosis, intelligent diagnostic methods such as expert systems have been introduced into the field of aircraft health management. In the process of rule-based reasoning, it is often encountered that the same fault state can trigger multiple diagnostic rules. How to select the optimal solution from these conflicting rules, i.e., "conflict resolution", has become a key link in determining the efficiency and accuracy of diagnosis.

[0004] Currently, conflict resolution strategies in aircraft power distribution system fault diagnosis mainly rely on static weight allocation methods or simple general dynamic models. These methods typically pre-set fixed priorities based solely on the inherent severity of the fault modes (such as short circuits and overloads), failing to fully consider the dynamic characteristics and historical statistical patterns during the fault occurrence process, and thus exhibiting the following significant shortcomings: 1) Inability to distinguish the trend differences of faults: Before a real physical fault (such as line overload or insulation aging) occurs, the relevant electrical parameters (such as current, temperature, and insulation resistance) often exhibit a physically meaningful gradual trend (such as a slow rise followed by accelerated deterioration); while the parameter changes of instantaneous spurious signals caused by electromagnetic interference, sensor noise, etc., are irregular instantaneous abrupt changes. Existing static methods cannot identify this essential difference in trend, which may lead to wasted resources on troubleshooting instantaneous interference, thus delaying the handling of real, gradual faults; 2) Ignoring historical frequency information of failures: During the long-term service of an aircraft, due to factors such as design characteristics, operating environment, and maintenance cycle, the actual probability of different failure modes varies significantly. For example, some connectors are prone to loosening due to vibration, and some lines are prone to aging due to environmental corrosion. Their historical failure frequency is much higher than that of other occasional failures. Existing methods fail to include this valuable historical statistical information, which is highly relevant to specific aircraft models or fleets, in the weighting consideration, resulting in a lack of specificity and adaptability in diagnostic strategies. 3) Limited adaptability and accuracy of diagnostic models: Due to the lack of integration of two key dynamic information types, real-time change trends and historical statistical frequencies, existing conflict resolution methods face bottlenecks in the reliability and accuracy of their inference results and their adaptability to different aircraft types / fleets when facing complex and coupled fault scenarios. This makes it difficult to meet the urgent needs of modern aviation equipment for high-precision and high-efficiency health management. Summary of the Invention

[0005] To address the above problems, the present invention aims to provide a method for conflict resolution in fault diagnosis of aircraft power distribution systems. By collecting key parameters in real time and calculating the trend weight and frequency weight of fault modes, and then integrating the basic weights to generate dynamic comprehensive weights, conflict resolution is performed based on weight ranking when multiple faults occur concurrently, which significantly improves the accuracy and robustness of fault diagnosis.

[0006] To achieve the above objectives, the present invention employs the following technical solution: In a first aspect, embodiments of this application provide a method for fault diagnosis and conflict resolution in an aircraft power distribution system, including: Real-time acquisition of key parameters associated with multiple preset fault modes in the aircraft's power distribution system; For each of the aforementioned failure modes, a basic weight is set based on its inherent severity. By analyzing the real-time changing trends of the key parameters, the trend weight corresponding to each failure mode is calculated. Calculate the frequency weight for each failure mode based on historical failure statistics. By integrating the basic weight, trend weight, and frequency weight, the dynamic comprehensive weight of each failure mode is calculated. In response to multiple fault modes being triggered during fault diagnosis of the aircraft power distribution system, all triggered fault modes are sorted according to the dynamic comprehensive weight, and the fault mode diagnosis result with the highest weight value is selected for output.

[0007] In an optional implementation, the step of calculating the trend weight corresponding to each fault mode by analyzing the real-time changing trend of the key parameters includes: For the key parameters associated with failure mode i, the formula is used. Calculate its current time Sample values Compared to the sampled values ​​of the previous n sampling periods rate of change , denoted as the rate of change of the key parameter of fault mode i; The rate of change of key parameters for all failure modes is normalized, and the normalized rate of change of key parameters for failure mode i is calculated. ; Based on the normalized rate of change of the key parameters The trend weight of failure mode i is calculated using the following formula. :

[0008] in, is the first standardized coefficient, and m is the number of key parameters.

[0009] In an optional implementation, the normalized rate of change of the key parameter of failure mode i is calculated using the following formula. :

[0010] in, It is the minimum rate of change of the key parameters among all failure modes. This represents the maximum rate of change of the key parameters across all failure modes.

[0011] In an optional implementation, calculating the frequency weight corresponding to each fault mode based on historical fault statistics includes: Count the number of times fault mode i occurs within a preset historical period. ; The frequency weight of failure mode i is calculated using the following formula. :

[0012] Where n is the total number of failure modes, This is the second standardized coefficient.

[0013] In an optional implementation, the calculation of the dynamic comprehensive weight for each failure mode by fusing the basic weight, trend weight, and frequency weight includes: The dynamic comprehensive weight of failure mode i is calculated using the following formula. :

[0014] in, The basic weights for fault mode i, These are the allocation coefficients for the base weight, trend weight, and frequency weight, respectively, and they satisfy... .

[0015] In an optional implementation, the default value of the allocation coefficient is: .

[0016] In one alternative implementation, the key parameters include current, voltage, temperature, and insulation resistance.

[0017] Secondly, embodiments of this application also provide an aircraft power distribution system fault diagnosis and conflict resolution system, comprising: The parameter acquisition module is used to acquire key parameters associated with multiple preset fault modes in the aircraft's power distribution system in real time. The basic weight setting module is used to set a basic weight for each of the aforementioned fault modes based on its inherent severity. The trend weight calculation module is used to calculate the trend weight corresponding to each fault mode by analyzing the real-time changing trend of the key parameters. The frequency weight calculation module is used to calculate the frequency weight corresponding to each fault mode based on historical fault statistics. The weight fusion module is used to calculate the dynamic comprehensive weight of each fault mode by fusing the basic weight, trend weight, and frequency weight. The diagnostic result filtering module is used to respond to multiple fault modes triggered during fault diagnosis of the aircraft power distribution system, sort all triggered fault modes according to the dynamic comprehensive weight, and output the diagnostic result of the fault mode with the highest weight value.

[0018] Thirdly, embodiments of this application also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the aircraft power distribution system fault diagnosis conflict resolution method as described in any of the above.

[0019] Fourthly, embodiments of this application also provide a storage medium storing a computer program thereon, which, when executed by a processor, implements the steps of the aircraft power distribution system fault diagnosis conflict resolution method as described in any of the above claims.

[0020] As can be seen from the above technical solutions, the present invention has the following advantages: The aircraft power distribution system fault diagnosis conflict resolution method provided in this application collects key parameters associated with each fault mode in real time. Based on setting basic weights to characterize the inherent severity of the fault, it further introduces trend weights and frequency weights. Trend weights, by analyzing the real-time change rate of key parameters, effectively distinguish between genuine faults with gradual physical changes and instantaneous abrupt changes caused by interference, avoiding wasting diagnostic resources on false signals. Frequency weights, based on historical fault statistics, enable the diagnostic strategy to adapt to the fault occurrence patterns of specific aircraft models or fleets, improving the model's specificity and adaptability. Finally, by integrating basic weights, trend weights, and frequency weights to calculate a dynamic comprehensive weight, when multiple fault modes are triggered simultaneously, the fault diagnosis result with the highest weight is output according to the comprehensive weight ranking. This method overcomes the shortcomings of traditional static weight allocation, which cannot reflect the dynamic evolution trend and historical statistical patterns of faults. It significantly improves the accuracy and robustness of fault diagnosis conflict resolution in complex fault scenarios, providing pilots and maintenance personnel with more reliable decision-making basis, thereby effectively improving the operational safety and intelligent health management level of the aircraft power distribution system.

[0021] This application constructs a dynamic weighting model that integrates basic weights, trend weights, and frequency weights, enabling a multi-dimensional and refined evaluation of fault evidence. It not only focuses on the inherent harmfulness of the fault but also sensitively captures the deterioration trend of parameters and draws on historical experience, thereby more accurately identifying the most likely real faults among numerous conflicting pieces of evidence, greatly reducing misjudgments and omissions.

[0022] The trend weight calculation model proposed in this application can quantify the continuity and directionality of parameter changes, give higher weight to gradual signals that characterize real physical processes (such as overheating and overload), and suppress irregular instantaneous abrupt signals. This effectively solves the problem that existing methods cannot distinguish between real fault precursors and instantaneous noise interference, and improves the robustness of diagnosis.

[0023] This application introduces frequency weights based on historical statistical data, enabling conflict resolution strategies to "learn" and adapt to the failure patterns of specific aircraft types, fleets, and even individual aircraft. For high-frequency failures, the system automatically increases their attention, making diagnostic strategies more targeted and practical, and enhancing the intelligence level of equipment support.

[0024] This application provides maintenance personnel with a higher-priority fault hypothesis list through dynamic and precise conflict resolution, guiding them to conduct the most effective troubleshooting, shortening fault location time, reducing unnecessary equipment replacement and downtime, thereby improving aircraft availability and reducing total lifecycle maintenance costs. Furthermore, the proposed dynamic weight model has a clear structure, with each weight component having a well-defined physical meaning and specific calculation formulas. This method can be easily integrated into existing aircraft health management or fault prediction and health management systems. The algorithm has a moderate computational load, making it suitable for real-time operation in airborne or ground support systems. Additionally, the weighting coefficients in the model can be adjusted according to different application scenarios, demonstrating good scalability. Attached Figure Description

[0025] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 A flowchart illustrating the aircraft power distribution system fault diagnosis and conflict resolution method provided in this application.

[0027] Figure 2 A flowchart illustrating another method for fault diagnosis and conflict resolution in aircraft power distribution systems provided in this application.

[0028] Figure 3 This is a schematic diagram of the aircraft power distribution system fault diagnosis and conflict resolution system provided in this application.

[0029] Figure 4 A schematic diagram of the structure of the electronic device provided in this application. Detailed Implementation

[0030] The various embodiments of this disclosure will be described more fully in the following detailed description of the specific steps of the method for troubleshooting and resolving conflicts in an aircraft power distribution system. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0031] In the following, the terms “comprising” or “may include”, which may be used in various embodiments of this disclosure, indicate the presence of the disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. Furthermore, as used in various embodiments of this disclosure, the terms “comprising,” “having,” and their cognates are intended only to indicate a particular feature, number, step, operation, element, component, or combination of the foregoing, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing, or the possibility of adding one or more combinations of the foregoing.

[0032] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0033] Please see Figure 1 The diagram shows a flowchart of a method for resolving conflicts in fault diagnosis of an aircraft power distribution system, as described in a specific embodiment. This method, running on the aircraft's central maintenance computer or a dedicated fault diagnostic tool, is used to filter out the most relevant diagnostic result from multiple possible fault modes when an abnormal alarm occurs in the system, providing accurate decision-making support for the flight crew or ground maintenance personnel. The core of this method lies in constructing a dynamic comprehensive weight model. This model integrates the inherent attributes of the fault, real-time dynamic characteristics, and historical statistical patterns, thereby effectively resolving the problem of conflicting multiple diagnostic evidence. The method includes the following steps: S101: Real-time acquisition of key parameters associated with multiple preset fault modes in the aircraft's power distribution system.

[0034] In this step, a comprehensive data acquisition and monitoring system is established. Various sensors are pre-installed at key nodes of the aircraft's power distribution system, such as the generator output, the input / output ports of the Intelligent Power Distribution Unit (IPDU), busbars, and power supply lines to important loads. These sensors are used to collect key parameters reflecting the system's health status in real time. Based on common fault mechanisms in aircraft power distribution systems, the key parameters set in this embodiment include at least current, voltage, temperature, and insulation resistance. For example, current and voltage values ​​are collected at the generator feed line, temperature values ​​are collected at the power module heatsink of the IPDU, and insulation resistance values ​​are collected between the busbar and ground. These analog signals are converted into digital quantities by the onboard data acquisition system at a fixed sampling period (e.g., once per second) and stored in a real-time database for use by the fault diagnosis module.

[0035] S102: For each of the aforementioned failure modes, set a basic weight based on its inherent severity.

[0036] In a specific implementation, the present invention pre-establishes a fault mode library for aircraft power distribution systems. This library covers various typical fault modes such as "generator feeder short circuit," "busbar overvoltage," "IPDU power module overheating," and "line insulation aging." For each fault mode in the library... It is necessary to set a basic weight for it. This weight represents the potential hazard to flight safety, mission completion, and equipment lifespan should the failure mode occur. The base weight is quantified and assigned by domain experts based on industry standards and engineering experience. For example, the severity is divided into high, medium, and low levels. For catastrophic failures like "generator feeder short circuit," which could lead to a complete power outage, the base weight can be set to the highest value. For critical faults such as "busbar overvoltage" that could damage electrical equipment, the basic weight can be set to [value missing]. For faults like "line insulation aging," which have a relatively small initial impact and develop slowly, the basic weight can be set to... The basic weights are the cornerstone of the entire conflict resolution model, reflecting the system's inherent tolerance to different faults.

[0037] S103: Calculate the trend weight corresponding to each fault mode by analyzing the real-time change trend of the key parameters.

[0038] In this specific implementation, the base weights are static and cannot reflect the dynamic characteristics during the fault occurrence process. Real physical faults (such as overload heating or insulation degradation) are often accompanied by gradual changes in key parameters, while false alarms caused by sensor noise or electromagnetic interference typically manifest as instantaneous changes in parameters. To capture this fundamental difference, this step introduces trend weights. The calculation process for trend weights is as follows: First, regarding the failure modes Calculate the rate of change of the relevant key parameters, using failure modes. For example, assuming the key parameter is current, let's say at the current moment... The sampled value ,forward Each sampling period (e.g.) Pick , that is, the former The sample value (seconds) Then the rate of change of the parameter Through formula The calculation yields this rate of change, which reflects the relative magnitude of the parameter's change over a recent period; a positive value indicates an increase, and a negative value indicates a decrease. For example, if the current in a certain line changes from... Rise to Then its rate of change Secondly, the rate of change of key parameters for all failure modes is normalized. Because the parameter types and dimensions differ across failure modes, their rates of change cannot be directly compared. Therefore, it is necessary to normalize the rate of change for all... Rate of change of each failure mode Perform normalization. Find the minimum value. and maximum value For failure modes Its normalized rate of change Through formula Calculation. Through this step, the rate of change of all failure modes is mapped to... Within a given range, these parameters are comparable. A larger value indicates a more drastic trend in the parameter's change.

[0039] Finally, trend weights are calculated based on the normalized rate of change. Failure Mode Trend weight Through formula Calculation. Where the denominator is the sum of the normalized rates of change of all failure modes, and the numerator is the number of failure modes. The normalized rate of change. This is the first standardization coefficient, whose function is to adjust the overall magnitude of the trend weights so that they match the numerical range of subsequent weights. In this embodiment, The value can be 10, ensuring that the sum of the trend weights of all failure modes does not exceed 10. The core idea of ​​this formula is that, within a unit of time, the more drastic the parameter changes in a failure mode, the higher its trend weight, indicating that the failure is in a rapid evolution phase and should be given greater attention.

[0040] S104: Calculate the frequency weight corresponding to each fault mode based on historical fault statistics.

[0041] In specific implementations, the failure patterns of aircraft exhibit statistical regularities during long-term service. For example, due to design or installation location, a particular connector on a certain type of aircraft may fail far more frequently than other components. To incorporate this valuable experience into the diagnostic model, this step introduces frequency weights. The calculation of frequency weights relies on historical failure data recorded in the aircraft health management system. First, the failure patterns within a preset historical period (e.g., the past year or since the aircraft entered service) are statistically analyzed. The number of times it occurs is denoted as Then, through the formula Calculate the frequency weight. Wherein, The total number of all fault modes in the fault mode library is represented by the denominator, which is the total number of historical occurrences of all fault modes. This is the second standardization factor, also used to adjust the magnitude of the weights, in this embodiment... It is also set to 10. The physical meaning of this formula is: the more frequently a failure mode has occurred in history, the higher its frequency weight, indicating that the failure mode has a high recurrence tendency in the current model or operating environment, and should be given priority in diagnosis.

[0042] S105: By integrating the basic weight, trend weight, and frequency weight, the dynamic comprehensive weight of each fault mode is calculated.

[0043] In a specific implementation, this step integrates the base weight representing inherent hazards, the trend weight representing real-time dynamics, and the frequency weight representing historical patterns to form a single comprehensive evaluation index—the dynamic comprehensive weight. The fusion formula is:

[0044] in, These are the allocation coefficients for the base weight, trend weight, and frequency weight, respectively, and they satisfy... These three coefficients determine the importance of information from different dimensions in the final decision. In a preferred embodiment of this invention, the allocation coefficient uses a default value: , , This default value reflects the design philosophy: ensuring that inherent hazards are the primary consideration. Under the premise of maximizing, fully absorb real-time trend information ( Secondly), and also taking into account historical statistical patterns ( (Again). Through this linear weighted formula, each failure mode All of them obtained a comprehensive weight value that dynamically adjusts over time. This weight value takes into account the severity, urgency, and recurrence of the fault, providing a quantitative basis for the final conflict resolution.

[0045] S106: In response to multiple fault modes being triggered during fault diagnosis of the aircraft power distribution system, all triggered fault modes are sorted according to the dynamic comprehensive weight, and the fault mode diagnosis result with the highest weight value is selected for output.

[0046] In a specific implementation, during the actual operation of the aircraft's power distribution system, an abnormal disturbance may cause multiple sensors to exceed their limits, thereby triggering multiple diagnostic rules in the fault diagnosis module and generating multiple candidate fault modes. At this point, the diagnostic system enters the conflict resolution process. First, it obtains the dynamic comprehensive weights of all triggered fault modes at the current moment. Then, the fault modes are sorted from largest to smallest according to their dynamic comprehensive weight values. Finally, the fault mode with the highest dynamic comprehensive weight value is selected as the final result of this diagnosis and displayed on the alarm interface in the cockpit or the fault report on the maintenance terminal. For example, when a power distribution line simultaneously triggers both "line overload" and "low insulation resistance" fault modes, the system will calculate the dynamic comprehensive weight of both in real time. Assuming that the current trend weight of "line overload" is high due to the continuous and rapid increase in current, while the basic weight and historical frequency of "low insulation resistance" are both low, the calculated comprehensive weight of "line overload" will inevitably be higher than the latter, and the system will select "line overload" as the primary alarm output. This result guides maintenance personnel to prioritize investigating the cause of the overload, thereby eliminating safety hazards more efficiently and avoiding delays in handling major faults due to false or secondary alarms.

[0047] In this embodiment, by collecting key parameters in real time and calculating trend weights, it is possible to effectively distinguish between the gradual physical changes in the actual fault and the instantaneous changes in interference signals, thus avoiding wasting diagnostic resources on false alarms. By introducing frequency weights based on historical statistical data, the diagnostic strategy can be adapted to the fault occurrence patterns of specific aircraft models or fleets, improving the model's relevance. Finally, by integrating the basic weights, trend weights, and frequency weights to generate dynamic comprehensive weights, a reliable quantitative decision-making basis is provided for scenarios with conflicting multi-diagnostic evidence, significantly improving the accuracy, robustness, and adaptability to different operating conditions of fault diagnosis, thereby effectively enhancing the operational safety and intelligent health management level of the aircraft power distribution system.

[0048] Furthermore, as a refinement and extension of the specific implementation of the above embodiments, and in order to fully illustrate the specific implementation process in this embodiment, an alternative method for conflict resolution in aircraft power distribution system fault diagnosis is provided, in conjunction with a fault diagnosis process for an aircraft 270V high-voltage DC power distribution branch. It is assumed that the potential fault modes monitored by the system include: F1 (line overload), F2 (poor contact), and F3 (short circuit to ground).

[0049] like Figure 2 As shown, the method includes the following steps: S201: Data Acquisition and Fault Mode Association.

[0050] Real-time data acquisition from key sensors in the power distribution system, including but not limited to branch current, connection point voltage, contactor contact temperature, and insulation resistance. Based on the aircraft model and power distribution system design, pre-define key parameters strongly correlated with each fault mode (F1, F2, F3). For example: Fault mode F1 (line overload): The associated key parameter is branch current I.

[0051] Fault mode F2 (poor contact): The key parameters associated with the contact point voltage drop ΔU and the contact temperature rise rate ΔT / Δt are the contact point voltage drop ΔU and the contact temperature rise rate ΔT / Δt.

[0052] Fault mode F3 (short circuit to ground): The associated key parameter is insulation resistance. .

[0053] S202: Pre-set static base weights based on the inherent hazard level of the failure mode and its impact on flight safety.

[0054] Set base weights This weight is typically determined by domain experts based on design specifications and historical experience. For example: F1 (Line Overload): May cause overheating and fire, highly dangerous. (Note: The last part, "setting," appears to be an error and is left untranslated.) =8.0.

[0055] F2 (Poor Contact): May cause electric arcing or unstable power supply; moderate hazard. (Setting) =5.0.

[0056] F3 (Short circuit to ground): May cause protective devices to blow, resulting in partial power loss of the system. This is extremely dangerous and should be noted. =9.0.

[0057] The setting of basic weights should ensure the differentiation between different failure modes.

[0058] S203: Perform trend analysis and calculate trend weights.

[0059] Trend weight This reflects the urgency level of the malfunction, which is "worsening".

[0060] First, calculate the rate of change of the key parameters. Taking fault mode F1 as an example, its key parameter is the current I. At time t, the current sampled value I is taken. And the value I from 10 sampling periods ago Calculate the rate of change:

[0061] Similarly, calculate the rate of change of the two parameters of F2 (voltage drop and rate of temperature rise). , And the rate of change of the parameter (insulation resistance) of F3. Note that for parameters such as resistance that indicate a decrease in fault condition, the rate of change is negative.

[0062] Then, normalization is performed: assuming the current calculation yields... = 0.15 (current increases by 15%) = 0.08, = 0.20, = -0.40 (insulation resistance decreased by 40%). Normalize all rates of change:

[0063] Where max(r) = 0.20, min(r) = -0.40. The calculation yields: ≈0.92, ≈0.80, =1.00, =0.00.

[0064] Finally, the trend weights of the failure modes are calculated: the trend weight of each failure mode is determined by the normalized rate of change of all its associated parameters. For F2, there are two parameters, which can be the average or the maximum value (in this example, the maximum value of 1.00 is used). Let the standardized coefficient C1 = 10, then: =4.79 =5.21 =0.00 The results show that the parameters of poor contact (F2) and overload (F1) are deteriorating and their weights are increased; while the current insulation resistance is deteriorating but the trend is relatively flat (0 after normalization), and its trend weight is 0, indicating that the fault is not urgent from the perspective of trend.

[0065] S204: Calculate frequency weights using historical data.

[0066] Frequency weight Historical data can be used to demonstrate the "commonness" of faults.

[0067] First, count the number of historical failures: From the historical maintenance database of this aircraft model or aircraft, count the number of occurrences of each failure mode in the past year. Assume: Count(1) = 3 times, Count(2) = 15 times, Count(3) = 1 time.

[0068] Then calculate the frequency weights: Assume the standardized coefficient C2 = 10, then: =1.58 =7.89 The results clearly show that poor contact (F2) is a common fault in this model, with a much higher frequency weight than the other two.

[0069] S205: Linearly fuse the weights of the three dimensions to calculate the dynamic comprehensive weight.

[0070] The weights of the three dimensions mentioned above are linearly fused to calculate the dynamic comprehensive weight. Take the default value for the allocation coefficient. =0.5, =0.3, =0.2.

[0071]

[0072] Substitute the data into the calculation: = 0.5×8.0 + 0.3×4.79 + 0.2×1.58 = 4.00 + 1.44 + 0.32 = 5.76 = 0.5×5.0 + 0.3×5.21 + 0.2×7.89 = 2.50 + 1.56 + 1.58 = 5.64 = 0.5×9.0 + 0.3×0.00 + 0.2×0.53 = 4.50 + 0.00 + 0.11 = 4.61 S206: Conflict resolution and diagnostic output.

[0073] Assuming that fault modes F1, F2 and F3 are triggered during the current fault diagnosis of the aircraft power distribution system, the fault modes are ranked according to the dynamic comprehensive weight: F1 (5.76)>F2 (5.64)>F3 (4.61).

[0074] Although short circuits to ground (F3), which has the highest basic weight, are the most dangerous, its overall priority is reduced based on real-time trends (not deteriorating rapidly) and historical data (occurring very rarely). Line overload (F1), due to its high danger, clear upward trend, and certain historical occurrences, is ranked first. Poor contact (F2), as a frequently occurring fault with a worsening trend, follows closely in weight.

[0075] The system will output "Line overload (F1)" as the highest priority diagnostic hypothesis, guiding maintenance personnel to first check the load and cooling status of the relevant lines. This represents a leap from static, single-point judgment to dynamic, comprehensive decision-making.

[0076] Therefore, this embodiment effectively solves the problem of evidence conflict in the diagnosis of complex faults in aircraft power distribution systems by introducing a multi-dimensional dynamic weight model, and significantly improves the accuracy and efficiency of diagnosis.

[0077] like Figure 3 As shown, the following is an embodiment of the aircraft power distribution system fault diagnosis conflict resolution system provided in this disclosure. This system and the aircraft power distribution system fault diagnosis conflict resolution method in the above embodiments belong to the same inventive concept. For details not described in detail in the embodiments of the aircraft power distribution system fault diagnosis conflict resolution system, please refer to the embodiments of the above aircraft power distribution system fault diagnosis conflict resolution method.

[0078] An aircraft power distribution system fault diagnosis and conflict resolution system, comprising: The parameter acquisition module is used to acquire key parameters associated with multiple preset fault modes in the aircraft's power distribution system in real time.

[0079] The basic weight setting module is used to set a basic weight for each of the aforementioned fault modes based on its inherent severity.

[0080] The trend weight calculation module is used to calculate the trend weight corresponding to each fault mode by analyzing the real-time changing trend of the key parameters.

[0081] The frequency weight calculation module is used to calculate the frequency weight corresponding to each fault mode based on historical fault statistics.

[0082] The weight fusion module is used to calculate the dynamic comprehensive weight of each fault mode by fusing the basic weight, trend weight, and frequency weight.

[0083] The diagnostic result filtering module is used to respond to multiple fault modes triggered during fault diagnosis of the aircraft power distribution system, sort all triggered fault modes according to the dynamic comprehensive weight, and output the diagnostic result of the fault mode with the highest weight value.

[0084] The aircraft power distribution system fault diagnosis conflict resolution system provided in this embodiment effectively distinguishes between the gradual physical changes of real faults and the instantaneous changes of interference signals by collecting key parameters in real time and calculating the trend weights of fault modes, thus avoiding the waste of diagnostic resources on false alarms. By introducing frequency weights based on historical statistical data, the diagnostic strategy adapts to the fault occurrence patterns of specific aircraft models or fleets, improving the model's relevance. Finally, the system integrates basic weights, trend weights, and frequency weights to generate dynamic comprehensive weights, providing a reliable quantitative decision-making basis for scenarios with conflicting multi-diagnostic evidence. This significantly improves the accuracy, robustness, and adaptability to different operating conditions of fault diagnosis, thereby effectively enhancing the operational safety and intelligent health management level of the aircraft power distribution system.

[0085] Figure 4 A schematic diagram of the hardware structure of an electronic device for implementing various embodiments of the present invention.

[0086] The aircraft power distribution system fault diagnosis conflict resolution method provided in this application embodiment can be applied to electronic devices. Those skilled in the art will understand that the electronic device structure involved in the embodiments of this invention does not constitute a limitation on the electronic device. An electronic device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. In the embodiments of this invention, the electronic device includes, but is not limited to, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the embodiments of this application described and / or claimed herein.

[0087] Electronic devices may include processors, external memory interfaces, internal memory, universal serial bus (USB) interfaces, charging management modules, power management modules, batteries, wireless communication modules, audio modules, speakers, microphones, sensor modules, buttons, cameras, displays, and SIM card interfaces, etc.

[0088] A processor may include one or more processing units, such as: a central processing unit (CPU), an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, memory, a video codec, a digital signal processor (DSP), a baseband processor, and / or a neural network processing unit (NPU). Different processing units may be independent devices or integrated into one or more processors.

[0089] The processor can serve as the nerve center and command center of an electronic device. The controller can generate operation control signals based on the instruction opcode and timing signals to control the fetching and execution of instructions.

[0090] The processor may also include memory for storing instructions and data. In some embodiments, the memory in the processor is a cache memory. This memory can store instructions or data that the processor has just used or that are used repeatedly. If the processor needs to use the instruction or data again, it can retrieve it directly from this memory. This avoids repeated accesses, reduces processor latency, and thus improves system efficiency.

[0091] An external storage interface (ESI) can be used to connect external memory cards, such as microSD cards, to expand the storage capacity of electronic devices. The external memory card communicates with the processor through the ESI to perform data storage functions, such as saving music and video files on the external memory card.

[0092] Internal memory can be used to store computer executable program code, which includes instructions. The processor executes various functional applications and data processing of electronic devices by running the instructions stored in internal memory. Internal memory can include a program storage area and a data storage area. Internal memory can include high-speed random access memory, and can also include non-volatile memory, such as at least one disk storage device, flash memory device, universal flash storage (UFS), etc.

[0093] Wireless communication functionality in electronic devices can be achieved through antennas, wireless communication modules, modem processors, and baseband processors.

[0094] Wireless communication modules can provide solutions for wireless communication applications in electronic devices, including wireless local area networks (WLANs) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), global navigation satellite system (GNSS), frequency modulation (FM), near field communication (NFC), and infrared (IR) technologies.

[0095] Electronic devices can implement audio functions through audio modules, speakers, receivers, microphones, headphone jacks, and application processors.

[0096] Electronic devices can achieve shooting functions through ISPs, cameras, video codecs, GPUs, displays, and application processors.

[0097] Electronic devices can achieve display functions through GPUs, displays, and application processors.

[0098] A GPU is a microprocessor for image processing, connected to the display screen and application processor. GPUs are used to perform mathematical and geometric calculations for graphics rendering. A processor may include one or more GPUs, which execute program instructions to generate or modify display information.

[0099] A display screen is used to display images, videos, etc. A display screen includes a display panel.

[0100] The aforementioned electronic equipment realizes the conflict resolution method for fault diagnosis of aircraft power distribution system of this application. By collecting key parameters in real time and calculating trend weights to distinguish between real faults and interference signals, introducing frequency weights to adapt to historical statistical patterns, and integrating basic weights to generate dynamic comprehensive weights, it achieves the beneficial effect of significantly improving the accuracy, robustness and adaptability of fault diagnosis, thereby effectively improving the operational safety and intelligence level of aircraft power distribution system.

[0101] The storage medium provided in this application stores a program product capable of implementing a fault diagnosis and conflict resolution method for aircraft power distribution systems.

[0102] Methods for fault diagnosis and conflict resolution in aircraft power distribution systems include: Real-time acquisition of key parameters associated with multiple preset fault modes in the aircraft's power distribution system; For each of the aforementioned failure modes, a basic weight is set based on its inherent severity. By analyzing the real-time changing trends of the key parameters, the trend weight corresponding to each failure mode is calculated. Calculate the frequency weight for each failure mode based on historical failure statistics. By integrating the basic weight, trend weight, and frequency weight, the dynamic comprehensive weight of each failure mode is calculated. In response to multiple fault modes being triggered during fault diagnosis of the aircraft power distribution system, all triggered fault modes are sorted according to the dynamic comprehensive weight, and the fault mode diagnosis result with the highest weight value is selected for output.

[0103] In some possible implementations, the aircraft power distribution system fault diagnosis conflict resolution method of this disclosure can be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps described in the "Exemplary Methods" section above according to various exemplary embodiments of this disclosure.

[0104] The storage medium disclosed herein may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0105] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for fault diagnosis and conflict resolution in an aircraft power distribution system, characterized in that, include: Real-time acquisition of key parameters associated with multiple preset fault modes in the aircraft's power distribution system; For each of the aforementioned failure modes, a basic weight is set based on its inherent severity. By analyzing the real-time changing trends of the key parameters, the trend weight corresponding to each failure mode is calculated. Calculate the frequency weight for each failure mode based on historical failure statistics. By integrating the basic weight, trend weight, and frequency weight, the dynamic comprehensive weight of each failure mode is calculated. In response to multiple fault modes being triggered during fault diagnosis of the aircraft power distribution system, all triggered fault modes are sorted according to the dynamic comprehensive weight, and the fault mode diagnosis result with the highest weight value is selected for output. The step of analyzing the real-time changing trends of the key parameters and calculating the trend weight corresponding to each fault mode includes: For the key parameters associated with failure mode i, the formula is used. Calculate its current time Sample values Compared to the sampled values ​​of the previous n sampling periods rate of change , denoted as the rate of change of the key parameter of fault mode i; The rate of change of key parameters for all failure modes is normalized, and the normalized rate of change of key parameters for failure mode i is calculated. ; Based on the normalized rate of change of the key parameters The trend weight of failure mode i is calculated using the following formula. : in, is the first standardized coefficient, and m is the number of key parameters; The step of calculating the frequency weight corresponding to each fault mode based on historical fault statistics includes: Count the number of times fault mode i occurs within a preset historical period. ; The frequency weight of failure mode i is calculated using the following formula. : Where n is the total number of failure modes, This is the second standardized coefficient.

2. The aircraft power distribution system fault diagnosis and conflict resolution method according to claim 1, characterized in that, The normalized rate of change of the key parameters of failure mode i is calculated using the following formula. : in, It is the minimum rate of change of the key parameters among all failure modes. This represents the maximum rate of change of the key parameters across all failure modes.

3. The aircraft power distribution system fault diagnosis and conflict resolution method according to claim 1, characterized in that, The dynamic comprehensive weight for each failure mode is calculated by integrating the basic weight, trend weight, and frequency weight, including: The dynamic comprehensive weight of failure mode i is calculated using the following formula. : in, The basic weights for fault mode i, These are the allocation coefficients for the base weight, trend weight, and frequency weight, respectively, and they satisfy... .

4. The aircraft power distribution system fault diagnosis and conflict resolution method according to claim 3, characterized in that, The default value for the allocation coefficient is: .

5. The aircraft power distribution system fault diagnosis and conflict resolution method according to claim 1, characterized in that, The key parameters include current, voltage, temperature, and insulation resistance.

6. A fault diagnosis and conflict resolution system for an aircraft power distribution system, characterized in that, The system employs the aircraft power distribution system fault diagnosis and conflict resolution method as described in any one of claims 1 to 5; The system includes: The parameter acquisition module is used to acquire key parameters associated with multiple preset fault modes in the aircraft's power distribution system in real time. The basic weight setting module is used to set a basic weight for each of the aforementioned fault modes based on its inherent severity. The trend weight calculation module is used to calculate the trend weight corresponding to each fault mode by analyzing the real-time changing trend of the key parameters. The frequency weight calculation module is used to calculate the frequency weight corresponding to each fault mode based on historical fault statistics. The weight fusion module is used to calculate the dynamic comprehensive weight of each fault mode by fusing the basic weight, trend weight, and frequency weight. The diagnostic result filtering module is used to respond to multiple fault modes triggered during fault diagnosis of the aircraft power distribution system, sort all triggered fault modes according to the dynamic comprehensive weight, and output the diagnostic result of the fault mode with the highest weight value.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the aircraft power distribution system fault diagnosis and conflict resolution method as described in any one of claims 1 to 5.

8. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the aircraft power distribution system fault diagnosis and conflict resolution method as described in any one of claims 1 to 5.

Images