A multi-type avionics bus data on-site fault diagnosis device and implementation method thereof

Abstract

The present invention relates to the technical field of avionics system fault diagnosis, and discloses a multi-type avionics bus data on-site fault diagnosis device and an implementation method thereof. The method comprises acquiring parameters of multi-type avionics bus signals, and collecting the rising edge, falling edge, voltage, frequency, and period of the signals to obtain preliminary data; then performing logic analysis and signal quality analysis on the data, extracting data characteristics, and generating a characteristic sequence. The fault diagnosis model is trained by a self-learning algorithm and a historical experience library, the signal to be diagnosed is input into the model, and the output is combined with a simulation signal comparison to generate a fault diagnosis result. The present invention can quickly and accurately diagnose multi-type avionics bus faults, improve the efficiency of on-site fault troubleshooting, and is suitable for fault diagnosis in complex flight missions.

Description

Technical Field

[0001] The present invention relates to the technical field of avionics system fault diagnosis and the field of new generation information technology, and in particular to a field fault diagnosis device for multi-type avionics bus data and an implementation method thereof. Background Art

[0002] With the increasing complexity of modern aircraft systems, the normal operation of the avionics bus, as an important communication channel between various systems within the aircraft, is crucial to flight safety. At present, there are many types of avionics bus protocols used in aviation missions, such as ARINC429, RS422 and RS232. Each bus protocol has its own unique signal characteristics and data format. How to effectively diagnose potential faults in these multi-type avionics bus signals has become a key issue in avionics system maintenance.

[0003] Traditional avionics bus fault diagnosis methods mostly rely on manual detection or single-protocol fault analysis equipment, which takes a long time to troubleshoot and has low diagnostic efficiency. In addition, due to the complexity of avionics systems, traditional methods often find it difficult to fully analyze the logical relationships and data content of multiple protocol signals, resulting in an inability to quickly identify complex fault sources. In this case, fast and accurate on-site fault diagnosis capabilities become particularly important to ensure the smooth progress of flight missions.

[0004] Although some existing fault diagnosis equipment can collect and analyze a single bus, it lacks a unified signal collection and fault analysis mechanism when facing multiple types of avionics buses. Especially in the process of on-site troubleshooting, the portability, diagnosis speed and accuracy of the equipment still have a lot of room for improvement. Therefore, there is an urgent need for a device and method that can comprehensively collect and analyze signals from multiple types of avionics buses and conduct rapid diagnosis in combination with a historical fault experience database to improve the efficiency and accuracy of troubleshooting. Summary of the invention

[0005] The present invention provides a multi-type avionics bus data on-site fault diagnosis device and an implementation method thereof, so as to solve the problem of how to quickly and accurately diagnose on-site faults of the avionics bus based on data collection, logic analysis and historical fault experience of multi-type avionics bus signals, and improve the troubleshooting efficiency in flight missions.

[0006] In order to solve the above technical problems, the present invention provides a multi-type avionics bus data on-site fault diagnosis device and an implementation method thereof, comprising:

[0007] Acquire parameters of multiple types of avionics bus signals, including ARINC429, RS422, and RS232 signals, collect the rising edge, falling edge, voltage, frequency, and period of the signals, and obtain preliminary collected data;

[0008] Performing logic analysis on the preliminary collected data to analyze the integrity and validity of the signal and obtain a logic analysis result of the signal, wherein the logic analysis includes checking the time interval between the rising edge and the falling edge of the bus protocol to determine whether it complies with the protocol standard;

[0009] Preprocessing the logic analysis result, performing signal quality analysis based on the deviation values ​​of voltage, frequency and period, and obtaining a signal quality analysis result;

[0010] Extracting data characteristics from the signal quality analysis result, the data characteristics including a checksum, a code rate (R_b) and a signal period (T_b) of a data packet, and generating a data characteristic sequence of multiple types of buses;

[0011] Analyze the data characteristic sequence, train the fault model based on signal quality and data content through a historical experience library and a self-learning algorithm, and obtain a pre-trained fault diagnosis model;

[0012] The bus signal data to be diagnosed is input into the pre-trained fault diagnosis model, and the abnormal conditions of the signal data to be diagnosed are analyzed to obtain preliminary fault diagnosis results; the bus simulation signal generated by the simulation module is combined to compare the signal data to be diagnosed with the simulation signal data, and a difference metric is used to evaluate the difference between the two groups of signals to verify the accuracy of the preliminary fault diagnosis results; and a final fault diagnosis report is generated based on the verification results.

[0013] Furthermore, in the step of acquiring signal parameters, the multi-type avionics bus signal parameters include continuously collected data of voltage U, frequency f, and period T.

[0014] Furthermore, in the signal quality analysis step, the deviation values ​​of the signal voltage, frequency and period are calculated to obtain the voltage deviation ΔU, the frequency deviation Δf and the period deviation ΔT respectively, and generate a signal quality index.

[0015] Furthermore, the data packet checksum is calculated by a CRC checksum algorithm in the protocol.

[0016] Furthermore, the code rate Calculated based on the signal frequency f and the data width specified by the protocol.

[0017] Furthermore, the fault diagnosis model is trained by a self-learning algorithm, and the data used are standardized signal characteristic sequences and historical fault data.

[0018] Furthermore, the simulation module generates a bus simulation signal corresponding to the signal to be diagnosed, and compares the difference measurement with the actual signal to verify the accuracy of the diagnosis result.

[0019] Furthermore, the fault diagnosis report includes a description of the signal abnormality characteristics, the diagnosed fault type and the fault location.

[0020] Furthermore, the device performance verification includes evaluation of fault diagnosis accuracy, multi-protocol compatibility and diagnosis speed.

[0021] The key innovative features of the present invention include:

[0022] (1) Multi-protocol support and signal acquisition integration: The device can simultaneously support signal acquisition and processing of multiple avionics bus protocols, solving the problem of compatibility of multiple types of bus signals in complex systems.

[0023] (2) Intelligent fault diagnosis model: By combining the historical experience database and self-learning algorithm, the fault diagnosis model can be dynamically optimized to improve the accuracy and reliability of the diagnosis results.

[0024] (3) Simulation signal verification mechanism: The simulation module generates simulation signals corresponding to actual signals to verify the accuracy of diagnostic results and ensure the reliability of the equipment in complex flight missions.

[0025] The following are its main beneficial effects:

[0026] The present invention uses real-time acquisition and logical analysis of multiple types of avionics bus signals, combined with a historical fault experience database and a self-learning algorithm, to quickly identify fault signals and generate accurate fault diagnosis results. Compared with traditional avionics bus diagnostic equipment, the present invention can simultaneously process multiple bus protocols such as ARINC429, RS422, and RS232, avoiding the limitations of single protocol analysis and improving the comprehensiveness of signal analysis. By performing logical analysis and quality assessment on the collected signals, and using mathematical calculation formulas to calculate the deviation value of the signal, data characteristics are extracted and a standardized fault diagnosis model is generated, which greatly improves the accuracy of diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A schematic diagram of a flow chart of a multi-type avionics bus data field fault diagnosis device and an implementation method thereof provided in an embodiment of the present application;

[0028] Figure 2 A structural block diagram of a multi-type avionics bus data field fault diagnosis device and its implementation method provided in an embodiment of the present application;

[0029] Figure 3 A principle block diagram of a multi-type avionics bus data field fault diagnosis device provided in an embodiment of the present application;

[0030] Figure 4An architecture diagram of a multi-type avionics bus data field fault diagnosis device provided in an embodiment of the present application;

[0031] Figure 5 A diagram of the internal module composition of a device provided in an embodiment of the present application;

[0032] Figure 6 A device design outline diagram provided for an embodiment of the present application;

[0033] Figure 7 A software analysis diagram of a multi-type avionics bus data field fault diagnosis device provided in an embodiment of the present application;

[0034] Figure 8 This is a physical working diagram of a multi-type avionics bus data field fault diagnosis device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0036] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0037] Embodiment 1:

[0038] Reference Figure 1 , is a flow chart of a multi-type avionics bus data field fault diagnosis device and an implementation method thereof provided by an embodiment of the present invention. The flow of the method may at least include steps S100-S400:

[0039] S100, obtaining signal parameters of multiple types of buses, and performing preliminary logic analysis, preprocessing the rising edge, falling edge, voltage, frequency, and period of the signal to obtain a signal quality analysis result;

[0040] S200, extracting data characteristics from the signal quality analysis result, the data characteristics including a checksum, a code rate (R_b), and a signal period (T_b) of a data packet, and generating a data characteristic sequence of multiple types of buses;

[0041] S300, analyzing the data characteristic sequence, and training the fault model based on signal quality and data content through a historical experience database and a self-learning algorithm to obtain a pre-trained fault diagnosis model;

[0042] S400, inputting the bus signal data to be diagnosed into the pre-trained fault diagnosis model, combining with the bus simulation signal generated by the simulation module, comparing the signal output of the test equipment, generating the final fault diagnosis result and verifying the equipment performance.

[0043] Step S100 at least includes steps S110-S130:

[0044] S110, acquiring signal parameters of multiple types of buses, including ARINC429, RS422, and RS232, and collecting rising edge, falling edge, voltage, frequency, and period of the signal to obtain preliminary collected data of the signal;

[0045] Specifically, the signal parameters are obtained from different types of avionics bus signals (including ARINC429, RS422, and RS232) through the signal acquisition module of the device. The acquired signal parameters include physical parameters such as rising edge, falling edge, voltage (U), frequency (f), and period (T). For each type of bus signal, the system determines the corresponding sampling rate and trigger conditions according to its specific protocol standard. For example, the ARINC429 signal uses a specific sampling rate and data width, while RS422 and RS232 set the sampling parameters according to their baud rate.

[0046] Specifically, the collected signal parameters are described by the collection formula as follows: , , ,in, represents the voltage signal corresponding to time point t, is the signal frequency at that time point, is the signal period, and i represents different bus types (such as ARINC429, RS422, RS232).

[0047] By continuously collecting these signals, the preliminary collected data sequence of each type of bus signal is obtained, which is recorded as: This sequence will be used for subsequent signal logic analysis.

[0048] S120, performing logic analysis on the preliminary collected data, analyzing the integrity and validity of the signal, and obtaining a logic analysis result of the signal;

[0049] Furthermore, the preliminary collected data enters the logic analysis module. Specifically, the system analyzes the logic integrity of each signal using the rising edge and falling edge time points. According to the standard of each bus protocol, the trigger voltage threshold and time delay range are set to detect whether the signal meets the logic conditions specified in the protocol.

[0050] For example, the logic analysis module verifies whether each signal transition is within a reasonable range based on the standard time interval between the rising and falling edges of the ARINC429 protocol: and in, is the time interval of the rising edge, is the time interval of the falling edge, and i represents the corresponding bus signal type.

[0051] By checking the integrity, waveform and phase of the logic signal, we can analyze whether the signal meets the logical relationship of the protocol standard. If the signal does not meet the protocol logic at any time point, it is marked as a logic error. Finally, we get the logic analysis result: This result is used in the subsequent signal quality analysis step S130.

[0052] S130, pre-processing the logic analysis result, performing signal quality analysis based on the deviation values ​​of voltage, frequency and period, and obtaining a signal quality analysis result.

[0053] Specifically, the signal quality analysis module further processes the collected signal based on the logic analysis result obtained in step S120, and calculates the deviation value of each signal by comparing the collected voltage, frequency, period and other parameters with the protocol standard value.

[0054] Set the standard parameters for each signal to: , , Then, calculate the deviation value of each acquired signal: These deviation values ​​are used to further quantify the quality of the signal and obtain the proportion of the signal distortion.

[0055] For each type of bus signal, the signal quality analysis result is generated by combining voltage deviation, frequency deviation and period deviation, which is recorded as: f( , , )in, It represents the quality index of the i-th type bus signal. The function f is used to perform weighted calculation on all deviation values ​​to generate a comprehensive quality score.

[0056] The signal quality analysis result is used in the subsequent module S200 to extract data characteristics and further perform fault diagnosis and analysis.

[0057] Step S200 at least includes steps S210-S230:

[0058] S210, extracting data characteristics from the signal quality analysis result, the data characteristics including a checksum, a code rate (R_b), and a signal period (T_b) of a data packet, to obtain basic data characteristics of a bus protocol;

[0059] Specifically, the signal quality analysis result obtained from step S130 Extract key data characteristics, including the checksum of the data packet, the code rate (R_b), and the signal period (T_b). These characteristics are derived from the basic data of signal acquisition and extracted according to different bus protocols (such as ARINC429, RS422, RS232). For each bus type, the extraction formula is as follows:

[0060] Packet checksum: Calculate the checksum of each packet based on a known protocol checksum algorithm (such as CRC checksum) :

[0061] modM

[0062] in, is the data in the kth data packet, M is the modulus specified by the protocol, n is the length of the data packet, and i represents different types of buses.

[0063] Code rate : The frequency recorded by the signal quality analysis results , calculate the code rate, the formula is as follows:

[0064] = ⋅data_

[0065] Among them, data_ It is the data bit width of the bus protocol.

[0066] cycle : From the signal acquisition sequence (t) to extract the cycle information for subsequent bus protocol characteristic analysis, which is defined as follows:

[0067]

[0068] These calculations provide basic data characteristics for each protocol type, forming a preliminary set of characteristics: Where n is the number of bus types.

[0069] S220, sorting and classifying the basic data characteristics to generate characteristic sequences of multiple types of buses;

[0070] In step S220, further, the various basic data features { Specifically, the characteristics are first grouped according to the type of bus protocol (such as ARINC429, RS422, RS232), and then the characteristic sequences are archived according to the characteristic requirements of different protocols to form a unified characteristic sequence.

[0071] The sorting process is as follows:

[0072] Classification and sorting: Classify the characteristics according to the bus protocol type and form a characteristic matrix:

[0073]

[0074] Each row of the matrix represents the basic data characteristics of a bus type.

[0075] Generate feature sequence: By performing feature serialization processing on the classified data feature matrix, the feature sequence of multiple types of buses is generated, which is recorded as:

[0076]

[0077] Where n is the number of bus types and m is the number of data features for each type of bus.

[0078] S230: normalize the characteristic sequence to generate standardized multi-type bus data characteristics.

[0079] In step S230, further, the multi-type bus characteristic sequence generated in step S220 Normalization is performed. Because the data characteristics of different bus protocols have orders of magnitude differences, such as code rate and cycle The units of the data are quite different, so all the characteristics need to be normalized for subsequent unified analysis and comparison.

[0080] The normalization process is as follows:

[0081] Normalization formula: For each element of the feature matrix M, use the minimum-maximum normalization formula:

[0082]

[0083] in, is the normalized characteristic matrix element, and are the minimum and maximum values ​​of the matrix M respectively.

[0084] Generate standardized characteristic sequence: After normalizing all characteristics, generate a standardized multi-type bus characteristic sequence:

[0085]

[0086] This standardized sequence will be used for subsequent intelligent diagnosis model training (step S300).

[0087] Step S300 at least includes steps S310-S330:

[0088] S310, analyzing the data characteristic sequences of the multi-type buses, and generating preliminary fault analysis data in combination with similar fault data extracted from a historical experience database;

[0089] In step S310, specifically, the standardized multi-type bus data characteristic sequence generated in step S230 As input, the fault data in the historical experience database is analyzed. The historical experience database stores a variety of similar fault cases, classified by bus type, covering different signal characteristics and fault modes. Compared with the data sequence in the experience library, similar fault data that matches it is extracted to generate a preliminary fault analysis data set.

[0090] The analysis process is as follows:

[0091] Sequence the characteristics Characteristic sequence in historical experience library Perform similarity calculation and use distance measurement methods (such as Euclidean distance or cosine similarity) to calculate the similarity between the two:

[0092]

[0093] When the similarity d is less than the set threshold, the corresponding fault data in the historical experience database is extracted. and compare it with Combined to generate a preliminary fault analysis data set , this dataset will be used for model training.

[0094] S320, based on the signal quality analysis result and the data characteristic sequence, the fault diagnosis model is trained by a self-learning algorithm to obtain a pre-trained fault diagnosis model;

[0095] In step S320, further, the preliminary fault analysis data set generated in step S310 is and from the signal quality analysis results As input, a self-learning algorithm is applied to train the fault diagnosis model. Specifically, the model uses a supervised learning algorithm to identify the association between specific signal characteristics and fault types by gradually optimizing parameters, thereby establishing a model that can automatically predict faults.

[0096] The training process is as follows:

[0097] Input data: and Combination as input data pair, denoted as:

[0098] , =Fault Label

[0099] in, It is a fault label marked based on the historical experience database.

[0100] Apply self-learning algorithms (such as gradient boosting, random forest, etc.) to train the model:

[0101]

[0102] in, is the fault diagnosis model, and L is the loss function, which is used to measure the difference between the model prediction output and the true fault label.

[0103] Through multiple rounds of training, the model parameters θ are adjusted to minimize the loss function, and finally a pre-trained fault diagnosis model is obtained. .

[0104] S330: verify the pre-trained fault diagnosis model to ensure the accuracy and stability of the model and obtain a final pre-trained model.

[0105] In step S330, further, the pre-trained fault diagnosis model generated in step S320 is Validation is performed to ensure its accuracy and stability. The validation process inputs independent datasets (data not included in the training set) into the model and evaluates its performance in different scenarios.

[0106] The verification process is as follows:

[0107] Select an independent validation set , , which is fed into the pre-trained model , and generate the prediction output :

[0108]

[0109] By comparing the prediction results With the real fault label , calculate the model's accuracy, recall, F1 score and other performance indicators:

[0110]

[0111] Among them, m is the number of samples in the validation set, and 1 is the indicator function, which is used to determine whether the predicted value is consistent with the true value.

[0112] After verification, the final pre-training model is obtained and use it in the subsequent fault diagnosis process.

[0113] Step S400 at least includes steps S410-S430:

[0114] S410, inputting the bus signal data to be processed into the pre-trained fault diagnosis model, analyzing the abnormality of the signal data to be processed, and obtaining a preliminary fault diagnosis result;

[0115] In step S410, the bus signal data to be processed (e.g., from ARINC429, RS422, RS232, etc.) is first input into the pre-trained fault diagnosis model previously trained and verified in S330. Specifically, the signal data to be processed is recorded as , whose data format is the same as the signal feature sequence used for training Keep consistent. Analyze the characteristic data of each signal through the model , detect abnormal conditions and identify possible fault types.

[0116] The model processing process is as follows:

[0117]

[0118] in, It is the fault type or label predicted by the model. By comparing it with the fault labels in the historical experience library, a preliminary fault diagnosis result is generated. The preliminary result includes key information such as the fault type, abnormal signal characteristics, and possible location of the fault.

[0119] S420, combining the bus simulation signal generated by the simulation module, comparing the signal data to be processed with the simulation signal data, and verifying the accuracy of the preliminary fault diagnosis result;

[0120] In step S420, further, the bus simulation signal generated by the simulation module is combined The simulation module can generate the same fault diagnosis signal as the protocol of the signal to be diagnosed (such as ARINC429, RS422, etc.). The corresponding simulation signal sequence , and compare it with the signal to be processed.

[0121] The comparison process uses a difference metric such as mean squared error (MSE) to assess the difference between the two sets of signals:

[0122]

[0123] When the signal difference MSE is lower than the set threshold, the accuracy of the preliminary fault diagnosis results is verified; otherwise, the simulation results may indicate that the model may have misdiagnosis and the results need to be further corrected. This step ensures that the fault diagnosis results are based on real data verification and enhances the reliability of diagnosis.

[0124] S430: Generate a final fault diagnosis report based on the verification result, and verify whether the device performance meets expectations.

[0125] In step S430, based on the results of verification in S420, a final fault diagnosis report is generated. The report includes:

[0126] Detailed description of the signal anomaly characteristics;

[0127] The fault type and fault location predicted by the model;

[0128] After comparing with the simulation signal, the accuracy of the fault diagnosis is verified.

[0129] In addition, the verification of device performance includes the evaluation of the device's diagnostic capabilities under different bus protocols. Performance verification indicators include:

[0130] Accuracy of fault diagnosis;

[0131] Diagnostic speed (the difference between the diagnosis time and the actual fault occurrence time);

[0132] Multi-protocol compatibility verification.

[0133] By analyzing the above indicators, we can ensure that the diagnostic effect of the device in the real application scenario meets the design expectations. If the device performance does not meet the requirements, the fault diagnosis model or simulation module may need to be further optimized.

[0134] The key innovative features of the present invention include:

[0135] (1) Multi-protocol support and signal acquisition integration: The device can simultaneously support signal acquisition and processing of multiple avionics bus protocols, solving the problem of compatibility of multiple types of bus signals in complex systems.

[0136] (2) Intelligent fault diagnosis model: By combining the historical experience database and self-learning algorithm, the fault diagnosis model can be dynamically optimized to improve the accuracy and reliability of the diagnosis results.

[0137] (3) Simulation signal verification mechanism: The simulation module generates simulation signals corresponding to actual signals to verify the accuracy of diagnostic results and ensure the reliability of the equipment in complex flight missions.

[0138] The following are its main beneficial effects:

[0139] The present invention uses real-time acquisition and logical analysis of multiple types of avionics bus signals, combined with a historical fault experience database and a self-learning algorithm, to quickly identify fault signals and generate accurate fault diagnosis results. Compared with traditional avionics bus diagnostic equipment, the present invention can simultaneously process multiple bus protocols such as ARINC429, RS422, and RS232, avoiding the limitations of single protocol analysis and improving the comprehensiveness of signal analysis. By performing logical analysis and quality assessment on the collected signals, and using mathematical calculation formulas to calculate the deviation value of the signal, data characteristics are extracted and a standardized fault diagnosis model is generated, which greatly improves the accuracy of diagnosis.

[0140] Embodiment 2:

[0141] Figure 2 The structure block diagram of a multi-type avionics bus data field fault diagnosis device and its implementation method according to an embodiment of the present invention is shown. Figure 2 As shown, the system may include:

[0142] The data acquisition module 10 is used to obtain signal parameters from multiple types of avionics buses (such as ARINC429, RS422, and RS232). The module uses a built-in high-precision acquisition device to obtain important signal parameters such as rising edge, falling edge, voltage, frequency, and period in real time, and converts them into a signal data sequence that can be analyzed.

[0143] Input: Multiple types of avionics bus signals (ARINC429, RS422, RS232, etc.).

[0144] Output: preliminary collected data sequence of the signal, including physical parameters such as voltage, frequency, and period.

[0145] The signal analysis and processing module 20 performs logic analysis and quality assessment on the collected signals. The signal analysis module compares various bus protocol standards and analyzes the integrity and logical validity of the signal. Next, the processing module performs preprocessing based on parameters such as frequency, voltage, and period, and calculates the deviation value of each type of signal to generate a signal quality analysis result.

[0146] Input: The preliminary collected data sequence provided by the data collection module.

[0147] Output: signal logic analysis results and quality analysis results.

[0148] The feature extraction and fault diagnosis module 30 extracts features such as packet checksum, code rate, and cycle from the signal quality analysis results and generates a feature sequence. Subsequently, the data is analyzed and trained using the historical fault experience library and self-learning algorithm to form a pre-trained fault diagnosis model. This module matches the data features with historical fault cases, identifies the abnormal features of the signal, and obtains preliminary fault diagnosis results.

[0149] Input: signal quality analysis results and historical fault data from the signal analysis and processing module.

[0150] Output: Preliminary fault diagnosis results, including potential fault types and fault locations.

[0151] The simulation and verification module 40 generates a bus simulation signal corresponding to the signal to be processed through the simulation module and compares it with the actual signal. This module generates a simulation signal for comparison and verification based on the output of the fault diagnosis model to ensure the accuracy of the diagnosis result. Finally, a fault diagnosis report is generated based on the verification result and the equipment performance is evaluated.

[0152] Input: preliminary fault analysis results from the fault diagnosis module and the signals generated by the simulation module.

[0153] Output: fault diagnosis report and equipment performance evaluation results.

[0154] Figure 3 A principle block diagram of a multi-type avionics bus data field fault diagnosis device provided in an embodiment of the present application;

[0155] Figure 4 An architecture diagram of a multi-type avionics bus data field fault diagnosis device provided in an embodiment of the present application;

[0156] Figure 5 A diagram of the internal module composition of a device provided in an embodiment of the present application;

[0157] Figure 6 A device design outline diagram provided for an embodiment of the present application;

[0158] Figure 7 A software analysis diagram of a multi-type avionics bus data field fault diagnosis device provided in an embodiment of the present application;

[0159] Figure 8 This is a physical working diagram of a multi-type avionics bus data field fault diagnosis device provided in an embodiment of the present application.

[0160] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for implementing a multi-type avionics bus data on-site fault diagnosis device, characterized in that: The steps include: Acquire parameters of multiple types of avionics bus signals, including ARINC429, RS422, and RS232 signals, collect the rising edge, falling edge, voltage, frequency, and period of the signals, and obtain preliminary collected data; Performing logic analysis on the preliminary collected data to analyze the integrity and validity of the signal and obtain a logic analysis result of the signal, wherein the logic analysis includes checking the time interval between the rising edge and the falling edge of the bus protocol to determine whether it complies with the protocol standard; Preprocessing the logic analysis result, performing signal quality analysis based on the deviation values ​​of voltage, frequency and period, and obtaining a signal quality analysis result; Extracting data characteristics from the signal quality analysis result, the data characteristics including a checksum, a code rate (R_b) and a signal period (T_b) of a data packet, and generating a data characteristic sequence of multiple types of buses; Analyze the data characteristic sequence, train the fault model based on signal quality and data content through a historical experience library and a self-learning algorithm, and obtain a pre-trained fault diagnosis model; Input the bus signal data to be diagnosed into the pre-trained fault diagnosis model, analyze the abnormal conditions of the signal data to be diagnosed, and obtain preliminary fault diagnosis results; combine the bus simulation signal generated by the simulation module, compare the signal data to be diagnosed with the simulation signal data, use the difference metric to evaluate the difference between the two groups of signals, and verify the accuracy of the preliminary fault diagnosis results; Generate a final fault diagnosis report based on the verification results.

2. The implementation method according to claim 1, characterized in that: The multi-type avionics bus signal parameters include continuously collected data of voltage U, frequency f, and period T.

3. The implementation method according to claim 1, characterized in that: In the signal quality analysis step, the deviation values ​​of the signal voltage, frequency and period are calculated to obtain the voltage deviation ΔU, the frequency deviation Δf and the period deviation ΔT respectively, and generate a signal quality index.

4. The implementation method according to claim 1, characterized in that: The data packet checksum is calculated using the CRC checksum algorithm in the protocol.

5. The implementation method according to claim 1, characterized in that: Code rate Calculated based on the signal frequency f and the data width specified by the protocol.

6. The implementation method according to claim 1, characterized in that: The fault diagnosis model is trained by a self-learning algorithm, and the data used include standardized signal characteristic sequences and historical fault data.

7. The implementation method according to claim 1, characterized in that: The simulation module generates a bus simulation signal corresponding to the signal to be diagnosed, and compares the difference measurement with the actual signal to verify the accuracy of the fault diagnosis result.

8. The implementation method according to claim 1, characterized in that: The generated fault diagnosis report includes a description of the signal abnormality characteristics, fault type and fault location.

Images