Aircraft-oriented test data comprehensive analysis method and system

Abstract

The invention belongs to the technical field of aircraft test data processing, and discloses an aircraft-oriented test data comprehensive analysis method and system, and the method comprises the steps: collecting aircraft test data, including engineering simulator data, test flight data and laboratory test data, and carrying out the preprocessing of the aircraft test data, the method comprises the following steps: establishing a data association model according to a sensor signal state of aircraft test data, airborne system and equipment state information and alarm logic, associating the aircraft test data, extracting alarm information, abnormal modes and fault features of the associated aircraft test data, generating a data chart related to fault alarm, and if the alarm information does not exist, executing the fault alarm; if yes, generating an abnormal data chart and generating an analysis report. According to the invention, multi-type data can be efficiently processed, faults can be rapidly positioned, data can be visually displayed, and aircraft maintenance is supported.

Description

Technical Field

[0001] This invention belongs to the field of aircraft test data processing technology, and relates to an analysis method and system for aircraft flight test data, specifically to a comprehensive analysis method and system for aircraft test data. Background Technology

[0002] In aircraft development, testing is an effective means of requirements confirmation and verification, and the analysis of test data is of great significance for requirements confirmation, flight test safety, requirements verification, and airworthiness certification. However, existing test data analysis methods face the following problems: Diverse data types: Test data for the same system / equipment comes from sources such as simulator test data, flight test data, and laboratory test data, with different data types and formats, making the analysis process complex and time-consuming.

[0003] Data volume and complexity: The experimental data is massive and involves multiple aspects such as the aircraft's physical state, sensor signals, airborne system / equipment status information, intermediate variables, etc. The data is diverse, and traditional manual analysis methods are inefficient.

[0004] Fault identification and localization are difficult: Existing methods are unable to quickly locate complex faults, especially combined fault scenarios, which affects the timeliness of fault handling and maintenance.

[0005] Insufficient data visualization: Existing tools are unable to intuitively display the correlation between multiple types of data, making it difficult to quickly understand and apply the analysis results. Summary of the Invention

[0006] To address this, the present invention provides a comprehensive analysis method and system for aircraft test data, which can efficiently process various types of data, including engineering simulator data, flight test data, and laboratory test data, and solves the shortcomings of existing methods in terms of data analysis efficiency, fault location, and visualization.

[0007] The technical solution of the present invention is as follows: A comprehensive analysis method for aircraft test data includes the following steps: S1 collects aircraft test data, including engineering simulator data, flight test data and laboratory test data, and preprocesses the aircraft test data; S2, based on the sensor signal status, airborne system and equipment status information, and alarm logic of the aircraft test data, establish a data association model to associate the aircraft test data; S3, extract alarm information, anomaly modes and fault characteristics from the correlated aircraft test data; S4, generate data charts related to fault alarms; if there are no alarms, generate abnormal data charts. S5 generates an analysis report.

[0008] Furthermore, in S1, preprocessing includes uniformly formatting and labeling the aircraft test data, and removing noise and redundant information.

[0009] Furthermore, in S2, the data association model is established based on the relationships between various airborne systems and equipment of the aircraft. Specifically, the relationships are the signal transmission relationships, mechanical transmission relationships, and control sequence relationships of all airborne systems and equipment in the aircraft operation.

[0010] Furthermore, in S2, the alarm logic and alarm triggering conditions for each airborne system and device of the aircraft are set in the association model. The alarm logic specifically includes airborne system and device alarms and all associated signals.

[0011] Furthermore, in S2, the correlation model also includes correlating all aircraft test data with the aircraft's flight phases.

[0012] Furthermore, in S3, the extraction methods include: Alarm signals and sensor fault signals are discrete quantities, where 0 represents normal and 1 represents fault. When a fault occurs, the occurrence and duration of the fault are recorded. At the same time, relevant equipment operating status and the current flight phase information of the aircraft are extracted based on the correlation model, and the changing trend of the analog quantities is analyzed through time series analysis.

[0013] Furthermore, in S3, if there is alarm information, the alarm-related data is organized according to the alarm information and alarm association rules, the integrated data is analyzed, potential faults are identified, and the faulty component or time point is located; if there is no alarm information, the data is analyzed according to the data anomaly judgment rules, the abnormal data is organized, and the time when the data anomaly occurred is located.

[0014] An aircraft-oriented test data comprehensive analysis system includes flight test data analysis software running on a computer. The flight test data analysis software runs a aforementioned aircraft-oriented test data comprehensive analysis method. It imports aircraft test data into the flight test data analysis software, then uses the association model generation module in the flight test data analysis software to edit the rules of the association model, and finally obtains an analysis report through the analysis report generation module.

[0015] Technical effects: 1. Efficiently process multiple data types: Improve the ability to process different data types through unified data preprocessing and integrated analysis.

[0016] 2. Rapid Fault Location: The fault identification algorithm based on association rules can quickly locate the source of the fault and reduce analysis time.

[0017] 3. Intuitive data display: Through highly visualized charts, it helps users quickly understand complex data relationships and failure modes.

[0018] 4. Support aircraft maintenance: Improve aircraft maintainability through analysis reports. Attached Figure Description

[0019] Figure 1 This is a flowchart of the experimental data analysis process of the present invention. Detailed Implementation

[0020] The features and illustrative embodiments of various aspects of the present invention will now be described in detail. Numerous specific design details are set forth in the following detailed description to provide a more complete understanding of the invention. However, it will be apparent to those skilled in the art that the invention can be practiced without some of these specific details. The following description of embodiments is merely intended to provide a better understanding of the invention by illustrating examples of the invention. The invention is by no means limited to any specific setup and method set forth below, but covers any improvements, substitutions, and modifications to the structures, methods, and devices without departing from the spirit of the invention. In the drawings and the following description, any parts not exhaustively described are considered to be common knowledge or conventional practices in the art.

[0021] It should be noted that, unless otherwise specified, the embodiments of the present invention and the features thereof can be combined with each other, and the various embodiments can be referenced and cited in each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0022] Example 1: A comprehensive analysis method for aircraft test data includes the following steps: S1 collects aircraft test data, including engineering simulator data, flight test data and laboratory test data, and preprocesses the aircraft test data; S2, based on the sensor signal status, airborne system and equipment status information, and alarm logic of the aircraft test data, establish a data association model to associate the aircraft test data; S3, extract alarm information, anomaly modes and fault characteristics from the correlated aircraft test data; S4, generate data charts related to fault alarms; if there are no alarms, generate abnormal data charts. S5 generates an analysis report.

[0023] In S1, preprocessing includes uniformly formatting and labeling the aircraft test data, and removing noise and redundant information.

[0024] In S2, the data association model is established based on the relationships between various airborne systems and equipment of the aircraft. Specifically, the relationships are the signal transmission relationships, mechanical transmission relationships, and control sequence relationships of all airborne systems and equipment in the aircraft operation.

[0025] In S2, the alarm logic and alarm triggering conditions for each airborne system and device of the aircraft are set in the association model. The alarm logic specifically includes airborne system and device alarms and all associated signals.

[0026] In S2, the correlation model also includes correlating all aircraft test data with the aircraft's flight phases.

[0027] In S3, the extraction methods include: Alarm signals and sensor fault signals are discrete quantities, where 0 represents normal and 1 represents fault. When a fault occurs, the occurrence and duration of the fault are recorded. At the same time, relevant equipment operating status and the current flight phase information of the aircraft are extracted based on the correlation model, and the changing trend of the analog quantities is analyzed through time series analysis.

[0028] In S3, if there is an alarm message, the alarm-related data is organized according to the alarm message and alarm association rules, the integrated data is analyzed, potential faults are identified, and the faulty component or time point is located. If there is no alarm message, the data is analyzed according to the data anomaly judgment rules, the abnormal data is organized, and the time when the data anomaly occurred is located.

[0029] An aircraft-oriented test data comprehensive analysis system includes flight test data analysis software running on a computer. The flight test data analysis software runs a aforementioned aircraft-oriented test data comprehensive analysis method. It imports aircraft test data into the flight test data analysis software, then uses the association model generation module in the flight test data analysis software to edit the rules of the association model, and finally obtains an analysis report through the analysis report generation module.

[0030] Example 2: The implementation steps of this invention are as follows: Data Acquisition and Preprocessing: Collect engineering simulator data, flight test data, and laboratory test data.

[0031] Format and clean the data to ensure data quality and consistency.

[0032] Data integration and correlation analysis: A data association model is established based on flight status, system components, and alarm design logic.

[0033] Based on the existing fault logic and alarm logic, extract the abnormal patterns in the data.

[0034] Fault identification and location: 1. Based on the alarm information and alarm logic, organize the data related to the alarm.

[0035] 2. Analyze and integrate abnormal data according to the preset fault identification rules.

[0036] Data visualization and results presentation: 1. Display key data charts related to fault alarms to help analysts quickly understand the causes and impacts of faults.

[0037] 2. If there are no alarm messages, display abnormal data charts to help analysts quickly locate hidden faults.

[0038] Analysis report generation: It automatically generates detailed analysis reports, including the time of the failure, charts, and analysis conclusions.

[0039] Suppose that during a test flight, the system detects a "flap half-speed" warning: Data Acquisition and Preprocessing: Collect signals related to the "flap half-speed" alarm logic, including flap control signals, hydraulic pressure signals, and engine speed, as well as other data related to the flap half-speed alarm.

[0040] Clean and format the data.

[0041] Data integration and correlation analysis: Based on the flight status, analyze the changes in the flap's speed. It was found that the flap was at half speed during the period when engine #4 had already been shut down.

[0042] Fault identification and location: The system detected that engine #4 was shut down, and the flaps were at half speed.

[0043] Data visualization and results presentation: Generate a trend graph of flap half-speed over time. Display data related to flap half-speed alarms.

[0044] Automatically generate fault analysis reports.

[0045] In another test or flight test, a certain data point was found to be abnormal, but no alarm message was issued.

[0046] Data Acquisition and Preprocessing: The fault diagnosis rules collect relevant data on abnormal data.

[0047] Clean and format the data.

[0048] Fault identification and location: Determine whether the data is abnormal based on the fault diagnosis rules, and organize the abnormal data.

[0049] Data visualization and results presentation: Generate trend charts of abnormal data over time and the time of failure occurrence for data analysts to reference and analyze.

[0050] The above description is only a preferred embodiment of the present invention. It should be noted that those skilled in the art can make several improvements without departing from the principle of the present invention, and these improvements should also be considered within the scope of protection of the present invention.

Claims

1. A method for aircraft-oriented comprehensive analysis of test data, characterized in that The method comprises the following steps: S1, collecting aircraft test data, including engineering simulator data, flight test data and laboratory test data, and preprocessing the aircraft test data; S2, establishing a data correlation model according to the sensor signal state of the aircraft test data, the state information of the airborne system and device, and the alarm logic, correlating the aircraft test data; S3, extracting the alarm information, abnormal mode and fault feature of the correlated aircraft test data; S4, generating a data chart related to fault alarm, and if there is no alarm information, generating an abnormal data chart; S5, generating an analysis report.

2. The aircraft-oriented test data synthesis analysis method according to claim 1, characterized in that, In S1, the preprocessing includes uniform formatting and labeling of the aircraft test data, and removing noise and redundant information.

3. The method of claim 1, wherein, In S2, in the establishment of the data correlation model, the correlation model is established according to the correlation relationship between each airborne system and device of the aircraft, and the correlation relationship is specifically the signal transmission relationship, mechanical transmission relationship and control sequence relationship of all airborne systems and devices of the aircraft during flight.

4. The method of claim 3, wherein, In S2, the alarm logic and the triggering condition of the alarm of each airborne system and device in the correlation model are set, and the alarm logic is specifically the alarm of the airborne system and device and all associated signals.

5. An aircraft-oriented test data synthesis analysis method according to claim 4, characterized in that, In S2, the correlation model also includes correlation of all aircraft test data and flight phases of the aircraft.

6. The method of claim 1, wherein, In S3, the extraction method includes: The alarm signal and the sensor fault signal are discrete quantities, where 0 represents normal and 1 represents fault. When a fault occurs, the time of fault occurrence and duration is recorded, and the related device working state and the current flight phase information of the aircraft are extracted according to the correlation model, and the change trend of the analog quantity is analyzed through time sequence analysis.

7. A method of aircraft oriented test data synthesis analysis according to claim 6, characterized in that, In S3, if there is alarm information, the data related to the alarm is sorted according to the alarm information and the alarm correlation rule, the sorted data is analyzed, potential faults are identified, and the fault occurrence component or time point is located; if there is no alarm information, the data is analyzed according to the data anomaly judgment rule, the abnormal data is sorted and the time of data anomaly occurrence is located.

8. An aircraft-oriented test data synthesis analysis system characterized by, The flight test data analysis software runs in a computer, the flight test data analysis software runs a flight-oriented test data comprehensive analysis method as claimed in any one of claims 1-7, imports aircraft test data in the flight test data analysis software, then edits the rules of the correlation model by using the correlation model generation module in the flight test data analysis software, and finally obtains an analysis report by using the analysis report generation module.

Images