A real-time monitoring system and method for low-altitude aircraft

Abstract

This invention provides a real-time monitoring system and method for low-altitude aircraft. It includes a vibration acceleration sensor (1), an integrated data acquisition and transmission unit (2), a 5G-A module (3), a flight status identification system (4), real-time diagnostic software based on big data remote experts (5), a big data-based proactive maintenance system (6), and a database (7). The 5G-A module (3) is mounted on the integrated data acquisition and transmission unit (2). Using modular design technology, it achieves integrated testing and remote transmission, real-time and historical data, fault analysis, and system maintenance, enabling automatic processing, diagnosis, and alarm functions. This significantly improves efficiency and features intelligence, multi-system integration, miniaturization, and low cost.

Description

Technical Field

[0001] This invention belongs to the field of aircraft flight safety technology, specifically relating to a real-time monitoring system and method for low-altitude aircraft. Background Technology

[0003] Aircraft testing and real-time monitoring is a complex task, primarily composed of a general airborne data acquisition subsystem, a dedicated airborne data recording subsystem, a network switching and timing subsystem, a telemetry monitoring subsystem, a test data preprocessing system, various specialized test systems, and test system debugging support equipment and application software. An airborne data acquisition and recording system is installed on the low-altitude aircraft, along with an airborne telemetry transmission system. Parameters requiring real-time monitoring on the ground are selected from the flight test parameters and transmitted to the ground via airborne telemetry equipment. A ground telemetry station is established, consisting of a telemetry receiving system and a computer data processing system. The telemetry computer and data terminal computer exchange data via Ethernet. The telemetry receiving system tracks and receives the airborne telemetry transmission signals. The telemetry terminal synchronizes and decodes the telemetry data and broadcasts it to the data processing terminal via the computer network. The data processing computer performs specialized processing and displays the data, and professional technicians monitor the data of the low-altitude aircraft in real time. This process involves numerous pieces of equipment, is costly, and lacks a standardized design technology system, making it impossible to achieve operational support throughout the entire lifecycle of the low-altitude aircraft. In addition, although current flight telemetry systems can meet the requirement of real-time downlink of core flight data, they have drawbacks such as insufficient data transmission bandwidth and distance, large requirements for support personnel, and the need for telemetry vehicles to move with the aircraft. Summary of the Invention

[0004] The purpose of this invention is to propose a real-time monitoring system for low-altitude aircraft, which adopts modular design technology and adds a 5G-A module to the existing general vibration test and acquisition system to achieve integrated testing, real-time transmission and autonomous analysis.

[0005] The second objective of this invention is to propose a real-time monitoring method for low-altitude aircraft, which enables the organic linking of real-time flight data with historical data. After real-time data processing by the service center, the evaluation results of the current action node are provided and transmitted to the cockpit integrated display via the 5G-A network to guide the pilot's flight.

[0006] In addition, this invention provides a method for proactive maintenance based on anomaly detection and analysis using post-flight data.

[0007] The technical solution of this invention: According to a first aspect of the present invention, a real-time monitoring system for low-altitude aircraft is proposed, comprising a vibration acceleration sensor (1), an integrated data acquisition and transmission unit (2), a 5G-A module (3), a flight status identification system (4), real-time diagnostic software based on big data remote experts (5), an active maintenance system based on big data (6), and a database (7). The vibration acceleration sensor (1) is used for vibration testing of moving parts such as rotors and engines (motors), and can convert vibration acceleration into electrical signals; The integrated acquisition and transmission machine (2) realizes real-time acquisition of vibration data of the whole machine and real-time transmission to the ground; The 5G-A module (3) is used to realize the transmission and reception of onboard signals; The flight status identification system (4) is used to identify the designated flight status of the aircraft; The big data-based remote expert real-time diagnostic software (5) is used for data analysis and hierarchical early warning of system faults; The big data-based proactive maintenance system (6) is used to diagnose and proactively maintain key equipment, ensuring the normal operation of the equipment while eliminating potential equipment failures in a timely manner. The database (7) is used for user data management, enabling real-time storage and management of raw data and data in different formats such as analysis and diagnostic results.

[0008] In one possible embodiment, the vibration acceleration sensor (1) includes multiple piezoelectric acceleration sensors and at least one piezoresistive acceleration sensor. The piezoelectric acceleration sensors are arranged on a structure with high stiffness, including the mounting bracket of the moving parts of the aircraft. The arrangement also includes the nose and tail of the aircraft, on a structure with high stiffness, for testing the transient acceleration response of the aircraft structure's inherent modes. Piezoresistive accelerometers are positioned near the aircraft's center of gravity and are used to measure the aircraft's overload acceleration.

[0009] In one possible embodiment, the 5G-A module (3) is mounted on the data acquisition and transmission integrated machine (2).

[0010] In one possible embodiment, the integrated acquisition and transmission unit (2) includes different types of acquisition cards, which can acquire vibration acceleration sensor data and aircraft airborne integrated processor formatted bus data. The specific card needs to be determined according to the data type of the processor bus. The integrated acquisition and transmission machine (2) includes a network output interface to transmit the acquired data in a formatted manner to the 5G-A module (3).

[0011] In one possible embodiment, the flight status identification system (3) employs an improved BP neural network model, including a multi-scale feature extraction module, a residual module, and a classification module; acquires real-time data of multiple flight parameters launched from the aircraft at the same time, preprocesses the multiple flight parameters of the helicopter to obtain a flight parameter sequence; inputs the flight parameter sequence into the helicopter flight status identification network to obtain the identification result of the helicopter flight status; wherein, the helicopter flight status identification network includes: The encoder module is used to capture long-range data features in the flight parameter sequence; A multi-scale feature extraction module is used to extract deep data features of different scales from the long-distance data features; The residual module is used to find key features of flight parameters from the deep data features at different scales; The classification module is used to identify the flight status of the aircraft based on the key features of the flight parameters, and obtain the identification result of the flight status of the aircraft.

[0012] In one possible embodiment, the flight status identification system (3) also includes a flight weight identification module. Its core principle is that the frequency of free vibration of the structure is determined by the system stiffness and mass. The stiffness of the aircraft structure remains unchanged. When the flight weight changes, the frequency of free vibration will change. This part consists of calibration test and data identification. The calibration test is conducted on the ground without the vehicle running. The test is performed to calibrate the weight and natural frequency of the aircraft structure. The aircraft is ballasted with different weights, and the dynamic characteristics of the structure are tested to establish the relationship between the weight of the aircraft and the natural frequency of the structure. Data identification involves time-frequency analysis of vibration acceleration signal data from the nose and tail of the aircraft to identify the aircraft's low-order natural frequencies, and obtaining the aircraft's weight based on calibration tests.

[0013] In one possible embodiment, the big data-based remote expert real-time diagnostic software (6) includes preprocessing, feature extraction, and fault mode classification or diagnosis: Preprocessing includes steps such as filtering (e.g., low-pass filtering, high-pass filtering), detrending, and standardization to reduce noise and interference and improve the accuracy of feature recognition. Feature extraction: Extracting information that reflects the working status of the equipment from the preprocessed vibration signal. This information can usually be divided into time domain features, including RMS, peak value, kurtosis, and skewness; frequency domain features, including peak frequency, frequency amplitude, and main frequency components; and statistical and trend features, including amplitude trend and frequency drift trend. Fault mode classification or diagnosis: Train the extracted signal features to establish a fault identification model; test the model based on newly collected data to determine whether the equipment has a specific type of fault.

[0014] In one possible embodiment, the big data-based proactive maintenance system (7) performs linear regression on time series data based on big data remote expert real-time diagnostic software analysis, calculates the trend slope and R² value, predicts the changes in the next hour, judges the severity of the trend based on the rate of change, and provides proactive maintenance measures to reduce the risk of failure.

[0015] According to a second aspect of the present invention, a method for real-time monitoring of low-altitude aircraft is provided, employing the aforementioned real-time monitoring system for low-altitude aircraft, comprising the following steps: Step 1: Vibration Signal Acquisition and Conversion Vibration acceleration sensors deployed on moving components such as rotors and engines are used to monitor vibration signals during aircraft operation in real time and convert them into corresponding electrical signals. Step 2: Real-time acquisition and transmission of vibration data The integrated acquisition and transmission unit receives electrical signals from various vibration acceleration sensors, performs signal conditioning and digital acquisition, and forms a full-scale vibration dataset. Through the 5G-A module integrated on the aircraft, the acquired vibration data is transmitted to the ground system in real time. Step 3: Flight Status Recognition The flight status identification system identifies and calibrates the specified flight status of the aircraft based on real-time received flight parameters and vibration data, providing a state context for subsequent data analysis. Step 4: Data Reception and Remote Diagnostic Analysis The ground system receives vibration data transmitted via a 5G-A network receiver and inputs it into a real-time remote expert diagnostic software based on big data. The software performs time-domain, frequency-domain, and feature analysis on the vibration data and, in conjunction with historical fault databases and expert databases, identifies and classifies system faults for early warning.

[0016] Step 5: Proactively Maintain Decision Generation Based on big data, the proactive maintenance system generates health assessment reports for key equipment according to diagnostic results and early warning levels, and outputs maintenance suggestions or fault hazard handling solutions, realizing a closed loop from early warning to maintenance decision-making.

[0017] Step Six: Data Storage and Management The database system provides unified storage and management for real-time collected raw vibration data, flight status labels, diagnostic analysis results, early warning information, and maintenance decisions. It supports real-time data import, classification archiving, and traceable querying of both structured and unstructured data.

[0018] Step 7: Maintenance Execution and Feedback Based on the maintenance recommendations output by the proactive maintenance system, corresponding inspection, repair, or component replacement operations are performed; maintenance results and subsequent operational data are fed back to the database to optimize diagnostic models and maintenance strategies.

[0019] Through the above steps, this method realizes a closed-loop monitoring and maintenance process from onboard vibration signal acquisition, real-time data transmission, flight status identification, ground intelligent diagnosis, maintenance decision generation to data management, demonstrating the system's real-time, intelligent and proactive nature in the health management of low-altitude aircraft.

[0020] Advantages and beneficial effects of the present invention: Based on 5G-A communication, this invention achieves a data transmission rate of over 100 Mbps, meeting the requirements for real-time flight communication and high bandwidth. Employing modular design technology, it integrates multiple aspects such as test acquisition and remote transmission, real-time and historical data, fault analysis, and system maintenance, enabling automatic processing, diagnosis, and alarms. This significantly improves efficiency and features intelligence, multi-system integration, miniaturization, and low cost. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. The 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.

[0022] Figure 1 System composition and interconnection diagram Figure 2 For flight status identification technology roadmap Figure 3 Overall architecture diagram of vibration data analysis software Figure 4 Examples of typical signal distributions and their kurtosis values Figure 5 The loss curve after training based on the BP neural network Figure 6 Flight status recognition test confusion matrix Figure 7 Time-domain data from vibration sensors near moving parts Figure 8 Time-domain data from vibration sensors at both ends of the fuselage structure Figure 9 Power spectrum analysis results of vibration sensors at both ends of the fuselage structure Figure 10 Data encapsulation of vibration sensors at both ends of the fuselage structure. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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, 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.

[0024] The features and illustrative embodiments of various aspects of the present invention will now be described in detail. Numerous specific details are set forth in the following detailed description to provide a thorough understanding of the invention. However, it will be apparent to those skilled in the art that the invention may be practiced without requiring 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 setups and methods set forth below, but covers any improvements, substitutions, and modifications to structures, methods, and devices without departing from the spirit of the invention. Well-known structures and techniques are not shown in the drawings and the following description to avoid unnecessarily obscuring the invention.

[0025] In the description of this invention, it should be noted that the directions or positional relationships indicated by terms such as "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer" are based on the directions or positional relationships shown in the accompanying drawings and are only for the convenience of describing and simplifying the invention, and should not be construed as limiting the invention. Furthermore, the use of ordinal numbers (e.g., "first and second," etc.) is for distinguishing objects and is not limited to this order, and should not be construed as indicating or implying relative importance.

[0026] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly, encompassing both direct connection and indirect connection via an intermediate medium. Those skilled in the art can understand the specific meaning of these terms in this invention based on the specific circumstances.

[0027] 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.

[0028] The present invention will be further described in detail below with reference to the embodiments and accompanying drawings, but the embodiments of the present invention are not limited thereto.

[0029] The implementation details are described using a conventional configuration helicopter as an example. Figure 1 As shown, this system comprises two parts: a vibration acceleration sensor, a data acquisition and transmission unit, a ground-based 5G-A module, a flight status identification system, real-time remote expert diagnostic software based on big data, a proactive maintenance system based on big data, and a database. The vibration acceleration sensor and the data acquisition and transmission unit are onboard components.

[0030] The vibration acceleration sensors include six sensors, one of which is a piezoresistive vibration acceleration sensor. The installation locations and sensor types are detailed in Table 1.

[0031] The vibration acceleration sensor acquisition and transmission integrated machine is based on the general acquisition unit UMA2160, with the addition of a general 5G-A dedicated module and a sampling rate of 1000 Hz.

[0032] The terrestrial 5G-A module and data distribution software include a 5G-A passive tag chip and data receiving platform components developed by the mobile company, and are provided by the telecommunications company.

[0033] The flight state recognition system selects the fewest flight parameters (see Table 2 for details) for identifying typical flight states of the test aircraft. Flight state = ['Ground effect hover', 'No ground effect hover', 'Level flight 120km / h', 'Level flight 160km / h', 'Level flight 200km / h', 'Level flight 240km / h', 'Climb', 'Horizontal turn', 'Glide', 'Unsteady state']. The specific technical approach for flight status recognition is detailed in [link to flight status recognition technology]. Figure 2 .

[0034] The flight status identification steps include: Step 1: Based on the signal collected during the test, there are a total of 8 parameters (see Table 2 for details). The time series data is divided into 60-second blocks. Three features (including mean, variance, and slope with respect to time) are extracted for each parameter and standardized to form a dataset.

[0035] Step 2, standardize the dataset Step 3: Construct and train the improved BP neural network; Step 4: Real-time display of training progress and results. Case recognition accuracy is 100%. See below. Figure 4 , Figure 5 and Figure 6 .

[0036] The flight status identification system further includes flight weight identification, comprising the following steps: Step 21: Use a dedicated LMS testing system to conduct dynamic characteristic tests on the entire structure and establish the relationship between the weight of the entire structure and the frequency values ​​of the first-order structural modes (see Table 3 for details). Step 22, signal preprocessing: First, extract the impact signal segment, then perform envelope analysis → Hilbert transform to obtain the envelope; Step 23: Parameter identification, curve fitting / spectral analysis; typical graphs are shown below. Figure 8 , Figure 9 , Figure 10 Based on the vertical acceleration data, the result is 5.75Hz, which can be identified as heavy.

[0037] The specific steps of the big data-based remote expert real-time diagnostic software are as follows: Step 31, press Figure 3 Perform routine time-frequency analysis on vibration data and statistical analysis of historical data based on the moving time window; Step 32: Calculate the relative deviation between the current feature value and the historical mean. Set different sensitivity thresholds for different features and configure alarms as follows: Alarm threshold value = { 'rms': 0.2,# 20% change 'peak': 0.3, # 30% change 'kurtosis': 0.4, # 40% change 'skewness': 0.4, # 40% change 'freq_peak': 0.1, # 10% change 'freq_magnitude': 0.3# 30% change } The flight status was categorized by time period, and the results of typical alarm information are shown in Table 5.

[0038] The aforementioned big data-based remote proactive maintenance system performs linear regression on the data based on big data-based remote expert real-time diagnostic software, calculates the trend slope and R² value, predicts the changes in the next hour, judges the severity of the trend based on the rate of change, and provides proactive maintenance suggestions. The implementation case results are shown in Table 6.

[0039] Table 1. Arrangement of helicopter vibration sensors

[0040] Table 2 Parameters required for BP neural network flight state recognition

[0041] Table 3. Natural frequencies of the entire aircraft under different takeoff weights (unit: Hz)

[0042] Table 4. Time-domain characteristic values ​​of some vibration acceleration sensors

[0043] Table 5. Analysis Results of Fault Alarms from Some Vibration Accelerometers

[0044] Table 6 shows some maintenance analysis results of moving parts based on vibration acceleration sensors.

[0045] The above detailed embodiments are a description of the present invention. It should not be considered that the specific embodiments of the present invention are limited to these descriptions. For those skilled in the art, several simple deductions and substitutions can be made without departing from the concept of the present invention, and all of these should be considered to fall within the protection scope of the present invention.

Claims

1. A real-time monitoring system for low-altitude aircraft, characterized in that, The system includes a vibration acceleration sensor (1), an integrated acquisition and transmission unit (2), a 5G-A module (3), a flight status identification system (4), a real-time diagnostic software based on big data remote experts (5), a proactive maintenance system based on big data (6), and a database (7). The vibration acceleration sensor (1) is used for vibration testing of moving parts such as rotors and engines (motors), and can convert vibration acceleration into electrical signals. The integrated acquisition and transmission unit (2) realizes real-time acquisition of vibration data of the entire aircraft and real-time transmission to the ground. The 5G-A module (3) is used to realize onboard signal transmission and reception. The flight status identification system (4) is used to identify the designated flight status of the aircraft. The real-time diagnostic software based on big data remote experts (5) is used for data analysis and graded early warning of system faults. The proactive maintenance system based on big data (6) can realize the diagnosis and proactive maintenance of key equipment, and ensure the normal operation of equipment while eliminating potential equipment faults in a timely manner. The database (7) is used for user data management, and realizes real-time storage and management of raw data and data in different formats such as analysis and diagnostic results.

2. The real-time monitoring system for low-altitude aircraft according to claim 1, characterized in that, The vibration acceleration sensor (1) includes multiple piezoelectric acceleration sensors and at least one piezoresistive acceleration sensor. The piezoelectric acceleration sensor is located on a structure with high rigidity, including the mounting bracket of the moving parts of the aircraft; it also includes the nose and tail of the aircraft, on a structure with high rigidity, and is used for testing the transient acceleration response of the inherent modes of the airframe structure. Piezoresistive accelerometers are positioned near the aircraft's center of gravity and are used to measure the aircraft's overload acceleration.

3. The real-time monitoring system for low-altitude aircraft according to claim 1, characterized in that, The 5G-A module (3) is installed on the data acquisition and transmission integrated machine (2).

4. The real-time monitoring system for low-altitude aircraft according to claim 1, characterized in that, The integrated acquisition and transmission unit (2) includes different types of acquisition cards, which can acquire vibration acceleration sensor data and aircraft airborne integrated processor formatted bus data; the integrated acquisition and transmission unit (2) includes a network output interface to format and transmit the acquired data to the 5G-A module (3).

5. A real-time monitoring system for low-altitude aircraft according to claim 1, characterized in that, The flight status identification system (3) adopts an improved BP neural network model, including a multi-scale feature extraction module, a residual module, and a classification module; it acquires real-time data of multiple flight parameters launched from the aircraft at the same time, preprocesses the multiple flight parameters of the helicopter to obtain a flight parameter sequence; and inputs the flight parameter sequence into the helicopter flight status identification network to obtain the identification result of the helicopter flight status; wherein, the helicopter flight status identification network includes: The encoder module is used to capture long-range data features in the flight parameter sequence; A multi-scale feature extraction module is used to extract deep data features of different scales from the long-distance data features; The residual module is used to find key features of flight parameters from the deep data features at different scales; The classification module is used to identify the flight status of the aircraft based on the key features of the flight parameters, and to obtain the identification result of the flight status of the aircraft.

6. The real-time monitoring system for low-altitude aircraft according to claim 1, characterized in that, The flight status identification system (3) also includes a flight weight identification module. The calibration test is conducted on the ground without the engine running. The calibration test of the aircraft weight and the natural frequency of the structure is completed. The aircraft is counterweighted according to different weights, and the structural dynamic characteristics test is conducted to establish the relationship between the aircraft weight and the natural frequency of the structure. Data identification involves time-frequency analysis of vibration acceleration signal data from the nose and tail of the aircraft to identify the aircraft's low-order natural frequencies, and obtaining the aircraft's weight based on calibration tests.

7. The real-time monitoring system for low-altitude aircraft according to claim 1, characterized in that, The big data-based remote expert real-time diagnostic software (6) includes preprocessing, feature extraction, and fault mode classification or diagnosis: Preprocessing includes filtering, detrending, and standardization steps to reduce noise and interference and improve the accuracy of feature recognition. Feature extraction: Extracting information that reflects the working status of the equipment from the preprocessed vibration signal. This information can usually be divided into time-domain features, including RMS, peak value, kurtosis, and skewness. Frequency domain characteristics, including peak frequency, frequency amplitude, main frequency components, and statistical and trend characteristics, including amplitude trend and frequency drift trend; Fault mode classification or diagnosis: Train the extracted signal features to establish a fault identification model; test the model based on newly collected data to determine whether the equipment has a specific type of fault.

8. A real-time monitoring system for low-altitude aircraft according to claim 1, characterized in that, The big data-based proactive maintenance system (7) performs linear regression on time series data based on big data remote expert real-time diagnostic software analysis, calculates the trend slope and R² value, predicts the changes in the next hour, judges the severity of the trend based on the rate of change, and provides proactive maintenance measures to reduce the risk of failure.

9. A method for real-time monitoring of low-altitude aircraft, characterized in that, The real-time monitoring system for low-altitude aircraft according to any one of claims 1-8 includes the following steps: S1. The vibration signals of the rotor and engine are collected by the vibration acceleration sensor and converted into electrical signals; S2. The electrical signal is collected and processed by the integrated acquisition and transmission device to form vibration data, and the vibration data is transmitted to the ground in real time through the 5G-A module; S3: The flight status identification system identifies and calibrates the specified flight status of the aircraft based on the received flight data. S4: Receive and analyze the vibration data and the specified flight status through the big data-based remote expert real-time diagnostic software, perform fault diagnosis, and generate graded early warning information; S5. Through the big data-based proactive maintenance system, proactive maintenance decisions for key equipment are generated based on the hierarchical early warning information; S6. The vibration data, the specified flight status, the graded early warning information, and the proactive maintenance decisions are stored and managed through the database.

Images