Predictive maintenance monitoring method and device for bleed air system and storage medium

Abstract

The invention relates to a predictive maintenance monitoring method and device for an air bleed system and a storage medium, the method is used for monitoring an overpressure turn-off fault of an air bleed valve of an engine, and the method comprises the steps that the performance of the air bleed valve is monitored in real time, and the performance comprises the downstream pressure of the air bleed valve of the engine and the pressure regulating time of the air bleed valve; real-time monitoring data are input into the predictive maintenance monitoring model, the predictive maintenance monitoring model takes the pressure fluctuation rate of the bleed air valve as a pressure abnormity monitoring index, different levels of alarms are triggered, and troubleshooting inspection is executed. Compared with the prior art, the method has the advantages that the abnormal work precursor of the component can be found in time, the actual work condition of the component can be observed more accurately, and the aviation material cost and the maintenance time are greatly saved by adopting technical intervention according to the performance decline trend and requirements.

Description

Technical Field

[0001] This invention relates to the field of aircraft bleed air system monitoring technology, and in particular to a predictive maintenance monitoring method, device and storage medium for bleed air systems. Background Technology

[0002] The bleed air system is a critical system that provides the necessary air supply to ensure the normal operation of other aircraft systems. It mainly includes engine bleed air, APU bleed air, and ground-based air supply. Engine bleed air, in particular, provides a stable and reliable air supply to the aircraft's air conditioning system during normal flight, ensuring the proper functioning of cabin pressurization, temperature regulation, and ventilation. It is also crucial for maintaining the safety and comfort of passengers at high altitudes. Furthermore, it provides necessary air for the normal operation of other aircraft systems, such as engine starting and wing leading-edge anti-icing. Bleed air system malfunctions account for a relatively high proportion of fleet malfunctions, frequently causing flight delays or prolonged grounding for troubleshooting. In severe cases, loss of bleed air from both engines can lead to high-altitude depressurization, resulting in the deployment of oxygen masks, emergency return to the airport, or diversionary landings—unsafe incidents that have occurred repeatedly in the history of global civil aviation.

[0003] Currently, Airbus's engine bleed air system fault alarm system works as follows: when the pressure, temperature, or related parameters of the bleed air system exceed a threshold, an ECAM warning is triggered, and the airline takes relevant measures based on the warning and fault information. Because there have been numerous unsafe incidents in the past caused by engine bleed air system failures, airlines, in order to ensure safety and increase safety margins, generally choose to directly increase the manufacturer's preset alarm thresholds to intervene early in troubleshooting and replacing parts to eliminate potential faults. This monitoring logic setting can directly obtain relevant bleed air parameters when a bleed air fault occurs and has high real-time performance. However, simply lowering the threshold to achieve early warning often leads to over-maintenance, high costs, and poor economic efficiency. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of existing air intake system monitoring technologies, such as excessive maintenance and poor economic efficiency, and to provide a predictive maintenance and monitoring method for air intake systems.

[0005] The objective of this invention can be achieved through the following technical solutions:

[0006] As a first aspect of the present invention, a predictive maintenance monitoring method for a bleed air system is provided, the method monitoring an overpressure shut-off fault of an engine bleed air valve, the steps of which include:

[0007] Real-time monitoring of the performance of the bleed air valve, including the downstream pressure of the engine bleed air valve and the pressure regulation time of the bleed air valve;

[0008] Real-time monitoring data is input into a predictive maintenance monitoring model, which uses the pressure fluctuation rate of the bleed air valve as a pressure anomaly monitoring indicator, triggers alarms of different levels, and performs troubleshooting checks.

[0009] As a preferred technical solution, the method monitors the performance of the bleed air valve in real time during the rapid increase of the engine power during aircraft takeoff.

[0010] As a preferred technical solution, the monitoring indicators set by the predictive maintenance monitoring model include abnormally high bleed air pressure and decreased pressure regulation capability of the bleed air valve.

[0011] As a preferred technical solution, the decrease in the pressure regulation capability of the bleed air valve is defined as: the number of times the peak pressure of the flight bleed air valve continuously exceeds the second pressure threshold is greater than the first set number.

[0012] As a preferred technical solution, the abnormally high bleed air pressure is defined as: the peak pressure of the bleed air valves in a second set number of flights continues to rise, and among them, the peak pressure of the bleed air valves in a third set number of flights is greater than the second pressure threshold.

[0013] As a preferred technical solution, when the two monitoring indicators of abnormally high bleed air pressure and decreased bleed air valve pressure regulation capability show the same trend and are developing in the direction of increasing and deterioration, the predictive maintenance monitoring model generates an alarm and performs troubleshooting checks.

[0014] As a preferred technical solution, the first set quantity, the second set quantity, the third set quantity, the first pressure threshold, and the second pressure threshold of the predictive maintenance monitoring model are set based on historical data.

[0015] As a preferred technical solution, the method tracks the replaced parts after appropriate technical intervention and updates and iterates the parameters of the predictive maintenance monitoring model.

[0016] As a second aspect of the present invention, a predictive maintenance monitoring device for a bleed air system is provided, comprising a memory, a processor, and a program stored in the memory, characterized in that the processor executes the program to implement the predictive maintenance monitoring method for the bleed air system as described above.

[0017] As a third aspect of the invention, a storage medium is provided having a program stored thereon, which, when executed, implements the predictive maintenance monitoring method for the bleed air system as described above.

[0018] Compared with the prior art, the present invention has the following beneficial effects:

[0019] 1) This invention can routinely monitor the performance of relevant components of the engine bleed air system by using process data of the rapid rise of engine power during aircraft takeoff. This can promptly detect early signs of abnormal component operation and take technical intervention as needed based on the performance degradation trend, which can greatly save on aircraft material costs and maintenance time.

[0020] 2) By routinely monitoring the relevant components, the actual working condition of the components can be observed more accurately, which can avoid misjudgment caused by short-term failure of components under certain extreme working conditions, avoid a large number of accidental disassembly and replacement, significantly reduce the NFF rate of aircraft parts sent for repair, save the cost of parts sent for repair, reduce the NFF rate of parts returned to the factory, and improve economic efficiency and aircraft parts availability.

[0021] 3) The predictive maintenance monitoring model has the ability to update and iterate. Compared with the current aircraft fault triggering logic, it is more flexible and has the ability to adjust the alarm logic autonomously according to the fleet operation status, which is not available to aircraft manufacturers when setting alarms. Attached Figure Description

[0022] Figure 1 This is a flowchart of the predictive maintenance and monitoring method for the air intake system of the present invention;

[0023] Figure 2 This is a comparison chart of the PRV overpressure failure rate after predictive maintenance monitoring of the bleed air system according to the present invention. Detailed Implementation

[0024] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. These embodiments are based on the technical solution of the present invention and provide detailed implementation methods and specific operating procedures. However, the scope of protection of the present invention is not limited to the following embodiments.

[0025] Example 1

[0026] This invention proposes a predictive maintenance monitoring method for bleed air systems. The predictive maintenance monitoring model can identify anomalies in engine bleed air-related components during daily operation and automatically issue alarms based on the severity of the anomaly trend, prompting engineers to take relevant measures and intervene technically in the abnormal components. This model is superior to existing fault alarm modes. Figure 1 As shown, the model establishment and operation mechanism of this method includes the following steps:

[0027] S1. Collect relevant parameters of the bleed air system (precooler outlet temperature, PRV downstream pressure, PRV upstream pressure, HPV position, PRV position, etc.), map and view the QAR parameter configuration information for each aircraft, and count the number of available flights in the fleet's historical database. Based on the mechanical principles and data relationships of the bleed air system, merge maintenance records and perform analysis.

[0028] S2. Combine the flight data decoding platform to clean the engine bleed air related parameters, extract and construct effective data features, and based on big data analysis methods, define the actual working state of the bleed air system under specific flight conditions, analyze the changing trend of abnormal data, and reflect the performance degradation of related components on the wing from the perspective of data analysis.

[0029] S3. A focused effort was made to address the numerous malfunctions and safety incidents that have occurred throughout the A330 fleet's history. Data analysis revealed that engine bleed air valve overpressure shutdown caused the most safety incidents in the A330 fleet's history, representing a significant pain point and challenge. Therefore, predictive maintenance modeling was developed to address this issue.

[0030] S4. After analyzing historical data on engine bleed air overpressure shutdown failures in the A330 fleet, it was found that the vast majority of these failures occurred during the rapid increase of engine power during takeoff. Therefore, the prediction model was established based on the characteristic parameters of this stage.

[0031] S5. The model monitors the performance of the PRV during the rapid rise of engine power by using the downstream pressure of the engine bleed air valve and the PRV pressure regulation time. It also triggers alarms of different levels (L low, M medium, H high) based on preset logic and formulates specific technical intervention plans for the alarms automatically triggered by the model.

[0032] S6. Monitor the return of replaced parts to the factory for testing and the performance of the repaired and reinstalled parts during technical intervention, and optimize and iterate the prediction model.

[0033] Regarding the engine bleed air valve overpressure shut-off fault, this embodiment uses the bleed air pressure fluctuation rate as a monitoring indicator for bleed air pressure transmission and regulation, based on data statistics of pressure peak values ​​greater than 57 PSI for a single flight.

[0034] For the selection of the maximum pressure value, after filtering out false pressure values, the data is smoothed, and the maximum pressure value of consecutive flight segments is greater than 65 PSI as a monitoring indicator. For example, if the maximum pressure value of an aircraft continuously increases within 10 flights and the pressure of 3 flights is greater than 65 PSI, we can define this as an abnormally high bleed air pressure. The number of consecutive flights with pressure values ​​greater than 57 PSI more than 8 times is used as a monitoring indicator of the decline in PRV pressure regulation capability.

[0035] In actual use, the two monitoring indicators of abnormal pressure are combined. When the trends of the two are consistent and deteriorate, an alarm is generated, and troubleshooting checks need to be performed.

[0036] 1) Using QAR data to routinely monitor the performance of engine bleed air system components can promptly detect early signs of component malfunctions. By observing performance degradation trends, technical intervention can be carried out as needed, greatly saving on aviation material costs and maintenance time.

[0037] 2) This invention can more accurately observe the actual working status of the components through routine monitoring of the relevant components, which can avoid misjudgment caused by short-term failure of components under certain extreme working conditions, avoid a large number of accidental disassembly and replacement, significantly reduce the fault-free detection rate (NFF) of aircraft parts sent for repair, save the cost of sending parts for repair, and improve economy and availability of aircraft parts.

[0038] 3) The algorithm model has the ability to update and iterate. Compared with the current aircraft fault triggering logic, it is more flexible and has the ability to adjust the alarm logic autonomously according to the fleet operation. This is something that aircraft manufacturers do not have when setting alarms.

[0039] 4) such as Figure 2 As shown, after adopting the above monitoring method, compared with the PRV overpressure failure rate in the same period of previous years, the PRV overpressure information of the A330 fleet was significantly reduced, and no unsafe events caused by this failure occurred.

[0040] Example 2

[0041] As a second aspect of the present invention, this application also provides an electronic device, comprising: one or more processors; a memory for storing one or more programs; wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the predictive maintenance monitoring method for the bleed air system described above. In addition to the processors, memory, and interfaces described above, any data processing device in the embodiments may also include other hardware depending on the actual function of the data processing device, which will not be elaborated further.

[0042] Example 3

[0043] As a third aspect of the present invention, this application also provides a computer-readable storage medium storing computer instructions thereon, which, when executed by a processor, implement the predictive maintenance monitoring method for the bleed air system described above. The computer-readable storage medium can be an internal storage unit of any data-processing device as described in any of the foregoing embodiments, such as a hard disk or memory. The computer-readable storage medium can also be an external storage device, such as a plug-in hard disk, smart media card (SMC), SD card, flash card, etc., equipped on the device. Furthermore, the computer-readable storage medium can include both internal storage units of any data-processing device and external storage devices. The computer-readable storage medium is used to store the computer program and other programs and data required by the data-processing device, and can also be used to temporarily store data that has been output or will be output.

[0044] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.

Claims

1. A predictive maintenance and monitoring method for an air intake system, characterized in that, The method monitors engine bleed air valve overpressure shut-off faults, and the steps include: Real-time monitoring of the performance of the bleed air valve, including the downstream pressure of the engine bleed air valve and the pressure regulation time of the bleed air valve; Real-time monitoring data is input into a predictive maintenance monitoring model, which triggers different alarms and performs troubleshooting checks based on the peak pressure of the bleed air valve and the pressure fluctuation rate of the bleed air valve.

2. The predictive maintenance and monitoring method for an air intake system according to claim 1, characterized in that, The method describes real-time monitoring of the bleed air valve's performance during the rapid increase in engine power during aircraft takeoff.

3. The predictive maintenance and monitoring method for an air intake system according to claim 1, characterized in that, The monitoring indicators set by the predictive maintenance monitoring model include abnormally high bleed air pressure and decreased pressure regulation capability of the bleed air valve.

4. The predictive maintenance and monitoring method for an air intake system according to claim 3, characterized in that, The decrease in the pressure regulation capability of the bleed air valve is defined as: the number of times the peak pressure of the flight bleed air valve continuously exceeds the second pressure threshold is greater than the first set number.

5. The predictive maintenance and monitoring method for an air intake system according to claim 3, characterized in that, The abnormally high bleed air pressure is defined as follows: the peak pressure of the bleed air valves in a second set number of flights continues to rise, and the peak pressure of the bleed air valves in a third set number of flights is greater than the second pressure threshold.

6. A predictive maintenance and monitoring method for an air intake system according to any one of claims 3-5, characterized in that, When the two monitoring indicators, namely, abnormally high bleed air pressure and decreased bleed air valve pressure regulation capability, show the same trend and are developing in a direction of increasing and deterioration, the predictive maintenance monitoring model generates an alarm and performs troubleshooting checks.

7. The predictive maintenance and monitoring method for an air intake system according to claim 6, characterized in that, The first set quantity, second set quantity, third set quantity, first pressure threshold, and second pressure threshold of the predictive maintenance monitoring model are set based on historical data.

8. The predictive maintenance and monitoring method for an air intake system according to claim 1, characterized in that, The method tracks the replaced components after appropriate technical intervention and updates and iterates the parameters of the predictive maintenance monitoring model.

9. A predictive maintenance monitoring device for a pneumatic air system, comprising a memory, a processor, and a program stored in the memory, characterized in that, When the processor executes the program, it implements the predictive maintenance and monitoring method for the bleed air system as described in any one of claims 1-8.

10. A storage medium having a program stored thereon, characterized in that, When the program is executed, it implements the predictive maintenance and monitoring method for the bleed air system as described in any one of claims 1-8.

Images