An aero-engine compressor outlet pressure signal anomaly monitoring method and system

Abstract

The application belongs to the technical field of aero-engine fault diagnosis, and provides an aero-engine compressor outlet pressure signal abnormality monitoring method and system, the method comprising: constructing a monitoring model based on a fan and compressor component characteristic map; monitoring the output state of a compressor outlet pressure sensor in real time, and if there is no output or the output is out of range, it is determined that there is a hard fault and the subsequent process is terminated; when no hard fault occurs, it is determined whether the model activation condition is met, the condition including that the engine is in a stable working state, the required source input signal of the model is valid, and the engine is not in a surge state; when the activation condition is met, the model input is calculated based on real-time sensor parameters, and the monitoring model value is obtained, and the deviation is calculated in combination with the measured value; when the deviation exceeds the abnormality determination threshold, it is determined that there is a soft fault. The application can realize hierarchical identification and early warning of hard / soft faults without adding new hardware, and improve the signal reliability evaluation capability and operation safety of the engine control system.

Description

Technical Field

[0001] This invention belongs to the field of aero-engine fault diagnosis technology, and relates to a method and system for monitoring abnormal pressure signals at the compressor outlet of an aero-engine. Background Technology

[0002] In the field of aero-engine control, compressor outlet pressure is one of the key parameters characterizing the core aerodynamic state of the engine. It participates in the calculation and decision-making of control functions such as engine steady-state control, transient acceleration / deceleration logic, and surge boundary protection. Therefore, the measurement accuracy and long-term reliability of this pressure signal are crucial to ensuring optimal engine performance, stable operation, and flight safety.

[0003] Currently, the compressor outlet pressure is monitored by installing a pressure probe at the compressor outlet, drawing gas through a dedicated bleed line to a pressure sensor, and then processing the pressure signal output by the sensor via a controller. However, this measurement method presents the following risks in the actual service environment of an engine:

[0004] a. At the sensor end, there may be performance drift of the pressure-sensitive core, permanent damage to the core, or failure of the acquisition circuit. b. At the bleed end, the probe and bleed tubing may leak or be partially blocked due to foreign objects, icing, or mechanical damage.

[0005] These fault modes will all cause the value of the compressor outlet pressure signal received by the digital electronic controller to deviate from the actual physical pressure.

[0006] A systematic deviation in the compressor outlet pressure signal will directly cause the engine control logic built upon that signal to fail. Specifically, if the signal remains consistently high, the control system will calculate an excessive amount of fuel for acceleration, forcing the engine operating line to shift upwards and increasing the risk of entering the surge region. Conversely, if the signal remains consistently low, it will lead to insufficient fuel supply during deceleration, causing the operating line to shift downwards and potentially causing combustion chamber shutdown. If these situations are not identified and addressed in a timely manner, they could even cause unplanned engine shutdowns under extreme operating conditions, seriously threatening flight safety.

[0007] In addition, while existing in-machine self-test (BIT) methods can usually effectively diagnose hard faults such as sensor circuit interruptions, they are often unable to effectively and timely detect and warn of "soft" signal distortion problems caused by partial blockage of the air duct or slow air leakage. Summary of the Invention

[0008] To address the technical problem that traditional in-flight inspection (BIT) methods for detecting bleed air line blockages, leaks, and sensor drift in aero-engine compressor outlet pressure signals are difficult to use effectively, which could lead to serious safety risks such as control inaccuracies, surge, engine shutdown, or even complete shutdown, this invention discloses a method for monitoring abnormal aero-engine compressor outlet pressure signals.

[0009] Specifically, the method includes the following steps: S1. A monitoring model is constructed based on the component characteristic diagrams of the engine fan and compressor. The monitoring model calculates the monitoring model value of the compressor outlet pressure based on the real-time sensor parameters of the engine. S2. Monitor the output status of the compressor outlet pressure sensor in real time. If the sensor has no output or the output exceeds the preset physical range, determine that a hard fault has occurred and terminate the soft fault monitoring process. S3. When it is determined that no hard fault has occurred, determine whether all the model activation conditions are met during engine operation. The model activation conditions include the engine being in a stable working state, all source input signals on which the monitoring model depends being determined to be valid, and the engine not being in a surge state. S4. When all the conditions for enabling the model are met, calculate the compressor relative conversion speed, fan relative conversion speed and engine inlet total pressure based on the real-time sensor parameters, and input them into the monitoring model to obtain the monitoring model value. At the same time, collect the measured value of the compressor outlet pressure sensor and calculate the deviation between the measured value and the monitoring model value. S5. When the deviation exceeds the abnormality judgment threshold, it is determined that there is a soft fault in the compressor outlet pressure signal.

[0010] Further, in step S1, the common working line relationship is determined based on the component characteristic diagram, and the monitoring model is constructed through the common working line relationship. The monitoring model is a functional relationship Pt3_cg=f(Ncc,Nfc,Pt2) with the compressor relative conversion speed, fan relative conversion speed and engine inlet total pressure as input and the monitoring model value as output. Wherein, Ncc is the relative equivalent speed of the compressor, which is calculated from the compressor physical speed Nc and the compressor inlet total temperature Tt25; Nfc is the relative equivalent speed of the fan, which is calculated from the fan physical speed Nf and the engine inlet total temperature Tt2; Pt2 is the engine inlet total pressure; and Pt3_cg is the monitoring model value.

[0011] Furthermore, step S1 also includes revising the monitoring model, specifically including the following steps: Using test data covering the engine's operating envelope, the known compressor relative equivalent speed, fan relative equivalent speed, and engine inlet total pressure are input into the monitoring model and compared with historical measured values ​​collected under fault-free engine conditions. The mean of the deviation is then superimposed onto the monitoring model to complete parameter correction. The mean of the deviation is calculated based on the comparison results and superimposed onto the monitoring model for model parameter correction.

[0012] Furthermore, in step S3, all source input signals on which the monitoring model depends are determined to be valid, including the real-time sensor parameters and the engine inlet total pressure, which are all fault-free. The real-time sensor parameters include the compressor physical speed, the fan physical speed, the engine inlet total temperature, and the compressor inlet total temperature.

[0013] Furthermore, in step S3, the rate of change of the engine throttle lever angle is monitored in real time. When the rate of change is not greater than the steady-state judgment threshold, the engine is judged to be in a stable working state (the steady-state judgment threshold is 3° / s).

[0014] Furthermore, in step S5, the anomaly determination threshold is a fixed percentage threshold (with a value of 10%) or a dynamic threshold that is dynamically adjusted according to the current operating point of the engine.

[0015] In an improved embodiment of the above-described method for monitoring abnormal pressure signals at the outlet of an aero-engine compressor, the method further includes: S6. Based on the numerical characteristics and time evolution characteristics of the deviation, identify the type of soft fault as airway blockage, airway leakage, or sensor drift.

[0016] In an improved embodiment of the above-described method for monitoring abnormal pressure signals at the outlet of an aero-engine compressor, the method further includes: S7. When a soft fault is detected, in the engine acceleration / deceleration control logic, the fuel limit value calculated based on the measured value is disabled, and the backup control logic based on the throttle lever angle change rate limit is enabled (the throttle lever angle change rate limit value is 10° / s).

[0017] In an improved embodiment of the above-described method for monitoring abnormal pressure signals at the outlet of an aero-engine compressor, the method further includes: S8. The monitoring model is connected to a network with the single monitoring models of other independent parameters on the engine. When a soft fault is detected, the single monitoring model in the network is called for auxiliary analysis and verification to improve the confidence of fault diagnosis.

[0018] This invention also provides an abnormal monitoring system for the outlet pressure signal of an aero-engine compressor, including a model building module, a hard fault judgment module, a model startup judgment module, a signal deviation calculation module, and a soft fault judgment module.

[0019] Specifically, the model building module is used to build a monitoring model based on the component characteristic diagrams of the engine fan and compressor. The monitoring model calculates the monitoring model value of the compressor outlet pressure based on the real-time sensor parameters of the engine. The hard fault detection module is used to monitor the output status of the compressor outlet pressure sensor in real time. If the sensor has no output or the output exceeds the preset physical range, a hard fault is detected and the soft fault monitoring process is terminated. The model activation judgment module is used to determine whether all model activation conditions are met during engine operation when no hard fault has occurred. The model activation conditions include the engine being in a stable operating state, all source input signals on which the monitoring model depends being determined to be valid, and the engine not being in a surge state. The signal deviation calculation module is used to determine that when all the model activation conditions are met, it calculates the compressor relative conversion speed, fan relative conversion speed and engine inlet total pressure based on the real-time sensor parameters, and inputs them into the monitoring model to obtain the monitoring model value. At the same time, it collects the measured value of the compressor outlet pressure sensor and calculates the deviation between the measured value and the monitoring model value. The soft fault detection module is used to determine that there is a soft fault in the compressor outlet pressure signal when the deviation exceeds the anomaly detection threshold.

[0020] This invention constructs a soft fault monitoring model (Pt3_cg = f(Ncc, Nfc, Pt2)) based on the component characteristic diagrams of the engine fan and compressor, and uses existing sensor signals to predict the theoretical value of the compressor outlet pressure in real time. Simultaneously, it designs a multi-condition collaborative real-time monitoring mechanism (including initial screening of hard faults, judgment of stable operating conditions, verification of input signal validity, and confirmation of non-surge conditions), initiating deviation comparison only when the model is reliable. When the deviation between the measured value and the model prediction exceeds a threshold, it is determined as a signal anomaly, and further, based on the deviation characteristics, specific fault modes are identified (such as bleed air line blockage, leakage, or sensor drift), thereby triggering corresponding graded safety response strategies (such as control logic switching, limiting the rate of throttle change, etc.).

[0021] Compared with the prior art, the method of the present invention has at least the following technical effects: 1. It can achieve early warning and pattern differentiation of soft faults: Traditional BIT can only detect hard faults of sensors, while this invention can effectively capture the small deviations caused by abnormal air intake system or slow sensor drift through a soft measurement model based on aerodynamic characteristics, realize early identification and type discrimination of soft faults, and significantly improve fault perception capability.

[0022] 2. Introduce a multi-condition collaborative activation mechanism to avoid false alarms: By using multiple conditions such as hard fault priority judgment, stable state confirmation, input signal validity verification, and surge state elimination to coordinate the activation timing of the control model, it is ensured that deviation analysis is only performed under high confidence conditions, which significantly reduces the false alarm rate caused by transient processes or signal anomalies and improves monitoring reliability.

[0023] 3. Supports graded safety response and enhances fault-tolerant control capabilities: After detecting an anomaly, the system can automatically trigger graded safety response strategies based on the fault type (such as disabling fuel limits based on anomaly signals and enabling backup logic such as throttle change rate limits), maintaining basic engine functions while ensuring flight safety and improving the fault tolerance and robustness of the control system.

[0024] 4. This method is based entirely on the engine's existing sensors and control architecture. No additional hardware is required. High-level signal health assessment can be achieved simply by upgrading the software algorithm. It has the advantages of low implementation cost, strong engineering adaptability, and easy promotion and application on existing models.

[0025] 5. Enhance signal reliability assessment and system safety: By dynamically comparing model predictions with measured values, the system provides the control system with the ability to assess the reliability of key parameters (Pt3) in real time. This not only supports fault diagnosis but also provides a basis for subsequent control decisions, thereby comprehensively improving the engine's operational safety and intelligence level. Attached Figure Description

[0026] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a flowchart of the method for monitoring abnormal pressure signals at the outlet of an aero-engine compressor disclosed in this invention. Figure 2 To determine the next steps in the event of a soft failure; Figure 3 Execution procedure for monitoring abnormal outlet pressure signals of the compressor. Figure 4This is an architecture diagram of the aero-engine compressor outlet pressure signal anomaly monitoring system of the present invention; Figure 5 To determine the subsequent processing architecture in the event of a soft failure; Among them, 401 is the model building module; 402 is the hard fault judgment module; 403 is the model start judgment module; 404 is the signal deviation calculation module; 405 is the soft fault judgment module; 501 is the soft fault type judgment module; 502 is the fault handling module; and 503 is the joint fault judgment module. Detailed Implementation

[0028] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0029] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. This application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, in the absence of conflict, the following embodiments and features of the embodiments can be combined with each other. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0030] This invention discloses a method for monitoring abnormal pressure signals at the compressor outlet of an aero-engine. (See also...) Figure 1 and Figure 3 As shown, the method includes the following steps: S1. A monitoring model is constructed based on the component characteristic diagrams of the engine fan and compressor. The monitoring model calculates the monitoring model value of the compressor outlet pressure based on the real-time sensor parameters of the engine. S2. Monitor the output status of the compressor outlet pressure sensor in real time. If the sensor has no output or the output exceeds the preset physical range, determine that a hard fault has occurred and terminate the soft fault monitoring process. S3. When it is determined that no hard fault has occurred, determine whether all the model activation conditions are met during engine operation. The model activation conditions include the engine being in a stable working state, all source input signals on which the monitoring model depends being determined to be valid, and the engine not being in a surge state. S4. When all the conditions for enabling the model are met, calculate the compressor relative conversion speed, fan relative conversion speed and engine inlet total pressure based on the real-time sensor parameters, and input them into the monitoring model to obtain the monitoring model value. At the same time, collect the measured value of the compressor outlet pressure sensor and calculate the deviation between the measured value and the monitoring model value. S5. When the deviation exceeds the abnormality judgment threshold, it is determined that there is a soft fault in the compressor outlet pressure signal.

[0031] In some embodiments of step S1, the failure modes of the compressor outlet pressure sensor can be analyzed. Based on the structure and functional characteristics of aero-engine pressure sensors, common failure modes of compressor outlet pressure sensors include the sensor failing to output (corresponding to cable breakage or open circuit) and abnormalities in the pressure sensor's bleed air line (leaking, blockage, icing, etc.). For the failure mode of the pressure sensor failing to output, self-testing (BIT) can often be used to achieve hard fault diagnosis. However, measurement abnormalities in the pressure sensor's bleed air line are soft faults, which are difficult to detect using conventional detection algorithms. Therefore, this invention is a monitoring model designed for measurement abnormalities in the compressor outlet pressure bleed air line.

[0032] In practical implementation, when analyzing the correlation between compressor outlet pressure and other control parameters, for an engine to meet performance design requirements, all its components must be mutually matched, i.e., operating on a common operating line. Therefore, the monitoring model can determine the common operating line relationship based on the component characteristic diagram, and construct the monitoring model through the common operating line relationship. The monitoring model uses the compressor relative equivalent speed, fan relative equivalent speed, and engine inlet total pressure as inputs, and the monitoring model value as the output, which is a functional relationship Pt3_cg=f(Ncc,Nfc,Pt2); Wherein, Ncc is the relative equivalent speed of the compressor, which is calculated from the compressor physical speed Nc and the compressor inlet total temperature Tt25; Nfc is the relative equivalent speed of the fan, which is calculated from the fan physical speed Nf and the engine inlet total temperature Tt2; Pt2 is the engine inlet total pressure; and Pt3_cg is the monitoring model value.

[0033] Specifically, based on the engine compressor operating characteristic curve, the corresponding relationship between the compressor's relative equivalent speed Ncc and pressure ratio (P3 / P25) can be obtained. Similarly, the corresponding relationship between the fan's relative equivalent speed Nfc and pressure ratio (P3 / P25) can be obtained on the fan operating characteristic curve. Based on the actual arrangement of the engine's measuring points (excluding the P25 measuring point), the corresponding relationships between Nfc, Ncc, and P3 / P2 can be obtained, thus yielding the P3 monitoring model: P3_cg = f(Ncc, Nfc, P2), where P25 is the compressor inlet total pressure.

[0034] In some embodiments of step S1, step S1 further includes a process for correcting the monitoring model to improve its inclusiveness and accuracy. The model correction process specifically includes the following steps: Using test data covering the engine's operating envelope, the known compressor relative equivalent speed, fan relative equivalent speed, and engine inlet total pressure are input into the monitoring model and compared with historical measured values ​​collected under fault-free engine conditions. The mean of the deviation is then superimposed onto the monitoring model to complete parameter correction. The mean of the deviation is calculated based on the comparison results and superimposed onto the monitoring model for model parameter correction.

[0035] In addition, the modified compressor outlet pressure monitoring model can be verified and evaluated under different engine operating conditions (ground test, high-altitude test) according to engine characteristics and usage requirements to ensure that the monitoring mode meets engine characteristics and usage requirements.

[0036] In some embodiments of step S2, a hard fault can be determined first by self-test (BIT). If a hard fault occurs, there is no need to use a monitoring model to determine a soft fault. The fault information can be output directly and the soft fault monitoring process can be terminated.

[0037] In some embodiments of step S3, before using the monitoring model, it is necessary to determine whether the monitoring model can be enabled. If the model is used for soft fault monitoring when it cannot be enabled, misjudgments may occur. Therefore, it is necessary to determine whether the engine is stable. Specifically, the engine is in a stable operating state when the driven engine starts and moves to idle. During the start-up process, the real-time collected Ncc, Nfc, and Pt2 are unstable, so the monitoring model is not applicable and cannot be used for soft fault monitoring.

[0038] Whether steady state is being processed can be determined by real-time monitoring of the rate of change of the engine throttle lever angle. When the rate of change is not greater than the steady state judgment threshold, the engine is judged to be in a stable working state. For example, the steady state judgment threshold can be designed to be 3° / s.

[0039] When the system is determined to be in a steady state, it is also necessary to analyze the applicability of the monitoring model, eliminating scenarios where the monitoring model is inapplicable or ineffective. This includes assessing the validity of the data used for the assessment. Specifically, the data used for assessment includes the absence of faults in the real-time sensor parameters and the total engine inlet pressure. The real-time sensor parameters include the compressor physical speed, fan physical speed, total engine inlet temperature, and total compressor inlet temperature.

[0040] In some embodiments of step S5, the anomaly determination threshold is a fixed percentage threshold (e.g., it can be 10%) or a dynamic threshold that is dynamically adjusted according to the current operating point of the engine.

[0041] In an improved embodiment of the above-mentioned method for monitoring abnormal pressure signals at the outlet of aero-engine compressors, such as... Figure 2 As shown, the method further includes: S6. Based on the numerical characteristics and time evolution characteristics of the deviation, identify the type of soft fault as airway blockage, airway leakage, or sensor drift.

[0042] In an improved embodiment of the above-mentioned method for monitoring abnormal pressure signals at the outlet of aero-engine compressors, such as... Figure 2 As shown, the method further includes: S7. When a soft fault is detected, in the engine acceleration / deceleration control logic, the fuel limit value calculated based on the measured value is disabled, and the backup control logic based on the throttle lever angle change rate limit is enabled (the throttle lever angle change rate limit value is 10° / s).

[0043] In an improved embodiment of the above-mentioned method for monitoring abnormal pressure signals at the outlet of aero-engine compressors, such as... Figure 2 As shown, the method further includes: S8. The monitoring model is connected to a network with the single monitoring models of other independent parameters on the engine. When a soft fault is detected, the single monitoring model in the network is called for auxiliary analysis and verification to improve the confidence of fault diagnosis.

[0044] The method of this invention constructs a soft fault monitoring model (Pt3_cg = f(Ncc, Nfc, Pt2)) based on the component characteristic diagrams of the engine fan and compressor, and uses existing sensor signals to predict the theoretical value of the compressor outlet pressure in real time. Simultaneously, it designs a real-time monitoring mechanism that is activated under multiple conditions (including initial screening of hard faults, judgment of stable operating conditions, verification of the validity of input signals, and confirmation of non-surge states), initiating deviation comparison only when the model is reliable. When the deviation between the measured value and the model prediction exceeds a threshold, it is determined to be a signal anomaly, and further, based on the deviation characteristics, specific fault modes (such as bleed air line blockage, leakage, or sensor drift) are identified, thereby triggering corresponding graded safety response strategies (such as control logic switching, limiting the rate of throttle change, etc.).

[0045] Based on the same inventive concept, this invention also provides an aero-engine compressor outlet pressure signal anomaly monitoring system, as described in the following embodiments. Since the principle of the aero-engine compressor outlet pressure signal anomaly monitoring system is similar to the aero-engine compressor outlet pressure signal anomaly monitoring method disclosed in the above embodiments, the implementation of the aero-engine compressor outlet pressure signal anomaly monitoring system can refer to the implementation of the aero-engine compressor outlet pressure signal anomaly monitoring method, and repeated details will not be elaborated further. As used below, the terms "unit" or "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0046] Figure 4 This is a structural block diagram of an abnormal monitoring system for the outlet pressure signal of an aero-engine compressor disclosed in an embodiment of the present invention, as shown below. Figure 4 As shown, the system includes a model building module 401, a hard fault judgment module 402, a model startup judgment module 403, a signal deviation calculation module 404, and a soft fault judgment module 405. The structure is described below.

[0047] Specifically, the model building module 401 is used to build a monitoring model based on the component characteristic diagrams of the engine fan and compressor. The monitoring model calculates the monitoring model value of the compressor outlet pressure based on the real-time sensor parameters of the engine. The hard fault judgment module 402 is used to monitor the output status of the compressor outlet pressure sensor in real time. If the sensor has no output or the output exceeds the preset physical range, it will determine that a hard fault has occurred and terminate the soft fault monitoring process. The model startup judgment module 403 is used to determine whether all model startup conditions are met during engine operation when no hard fault has occurred. The model startup conditions include the engine being in a stable working state, all source input signals on which the monitoring model depends being determined to be valid, and the engine not being in a surge state. The signal deviation calculation module 404 is used to determine that when all the model activation conditions are met, it calculates the compressor relative conversion speed, fan relative conversion speed and engine inlet total pressure based on the real-time sensor parameters, and inputs them into the monitoring model to obtain the monitoring model value. At the same time, it collects the measured value of the compressor outlet pressure sensor and calculates the deviation between the measured value and the monitoring model value. The soft fault detection module 405 is used to determine that there is a soft fault in the compressor outlet pressure signal when the deviation exceeds the abnormality detection threshold.

[0048] In an improved embodiment of the above system, such as Figure 5This is a diagram of the subsequent processing architecture when a soft fault occurs, including a soft fault type judgment module 501, a fault processing module 502, and a fault joint judgment module 503. The structure is described below.

[0049] Specifically, the soft fault type determination module 501 is used to identify the type of soft fault as air duct blockage, air duct leakage, or sensor drift based on the numerical characteristics and time evolution characteristics of the deviation. The fault handling module 502 is used to determine when a soft fault occurs, and in the engine acceleration and deceleration control logic, disable the fuel limit value calculated based on the measured value, and enable the backup control logic based on the throttle lever angle change rate limit (the throttle lever angle change rate limit value is 10° / s). The fault joint judgment module 503 is used to form an association network between the monitoring model and the single monitoring models of other independent parameters on the engine; when a soft fault is judged to occur, the single monitoring model in the association network is called for auxiliary analysis and verification to improve the confidence of fault diagnosis.

[0050] The embodiments of the present invention achieve the following technical effects: 1. It can achieve early warning and pattern differentiation of soft faults: Traditional BIT can only detect hard faults of sensors, while this invention can effectively capture the small deviations caused by abnormal air intake system or slow sensor drift through a soft measurement model based on aerodynamic characteristics, realize early identification and type discrimination of soft faults, and significantly improve fault perception capability.

[0051] 2. Introduce a multi-condition collaborative activation mechanism to avoid false alarms: By using multiple conditions such as hard fault priority judgment, stable state confirmation, input signal validity verification, and surge state elimination to coordinate the activation timing of the control model, it is ensured that deviation analysis is only performed under high confidence conditions, which significantly reduces the false alarm rate caused by transient processes or signal anomalies and improves monitoring reliability.

[0052] 3. Supports graded safety response and enhances fault-tolerant control capabilities: After detecting an anomaly, the system can automatically trigger graded safety response strategies based on the fault type (such as disabling fuel limits based on anomaly signals and enabling backup logic such as throttle change rate limits), maintaining basic engine functions while ensuring flight safety and improving the fault tolerance and robustness of the control system.

[0053] 4. This method is based entirely on the engine's existing sensors and control architecture. No additional hardware is required. High-level signal health assessment can be achieved simply by upgrading the software algorithm. It has the advantages of low implementation cost, strong engineering adaptability, and easy promotion and application on existing models.

[0054] 5. Enhance signal reliability assessment and system safety: By dynamically comparing model predictions with measured values, the system provides the control system with the ability to assess the reliability of key parameters (Pt3) in real time. This not only supports fault diagnosis but also provides a basis for subsequent control decisions, thereby comprehensively improving the engine's operational safety and intelligence level.

[0055] In this embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements any of the above-described methods for monitoring abnormal pressure signals at the outlet of an aero-engine compressor.

[0056] Specifically, the computer device can be a computer terminal, a server, or a similar computing device.

[0057] In this embodiment, a computer-readable storage medium is provided, which stores a computer program that executes any of the above-described methods for monitoring abnormal pressure signals at the outlet of an aero-engine compressor.

[0058] Specifically, computer-readable storage media, including both permanent and non-permanent, removable and non-removable media, can store information using any method or technology. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer-readable storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable storage media does not include transient media, such as modulated data signals and carrier waves.

[0059] Obviously, those skilled in the art should understand that the modules or steps of the above-described embodiments of the present invention can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the embodiments of the present invention are not limited to any particular hardware and software combination.

[0060] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, various modifications and variations can be made to the embodiments of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for monitoring abnormal outlet pressure signals of an aero-engine compressor, characterized in that, include: A monitoring model is constructed based on the component characteristic diagrams of the engine fan and compressor. The monitoring model calculates the monitoring model value of the compressor outlet pressure based on the real-time sensor parameters of the engine. Real-time monitoring of the output status of the compressor outlet pressure sensor. If the sensor has no output or the output exceeds the preset physical range, a hard fault is determined and the soft fault monitoring process is terminated. When it is determined that no hard fault has occurred, it is determined whether all the model activation conditions are met during engine operation. The model activation conditions include the engine being in a stable operating state, all source input signals on which the monitoring model depends being determined to be valid, and the engine not being in a surge state. When all the conditions for the model to be activated are met, the relative equivalent speed of the compressor, the relative equivalent speed of the fan, and the total pressure at the engine inlet are calculated based on the real-time sensor parameters, and then input into the monitoring model to obtain the monitoring model value. At the same time, the measured value of the compressor outlet pressure sensor is collected, and the deviation between the measured value and the monitoring model value is calculated. When the deviation exceeds the anomaly detection threshold, it is determined that there is a soft fault in the compressor outlet pressure signal.

2. The method for monitoring abnormal pressure signals at the outlet of an aero-engine compressor according to claim 1, characterized in that, Based on the component characteristic diagram, the common working line relationship is determined, and the monitoring model is constructed through the common working line relationship. The monitoring model is a function relationship Pt3_cg=f(Ncc,Nfc,Pt2) with the compressor relative conversion speed, fan relative conversion speed and engine inlet total pressure as input and the monitoring model value as output. Wherein, Ncc is the relative equivalent speed of the compressor, which is calculated from the compressor physical speed Nc and the compressor inlet total temperature Tt25; Nfc is the relative equivalent speed of the fan, which is calculated from the fan physical speed Nf and the engine inlet total temperature Tt2; Pt2 is the engine inlet total pressure; and Pt3_cg is the monitoring model value.

3. The method for monitoring abnormal outlet pressure signals of an aero-engine compressor according to claim 1 or 2, characterized in that, Also includes: Using test data covering the engine's operating envelope, the known compressor relative equivalent speed, fan relative equivalent speed, and engine inlet total pressure are input into the monitoring model and compared with historical measured values ​​collected under fault-free engine conditions. The mean of the deviation is then superimposed onto the monitoring model to complete parameter correction. The mean of the deviation is calculated based on the comparison results and superimposed onto the monitoring model for model parameter correction.

4. The method for monitoring abnormal outlet pressure signals of an aero-engine compressor according to claim 1 or 2, characterized in that, All source input signals on which the monitoring model relies are deemed valid, including the absence of faults in the real-time sensor parameters and the total engine inlet pressure. The real-time sensor parameters include the compressor physical speed, fan physical speed, total engine inlet temperature, and total compressor inlet temperature.

5. The method for monitoring abnormal outlet pressure signals of aero-engine compressors according to claim 1, characterized in that, The engine throttle lever angle is monitored in real time. When the rate of change of this rate of change is not greater than the steady-state judgment threshold, the engine is judged to be in a stable working state.

6. The method for monitoring abnormal outlet pressure signals of aero-engine compressors according to claim 1, characterized in that, The anomaly detection threshold is either a fixed percentage threshold or a dynamic threshold that is dynamically adjusted based on the engine's current operating point.

7. The method for monitoring abnormal outlet pressure signals of aero-engine compressors according to claim 1, characterized in that, Also includes: Based on the numerical and temporal evolution characteristics of the deviation, the soft fault type is identified as airway blockage, airway leakage, or sensor drift.

8. The method for monitoring abnormal pressure signals at the outlet of an aero-engine compressor according to claim 1, characterized in that, Also includes: When a soft fault is detected, the fuel limit value calculated based on the measured value is disabled in the engine acceleration / deceleration control logic, and the backup control logic based on the throttle lever angle change rate limit is enabled.

9. The method for monitoring abnormal outlet pressure signals of aero-engine compressors according to claim 1, characterized in that, Also includes: The monitoring model is then linked to a network of individual monitoring models for other independent parameters on the engine. When a soft fault is detected, a single monitoring model in the associated network is invoked for auxiliary analysis and verification.

10. A system for monitoring abnormal outlet pressure signals of an aero-engine compressor, characterized in that, include: The model building module is used to build a monitoring model based on the component characteristic diagrams of the engine fan and compressor. The monitoring model calculates the monitoring model value of the compressor outlet pressure based on the real-time sensor parameters of the engine. The hard fault detection module is used to monitor the output status of the compressor outlet pressure sensor in real time. If the sensor has no output or the output exceeds the preset physical range, a hard fault is detected and the soft fault monitoring process is terminated. The model activation judgment module is used to determine whether all model activation conditions are met during engine operation when no hard fault has occurred. The model activation conditions include the engine being in a stable operating state, all source input signals on which the monitoring model depends being determined to be valid, and the engine not being in a surge state. The signal deviation calculation module is used to determine that when all the model activation conditions are met, it calculates the compressor relative conversion speed, fan relative conversion speed and engine inlet total pressure based on the real-time sensor parameters, and inputs them into the monitoring model to obtain the monitoring model value. At the same time, it collects the measured value of the compressor outlet pressure sensor and calculates the deviation between the measured value and the monitoring model value. The soft fault detection module is used to determine that there is a soft fault in the compressor outlet pressure signal when the deviation exceeds the anomaly detection threshold.

Images