Method and device for monitoring fuel pressure of aviation turboshaft engine

Abstract

The invention relates to the technical field of aero-engines, and discloses an aero-turboshaft engine fuel pressure monitoring method and device, and the method comprises the steps: obtaining historical operation data of a target turboshaft engine in a normal working state after the target turboshaft engine is installed, and building a fuel pressure identity card model of the target turboshaft engine based on the historical operation data; in the working process of the target turboshaft engine, the fuel gas generator rotating speed, the engine fuel oil pressure and the atmospheric pressure of the target turboshaft engine are collected in real time and substituted into the fuel oil pressure identity card model for interpretation, and if the interpretation result is abnormal, an abnormal signal is output. According to the method, the passive and lagging modes of traditional single threshold monitoring are thoroughly changed, and early-stage, intelligent and personalized dynamic diagnosis of the health state of the aviation turboshaft engine fuel system is achieved.

Description

Technical Field

[0001] This invention relates to the field of aero-engine technology, specifically to a method and device for monitoring fuel pressure in an aero-engine turboshaft. Background Technology

[0002] The turboshaft engine equipped with a centrifugal fuel pump is the core power unit of the helicopter. The stability and normality of its fuel pressure are directly related to flight safety, and fuel pressure monitoring is a key aspect of engine health management.

[0003] Current monitoring solutions measure fuel pressure after the centrifugal fuel pump using fuel pressure sensors, using only a single low fuel pressure limit as the criterion. When the measured value falls below this limit, an anomaly is identified and action is taken. However, the fuel pressure at the centrifugal fuel pump outlet is affected by multiple factors, including the gas generator speed, fuel system piping condition, helicopter booster pump operating conditions, and atmospheric pressure. In actual operation, many faults or anomalies do not cause the fuel pressure to fall below the low limit. For example, the existing solution cannot identify situations such as abnormal fluctuations in fuel pressure sensor readings or pressure drops that do not reach the low limit due to helicopter fuel pump malfunctions at high speeds.

[0004] Such undetected potential faults can accumulate and may lead to serious malfunctions during flight, posing significant safety hazards. Summary of the Invention

[0005] This invention provides a method and apparatus for monitoring fuel pressure in aero-turboshaft engines, in order to solve the problem that existing monitoring schemes cannot accurately identify faults or anomalies where the fuel pressure is not below the minimum limit.

[0006] In a first aspect, the present invention provides a method for monitoring fuel pressure in an aero-turboshaft engine, the method comprising:

[0007] Acquire historical operating data of the target turboshaft engine under normal operating conditions after installation, and establish a fuel pressure identification model of the target turboshaft engine based on the historical operating data; During the operation of the target turboshaft engine, the gas generator speed, engine fuel pressure, and atmospheric pressure of the target turboshaft engine are collected in real time. The real-time collected data on the gas generator speed, engine fuel pressure, and atmospheric pressure are substituted into the fuel pressure identification model for analysis. If the analysis result is abnormal, an abnormal signal is output.

[0008] The aforementioned solution first establishes a fuel pressure identification model for the target turboshaft engine, constructing a dynamic benchmark reflecting the inherent correlation between fuel pressure and key operating parameters such as gas generator speed and atmospheric pressure under normal conditions. This benchmark is not a fixed value but a range that varies with engine speed, enabling timely detection and alarm of abnormal signals. Secondly, this fuel pressure identification model is built based on the historical operating data of the target turboshaft engine after installation, automatically learning and incorporating the individual characteristics of the target turboshaft engine and its fuel pipeline system. This eliminates the risk of misjudgment caused by inter-engine differences, making the monitoring standard more accurate. Furthermore, by real-time acquisition of gas generator speed, engine fuel pressure, and atmospheric pressure and performing model interpretation, continuous online monitoring and immediate feedback are achieved. Therefore, this solution completely changes the passive and lagging mode of traditional single-threshold monitoring, realizing early, intelligent, and personalized dynamic diagnosis of the health status of the fuel system of aero-turboshaft engines.

[0009] In one optional implementation, the historical operational data is obtained in the following manner: After the target turboshaft engine is assembled into the helicopter, it undergoes prescribed ground tests and multiple flight missions. While the target turboshaft engine is at idle or above, the gas generator speed, engine fuel pressure, and atmospheric pressure are continuously collected over time.

[0010] The aforementioned approach collects data by requiring high-speed ground tests and multiple, full-envelope flight missions after installation. This allows for the acquisition of operating parameters of the target engine under various typical and boundary conditions, ensuring that the established model reliably reflects the engine's entire normal operating range from idle to high power. Furthermore, by explicitly limiting the data collection to data from the target turboshaft engine at idle and above stable conditions, atypical interferences to fuel pressure caused by transient processes such as start-up and shutdown are effectively eliminated. This ensures that the modeling data originates from stable operating processes, thereby improving the accuracy and reliability of the constructed model.

[0011] In one optional implementation, establishing the fuel pressure identification model of the target turboshaft engine based on the historical operating data includes: Based on the historical operating data, an analysis model was developed to determine the correlation between the gas generator speed and the engine fuel pressure and atmospheric pressure. Based on the aforementioned correlation model, a permissible range for pressure difference with the gas generator speed as the independent variable is determined, and a fuel pressure identification model is configured; the pressure difference is the difference between the engine fuel pressure and the atmospheric pressure; the fuel pressure identification model is configured such that if the real-time pressure difference corresponding to any given gas generator speed falls within the permissible range for pressure difference, it is considered normal.

[0012] The above solution establishes a correlation between gas generator speed and pressure difference by analyzing historical data, and determines an allowable range of pressure difference with gas generator speed as the independent variable. This simplifies the judgment of the health status of the engine fuel system to checking whether the real-time pressure difference falls within the expected reasonable range at its corresponding speed, and can more sensitively capture changes in fuel supply characteristics caused by fuel pump, pipeline or accessory failures.

[0013] In one optional implementation, the step of analyzing the correlation model between the gas generator speed and the engine fuel pressure and the atmospheric pressure based on the historical operating data includes: Based on the historical operating data, the correlation model is obtained by linear fitting with the gas generator speed as the independent variable and the difference between the engine fuel pressure and the atmospheric pressure as the dependent variable.

[0014] The above scheme uses a linear fitting method, which makes the establishment of the correlation model and subsequent real-time interpretation highly efficient.

[0015] In one alternative implementation, the permissible pressure difference range is defined by an upper boundary and a lower boundary, both of which are linear functions of the gas generator rotation speed.

[0016] The above scheme clearly defines the permissible range of pressure difference as a linear band region with the gas generator speed as the variable in the mathematical model. This linear band model has high computational efficiency and requires less storage resources.

[0017] In one optional implementation, the step of substituting the real-time collected gas generator speed, engine fuel pressure, and atmospheric pressure into the fuel pressure identification model for interpretation includes: Based on the real-time collected gas generator speed, the permissible range of pressure difference corresponding to the gas generator speed is obtained from the fuel pressure identification model; Calculate the actual difference between the engine fuel pressure and the atmospheric pressure collected in real time; Determine whether the actual difference is within the permissible range of the pressure difference, and interpret the result.

[0018] The above scheme first queries the corresponding permissible range from the fuel pressure ID model based on the real-time gas generator speed, then calculates the current actual difference, and finally performs range comparison. This ensures the determinism and reliability of the judgment algorithm, reduces the risk of logical errors in the implementation process, and makes the judgment results of the entire monitoring method consistent and reliable.

[0019] In an optional implementation, if the reading result is abnormal, the method further includes: While outputting the abnormal signal, if the real-time collected engine fuel pressure is lower than the preset absolute pressure low limit threshold, a low fuel pressure alarm signal is generated and output simultaneously.

[0020] The above solution constructs a multi-layered and complementary fusion alarm strategy. When the dynamic model (i.e., the fuel pressure identification model) identifies an anomaly, an early warning is immediately triggered. If this anomaly also causes the pressure to drop below the absolute safety threshold, a more urgent low fuel pressure alarm is superimposed. This achieves coverage from early warning to emergency alarm, providing both a longer fault response time and ensuring safety redundancy in extreme situations.

[0021] In an optional implementation, if the reading result is abnormal, the method further includes: After the abnormal signal is output, if the fuel system is confirmed to be fault-free after inspection, the fuel pressure identification model is corrected based on the real-time data collected at the time of the abnormality.

[0022] When the fuel pressure ID model alarms but no fault is found after inspection, the above solution uses this data to correct the model parameters (such as the upper and lower boundaries of the allowable range of pressure difference). This allows the fuel pressure ID model to adaptively track engine performance, avoid false alarms caused by model obsolescence, and thus maintain high accuracy and reliability in long-term operation.

[0023] In a second aspect, the present invention provides a fuel pressure monitoring device for an aircraft turboshaft engine, the device comprising: The fuel pressure ID model acquisition module is used to acquire historical operating data of the target turboshaft engine under normal operating conditions after installation, and to establish a fuel pressure ID model of the target turboshaft engine based on the historical operating data. The real-time acquisition module is used to acquire the gas generator speed, engine fuel pressure and atmospheric pressure of the target turboshaft engine in real time during the operation of the target turboshaft engine. The result interpretation module is used to substitute the real-time collected gas generator speed, engine fuel pressure and atmospheric pressure into the fuel pressure identification model for interpretation. If the interpretation result is abnormal, an abnormal signal is output.

[0024] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the fuel pressure monitoring method for an aero-engine turboshaft engine described in the first aspect or any corresponding embodiment.

[0025] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute a fuel pressure monitoring method for an aero-engine turboshaft engine as described in the first aspect or any corresponding embodiment.

[0026] Fifthly, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute a fuel pressure monitoring method for an aero-engine turboshaft engine as described in the first aspect or any corresponding embodiment. Attached Figure Description

[0027] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0028] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a first flowchart of a fuel pressure monitoring method for an aircraft turboshaft engine according to an embodiment of the present invention. Figure 3 This is a second flowchart of a fuel pressure monitoring method for an aero-turboshaft engine according to an embodiment of the present invention. Figure 4 This is a third flowchart of a fuel pressure monitoring method for an aircraft turboshaft engine according to an embodiment of the present invention. Figure 5 This is a structural block diagram of a fuel pressure monitoring device for an aircraft turboshaft engine according to an embodiment of the present invention; Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0029] 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.

[0030] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0031] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0032] As an optional application scenario of this invention, such as Figure 1 As shown, this aircraft turboshaft engine fuel pressure monitoring system may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0033] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.

[0034] Fuel pressure monitoring for aircraft turboshaft engines equipped with centrifugal fuel pumps is generally achieved by measuring the fuel pressure value after the engine's centrifugal fuel pump using a fuel pressure sensor. The relevant technology usually specifies a lower limit for fuel pressure. If the measured fuel pressure value is lower than the lower limit, an anomaly is identified, and the result is reported to the helicopter, where the pilot and mechanic take appropriate action. However, if a fuel system malfunction or anomaly does not cause the engine fuel pressure value to fall below the lower limit, the relevant technology may not be able to identify it.

[0035] Specifically, the outlet fuel pressure of a centrifugal fuel pump is mainly related to the fuel system lines, the helicopter fuel pump, the centrifugal fuel pump speed, and atmospheric pressure. Blockages or leaks in the fuel system lines can cause fuel pressure to rise or fall; the boosting effect of the helicopter fuel pump on fuel pressure is generally relatively constant; the centrifugal fuel pump and the engine gas generator speed are connected via gears, so an increase in the engine gas generator speed also increases the centrifugal fuel pump speed, leading to a higher outlet fuel pressure; atmospheric pressure has a relatively small impact on the outlet fuel pressure of the centrifugal fuel pump, with higher atmospheric pressure resulting in a slight increase in outlet fuel pressure. As can be seen from the above, the outlet fuel pressure of a centrifugal fuel pump is affected by many factors, primarily the centrifugal fuel pump speed, followed by whether the fuel system lines are blocked / leaking and whether the helicopter booster pump is on, and finally atmospheric pressure. Because engine fuel pressure is affected by many factors, the relevant engine fuel pressure monitoring scheme is relatively simple. It specifies a lower limit for fuel pressure. During engine operation, if the measured engine fuel pressure value is lower than the lower limit, the fuel pressure is considered abnormal, and the result is reported to the helicopter, allowing the pilot and mechanic to take appropriate action.

[0036] As described above, some fuel system malfunctions or anomalies in related technologies cannot be identified unless the engine fuel pressure falls below the minimum fuel pressure limit. This prevents timely alerts to pilots and mechanics, posing a safety hazard. For example, a malfunctioning fuel pressure sensor may cause abnormal fluctuations in the measured value, but if the fluctuation does not fall below the minimum fuel pressure limit, it cannot be identified. At high gas generator speeds, engine fuel pressure is higher. At this time, some malfunctions, such as a helicopter fuel pump malfunction, may cause a decrease in fuel pressure, but it may still remain above the minimum fuel pressure limit, thus failing to be identified.

[0037] This invention provides a method and device for monitoring fuel pressure in an aircraft turboshaft engine. It can identify faults or anomalies where the engine fuel pressure value is not lower than the lower limit of the fuel pressure value, greatly improving the identification rate of faults or anomalies. It can detect faults or anomalies in their early stages, allowing pilots and mechanics to take timely measures and improve flight safety.

[0038] According to an embodiment of the present invention, a method for monitoring fuel pressure in an aircraft turboshaft engine is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0039] This embodiment provides a method for monitoring fuel pressure in an aero-engine turboshaft, which can be used on the aforementioned mobile terminals, such as mobile phones and tablets. Figure 2 This is a first flowchart of a fuel pressure monitoring method for an aero-turboshaft engine according to an embodiment of the present invention, as shown below. Figure 2 As shown, the process includes the following steps: Step S201: Obtain historical operating data of the target turboshaft engine under normal operating conditions after installation, and establish a fuel pressure identification model of the target turboshaft engine based on the historical operating data.

[0040] Furthermore, the goal of this embodiment is to create a dynamic fuel pressure identification model for each specific turboshaft engine. This fuel pressure identification model is not a simple static rule that the pressure should be greater than a certain value, but a mathematical relationship that indicates the reasonable changes in engine fuel pressure with core operating parameters and environmental parameters under normal operating conditions. This embodiment first needs to acquire the historical operating data of the target turboshaft engine after installation (i.e., after installation on the helicopter and completion of joint testing). This historical operating data can represent the normal performance of the engine within the entire expected operating envelope. Therefore, it is necessary to collect data by arranging ground tests covering different altitudes and speeds and multiple flight missions. The key historical operating data collected include gas generator speed (Ng), which is the speed of the engine's core rotor (the part that drives the compressor and high-pressure turbine), which directly determines the engine's output power and the speed of the centrifugal fuel pump; engine fuel pressure (Pt), which refers to the fuel pressure at the outlet of the centrifugal fuel pump; and atmospheric pressure (P0), which is the absolute pressure of the flight environment, and its changes will affect the inlet conditions of the fuel pump, thus having a certain impact on the outlet pressure. When collecting this data, it is essential to ensure that the engine is in a stable operating state (such as at idle or above) to eliminate interference from transient processes such as starting and stopping.

[0041] Subsequently, a fuel pressure identification model was established based on this historical data. The stable intrinsic relationship between engine fuel pressure (Pt), gas generator speed (Ng), and atmospheric pressure (P0) under normal conditions was analyzed and quantified. This fuel pressure identification model indicates that for any given gas generator speed (Ng) and atmospheric pressure (P0), the corresponding engine fuel pressure (Pt) should fall within a reasonable range. This range is not fixed but dynamically changes as the gas generator speed (Ng) increases. The final fuel pressure identification model is a dynamic permissible range with gas generator speed (Ng) as the primary variable. It defines the upper and lower boundaries of the legitimate fluctuations of engine fuel pressure (Pt) (or engine fuel pressure corrected for atmospheric pressure) at a specific speed, uniquely encoding its characteristics under healthy conditions.

[0042] Step S202: During the operation of the target turboshaft engine, the gas generator speed, engine fuel pressure and atmospheric pressure of the target turboshaft engine are collected in real time.

[0043] Furthermore, this embodiment requires the collection of three key parameters: gas generator speed (Ng), engine fuel pressure (Pt), and atmospheric pressure (P0). The acquisition of these data relies on corresponding sensor networks installed on the engine and aircraft, and is transmitted in real-time to the computing unit responsible for health monitoring via the onboard data bus. Gas generator speed (Ng) reflects the engine's instantaneous power status and is measured by a magnetoelectric or photoelectric speed sensor located on the engine core, outputting it as a frequency or percentage signal. Engine fuel pressure (Pt) is a health indicator directly characterizing the fuel system's supply capacity, measured by a piezoresistive or capacitive pressure sensor installed in the high-pressure fuel line. Atmospheric pressure (P0) is an external parameter describing the flight altitude environment and is provided by the aircraft's atmospheric data computer. Real-time synchronous acquisition of these three data points ensures that each interpretation is based on a complete snapshot of the current operating conditions.

[0044] Step S203: Substitute the real-time collected gas generator speed, engine fuel pressure, and atmospheric pressure into the fuel pressure identification model for judgment. If the judgment result is abnormal, an abnormal signal is output.

[0045] Furthermore, this embodiment utilizes the ID card model established in step S201 to perform online analysis and diagnosis on the real-time data obtained in step S202, ultimately making a health status judgment and outputting corresponding signals. Upon receiving the real-time data stream, the judgment logic is immediately initiated. First, based on the current gas generator speed (Ng), the system queries the pre-loaded fuel pressure ID card model to find the allowable normal fluctuation range of fuel pressure (or pressure corrected for ambient pressure) at this specific speed. This range is dynamic; as the speed increases, the range position also rises accordingly. Next, the system compares the real-time measured value with this dynamic range, calculating the relationship between the current measured pressure and the model's expected range. If the measured value falls exactly within the reasonable range expected by the model, the system determines that the current fuel system's operating characteristics conform to the engine's historical normal patterns, indicating a healthy state, and no alarm is generated. Conversely, if the measured value deviates from the reasonable range defined by the model, the system immediately determines it to be abnormal. This abnormality may occur before the absolute value of the fuel pressure falls below the minimum safety threshold. For example, at high RPMs, fuel pressure may fall significantly below its expected level due to some malfunction (such as decreased fuel pump efficiency), but the absolute value may still be higher than the uniform lower limit set for the entire flight envelope. Related technologies cannot detect this, but this embodiment can capture it through dynamic model comparison. Once an anomaly is identified, the system immediately generates and outputs an anomaly signal. This signal can be integrated into the cockpit warning system, illuminating an indicator light or generating maintenance information; it can also be relayed to the ground support system.

[0046] In summary, this invention first establishes a fuel pressure identification model for the target turboshaft engine, constructing a dynamic benchmark reflecting the inherent correlation between fuel pressure and core operating parameters such as gas generator speed and atmospheric pressure under normal conditions. This benchmark is not a fixed value but a range that varies with engine speed, enabling timely capture and alarm of abnormal signals. Secondly, this fuel pressure identification model is built based on the historical operating data of the target turboshaft engine after installation, automatically learning and incorporating the individual characteristics of the target turboshaft engine and its fuel pipeline system, eliminating the risk of misjudgment caused by inter-engine differences and making the monitoring standard more accurate. Furthermore, by real-time acquisition of gas generator speed, engine fuel pressure, and atmospheric pressure and performing model interpretation, continuous online monitoring and immediate feedback are achieved. Therefore, the above solution completely changes the passive and lagging mode of traditional single-threshold monitoring, realizing early, intelligent, and personalized dynamic diagnosis of the health status of the fuel system of aero-turboshaft engines.

[0047] This embodiment provides a method for monitoring fuel pressure in an aero-engine turboshaft, which can be used on the aforementioned mobile terminals, such as mobile phones and tablets. Figure 3This is a second flowchart of a fuel pressure monitoring method for an aero-turboshaft engine according to an embodiment of the present invention, as shown below. Figure 3 As shown, the process includes the following steps: Step S301: Obtain historical operating data of the target turboshaft engine under normal operating conditions after installation.

[0048] In one alternative implementation, the historical runtime data is obtained in the following way: After the target turboshaft engine is installed on the helicopter, it undergoes the prescribed ground tests and multiple flight missions. While the target turboshaft engine is at idle or above, the gas generator speed, engine fuel pressure, and atmospheric pressure are continuously collected over time.

[0049] Furthermore, the target turboshaft engine is an aviation turboshaft engine equipped with a centrifugal fuel pump. As the core power source of the helicopter, its fuel pressure stability directly determines flight safety. Historical operating data refers to the continuous parameter data collected during specified tests after the engine is installed in the helicopter. It is the basis for reflecting the normal operating characteristics of the engine. Idle and above states refer to the operating state of the engine at the minimum stable operating speed and higher speeds. In this state, the engine parameters are stable and can effectively avoid the interference of unstable operating conditions such as the start-up phase on the data.

[0050] In this embodiment, after the engine is initially installed, specific ground tests and multiple flight missions are conducted to collect data. Ground tests require the engine gas generator speed to be as high as possible; for example, in a multi-engine helicopter, a single-engine test can be performed to obtain data under high-power conditions. Flight tests require altitude coverage of the engine's full envelope, with climb and descent speeds as fast as possible to simulate various typical flight conditions. The core parameters for data acquisition include gas generator speed (Ng), engine fuel pressure (Pt), and atmospheric pressure (P0), and must be conducted over a continuous period when the target turboshaft engine is at idle or higher. This idle or higher state refers to the engine's stable operating state, excluding transient processes such as startup and shutdown. For helicopters equipped with multiple engines, data needs to be discarded when the target turboshaft engine is operating while other engines on the helicopter are starting up, to avoid pressure disturbances to the fuel system caused by other engine startup interfering with the purity of the engine's baseline data. The continuous data obtained in this way constitutes the sole and reliable data source for subsequently building personalized models.

[0051] Step S302: Based on the historical operating data, analyze the correlation model between the gas generator speed and the engine fuel pressure and atmospheric pressure.

[0052] In one optional implementation, step S302 includes: Based on the historical operating data, the correlation model was obtained by using the gas generator speed as the independent variable and the difference between the engine fuel pressure and the atmospheric pressure as the dependent variable, through linear fitting.

[0053] Furthermore, the correlation model is a model used to describe the mathematical correspondence between different parameters. In this embodiment, it is used to quantify the influence of gas generator speed (Ng) on ​​engine fuel pressure (Pt) (after correction for atmospheric pressure (P0)). The independent variable refers to the parameter that can change autonomously (here, the gas generator speed (Ng)), and the dependent variable refers to the parameter that changes with the independent variable (here, the difference between engine fuel pressure (Pt) and atmospheric pressure (P0)). The linear fitting aims to find a straight line that minimizes the sum of the squares of the vertical distances from all data points to this line.

[0054] In this embodiment, the gas generator speed (Ng) is used as the independent variable, and the difference between engine fuel pressure (Pt) and atmospheric pressure (P0) is used as the dependent variable. Pt-P0 is chosen as the dependent variable to eliminate the environmental impact of different flight altitudes (corresponding to different atmospheric pressures) on fuel pressure readings, allowing the analysis to focus on the performance of the fuel system itself. Next, a linear fit is performed using the least squares method on a large number of historical data points (i.e., Ng, Pt-P0). The general form of the fitted relationship is Pt-P0 = k Ng + b, where k and b are coefficients determined by the fitting. This linear relationship (correlation model) indicates the trend line of fuel pressure variation with engine speed after atmospheric pressure (P0) correction under the target turboshaft engine's healthy state, and is a mathematical abstraction of the normal operating characteristics of the engine's fuel system.

[0055] Step S303: Based on the correlation model, determine a pressure difference allowable range with the gas generator speed as the independent variable, and configure a fuel pressure identification model; the pressure difference is the difference between the engine fuel pressure and the atmospheric pressure; the fuel pressure identification model is configured such that: if the real-time pressure difference corresponding to any given gas generator speed falls within the pressure difference allowable range, it is considered normal.

[0056] In one alternative implementation, the permissible pressure difference range is defined by an upper boundary and a lower boundary, both of which are linear functions of the gas generator rotation speed.

[0057] Furthermore, the permissible pressure difference range is the allowable fluctuation range of the difference between engine fuel pressure (Pt) and atmospheric pressure (P0) when the target turboshaft engine is operating normally, under the condition that all helicopter engines are at idle or above. It is the core standard for judging whether the parameter is normal. The fuel pressure identification model is a monitoring model adapted to the individual characteristics of a single engine, which can accurately distinguish between normal fluctuations and abnormal states. The linear function is used to define the upper and lower boundaries of the permissible range, ensuring that the range can be dynamically adjusted with the gas generator speed.

[0058] This embodiment transforms the mathematical relationship in step S302 into a monitoring model that can be used for practical interpretation, namely, the fuel pressure identification model. The trend line (kNg + b) obtained by linear fitting represents the theoretical center value, but the actual data of a healthy engine will fluctuate normally around this center value. Therefore, it is necessary to determine a reasonable fluctuation range, namely the permissible range of pressure difference, based on all historical data. In this embodiment, the slope k of the trend line remains unchanged, and each historical data point is substituted into the formula b_i = (Pt - P0) - kNg to calculate a series of offset coefficients b_i. From this set of b_i values, the maximum value b_max and the minimum value b_min are found. Thus, the upper boundary of the permissible range of pressure difference is kNg + b_max, and the lower boundary is kNg + b_min. It can be seen that both the upper and lower boundaries are linear functions of the gas generator speed (Ng) and are parallel to the central trend line, jointly defining a band-shaped region that varies with the speed. The final fuel pressure identification model is defined as follows: for any given gas generator speed (Ng), if the real-time calculated pressure difference (Pt-P0) falls within the range of (kNg + b_min, kNg + b_max) (i.e., the permissible pressure difference range), then the condition is considered normal. This fuel pressure identification model essentially sets a dynamic and personalized standard for the target turboshaft engine, rather than a fixed pressure value.

[0059] Step S304: During the operation of the target turboshaft engine, the gas generator speed, engine fuel pressure, and atmospheric pressure of the target turboshaft engine are collected in real time. For details, please refer to [link to relevant documentation]. Figure 2 Step S202 of the illustrated embodiment will not be repeated here. However, the three key operating parameters collected in real time—gas generator speed (Ng), engine fuel pressure (Pt), and atmospheric pressure (P0)—specifically refer to the parameters of the target turboshaft engine itself, not the parameters of all engines on the helicopter (the same applies to historical operating data).

[0060] Step S305: Substitute the real-time collected gas generator speed, engine fuel pressure, and atmospheric pressure into the fuel pressure identification model for interpretation.

[0061] In one optional implementation, step S305 includes: Based on the real-time collected speed of the gas generator, the permissible range of pressure difference corresponding to the speed of the gas generator is obtained from the fuel pressure identification model; Calculate the actual difference between the real-time collected engine fuel pressure and the atmospheric pressure; Determine whether the actual difference is within the permissible range of the pressure difference and interpret the result.

[0062] Furthermore, in this embodiment, the real-time data collected in step S304 is compared and interpreted using the established fuel pressure identification model. First, when the target turboshaft engine is operating normally, with all helicopter engines at idle or higher, the permissible pressure difference range corresponding to the real-time gas generator speed (Ng) is retrieved from the fuel pressure identification model (i.e., the upper boundary value kNg + b_max and the lower boundary value kNg + b_min at that speed are obtained). Second, the actual pressure difference at the current moment is calculated, i.e., the real-time atmospheric pressure (P0) is subtracted from the real-time engine fuel pressure (Pt). Finally, if the calculated actual difference is within the retrieved permissible range, the interpretation result is normal; if the actual difference is higher than the upper boundary or lower than the lower boundary, the interpretation result is abnormal. This process achieves a dynamic and continuous comparison between real-time measurements and personalized health benchmarks.

[0063] Step S306: If the reading result is abnormal, while outputting the abnormal signal, if the real-time collected engine fuel pressure is lower than the preset absolute pressure low limit threshold, a fuel pressure low alarm signal is generated and output simultaneously.

[0064] Furthermore, this embodiment also enhances the alarm processing for abnormal reading results. When the reading result in step S305 is abnormal, the system outputs an abnormal signal. Based on this, this step simultaneously checks whether the absolute value of the real-time collected engine fuel pressure (Pt) is lower than a preset, fixed safety threshold (i.e., a preset absolute pressure low limit threshold). This preset absolute pressure low limit threshold is a single alarm threshold used in related monitoring methods. If both conditions are met simultaneously (i.e., the model reading is abnormal and the absolute pressure is below the low limit), the system will synchronously generate and output a higher-level fuel pressure low alarm signal. This approach balances early warning and severe fault alarm; model abnormalities provide early and sensitive fault indications, while the combination of an absolute low limit alarm provides a clear and strong warning when the fault develops to a more severe level, ensuring safety redundancy.

[0065] Step S307: If the reading result is abnormal, after the abnormal signal is output, if the fuel system is confirmed to be fault-free after inspection, the fuel pressure ID model is corrected based on the real-time data collected when the abnormality is triggered.

[0066] Furthermore, this embodiment introduces a self-learning and adaptation mechanism for the model. When an abnormal signal is output, ground maintenance personnel (or system self-check) will inspect the fuel system (such as centrifugal fuel pumps, pipelines, helicopter booster pumps, etc.) according to the manual. If a thorough inspection confirms that there is no substantial fault in the fuel system, then the abnormality may stem from a legitimate, slow change in engine performance (such as performance stabilizing after the break-in period) or a rare but normal operating condition not fully covered by the initial modeling data. In this case, the system should not continue to issue false alarms. Therefore, this step allows the real-time data (Ng, Pt, P0) collected at the time of the triggered abnormality to be used to correct the fuel pressure identification model. The core of the correction is to update the upper and lower boundary parameters (b_max or b_min) of the model. The offset b_i calculated from the new data can be compared with the original b_max or b_min, and the boundaries can be appropriately widened so that the model can accommodate this newly emerging but proven normal data feature. In this way, the fuel pressure identification model of this embodiment can be dynamically optimized as the engine is used, reducing false alarms, improving fault identification accuracy, and forming a closed loop of a health management system with learning capabilities.

[0067] In summary, please refer to Figure 4 The flowchart shown is a third method for monitoring fuel pressure in an aero-turboshaft engine. This embodiment mainly monitors fuel pressure in the aero-turboshaft engine based on parameters such as gas generator speed (Ng), engine fuel pressure (Pt), and atmospheric pressure (P0) tested by the aero-turboshaft engine's numerical control system. The main steps are as follows: 1. Ground tests and flight of the target turboshaft engine installed on a helicopter for the first time: After the target turboshaft engine is first installed on a helicopter, it will undergo one ground test and no less than three flights. The ground test requires the engine gas generator speed (Ng) to be as high as possible. For multi-engine helicopters, a single engine can be used for the ground test. The flight test requires the altitude to cover the entire envelope and the climb and descent speeds to be as fast as possible.

[0068] 2. Obtain ground test and flight data for the first helicopter installation (i.e., historical operational data): Continuous data on the gas generator speed (Ng), engine fuel pressure (Pt), and atmospheric pressure (P0) of the target turboshaft engine at idle and above, over time, are obtained through an engine data recorder or similar parameter storage device during ground tests and flights after the initial installation on the helicopter. It should be noted that for multi-engine helicopters, data from the primary engine at idle or above, but from other engines during startup, should be deleted.

[0069] 3. Establish an engine fuel pressure identification model: Plotting gas generator speed (Ng) on ​​the x-axis and the difference between engine fuel pressure (Pt) and atmospheric pressure (P0) on the y-axis, a scatter plot of all historical operating data is created. A linear fit is then performed using the least squares method to obtain the relationship between gas generator speed (Ng) and the difference between engine fuel pressure (Pt) and atmospheric pressure (P0). The above correlation model can be obtained through the following formula: ; Where k and b are fitting coefficients.

[0070] Based on the above correlation model, it can be transformed into the following optimization formula: ; Keeping the fitting coefficient k obtained from the above correlation model unchanged, substituting the gas generator speed (Ng), engine fuel pressure (Pt), and atmospheric pressure (P0) of all data rows in the historical operating data into the optimization formula, a set of coefficients b can be calculated. The maximum value of this set of coefficients b is defined as bmax, and the minimum value as bmin. Then, all data rows in Table 1 conform to the following formula (i.e., the fuel pressure identification model of the target turboshaft engine): ; It is evident that the fuel pressure identification model of this target turboshaft engine indicates that, under normal conditions when the target turboshaft engine is installed on a helicopter, with all helicopter engines at idle or above, the difference between the engine fuel pressure and atmospheric pressure should be within ( ). Within the specified range, otherwise it is abnormal.

[0071] 4. Real-time fuel pressure reading during the operation of the target turboshaft engine: During the operation of the target turboshaft engine, under the condition that all helicopter engines are at idle or above, the engine fuel pressure (Pt) and atmospheric pressure (P0) are used to determine in real time whether the requirements of the engine fuel pressure identification model are met. Specifically, the difference between the engine fuel pressure (Pt) and atmospheric pressure (P0) is considered. If the output is within the specified range, the engine fuel pressure is normal; otherwise, it is abnormal. If the output is abnormal and the engine fuel pressure is lower than the engine fuel pressure low limit, a low fuel pressure alarm will be output simultaneously.

[0072] 5. Anomaly Investigation: If the target turboshaft engine's fuel pressure output is abnormal, the centrifugal fuel pump, fuel system pipelines, helicopter booster pump, etc., should be checked according to the engine and helicopter user and maintenance manual.

[0073] 6. Anomaly Maintenance: If any abnormality is found, perform maintenance in accordance with the engine and helicopter user manual, and eliminate the abnormality by replacing parts or other means.

[0074] 7. Engine fuel pressure ID model correction: If the target turboshaft engine's fuel pressure output becomes abnormal in step 5, and the centrifugal fuel pump, fuel system pipelines, helicopter booster pump, etc., are inspected and maintained according to the engine's operation and maintenance manual, and no abnormalities are found, then the coefficient b can be recalculated based on the data from the abnormal output line according to the optimization formula, and bmax or bmin can be updated, thus correcting the target turboshaft engine's fuel pressure identification model. This embodiment can eliminate the influence of engine fuel system dispersion and can also be continuously corrected based on the working results, improving the accuracy of fault or abnormality identification.

[0075] In summary, this invention first establishes a fuel pressure identification model for the target turboshaft engine, constructing a dynamic benchmark reflecting the inherent correlation between fuel pressure and core operating parameters such as gas generator speed and atmospheric pressure under normal conditions. This benchmark is not a fixed value but a range that varies with engine speed, enabling timely capture and alarm of abnormal signals. Secondly, this fuel pressure identification model is built based on the historical operating data of the target turboshaft engine after installation, automatically learning and incorporating the individual characteristics of the target turboshaft engine and its fuel pipeline system, eliminating the risk of misjudgment caused by inter-engine differences and making the monitoring standard more accurate. Furthermore, by real-time acquisition of gas generator speed, engine fuel pressure, and atmospheric pressure and performing model interpretation, continuous online monitoring and immediate feedback are achieved. Therefore, the above solution completely changes the passive and lagging mode of traditional single-threshold monitoring, realizing early, intelligent, and personalized dynamic diagnosis of the health status of the fuel system of aero-turboshaft engines.

[0076] This embodiment also provides a fuel pressure monitoring device for an aircraft turboshaft engine, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0077] This embodiment provides a fuel pressure monitoring device for an aircraft turboshaft engine, such as... Figure 5 As shown, it includes: The fuel pressure ID model acquisition module 501 is used to acquire historical operating data of the target turboshaft engine under normal operating conditions after installation, and to establish the fuel pressure ID model of the target turboshaft engine based on the historical operating data. The real-time acquisition module 502 is used to acquire the gas generator speed, engine fuel pressure and atmospheric pressure of the target turboshaft engine in real time during the operation of the target turboshaft engine. The result interpretation module 503 is used to substitute the real-time collected gas generator speed, engine fuel pressure and atmospheric pressure into the fuel pressure identification model for interpretation. If the interpretation result is abnormal, an abnormal signal is output.

[0078] In some alternative implementations, this historical operational data is obtained in the following ways: After the target turboshaft engine is installed on the helicopter, it undergoes the prescribed ground tests and multiple flight missions. While the target turboshaft engine is at idle or above, the gas generator speed, engine fuel pressure, and atmospheric pressure are continuously collected over time.

[0079] In some alternative implementations, the fuel pressure ID model acquisition module 501 is further configured to: Based on the historical operating data, an analysis model was developed to determine the correlation between the gas generator speed and the engine fuel pressure and atmospheric pressure. Based on this correlation model, a permissible range of pressure difference with the gas generator speed as the independent variable is determined, and a fuel pressure identification model is configured; the pressure difference is the difference between the engine fuel pressure and the atmospheric pressure; the fuel pressure identification model is configured such that if the real-time pressure difference corresponding to any given gas generator speed falls within the permissible range of pressure difference, it is considered normal.

[0080] In some alternative implementations, the fuel pressure ID model acquisition module 501 is further configured to: Based on the historical operating data, an analysis model is developed to determine the correlation between the gas generator speed and the engine fuel pressure and atmospheric pressure, including: Based on the historical operating data, the correlation model was obtained by using the gas generator speed as the independent variable and the difference between the engine fuel pressure and the atmospheric pressure as the dependent variable, through linear fitting.

[0081] In some alternative implementations, the permissible pressure difference range is defined by an upper boundary and a lower boundary, both of which are linear functions of the gas generator rotation speed.

[0082] In some optional implementations, the result interpretation module 503 is further configured to: Based on the real-time collected speed of the gas generator, the permissible range of pressure difference corresponding to the speed of the gas generator is obtained from the fuel pressure identification model; Calculate the actual difference between the real-time collected engine fuel pressure and the atmospheric pressure; Determine whether the actual difference is within the permissible range of the pressure difference and interpret the result.

[0083] In some alternative embodiments, the device is also used for: If the reading result is abnormal, while outputting the abnormal signal, if the real-time collected engine fuel pressure is lower than the preset absolute pressure low limit threshold, a fuel pressure low alarm signal will be generated and output simultaneously.

[0084] In some alternative embodiments, the device is also used for: If the reading result is abnormal, after the abnormal signal is output, if the fuel system is confirmed to be fault-free after inspection, the fuel pressure ID model is corrected based on the real-time data collected at the time of the abnormality trigger.

[0085] The fuel pressure monitoring device for an aero-turboshaft engine provided in this embodiment of the invention can execute the fuel pressure monitoring method for an aero-turboshaft engine provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the various modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0086] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0087] The following is a detailed reference. Figure 6This diagram illustrates a suitable structural design for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 601, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 602 or a program loaded from memory 608 into random access memory (RAM) 603. RAM 603 also stores various programs and data required for the operation of the electronic device. The processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0088] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0089] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a memory 608, or installed from a ROM 602. When the computer program is executed by the processor 601, it performs the functions defined in the embodiment of the present invention for monitoring fuel pressure in an aero-engine turboshaft engine.

[0090] Figure 6 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0091] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, it implements the fuel pressure monitoring method for an aero-engine turboshaft engine shown in the above embodiments.

[0092] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0093] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and all such modifications and variations fall within the scope defined by the invention.

Claims

1. A method for monitoring fuel pressure in an aero-turboshaft engine, characterized in that, The method includes: Acquire historical operating data of the target turboshaft engine under normal operating conditions after installation, and establish a fuel pressure identification model of the target turboshaft engine based on the historical operating data; During the operation of the target turboshaft engine, the gas generator speed, engine fuel pressure, and atmospheric pressure of the target turboshaft engine are collected in real time. The real-time collected data on the gas generator speed, engine fuel pressure, and atmospheric pressure are substituted into the fuel pressure identification model for analysis. If the analysis result is abnormal, an abnormal signal is output.

2. The method according to claim 1, characterized in that, The historical operational data was obtained through the following methods: After the target turboshaft engine is assembled into the helicopter, it undergoes prescribed ground tests and multiple flight missions. While the target turboshaft engine is in idle or higher conditions, the gas generator speed, engine fuel pressure, and atmospheric pressure are continuously collected over time.

3. The method according to claim 1, characterized in that, The process of establishing a fuel pressure identification model for the target turboshaft engine based on the historical operating data includes: Based on the historical operating data, an analysis model was developed to determine the correlation between the gas generator speed and the engine fuel pressure and atmospheric pressure. Based on the aforementioned correlation model, a permissible range for pressure difference with the gas generator speed as the independent variable is determined, and a fuel pressure identification model is configured; the pressure difference is the difference between the engine fuel pressure and the atmospheric pressure; the fuel pressure identification model is configured such that if the real-time pressure difference corresponding to any given gas generator speed falls within the permissible range for pressure difference, it is considered normal.

4. The method according to claim 3, characterized in that, The model for analyzing the correlation between the gas generator speed and the engine fuel pressure and atmospheric pressure based on the historical operating data includes: Based on the historical operating data, the correlation model is obtained by linear fitting with the gas generator speed as the independent variable and the difference between the engine fuel pressure and the atmospheric pressure as the dependent variable.

5. The method according to claim 3, characterized in that, The permissible range of the pressure difference is composed of an upper boundary and a lower boundary, both of which are linear functions of the rotational speed of the gas generator.

6. The method according to claim 3, characterized in that, The step of substituting the real-time collected data of the gas generator speed, engine fuel pressure, and atmospheric pressure into the fuel pressure identification model for interpretation includes: Based on the real-time collected gas generator speed, the permissible range of pressure difference corresponding to the gas generator speed is obtained from the fuel pressure identification model; Calculate the actual difference between the engine fuel pressure and the atmospheric pressure collected in real time; Determine whether the actual difference is within the permissible range of the pressure difference, and interpret the result.

7. The method according to any one of claims 1 to 6, characterized in that, If the interpretation result is abnormal, the method further includes: While outputting the abnormal signal, if the real-time collected engine fuel pressure is lower than the preset absolute pressure low limit threshold, a low fuel pressure alarm signal is generated and output simultaneously.

8. The method according to any one of claims 1 to 6, characterized in that, If the interpretation result is abnormal, the method further includes: After the abnormal signal is output, if the fuel system is confirmed to be fault-free after inspection, the fuel pressure identification model is corrected based on the real-time data collected at the time of the abnormality.

9. A fuel pressure monitoring device for an aircraft turboshaft engine, characterized in that, The device includes: The fuel pressure ID model acquisition module is used to acquire historical operating data of the target turboshaft engine under normal operating conditions after installation, and to establish a fuel pressure ID model of the target turboshaft engine based on the historical operating data. The real-time acquisition module is used to acquire the gas generator speed, engine fuel pressure and atmospheric pressure of the target turboshaft engine in real time during the operation of the target turboshaft engine. The result interpretation module is used to substitute the real-time collected gas generator speed, engine fuel pressure and atmospheric pressure into the fuel pressure identification model for interpretation. If the interpretation result is abnormal, an abnormal signal is output.

10. An electronic device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform a fuel pressure monitoring method for an aircraft turboshaft engine according to any one of claims 1 to 8.

Images