A method and system for optimizing fuel consumption of an aircraft engine in operation

Abstract

This application relates to a method and system for optimizing fuel consumption during aero-engine operation. The method includes: acquiring high-frequency operating parameters of the engine during thrust adjustment; identifying engine thrust adjustment events within the high-frequency operating parameters and extracting data segments of the high-frequency operating parameters corresponding to the thrust adjustment events; extracting transient response features of the engine from the data segments, and based on the transient response features, distinguishing between the contribution of compressor fouling and the contribution of internal component wear to engine performance degradation; quantifying the additional fuel consumption caused by compressor fouling based on the compressor fouling contribution; and providing a decision recommendation on the timing of engine cleaning based on the additional fuel consumption. This invention avoids the waste of cleaning agents, water resources, manpower, and aircraft downtime, and also ensures that the engine operates under optimal performance conditions, reducing fuel consumption.

Description

Technical Field

[0001] This application relates to the field of aircraft engine operation management, and in particular to a method and system for optimizing fuel consumption during aircraft engine operation. Background Technology

[0002] As the core of an aircraft, the operating efficiency of modern aero engines directly impacts airline operating costs and flight safety. Therefore, meticulous fuel consumption management is crucial for ensuring optimal performance throughout the entire service life. During long-term use, the gradual and complex changes in the internal condition of the engine lead to a decline in fuel efficiency. Compressor blade fouling and internal component wear are the main contributing factors. While their mechanisms differ, both directly result in increased fuel consumption.

[0003] Currently, the industry's common maintenance strategy is to schedule engine cleaning based on fixed calendar dates or flight cycles. This "one-size-fits-all" approach is not economically efficient. For engines operating on relatively clean routes, cleaning may be scheduled before performance degradation is severe, resulting in a waste of cleaning agents, water resources, manpower, and aircraft downtime. Conversely, for engines operating in harsh environments, fixed cleaning cycles may be too long, causing the engines to operate with severely degraded performance for extended periods, resulting in significant fuel waste that far exceeds the cost of a pre-cleaning procedure.

[0004] To achieve refined management, the industry has attempted to assess engine health by monitoring on-orbit operational data (such as exhaust temperature, fuel flow, and engine speed). Changes in exhaust temperature margin are a commonly used indicator—as compressor efficiency declines, the combustion chamber needs to increase temperature to maintain thrust, leading to an increase in exhaust temperature. However, this method has significant limitations: the factors affecting macroscopic parameters such as exhaust temperature are diverse, including both "soft degradation" that can be reversed through cleaning (such as compressor fouling) and irreversible "hard degradation" (such as increased component clearances, seal wear, and turbine blade erosion). Monitoring systems struggle to accurately distinguish the contribution of fouling to performance degradation from hardware wear based solely on comprehensive parameters. This information ambiguity severely impacts the accuracy of maintenance decisions. Mistaking hardware wear for fouling and scheduling cleaning not only wastes resources but also masks the true fault, creating potential risks. Conversely, mistaking severe fouling for normal hardware aging misses the optimal opportunity to restore performance and save fuel through cleaning.

[0005] To address this, we propose a method and system for optimizing fuel consumption during aero-engine operation. Summary of the Invention

[0006] This application provides a method and system for optimizing fuel consumption during aircraft engine operation, which at least solves the problem in existing aircraft engine maintenance strategies that make it difficult to accurately distinguish the causes of performance degradation, leading to uneconomical cleaning timing, resource waste, or increased fuel consumption.

[0007] In a first aspect, this application provides a method for optimizing fuel consumption during aircraft engine operation, comprising the following steps:

[0008] Acquire high-frequency operating parameters of the engine during thrust adjustment;

[0009] Identify engine thrust adjustment events in the high-frequency operating parameters and extract the data segment of the high-frequency operating parameters corresponding to the thrust adjustment event;

[0010] Extract the engine transient response features from the data segment, and based on the transient response features, distinguish the contribution of compressor fouling and internal component wear in the engine performance degradation.

[0011] Based on the compressor fouling contribution, the additional fuel consumption caused by compressor fouling is quantified;

[0012] Based on the aforementioned additional fuel consumption, recommendations are provided regarding when to clean the engine.

[0013] Optionally, the step of distinguishing the contribution of compressor fouling and internal component wear in engine performance degradation based on the transient response characteristics includes:

[0014] Acquire engine operating parameters, environmental parameters, and control intent signals from within the engine control system;

[0015] Calculate the instantaneous compensation amount of the control intention signal to the engine operating parameters;

[0016] Based on the transient response characteristics, an instantaneous response curve is constructed, and the instantaneous compensation amount is removed from the instantaneous response curve to obtain the instantaneous response curve of performance degradation.

[0017] The transient response features of the performance degradation are extracted from the transient response curve, and the transient response features of the degradation are imported into a pre-built degradation mode feature library for comparison to distinguish the contribution of the compressor fouling and the contribution of the internal component wear.

[0018] Optionally, extracting the degradation transient response features from the performance degradation transient response curve includes:

[0019] The instantaneous response curve of the performance degradation is decomposed into components at different time scales.

[0020] The statistical moments of the components are calculated, and the marked statistical moments with significant differences are identified. These marked statistical moments are then used as the characteristics of the decay transient response.

[0021] Optionally, the step of importing the decay transient response features into a pre-built decay mode feature library for comparison, and distinguishing between the compressor fouling contribution and the internal component wear contribution, includes:

[0022] The transient response features of the decay are dynamically matched with the features of each decay mode in the decay mode feature library to identify the current decay mode;

[0023] Based on the dynamic matching results, the evolution rate of the current decay mode is calculated, and the decay trend of the engine in the future is predicted according to the evolution rate.

[0024] Based on the described decline trend, distinguish the decline patterns of samples with similar instantaneous characteristics but different decline rates;

[0025] Based on the aforementioned degradation trend and sample degradation patterns, the engine cleaning timing decision recommendations are dynamically optimized.

[0026] Optionally, the step of dynamically optimizing the engine cleaning timing decision recommendation based on the degradation trend and sample degradation patterns includes:

[0027] Obtain the degradation trend and sample degradation patterns of all engines in the aircraft fleet;

[0028] Obtain the operating plans for all engines in the aircraft fleet, wherein the operating plans include estimated flight hours, route arrangements and planned parking maintenance windows, and identify and eliminate cleaning opportunities that conflict with the planned parking maintenance windows;

[0029] Obtain cleaning resource information, wherein the cleaning resource information includes the number of available cleaning equipment, maintenance personnel shifts, and cleaning agent inventory;

[0030] Calculate the economic benefits for each engine at different cleaning times, whereby the economic benefits include fuel savings, cleaning costs, and downtime losses;

[0031] Based on the limitations of the cleaning resource information, and according to the economic benefits and operating plans of each engine, the cleaning timing of multiple engines is coordinated to generate a comprehensive cleaning scheduling scheme.

[0032] Optionally, based on the limitations of the cleaning resource information, and according to the economic benefits and operating plans of each engine, a comprehensive cleaning scheduling scheme is generated by coordinating the cleaning timing of multiple engines, including:

[0033] Obtain the operational flight path information and mission type for each engine;

[0034] Based on the flight route information and mission type, identify special operating scenarios that have special requirements for engine performance, and set engine performance margin thresholds for the special operating scenarios.

[0035] Using the performance margin threshold as a constraint, the economic benefits of each engine under different cleaning times are calculated.

[0036] Under the constraints of the cleaning resource information, a comprehensive cleaning scheduling scheme is generated by coordinating the cleaning timing of multiple engines based on the economic benefits of each engine, the operation plan, and the engine performance margin threshold.

[0037] Optionally, under the constraints of the cleaning resource information, the step of coordinating the cleaning timing of multiple engines based on the economic benefits of each engine, the operating plan, and the engine performance margin threshold, to generate a comprehensive cleaning scheduling scheme, includes:

[0038] Obtain information on the degradation trends, sample degradation patterns, operational plans, performance margin thresholds, and cleaning resources for all engines in the aircraft fleet;

[0039] For each engine, considering its degradation trend, degradation mode, operating plan and performance margin threshold, a dynamic priority score is calculated for different cleaning times, where the dynamic priority score reflects the urgency and potential economic benefits of cleaning.

[0040] Based on the cleaning resource information, identify the currently available cleaning capacity and time window to obtain the available cleaning resources;

[0041] Based on the dynamic priority score and the available cleaning resources, an iterative allocation strategy is adopted. Within each time window, the engine with the highest priority score is given priority for cleaning, and the remaining cleaning resources are updated.

[0042] After each allocation, the dynamic priority score of the affected engines is recalculated, and the allocation strategy for subsequent time windows is adjusted until all cleaning needs are met or resources are exhausted, generating a comprehensive cleaning scheduling scheme.

[0043] Optionally, the step of recalculating the dynamic priority score of the affected engines and adjusting the allocation strategy for subsequent time windows after each allocation includes:

[0044] After each cleaning resource allocation, identify the directly associated engines of the allocated cleaning engine, as well as the indirectly affected engines that are affected by the release or occupation of cleaning resources.

[0045] For the directly associated engine, its dynamic priority score is updated based on its state change after cleaning;

[0046] For the indirectly affected engines, based on their correlation with the allocated resources and the urgency of their operational plans, an incremental calculation method is used to locally update only the affected priority scores.

[0047] After updating the priority score, the allocation strategy for subsequent time windows is adjusted based on the latest priority score and remaining cleaning resources using a rolling optimization strategy based on time windows.

[0048] Secondly, this application provides a fuel consumption optimization system for aircraft engine operation, the system comprising:

[0049] The parameter acquisition module is used to acquire high-frequency operating parameters of the engine during the thrust adjustment process;

[0050] An event recognition module is used to identify engine thrust adjustment events in the high-frequency operating parameters and extract the data segment of the high-frequency operating parameters corresponding to the thrust adjustment event;

[0051] The contribution differentiation module is used to extract the engine transient response features in the data segment, and based on the transient response features, to differentiate the contribution of compressor fouling and internal component wear in the engine performance degradation.

[0052] The consumption quantification module is used to quantify the additional fuel consumption caused by compressor fouling based on the contribution of compressor fouling.

[0053] The decision suggestion module is used to provide a decision suggestion on when to clean the engine based on the additional fuel consumption.

[0054] Thirdly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method provided in the first aspect above.

[0055] Compared with related technologies, the fuel consumption optimization method and system for aero-engine operation provided in this application have at least the following technical advantages:

[0056] By acquiring high-frequency operating parameters of the engine during thrust adjustment and identifying thrust adjustment events, the transient response characteristics of the engine under dynamic operating conditions are captured. Subsequently, based on these transient response characteristics, the contributions of compressor fouling and internal component wear to engine performance degradation are accurately distinguished. This solves the problem in existing technologies of accurately distinguishing between "soft" degradation (cleanable fouling) and "hard" degradation (irreversible hardware wear), avoiding situations where hardware wear is misjudged as fouling and ineffective cleaning is performed, or severe fouling is mistaken for hardware aging and the optimal cleaning opportunity is missed. Finally, by quantifying the additional fuel consumption caused by compressor fouling, precise decision-making suggestions are provided for the timing of engine cleaning, achieving refined management and optimization of fuel consumption during aero-engine operation.

[0057] In summary, this application transforms the traditional "one-size-fits-all" maintenance strategy based on fixed calendar time or flight cycle number into on-demand maintenance based on the actual cause and extent of performance degradation. This not only effectively avoids the waste of cleaning agents, water resources, manpower, and aircraft downtime, but also ensures that the engine operates in optimal performance condition, reduces fuel consumption, and improves the economic benefits of airlines.

[0058] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent. Attached Figure Description

[0059] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0060] Figure 1 This is a flowchart illustrating a method for optimizing fuel consumption during aircraft engine operation, according to an exemplary embodiment.

[0061] Figure 2 This is a partial flowchart illustrating step S3 according to an exemplary embodiment.

[0062] Figure 3 This is a flowchart illustrating step S34 according to an exemplary embodiment.

[0063] Figure 4 This is a flowchart illustrating step S35 according to an exemplary embodiment.

[0064] Figure 5 This is a flowchart illustrating step S354 according to an exemplary embodiment.

[0065] Figure 6 This is a flowchart illustrating step S3545 according to an exemplary embodiment.

[0066] Figure 7 This is a flowchart illustrating step S35454 according to an exemplary embodiment.

[0067] Figure 8 This is a block diagram illustrating an aircraft engine operation fuel consumption optimization system according to an exemplary embodiment. Detailed Implementation

[0068] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0069] Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without any creative effort. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, any changes to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0070] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0071] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following objects are in an "or" relationship. The terms "first," "second," and "third" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0072] Existing optimization strategies in related technologies have significant limitations: the factors affecting macroscopic parameters such as exhaust temperature are diverse, including both "soft degradation" that can be reversed by cleaning (such as compressor fouling) and irreversible "hard degradation" (such as increased component clearances, seal wear, and turbine blade erosion). Monitoring systems struggle to accurately distinguish the contribution of fouling to performance degradation from hardware wear based solely on comprehensive parameters, and this information ambiguity severely impacts the accuracy of maintenance decisions. Mistaking hardware wear for fouling and scheduling cleaning not only wastes resources but also masks the true fault, leading to potential risks; conversely, mistaking severe fouling for normal hardware aging misses the optimal opportunity to restore performance and save fuel through cleaning.

[0073] Based on the above, embodiments of the present invention provide a method and system for optimizing fuel consumption during aero-engine operation, which will be described in detail below with reference to specific embodiments and accompanying drawings.

[0074] Example 1

[0075] This invention provides a method for optimizing fuel consumption during aircraft engine operation. Figure 1 This is a flowchart illustrating a method for optimizing fuel consumption during aircraft engine operation, according to an exemplary embodiment. Figure 1 As shown, the method consists of the following steps:

[0076] S1. Obtain high-frequency operating parameters of the engine during thrust adjustment;

[0077] In this embodiment, high-frequency operating parameters refer to various data collected at a high sampling frequency (e.g., tens or even hundreds of times per second) during engine operation, including but not limited to engine speed, fuel flow rate, exhaust temperature, compressor outlet pressure, and turbine inlet temperature. These parameters reflect the dynamic changes of the engine over a short period, especially the trends and characteristics under transient conditions such as thrust adjustment. In this embodiment, the high-frequency operating parameters are acquired by directly reading and recording these parameters through the engine's Full Authority Digital Electronic Control (FADEC) system. FADEC systems typically integrate various sensors, enabling real-time monitoring of key operating data such as engine speed, temperature, pressure, and fuel flow rate, and storing them at a high sampling rate.

[0078] S2. Identify engine thrust adjustment events in high-frequency operating parameters and extract the data segment of the high-frequency operating parameters corresponding to the thrust adjustment event;

[0079] In this embodiment, a thrust adjustment event refers to an operating condition during engine operation where the engine thrust changes significantly due to flight mission requirements (such as takeoff, climb, cruise, descent, and landing) or pilot operation. Examples include rapidly accelerating from idle to takeoff thrust, or decreasing from cruise thrust to descent thrust. Engine thrust adjustment events are typically accompanied by rapid changes in the engine's internal operating point and operating parameters. This embodiment of the application uses a threshold-based method for identifying engine thrust adjustment events. For example, when the engine's fuel flow rate or thrust command changes beyond a preset threshold within a short period, it can be identified as a thrust adjustment event. Once a thrust adjustment event is identified, the data segment corresponding to the event can be extracted from a continuous high-frequency operating parameter stream based on the time of the event. For example, data from several seconds before the event to several seconds after the event can be extracted to fully capture the transient response process of the engine transitioning from one stable state to another.

[0080] S3. Extract the engine transient response features from the data segment, and based on the transient response features, distinguish the contribution of compressor fouling and internal component wear in the engine performance degradation.

[0081] In this embodiment, transient response characteristics refer to the dynamic characteristics of the engine's high-frequency operating parameters changing over time when a thrust adjustment event occurs. These transient response characteristics include the rate of parameter change, overshoot, settling time, and oscillation mode. Different performance degradation modes (such as compressor fouling or internal component wear) will cause the engine to exhibit different characteristics in its transient response. When extracting the engine's transient response characteristics from the data segment, time-domain or frequency-domain analysis is performed on the extracted data segment. For example, the maximum rate of change of each parameter during the thrust adjustment process, overshoot, and time required to reach stability can be calculated as time-domain characteristics. Fourier transform is then performed on the data to analyze its spectral characteristics, and the energy or amplitude of specific frequency components is extracted as frequency-domain characteristics. Combining time-domain and frequency-domain characteristics reflects the working state and performance of the engine's internal components under dynamic operating conditions.

[0082] Compressor fouling refers to the degree to which the aerodynamic performance of compressor blades deteriorates due to the accumulation of contaminants (such as dust, salt, and oil), thereby affecting the overall performance of the engine. Fouling reduces compressor efficiency and flow rate, leading to increased fuel consumption, but it can usually be restored through cleaning.

[0083] Internal component wear contribution refers to the degree of performance degradation caused by irreversible damage such as wear, corrosion, and fatigue to internal engine components (e.g., bearings, gears, seals, turbine blades, etc.) during long-term operation. Internal component wear usually cannot be restored by cleaning and requires replacement or repair of the components.

[0084] S4. Quantify the additional fuel consumption caused by compressor fouling based on the contribution of compressor fouling.

[0085] In this embodiment, additional fuel consumption refers to the extra amount of fuel consumed compared to a healthy state in order to maintain the same thrust or complete the same flight mission under conditions of engine performance degradation (especially compressor fouling). When quantifying the additional fuel consumption caused by compressor fouling, a performance model can be used for calculation based on the contribution of compressor fouling. For example, an engine performance simulation model can be established that can predict the engine's fuel consumption under different operating conditions based on the degree of compressor fouling (e.g., the percentage decrease in compressor efficiency). By inputting the currently identified compressor fouling contribution into this model, the additional fuel consumption caused by fouling can be calculated.

[0086] S5. Provides engine cleaning timing recommendations based on additional fuel consumption;

[0087] In this embodiment, an economic threshold is set. When the predicted additional fuel consumption exceeds a preset economic threshold, the system can suggest cleaning. This threshold can be determined comprehensively based on factors such as fuel prices, cleaning costs, and downtime losses. More complex optimization algorithms can also be used, for example, considering factors such as future flight plans, available cleaning resources, and the expected performance recovery effect of cleaning, to construct a multi-objective optimization model to determine the optimal cleaning timing, thereby maximizing economic benefits or minimizing total operating costs.

[0088] The technical solution described above, by analyzing the high-frequency operating parameters and transient response characteristics of the engine during thrust adjustment, can accurately distinguish the contributions of compressor fouling and internal component wear. This analysis method based on transient response characteristics can capture more subtle and fundamental performance changes of the engine under dynamic operating conditions, thereby overcoming the limitations of traditional methods in differentiating the causes of performance degradation. This application avoids misjudging performance degradation caused by hardware wear as fouling and performing ineffective cleaning, and also avoids mistaking severe fouling problems for normal aging and missing the optimal cleaning opportunity.

[0089] In one possible design, Figure 2 This is a partial flowchart illustrating step S3 according to an exemplary embodiment. (Refer to the attached diagram.) Figure 2 In step S3, based on transient response characteristics, the contribution of compressor fouling and internal component wear to the engine performance degradation is distinguished, including:

[0090] S31. Acquire engine operating parameters, environmental parameters, and control intent signals from within the engine control system;

[0091] In this embodiment, to distinguish between the contribution of compressor fouling and the contribution of internal component wear in engine performance degradation, it is first necessary to obtain engine operating parameters, environmental parameters, and control intent signals from within the engine control system. Engine operating parameters may include, but are not limited to, engine speed, temperature, pressure, and fuel flow rate; environmental parameters include atmospheric pressure and ambient temperature; control intent signals refer to the internal control commands issued by the engine control system (such as FADEC) based on pilot instructions or automatic flight system instructions to achieve specific thrust or speed targets, such as fuel flow rate commands and adjustable blade angle commands. These signals reflect the control system's expectations and adjustment strategies for engine performance.

[0092] S32. Calculate the instantaneous compensation amount of the control intention signal to the engine operating parameters;

[0093] In this embodiment, instantaneous compensation refers to the immediate correction or offsetting effect of the control system on the transient response of the engine during the engine thrust adjustment process, achieved by adjusting fuel flow, adjustable geometry, etc., to maintain or achieve a preset performance target. For example, when engine performance slightly decreases due to fouling, the control system may instantaneously increase fuel flow to maintain thrust; this increased fuel flow is an instantaneous compensation.

[0094] S33. Construct an instantaneous response curve based on the transient response characteristics, and remove the instantaneous compensation amount from the instantaneous response curve to obtain the instantaneous response curve of performance degradation;

[0095] In this embodiment, the instantaneous response curve can be used as the trajectory of the engine's operating parameters (such as speed, exhaust temperature, etc.) changing over time when a thrust adjustment event occurs. By subtracting or correcting the instantaneous compensation amount generated by the control intention signal from the instantaneous response curve, the transient response change caused purely by the degradation of engine physical performance can be isolated, thereby obtaining a performance degradation instantaneous response curve that more realistically reflects the engine performance degradation status.

[0096] S34. Extract the transient response characteristics of performance degradation from the transient response curve of performance degradation;

[0097] In this embodiment, the transient response characteristics of the degradation are manifested as the shape parameters, peak value, response time, damping ratio, frequency characteristics, etc. of the curve, which can quantify and characterize the unique transient behavior of the engine under performance degradation.

[0098] S35. Import the decay transient response characteristics into a pre-built decay mode feature library for comparison, and distinguish the contributions of compressor fouling and internal component wear.

[0099] In this embodiment, the degradation mode feature library stores different types of engine performance degradation modes (such as compressor fouling, internal component wear, etc.) and their corresponding degradation transient response features. By comparing the currently extracted degradation transient response features with known patterns in the library (e.g., using pattern recognition, machine learning algorithms, etc.), the main causes of the current engine performance decline and their respective contributions can be identified.

[0100] The technical solution of the above embodiments, by incorporating consideration of the control intent signals within the engine control system and calculating their instantaneous compensation to engine operating parameters, can more accurately isolate transient responses purely caused by engine physical performance degradation. Subsequently, by removing the instantaneous compensation, the resulting performance degradation transient response curve more realistically reflects changes in the engine's internal physical state, making the degradation transient response features extracted from this curve more representative. Furthermore, comparing these more accurate degradation transient response features with a pre-built degradation mode feature library can effectively avoid control system interference, thereby making the distinction between compressor fouling contributions and internal component wear contributions more accurate, avoiding misjudgments, and ensuring a more reliable diagnosis of the causes of engine performance degradation.

[0101] In one example, suppose an aircraft engine adjusts its thrust from cruise thrust to climb thrust during a flight. During this thrust adjustment event, the parameter acquisition module acquires high-frequency operating parameters of the engine, such as N1 speed, EGT exhaust temperature, and fuel flow rate. Simultaneously, the system also acquires environmental parameters (such as atmospheric pressure and ambient temperature) and control intent signals from within the engine control system (FADEC), such as fuel flow commands and adjustable blade angle commands.

[0102] After identifying the thrust adjustment event, the corresponding data segment is extracted. First, based on the FADEC's control intent signal, the instantaneous adjustments made by the FADEC to fuel flow, adjustable geometry, etc., to maintain the target thrust or engine speed during the thrust adjustment process are calculated; this is the instantaneous compensation amount. For example, if the FADEC detects a slight decrease in engine performance, it may increase the fuel flow by an additional 5% during the transient response to compensate for the thrust loss; this 5% increase in fuel flow is the instantaneous compensation amount.

[0103] Subsequently, an instantaneous response curve is constructed based on the original transient response characteristics (such as the response curve for N1 speed). Then, the instantaneous compensation amount calculated above is subtracted or corrected from this original curve. For example, if the original N1 response curve appears "better" at a certain moment due to FADEC compensation, removing the compensation amount will allow the N1 response curve to more accurately reflect the degradation of engine physical performance. This results in an instantaneous response curve for performance degradation.

[0104] Next, a series of transient response features are extracted from the performance degradation transient response curve, such as rise time, overshoot, settling time, and damping characteristics. These features are then imported into a pre-built degradation pattern feature library for comparison. This library stores a large amount of historical data, including typical transient response features of the engine during thrust adjustment under known compressor fouling and internal component wear modes. Using machine learning algorithms (such as support vector machines, neural networks, or decision trees), the currently extracted transient response features are matched with patterns in the library to accurately distinguish what percentage of the current engine performance degradation is due to compressor fouling and what percentage is due to internal component wear. For example, the comparison results might show that 70% of the current performance degradation is attributed to compressor fouling and 30% to internal component wear.

[0105] In one possible design, Figure 3 This is a flowchart illustrating step S34 according to an exemplary embodiment. (Refer to the attached document.) Figure 3 Step S34 includes:

[0106] S341. Multi-scale decomposition of the instantaneous response curve of performance degradation to obtain components at different time scales;

[0107] In this embodiment, signal processing techniques such as wavelet transform, empirical mode decomposition (EMD), or variational mode decomposition (VMD) are used to decompose the original transient response curve of performance degradation into multiple components that reflect the characteristics of engine performance degradation at different time scales. These multiple components represent the variation patterns of the transient response at different frequencies or time resolutions. For example, high-frequency components may reflect rapid transient response changes, while low-frequency components may reflect slow, trend-based degradation.

[0108] S342. Calculate the statistical moments of the components and identify the marked statistical moments with significant differences, and use the marked statistical moments as features of the decay transient response;

[0109] In this embodiment, statistical characteristics such as mean, variance, skewness, and kurtosis are calculated for each time-scale component obtained through multi-scale decomposition. These statistical moments can quantify the distribution characteristics and fluctuation patterns of each component. By analyzing these statistical moments, those statistical moments that show significant changes during engine performance degradation can be identified, namely labeled statistical moments. Labeled statistical moments can capture the transient response characteristics unique to different degradation modes such as compressor fouling or internal component wear, and thus serve as degradation transient response characteristics for subsequent degradation mode identification and contribution differentiation.

[0110] The technical solution described above decomposes the transient response curve of performance degradation into simple components with physical meaning at different time scales by performing multi-scale decomposition. This makes different degradation modes (such as compressor fouling and internal component wear) exhibit clearer and more distinguishable characteristics at specific time scales. For example, compressor fouling may primarily affect transient response characteristics within certain frequency ranges, while internal component wear may have a more significant impact in other frequency ranges.

[0111] Based on this, the distribution characteristics and fluctuation patterns of these components at each time scale are quantitatively described by calculating the statistical moments of these components. Statistical moments, especially higher-order statistical moments (such as skewness and kurtosis), are highly sensitive to the non-Gaussian and nonlinear characteristics of the signal, and can more precisely capture the shape changes of the transient response curves caused by different degradation modes. By identifying the marked statistical moments with significant differences—that is, those statistics that show obvious changes during engine performance degradation—the most critical and sensitive feature information for distinguishing the contributions of compressor fouling and internal component wear can be extracted. Using the marked statistical moments as transient response features of degradation provides a more discriminative input for subsequent degradation mode comparison, and can more accurately identify and quantify the respective contributions of compressor fouling and internal component wear to engine performance degradation.

[0112] In one possible design, Figure 4 This is a flowchart illustrating step S35 according to an exemplary embodiment. (Refer to the attached diagram.) Figure 4 Step S35 includes:

[0113] S351. Dynamically match the transient response features of the decay with the features of each decay mode in the decay mode feature library to identify the current decay mode;

[0114] In this embodiment, time series analysis, pattern recognition algorithms (such as Dynamic Time Warping (DTW), Hidden Markov Models (HMM), or machine learning models are used to continuously or periodically compare the currently extracted transient response features of degradation with the features of various known degradation patterns stored in the feature library. This allows for a more accurate capture of the real-time state and pattern of current engine performance degradation, rather than simply performing static feature point comparisons.

[0115] S352. Based on the dynamic matching results, calculate the evolution rate of the current decay mode, and predict the engine decay trend in the future based on the evolution rate.

[0116] In this embodiment, the rate of change of the current degradation pattern over time, i.e., the evolution rate, is quantified by analyzing the dynamic matching results at continuous time points. For example, the rate of change of matching degree and the drift rate of characteristic parameters can be calculated, thus providing a quantitative basis for subsequent prediction of engine degradation trends. Subsequently, historical data and prediction models (such as regression analysis, time series prediction models ARIMA, LSTM, etc.) are used, combined with the evolution rate of the current degradation pattern, to infer the possible direction and magnitude of engine performance changes in a specific future time period, thereby achieving early warning and management of engine performance degradation.

[0117] S353. Based on the decline trend, distinguish the decline patterns of samples with similar instantaneous characteristics but different decline rates;

[0118] In this embodiment, within the decay pattern feature library, multiple decay patterns may exhibit similar characteristics at a given moment, but their long-term evolution rates may differ significantly. By combining the predicted decay trend, these patterns can be distinguished more accurately. For example, it can differentiate between rapid scaling and slow wear, which initially show similar characteristics but develop at different rates, thereby improving the precision and accuracy of decay pattern recognition.

[0119] S354. Based on the degradation trend and sample degradation pattern, dynamically optimize the decision-making recommendations for engine cleaning timing;

[0120] In this embodiment, the recommended cleaning timing is adjusted or updated in real time, taking into account both the future degradation trend of engine performance and the identified precise degradation patterns (including their evolution rate). For example, for engines predicted to degrade rapidly, the cleaning timing may be brought forward; for engines with slow degradation, the cleaning timing may be appropriately delayed to maximize economic benefits.

[0121] The technical solutions described above can more accurately and precisely identify and differentiate the contributions of compressor fouling and internal component wear to engine performance degradation. Compared to methods that only perform static feature comparison, this solution, through dynamic matching and trend prediction, can capture the dynamic evolution of degradation patterns, thereby improving the accuracy and foresight of degradation pattern identification. This avoids inappropriate cleaning timing due to inaccurate assessment of degradation patterns, reduces unnecessary fuel consumption, and extends the service life of engine components. Furthermore, dynamically optimized cleaning timing recommendations make maintenance plans more adaptable, helping airline operators maximize economic benefits and reduce operating costs while ensuring operational safety.

[0122] In one example, suppose an aircraft engine is continuously acquiring its instantaneous performance degradation response characteristics during operation. The system first dynamically matches these characteristics with known patterns in a degradation pattern feature library. For instance, within a certain time period, the system identifies that the engine's degradation pattern highly matches the "initial compressor slight fouling" pattern, and through calculation, it finds that its evolution rate shows an accelerating trend.

[0123] Based on this accelerating trend, the system predicts that compressor fouling will reach a critical point requiring cleaning within the next 50 flight hours. Simultaneously, through analysis, the system distinguishes this fouling pattern from another "early minor wear" pattern, although they share similar instantaneous characteristics, their degradation rates are significantly different. Based on this information, the system dynamically advances the engine cleaning recommendation from the originally planned 100 flight hours to 45 flight hours to avoid a significant increase in fuel consumption due to escalating fouling.

[0124] This decision recommendation was then provided to the maintenance management department for appropriate scheduling arrangements.

[0125] In one possible design, Figure 5 This is a flowchart illustrating step S354 according to an exemplary embodiment. (Refer to the attached document.) Figure 5 Step S354 includes:

[0126] S3541. Obtain the decay trend and sample decay patterns of all engines in the aircraft fleet;

[0127] In this embodiment, the degradation trend reflects the predicted trend of engine performance changes over time, while the sample degradation pattern is used to identify the specific type and cause of the current engine performance decline, such as the contribution of compressor fouling and the contribution of internal component wear.

[0128] S3542. Obtain the operating plans for all engines in the aircraft fleet, including the estimated flight hours, route arrangements and planned maintenance windows, and identify and eliminate cleaning opportunities that conflict with the planned maintenance windows.

[0129] In this embodiment, based on this, cleaning opportunities that conflict with planned downtime maintenance windows are identified and eliminated to avoid conflicts between cleaning activities and scheduled major maintenance work, thus ensuring smooth operation.

[0130] S3543. Obtain cleaning resource information, including the number of available cleaning equipment, maintenance personnel shifts, and cleaning agent inventory.

[0131] In this embodiment, cleaning resource information is a necessary condition for engine cleaning, and its availability directly affects the selection of cleaning timing and the formulation of scheduling plans.

[0132] S3544. Calculate the economic benefits for each engine under different cleaning times, including fuel savings, cleaning costs, and downtime losses.

[0133] In this embodiment, economic benefit is a comprehensive indicator, which includes fuel savings resulting from cleaning, the cost of the cleaning operation itself, and potential losses caused by engine downtime for cleaning. Quantifying these factors can provide an economic basis for decision-making.

[0134] S3545. Based on the constraints of cleaning resource information, and according to the economic benefits and operation plans of each engine, coordinate the cleaning timing of multiple engines to generate a comprehensive cleaning scheduling plan.

[0135] In this embodiment, by balancing the cleaning needs of each engine in the fleet with limited cleaning resources, an optimal cleaning schedule is formulated while ensuring the overall operational efficiency and economy of the fleet.

[0136] The technical solution described above effectively addresses the limitations of single-engine optimization decisions by introducing fleet-level operational plans, cleaning resource information, and economic benefit assessments. Specifically, by acquiring the degradation trends and sample degradation patterns of all engines, a comprehensive perspective is provided for overall fleet performance management. The inclusion of operational plans allows for coordination between cleaning timing and actual flight missions and maintenance windows, avoiding unnecessary conflicts and downtime losses. Cleaning resource information ensures the feasibility of scheduling schemes, preventing plan delays due to insufficient resources. Quantitative calculation of economic benefits enables cleaning decisions to comprehensively consider fuel savings, cleaning costs, and downtime losses, thereby maximizing fleet operational efficiency from an economic perspective. Ultimately, by coordinating the cleaning timing of multiple engines, a globally optimal integrated cleaning scheduling scheme is generated. This not only ensures that each engine is cleaned at the optimal time but also provides the entire fleet with a comprehensive cleaning strategy that balances performance, cost, and operational needs under limited resources, thereby achieving overall optimization of fuel consumption and intelligent maintenance management of the aircraft fleet.

[0137] In one example, suppose an airline has a fleet of 50 aircraft engines. These engines have varying operating times, flight routes, and performance degradation. For instance, five engines have significant compressor fouling and are expected to experience a significant performance decline within the next two weeks, requiring urgent cleaning; another ten engines have a more gradual performance decline and can be cleaned within the next month. The airline has three cleaning bays, can deploy six maintenance personnel daily, and has sufficient cleaning agents. Furthermore, some engines have important long-haul flights scheduled for next week, while others are planned for routine overhauls in two weeks.

[0138] First, we acquired data on the degradation trends and sample degradation patterns of these 50 engines. Next, we collected the operational plans for each engine, including its estimated flight hours and flight schedule, and identified and eliminated cleaning opportunities that conflicted with planned overhaul windows (e.g., routine overhauls two weeks later). Simultaneously, we obtained information on cleaning resources, namely 3 cleaning bays, 6 maintenance personnel, and sufficient cleaning agents.

[0139] Subsequently, the economic benefits for each engine were calculated at different cleaning times (e.g., next week, two weeks later, three weeks later), including the expected fuel cost savings after cleaning, the cost of the cleaning operation itself, and potential flight delays or cancellations caused by downtime for cleaning.

[0140] Finally, considering the resource constraints of 3 cleaning bays and 6 maintenance personnel, the system will coordinate the cleaning timing of these 50 engines based on the economics and operational schedule of each engine. For example, the system might prioritize cleaning the 5 engines that urgently need cleaning and have no operational conflicts next week, while scheduling engines with gradual performance degradation and important flight missions for later periods. Through this coordination, the system will generate a comprehensive cleaning scheduling plan, clearly specifying the cleaning date and required resources for each engine, and provide it to the maintenance management department to guide actual cleaning operations. This ensures optimal control of the fleet's overall fuel consumption while maximizing operational efficiency with limited resources.

[0141] In one possible design, Figure 6 This is a flowchart illustrating step S3545 according to an exemplary embodiment. (Refer to the attached document.) Figure 6 Step S3545 includes:

[0142] S35451. Obtain the operating route information and mission type for each engine;

[0143] In this embodiment, the flight route information refers to the flight route, flight distance, flight altitude, and other data that the engine will execute in the future, while the mission type refers to the transportation mission undertaken by the engine (such as passenger transport, freight transport, special missions, etc.).

[0144] S35452. Based on the flight route information and mission type, identify special operating scenarios that have special requirements for engine performance, and set engine performance margin thresholds for special operating scenarios.

[0145] In this embodiment, special operating scenarios refer to flight missions or environmental conditions that place higher or specific demands on engine performance, such as takeoffs and landings at high-altitude airports, long-duration flights in high-temperature and high-humidity environments, or emergency missions requiring high thrust output. In these scenarios, the engine's performance margin must be maintained above a certain level to ensure safety and reliability. The performance margin threshold is the minimum performance reserve value set to ensure that the engine can meet performance requirements under specific operating scenarios. This performance margin threshold is dynamically adjusted based on factors such as engine model, operating environment, mission type, and safety standards. For example, for routes requiring high thrust output, the performance margin threshold will be set higher.

[0146] S35453. Using the performance margin threshold as a constraint, calculate the economic benefits of each engine under different cleaning times; under the constraint of cleaning resource information, coordinate the cleaning times of multiple engines based on the economic benefits, operation plans and engine performance margin thresholds of each engine, and generate a comprehensive cleaning scheduling scheme.

[0147] In this embodiment, using a performance margin threshold as a constraint means that when calculating the economic benefits of each engine at different cleaning times, it must first be ensured that the cleaning time enables the engine's performance to meet the performance margin threshold requirements for all special operating scenarios in its future operating plan. If a cleaning time fails to meet this condition, that time will be excluded or its economic benefits will be significantly reduced.

[0148] The technical solution described above addresses the problem that coordinating cleaning timing solely based on economic benefits and operational plans might overlook engine performance requirements in specific operational scenarios by introducing engine performance margin thresholds. Specifically, it first acquires the operational flight path information and mission type for each engine to comprehensively understand its future operational load and potential performance challenges. Secondly, based on this information, it identifies special operational scenarios with specific engine performance requirements and sets corresponding performance margin thresholds for these scenarios, ensuring the identification and quantification of critical performance needs. Subsequently, these performance margin thresholds are used as hard constraints, prioritizing the engine's ability to meet the performance requirements of its future missions when calculating the economic benefits of each engine at different cleaning times. Thus, under the constraint of cleaning resource information, coordinating the cleaning times of multiple engines not only considers economic factors such as fuel savings, cleaning costs, and downtime losses but also fully considers engine performance assurance in special operational scenarios, thereby generating a more comprehensive and secure integrated cleaning scheduling scheme and optimizing the cleaning timing of aero engines more comprehensively and safely.

[0149] In one example, suppose one engine (engine A) in an aircraft fleet is scheduled to perform multiple takeoffs and landings at high-altitude airports within the next month, while another engine (engine B) will primarily operate on regular low-altitude routes. According to the optimization method described above, if engine A has relatively low additional fuel consumption and its planned maintenance window is far in the future, it might be scheduled for cleaning at a later time. However, takeoffs and landings at high-altitude airports place higher demands on the engine's thrust margin.

[0150] First, the system acquires the operational route information (high-altitude route) and mission type (high-altitude takeoff and landing) for engine A, identifying high-altitude takeoff and landing as a special operational scenario. Then, a higher performance margin threshold is set for engine A to ensure it can provide sufficient thrust in high-altitude environments. When calculating the economic benefits of engine A, if a cleaning opportunity causes its performance margin during a high-altitude mission to fall below the set threshold, it will be excluded or its economic benefits will be significantly reduced, even if the opportunity appears economically advantageous. Therefore, even if engine A's current additional fuel consumption is not high, the system may prioritize cleaning engine A to meet its performance margin threshold due to the stringent performance requirements of the special mission it is about to perform, thereby ensuring flight safety. In contrast, engine B, performing routine missions, may have a lower performance margin threshold set, and its cleaning timing is more coordinated based on economic benefits and resource availability.

[0151] In one possible design, Figure 7 This is a flowchart illustrating step S35454 according to an exemplary embodiment. See attached diagram. Figure 7 Step S35454 includes:

[0152] S354541. Obtain the degradation trend, sample degradation mode, operation plan, performance margin threshold and cleaning resource information of all engines in the aircraft fleet.

[0153] In this embodiment, the current performance degradation status (including the contribution of compressor fouling and internal component wear) of each engine in the entire aircraft fleet, historical degradation patterns, future flight mission schedules, required performance margins, and information such as the number of available cleaning equipment, maintenance personnel shifts, and cleaning agent inventory are collected as basic data.

[0154] S354542. For each engine, based on its degradation trend, degradation mode, operation plan and performance margin threshold, calculate its dynamic priority score at different cleaning times. The dynamic priority score reflects the urgency and potential economic benefits of cleaning.

[0155] In this embodiment, each engine is comprehensively evaluated at different potential cleaning time points to generate a quantitative score. This score takes into account the engine's current performance degradation level, the expected rate of degradation, the urgency of future tasks, the required performance margin, and the economic benefits (such as fuel savings) and costs (such as downtime) of cleaning. The higher the dynamic priority score, the greater the urgency and potential benefits of cleaning the engine in the current or specific time window.

[0156] S354543. Based on the cleaning resource information, identify the currently available cleaning capacity and time window to obtain the available cleaning resources;

[0157] In this embodiment, based on the number of cleaning equipment, the schedule of maintenance personnel, and the inventory of cleaning agents, it is determined how much cleaning capacity can be utilized during which time periods in the future.

[0158] S354544. Based on dynamic priority scores and available cleaning resources, an iterative allocation strategy is adopted. Within each time window, the engine with the highest priority score is given priority for cleaning, and the remaining cleaning resources are updated.

[0159] In this embodiment, within each available cleaning time window, the system first selects the engine with the highest current dynamic priority score for cleaning. Once a cleaning resource is allocated to an engine, the corresponding cleaning resources (such as equipment, personnel, and time) will be occupied, and the remaining available cleaning resources need to be updated. This process is iterative, ensuring that resources are always prioritized for the engine that needs them most.

[0160] S354545. After each allocation, recalculate the dynamic priority score of the affected engines and adjust the allocation strategy for subsequent time windows until all cleaning needs are met or resources are exhausted, and generate a comprehensive cleaning scheduling scheme.

[0161] In this embodiment, each cleaning allocation affects the scheduling of the entire fleet. For example, after an engine is cleaned, its performance recovers, and its dynamic priority score decreases. Simultaneously, due to the occupation or release of cleaning resources, the dynamic priority scores or cleaning timing of other engines may also be affected. Therefore, it is necessary to dynamically reassess the dynamic priority scores of all affected engines and adjust subsequent cleaning allocation plans based on the latest situation to achieve global optimization.

[0162] The technical solution described above addresses the problems of static decision-making and inflexible resource allocation that may exist in traditional methods for scheduling cleaning multiple engines by introducing dynamic priority scores and iterative allocation strategies. Specifically, by comprehensively considering multiple dimensions such as engine degradation trends, degradation modes, operating plans, and performance margin thresholds, a dynamic priority score reflecting the urgency and potential economic benefits of cleaning is calculated. This allows for the real-time identification of the engines most in need of cleaning, enabling efficient allocation of cleaning resources. Furthermore, the iterative allocation strategy, which recalculates the dynamic priority scores of affected engines after each allocation, ensures the real-time nature and adaptability of the scheduling scheme. This avoids resource waste or delays in critical engine maintenance due to improper initial allocation, achieving refined management and optimized utilization of cleaning resources.

[0163] In one possible design, step S354545 includes:

[0164] S3545451. After each cleaning resource allocation, identify the directly associated engines of the allocated cleaning engine, as well as the indirectly affected engines that are affected by the release or occupation of cleaning resources.

[0165] In this embodiment, after a cleaning resource is allocated to an engine, the system determines which other engines' priority scores or scheduling will be affected. Directly affected engines typically refer to those sharing the same cleaning resource pool or competing with the engine being cleaned within the same maintenance window. Indirectly affected engines may be those whose original scheduling schemes or priority scores need to be re-evaluated after the resource is occupied or released. For example, if a cleaning resource is occupied, another engine originally scheduled to use that resource may need to re-queue or find an alternative resource.

[0166] S3545452. For directly associated engines, update their dynamic priority scores based on their post-cleaning status changes.

[0167] In this embodiment, once an engine has completed cleaning, its performance will be significantly improved, and its future fuel consumption, performance margin, and other parameters will change. Therefore, it is necessary to recalculate its dynamic priority score based on these new state parameters to accurately reflect its latest cleaning urgency and potential economic benefits.

[0168] S3545453. For engines that are indirectly affected, an incremental calculation method is used based on their correlation with the allocated resources and the urgency of their operation plan, and only the priority scores of the affected engines are locally updated.

[0169] In this embodiment, for engines that are not directly cleaned but are affected by resource allocation, there is no need to recalculate the global priority score. Instead, based on the degree of impact (e.g., whether they need to wait for occupied resources, whether their operation plan is nearing a critical node, etc.), a more efficient incremental calculation is used to adjust only the affected part of their priority score, thereby reducing the amount of computation and improving the response speed.

[0170] S3545454. After updating the priority score, based on the latest priority score and remaining cleaning resources, adjust the allocation strategy for subsequent time windows according to the rolling optimization strategy based on the time window.

[0171] In this embodiment, after the priority score is updated, the allocation of cleaning tasks within the subsequent time window is reassessed based on the current remaining cleaning resources. The rolling optimization strategy means that the system continuously looks ahead and dynamically adjusts future scheduling plans to adapt to constantly changing engine states and resource availability.

[0172] The technical solution of the above embodiments, after each resource allocation cleanup, meticulously identifies directly related engines and indirectly affected engines, and adopts different priority score update strategies accordingly. Specifically, firstly, by comprehensively updating the priority scores of directly related engines, the performance improvement after cleanup can be accurately reflected, ensuring the accuracy of subsequent scheduling decisions. Simultaneously, for indirectly affected engines, an incremental calculation method is used for local updates, avoiding unnecessary global recalculation, significantly reducing computational complexity and resource consumption. This enables the entire scheduling system to respond to dynamic changes more quickly and flexibly, and continuously adjusts and optimizes subsequent cleanup allocations based on a rolling optimization strategy using time windows, ensuring the maximization of overall fleet operating efficiency under limited resources.

[0173] In one example, suppose an aircraft fleet has engines A, B, and C. Currently, there is only one cleaning slot available. The system first allocates the cleaning slot to engine A based on its dynamic priority score. After engine A is assigned a cleaning slot, the system identifies it as an "allocated cleaning engine." At this point, engine A's performance status will improve, and its dynamic priority score needs a complete update based on the new performance parameters. Meanwhile, engines B and C may share the same cleaning resource pool as engine A, or their originally planned cleaning times may be affected by engine A's cleaning; therefore, they are identified as "indirectly affected engines." For engines B and C, the system does not perform a full priority score recalculation. Instead, it uses an incremental calculation method based on their correlation with the allocated resource (e.g., whether they are the next engine waiting for the cleaning slot) and the urgency of their operational plans (e.g., whether they are about to reach a performance margin threshold), making only local adjustments to the affected portion of their priority scores. For example, if engine B was originally scheduled to be cleaned immediately after engine A, its priority score might slightly increase due to the increased waiting time because the cleaning resource is occupied. After these priority scores are updated, the system, considering the remaining cleaning resources (where the cleaning slot is still occupied by engine A or released after A has finished cleaning), reassesses the allocation of cleaning tasks within subsequent time windows using a rolling optimization strategy based on time windows. For example, after engine A has finished cleaning, the allocation of the next cleaning task is determined based on the updated priority scores of engines B and C. This dynamic, incremental adjustment mechanism ensures the flexibility and efficiency of the scheduling scheme.

[0174] In summary, the fuel consumption optimization method for aero-engine operation provided by this invention captures the transient response characteristics of the engine under dynamic operating conditions by acquiring high-frequency operating parameters of the engine during thrust adjustment and identifying thrust adjustment events. Subsequently, based on these transient response characteristics, the method accurately distinguishes the contributions of compressor fouling and internal component wear to engine performance degradation. This solves the problem in existing technologies of accurately distinguishing between "soft" degradation (cleanable fouling) and "hard" degradation (irreversible hardware wear), avoiding the misjudgment of hardware wear as fouling leading to ineffective cleaning, or the misinterpretation of severe fouling as hardware aging, resulting in missed optimal cleaning opportunities. Finally, by quantifying the additional fuel consumption caused by compressor fouling, the method provides precise decision-making suggestions for engine cleaning timing, achieving refined management and optimization of fuel consumption during aero-engine operation.

[0175] Example 2

[0176] Embodiment 2 of the present invention provides a fuel consumption optimization system for aircraft engine operation. Figure 8This is a block diagram illustrating an aircraft engine fuel consumption optimization system according to an exemplary embodiment. (Refer to the attached diagram.) Figure 8 The system includes:

[0177] The parameter acquisition module 01 is used to acquire high-frequency operating parameters of the engine during the thrust adjustment process;

[0178] Event recognition module 02 is used to identify engine thrust adjustment events in high-frequency operating parameters and extract the data segment of the high-frequency operating parameters corresponding to the thrust adjustment event;

[0179] The contribution differentiation module 03 is used to extract the engine transient response features in the data segment and, based on the transient response features, differentiate the contribution of compressor fouling and internal component wear in the engine performance degradation.

[0180] Consumption quantification module 04 is used to quantify the additional fuel consumption caused by compressor fouling based on the contribution of compressor fouling.

[0181] Decision suggestion module 05 is used to provide decision suggestions on when to clean the engine based on additional fuel consumption.

[0182] The aircraft engine fuel consumption optimization system provided in Embodiment 2 of this invention transforms the traditional "one-size-fits-all" maintenance strategy based on fixed calendar time or flight cycle number into on-demand maintenance based on the actual cause and extent of performance degradation. This not only effectively avoids the waste of cleaning agents, water resources, manpower, and aircraft downtime, but also ensures that the engine operates in the best performance condition, reduces fuel consumption, and improves the economic benefits of airlines.

[0183] Example 3

[0184] Embodiment 3 of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method provided in Embodiment 1.

[0185] The readable storage medium may be more specifically adopted, including but not limited to: portable disk, hard disk, random access memory, read-only memory, erasable programmable read-only memory, optical storage device, magnetic storage device, or any suitable combination thereof.

[0186] In a possible implementation, the present invention can also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of implementing the method provided in Embodiment 1.

[0187] The program code for executing the present invention can be written in any combination of one or more programming languages. The program code can be executed entirely on the user device, partially on the user device, as a standalone software package, partially on the user device and partially on a remote device, or entirely on a remote device.

[0188] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0189] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. An aeroengine operating fuel consumption optimisation method, characterised by, Includes the following steps: Acquire high-frequency operating parameters of the engine during thrust adjustment; Identify engine thrust adjustment events in the high-frequency operating parameters and extract the data segment of the high-frequency operating parameters corresponding to the thrust adjustment event; Extract the engine transient response features from the data segment, and based on the transient response features, distinguish the contribution of compressor fouling and internal component wear in the engine performance degradation. Based on the contribution of compressor fouling, the additional fuel consumption caused by compressor fouling is quantified; Based on the aforementioned additional fuel consumption, a decision recommendation on when to clean the engine is provided; The distinction between compressor fouling contribution and internal component wear contribution in engine performance degradation based on the transient response characteristics includes: Acquire engine operating parameters, environmental parameters, and control intent signals from within the engine control system; Calculate the instantaneous compensation amount of the control intention signal to the engine operating parameters; Based on the transient response characteristics, an instantaneous response curve is constructed, and the instantaneous compensation amount is removed from the instantaneous response curve to obtain the instantaneous response curve of performance degradation. The transient response features of the performance degradation are extracted from the transient response curve, and the transient response features of the degradation are imported into a pre-built degradation mode feature library for comparison to distinguish the contribution of the compressor fouling and the contribution of the internal component wear.

2. The optimization method of claim 1, wherein, Extracting the transient response features from the performance degradation transient response curve includes: The instantaneous response curve of the performance degradation is decomposed into components at different time scales. The statistical moments of the components are calculated, and the marked statistical moments with significant differences are identified. These marked statistical moments are then used as the characteristics of the decay transient response.

3. The optimization method of claim 1, wherein, The step of importing the degradation transient response features into a pre-built degradation mode feature library for comparison, and distinguishing between the compressor fouling contribution and the internal component wear contribution, includes: The transient response features of the decay are dynamically matched with the features of each decay mode in the decay mode feature library to identify the current decay mode; Based on the dynamic matching results, the evolution rate of the current decay mode is calculated, and the decay trend of the engine in the future is predicted according to the evolution rate. Based on the described decline trend, distinguish the decline patterns of samples with similar instantaneous characteristics but different decline rates; Based on the aforementioned degradation trend and sample degradation patterns, the engine cleaning timing decision recommendations are dynamically optimized.

4. The optimization method of claim 3, wherein, The step of dynamically optimizing the engine cleaning timing decision based on the degradation trend and sample degradation patterns includes: Obtain the degradation trend and sample degradation patterns of all engines in the aircraft fleet; Obtain the operating plans for all engines in the aircraft fleet, wherein the operating plans include estimated flight hours, route arrangements and planned parking maintenance windows, and identify and eliminate cleaning opportunities that conflict with the planned parking maintenance windows; Obtain cleaning resource information, wherein the cleaning resource information includes the number of available cleaning equipment, maintenance personnel shifts, and cleaning agent inventory; Calculate the economic benefits for each engine at different cleaning times, whereby the economic benefits include fuel savings, cleaning costs, and downtime losses; Based on the limitations of the cleaning resource information, and according to the economic benefits and operating plans of each engine, the cleaning timing of multiple engines is coordinated to generate a comprehensive cleaning scheduling scheme.

5. The optimization method of claim 4, wherein, Under the constraints of the cleaning resource information, and based on the economic benefits and operating plans of each engine, a comprehensive cleaning scheduling scheme is generated by coordinating the cleaning timing of multiple engines, including: Obtain the operational route information and mission type for each engine; Based on the flight route information and mission type, special operating scenarios with special requirements for engine performance are identified, and engine performance margin thresholds are set for the special operating scenarios. The special operating scenarios include take-off and landing at high-altitude airports, long-duration flights in high-temperature and high-humidity environments, or emergency missions requiring high thrust output. The special requirements refer to the requirement that the engine performance margin be maintained above a certain level under the special operating scenarios to ensure safety and reliability. Using the performance margin threshold as a constraint, the economic benefits of each engine under different cleaning times are calculated. Under the constraints of the cleaning resource information, a comprehensive cleaning scheduling scheme is generated by coordinating the cleaning timing of multiple engines based on the economic benefits of each engine, the operation plan, and the engine performance margin threshold.

6. The optimization method of claim 5, wherein, Under the constraints of the cleaning resource information, and based on the economic benefits of each engine, the operating plan, and the engine performance margin threshold, the cleaning timing of multiple engines is coordinated to generate a comprehensive cleaning scheduling scheme, including: Obtain information on the degradation trends, sample degradation patterns, operational plans, performance margin thresholds, and cleaning resources for all engines in the aircraft fleet; For each engine, considering its degradation trend, degradation mode, operating plan and performance margin threshold, a dynamic priority score is calculated for different cleaning times, where the dynamic priority score reflects the urgency and potential economic benefits of cleaning. Based on the cleaning resource information, identify the currently available cleaning capacity and time window to obtain the available cleaning resources; Based on the dynamic priority score and the available cleaning resources, an iterative allocation strategy is adopted. Within each time window, the engine with the highest priority score is given priority for cleaning, and the remaining cleaning resources are updated. After each allocation, the dynamic priority score of the affected engines is recalculated, and the allocation strategy for subsequent time windows is adjusted until all cleaning needs are met or resources are exhausted, generating a comprehensive cleaning scheduling scheme.

7. The optimization method of claim 6, wherein, The process of recalculating the dynamic priority scores of the affected engines after each allocation and adjusting the allocation strategy for subsequent time windows includes: After each cleaning resource allocation, identify the directly associated engines of the allocated cleaning engine, as well as the indirectly affected engines that are affected by the release or occupation of cleaning resources. For the directly associated engine, its dynamic priority score is updated based on its state change after cleaning; For the indirectly affected engines, based on their correlation with the allocated resources and the urgency of their operational plans, an incremental calculation method is used to locally update only the affected priority scores. After updating the priority score, the allocation strategy for subsequent time windows is adjusted based on the latest priority score and remaining cleaning resources using a rolling optimization strategy based on time windows.

8. An aircraft engine operating fuel consumption optimization system, characterized by, The system includes: The parameter acquisition module is used to acquire high-frequency operating parameters of the engine during the thrust adjustment process; An event recognition module is used to identify engine thrust adjustment events in the high-frequency operating parameters and extract the data segment of the high-frequency operating parameters corresponding to the thrust adjustment event; The contribution differentiation module is used to extract the engine transient response features in the data segment, and based on the transient response features, to differentiate the contribution of compressor fouling and internal component wear in the engine performance degradation. The consumption quantification module is used to quantify the additional fuel consumption caused by compressor fouling based on the contribution of compressor fouling. The decision suggestion module is used to provide a decision suggestion on when to clean the engine based on the additional fuel consumption; The distinction between compressor fouling contribution and internal component wear contribution in engine performance degradation based on the transient response characteristics includes: Acquire engine operating parameters, environmental parameters, and control intent signals from within the engine control system; Calculate the instantaneous compensation amount of the control intention signal to the engine operating parameters; Based on the transient response characteristics, an instantaneous response curve is constructed, and the instantaneous compensation amount is removed from the instantaneous response curve to obtain the instantaneous response curve of performance degradation. The transient response features of the performance degradation are extracted from the transient response curve, and the transient response features of the degradation are imported into a pre-built degradation mode feature library for comparison to distinguish the contribution of the compressor fouling and the contribution of the internal component wear.

9. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method according to any one of claims 1-7.

Images