Active stability control system based on aero-engine stability margin estimation

Abstract

The invention relates to the technical field of aero-engine control, in particular to an active stability control system based on aero-engine stability margin estimation, which is used for solving the problems that the surge risk cannot be accurately evaluated and the surge phenomenon cannot be prevented through real-time monitoring and dynamic adjustment in the prior art. According to the system, the surge risk can be accurately evaluated through the surge margin estimation module, the surge phenomenon is effectively prevented through real-time monitoring and dynamic adjustment, safe operation of the engine is ensured, the system allows safe operation closer to the performance limit, and therefore the working efficiency and the performance expression are optimized; the module with the self-adaptive capability can be automatically adjusted according to flight conditions, the adaptability of the aircraft in a changeable environment is enhanced, meanwhile, the system carries out intelligent decision making through historical and real-time data, and quick response and high reliability are guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of aircraft engine control, and more specifically, to an active stability control system based on aircraft engine stability margin estimation. Background Art

[0002] At present, the aerodynamic stability control of aircraft engines mainly adopts the passive control method. Its control strategy is based on the instability control line, combining the short-term stability augmentation control system and the instability recovery control system to solve the unstable operation problem of the engine. However, this traditional instability control strategy has many defects, such as the conservative stability margin of the instability control line, the open-loop nature of the short-term stability augmentation control system and the ex post facto nature of the instability recovery control system, which limits the improvement of engine performance.

[0003] Patent application with reference publication number CN109344510A discloses an active stability control method based on aircraft engine stability margin estimation, the method comprising: (1) aircraft engine surge real-time model; (2) surge margin estimation algorithm and simulation; (3) aircraft engine active stability control law; the present invention aims at the aerodynamic stability problem of aircraft engines, improves the aerodynamic stability of engines by utilizing the residual stability margin, establishes an engine surge real-time model and an engine stability margin estimation model, designs an active stability control law by a robust control method, constructs an engine stability margin closed-loop control loop, ensures that the dynamic performance brought by the residual stability margin is maximized under the premise of stable operation of the engine in the transition state; in addition, the scheme enables the engine to operate at a high-performance point with a smaller surge margin during acceleration, improves the acceleration performance of the engine, and enhances the maneuverability of the aircraft;

[0004] However, the above-mentioned reference patent optimizes engine stability through residual stability margin and robust control, constructs closed-loop control to ensure transition state stability and improve dynamic performance, and enables the engine to operate at a high-performance point during acceleration, thereby enhancing the acceleration performance and maneuverability of the aircraft. However, it is unable to accurately assess the risk of surge, and is unable to prevent surge through real-time monitoring and dynamic adjustment. It is unable to accurately assess the risk of engine stall, and is unable to achieve real-time monitoring and early warning, and is unable to ensure safe operation of the engine. At the same time, it is unable to accurately assess the engine operating status, and is unable to reasonably adjust the engine status according to the engine operating risk.

[0005] To this end, we propose an active stability control system based on aircraft engine stability margin estimation to address the above problems. Summary of the invention

[0006] The purpose of the present invention is to provide an active stability control system based on aircraft engine stability margin estimation, which solves the problems that the prior art cannot accurately assess the surge risk, cannot prevent surge through real-time monitoring and dynamic adjustment, cannot accurately assess the engine stall risk, cannot achieve real-time monitoring and early warning, cannot ensure the safe operation of the engine, and cannot accurately assess the engine operating status and cannot reasonably adjust the engine status according to the engine operating risk.

[0007] The purpose of the present invention is achieved through the following technical solutions:

[0008] An active stability control system based on aircraft engine stability margin estimation includes an aviation stability control platform, an inlet flow control module, a surge margin estimation module, a stall monitoring module, a controller decision module and a protection execution module;

[0009] The inlet flow control module is used to collect the inlet flow, engine flow and flight attack angle in real time, calculate the optimal angle of the inclined plate, and obtain the inclined plate adjustment angle value according to the calculation result;

[0010] A surge margin estimation module is used to collect historical surge margin estimation parameters, build a surge margin estimation model, and calculate a real-time surge margin estimation value based on the model;

[0011] Stall monitoring module, used to monitor engine operating parameters and flight status parameters in real time, and monitor and evaluate the engine stall risk;

[0012] A controller decision module is used to comprehensively evaluate the engine operating state according to the swash plate adjustment angle value, the real-time surge margin estimation value and the stall risk assessment result, and make a control decision according to the assessment result;

[0013] The protection execution module is used to control the corresponding execution agency to execute control measures according to the control decision.

[0014] As a preferred embodiment of the present invention, the specific process of the intake flow control module calculating the optimal inclined plate angle is as follows:

[0015] The intake flow, engine flow, flight angle of attack and current ramp angle are collected in real time through sensors. The intake flow refers to the air flow entering the intake duct, and the intake flow is marked as Q j , engine flow refers to the air flow required by the engine, and the engine flow is marked as Q f , the flight angle of attack refers to the angle of attack of the aircraft relative to the airflow, and the flight angle of attack is marked as β. The ramp angle refers to the angle between the ramp of the inlet duct and the axis of the inlet duct, and the current ramp angle is marked as θ;

[0016] In order to ensure the normal operation of the engine, the intake flow must meet or slightly exceed the engine's demand, that is: Q j ≥Q f ;

[0017] The change of flight angle of attack will directly affect the airflow distribution and flow rate of the inlet. The relationship between the flight angle of attack and the inlet flow rate is expressed as follows:

[0018] Q j (β) = Q j0 f(β);

[0019] Where Q j0 is the inlet flow at zero flight angle of attack, and f(β) is a function related to the flight angle of attack;

[0020] Adjusting the angle of the ramp will change the airflow distribution of the intake duct, thereby affecting the intake duct flow rate. The relationship between the ramp angle and the intake duct flow rate is expressed as follows:

[0021] Q j (θ) = Q j0 g(θ);

[0022] Where Q j0 is the intake flow rate at zero ramp angle, and g(θ) is a function related to the ramp angle.

[0023] As a preferred embodiment of the present invention, in order to ensure that the intake flow meets the requirements of the engine, the influence of the flight angle of attack and the angle of the inclined plate are comprehensively considered, and the relationship between the intake flow and the engine flow is expressed as follows:

[0024] Q j (θ,β)=Q f ;

[0025] Substituting the relationship between the flight angle of attack, the angle of the inclined plate and the intake flow rate into the equation, we get:

[0026] Q j0 f(β) g(θ) = Q f ;

[0027] By solving this equation, we can get the optimal inclined plate angle θ * :

[0028]

[0029] where g -1 It is the inverse function of the function g(θ);

[0030] The inclined plate adjustment angle value θ is obtained by the following formula t :θ t =θ *-θ;

[0031] The calculated inclined plate adjustment angle value θ t Sent to the aviation stabilization platform.

[0032] As a preferred implementation of the present invention, the specific process of the surge margin estimation module constructing the surge margin estimation model is as follows:

[0033] Obtain historical surge margin estimation parameters, including flight angle of attack, compressor flow coefficient, engine speed, and compressor inlet total pressure, generate a collection period, and divide the collection period S into multiple collection periods {s1, s2, …, sn}, that is, S = {s1, s2, …, sn};

[0034] The flight angle of attack of the aircraft in multiple collection periods is obtained to construct a set A of the flight angle of attack, and the average of the difference between the maximum subset and the minimum subset in the set A is recorded as the flight angle of attack difference FGC;

[0035] The compressor flow coefficient of the aircraft in multiple collection periods is obtained. The compressor flow coefficient represents the dimensionless ratio of the air mass flow through a certain section of the compressor per unit time to the area of ​​the section and the local sound speed. A set B of compressor flow coefficients is constructed based on this, and the average of the difference between the largest subset and the smallest subset in set B is recorded as the compressor flow coefficient difference YLC;

[0036] Obtain the engine speed of the aircraft in multiple collection periods. The engine speed represents the number of complete rotations of the crankshaft or main shaft of the engine in one minute, thereby constructing a set C of engine speeds, and recording the average of the difference between the maximum subset and the minimum subset in the set C as the engine speed difference FZC;

[0037] The compressor inlet total pressure of the aircraft in multiple collection periods is obtained. The compressor inlet total pressure represents the total pressure of the gas before entering the compressor. The set D of compressor inlet total pressures is constructed based on this, and the average of the difference between the maximum subset and the minimum subset in the set D is recorded as the compressor inlet total pressure difference value YYC.

[0038] As a preferred embodiment of the present invention, the flight angle of attack difference FGC, the compressor flow coefficient difference YLC, the engine speed difference FZC and the compressor inlet total pressure difference YYC are obtained, and the flight angle of attack difference FGC, the compressor flow coefficient difference YLC, the engine speed difference FZC and the compressor inlet total pressure difference YYC are used to construct a feature matrix TJ, and the feature matrix TJ is used as the input of the machine learning model, and the surge margin corresponding to each group of feature matrices TJ is used as the output of the machine learning model. The surge margin is used as the estimation target, and the minimum sum of the estimation errors of all training data is used as the training target. The machine learning model is trained until the sum of the estimation errors reaches convergence and the training is stopped to obtain a surge margin estimation model. The surge margin estimation model is expressed as follows:

[0039] CY=γ0+γ1·FGJ+γ2·YLJ+γ3·FZJ+γ4·YYJ;

[0040] Where CY is the estimated value of surge margin, γ0, γ1, γ2, γ3 and γ4 are regression coefficients;

[0041] The real-time surge margin estimation parameters are obtained, converted into corresponding feature matrices and input into the surge margin estimation model. The real-time surge margin estimation value CY is calculated by the surge margin estimation model. 实时 , the calculated real-time surge margin estimate CY 实时 Sent to the aviation stabilization platform.

[0042] As a preferred embodiment of the present invention, the specific process of the stall monitoring module monitoring and evaluating the engine stall risk is as follows:

[0043] Obtain historical engine operating parameters and historical flight status parameters. The engine operating parameters include engine speed and compressor inlet total pressure. The flight status parameters include flight speed, flight angle of attack, and flight sideslip angle. Generate a monitoring cycle, divide the monitoring cycle into g consecutive sub-cycles, and mark the midpoint of each sub-cycle to obtain g midpoints.

[0044] Taking g midpoint moments as the base point, expand forward and backward by equal time lengths, mark h-1 expansion moments, and then summarize the midpoint moments and h-1 expansion moments to obtain h detection moments;

[0045] The engine speed values ​​at h detection moments are measured by the sensor respectively to obtain h detection engine speed values, and the h detection engine speed values ​​are accumulated and averaged to obtain g sub-engine speed values;

[0046] The expression of the sub-engine speed value is:

[0047] Where, FZ zg is the sub-engine speed value of the g-th sub-cycle, FZ jcgn is the nth detected engine speed value in the gth sub-cycle;

[0048] Remove the maximum and minimum sub-engine speed values, and add up the remaining g-2 sub-engine speed values ​​and calculate the average to obtain the engine speed mean;

[0049] The expression of the mean engine speed is:

[0050] Where, FZ jz is the mean engine speed, FZ zo is the sub-engine speed value of the oth sub-cycle.

[0051] As a preferred embodiment of the present invention, the method of calculating the mean value of the engine speed can be used to obtain the mean value of the total pressure at the compressor inlet YY jy , flight speed mean FS js , mean flight angle of attack FG jg And the mean side slip angle FH jh , the average engine speed FZ jz , Average value of total pressure at compressor inlet YY jy , flight speed mean FS js , mean flight angle of attack FG jg And the mean side slip angle FH jh Combine and construct the risk assessment feature matrix FP;

[0052] The constructed risk assessment feature matrix FP is used as the input of the logistic regression model, and the label vector v is used as the output of the logistic regression model. The label vector v indicates whether the engine has a stall risk. The output of the label vector v is 0 or 1, 0 indicates that the engine has no stall risk, and 1 indicates that the engine has a stall risk. The label vector v is used as the prediction target, and the sum of the prediction errors of all training data is minimized as the training target. The logistic regression model is trained until the sum of the prediction errors converges, and the training is stopped to obtain a logistic regression model that predicts the label vector v.

[0053] As a preferred embodiment of the present invention, the expression formula of the logistic regression model is:

[0054]

[0055] Where P(v=1) represents the probability value of engine stall, μ0 represents the intercept term, which represents the baseline probability of engine stall, and μ0, μ1, μ2, μ3, μ4 and μ5 are all regression coefficients;

[0056] Obtain real-time engine operating parameters and real-time flight status parameters, process them and construct the risk assessment feature matrix FP 实时 , the probability value P of engine stall is calculated by the trained logistic regression model 实时 , the calculated probability value P of engine stall 实时 Sent to the aviation stabilization platform.

[0057] As a preferred embodiment of the present invention, the specific process of the controller decision module performing comprehensive evaluation on the engine operating state is as follows:

[0058] Get the inclined plate adjustment angle value θ t , Real-time surge margin estimation value CY 实时 And the probability value P of engine stall 实时 , calculate the operating status assessment coefficient YZP by the following formula:

[0059]

[0060] Wherein b1, b2 and b3 are all preset proportional factor coefficients, b3>b2>b1>0, the operation state assessment coefficient YZP is compared with the preset first operation state assessment coefficient threshold and the preset second operation state assessment coefficient threshold, and the preset first operation state assessment coefficient threshold is less than the preset second operation state assessment coefficient threshold;

[0061] If the operating state assessment coefficient is less than the preset first operating state assessment coefficient threshold, it indicates that the engine operation is in a low risk state;

[0062] If the operating state assessment coefficient is greater than or equal to the preset first operating state assessment coefficient threshold, and the operating state assessment coefficient is less than the preset second operating state assessment coefficient threshold, it indicates that the engine operation is in a medium risk state;

[0063] If the operating state assessment coefficient is greater than or equal to the preset second operating state assessment coefficient threshold, it indicates that the engine operation is in a high-risk state;

[0064] Make corresponding control decisions based on the evaluation results of the engine operating status and send the control decisions to the protection execution module.

[0065] As a preferred implementation of the present invention, the specific process of the protection execution module executing the corresponding control measures is as follows:

[0066] After receiving the control decision, the protection execution module immediately sends the control instruction to the corresponding execution agency, and the execution agency executes the corresponding control measures according to the control instruction. The specific contents of the control measures are as follows:

[0067] If the control decision is to maintain the current state, there is no need to adjust the ramp angle, engine speed, or flight attitude;

[0068] If the control decision is to make a slight adjustment, then the angle of the inclined plate is appropriately increased or decreased to optimize the intake conditions, the engine speed is appropriately increased or decreased to optimize the compressor working state, the flight angle of attack and sideslip angle are appropriately adjusted to improve the intake duct working conditions;

[0069] If the control decision is to make an emergency adjustment, the ramp angle will be greatly increased, the intake flow will be increased, the compressor working condition will be improved, the engine speed will be greatly increased, the compressor flow will be increased, entering the stall area will be avoided, the flight angle of attack and sideslip angle will be greatly adjusted, the inlet working conditions will be improved, and the stall risk will be reduced.

[0070] Compared with the prior art, the advantages of the present invention are:

[0071] (1) In the present invention, the surge risk can be accurately assessed through the surge margin estimation module, and the surge phenomenon can be effectively prevented through real-time monitoring and dynamic adjustment, thereby ensuring the safe operation of the engine. The system allows safe operation closer to the performance limit, thereby optimizing work efficiency and performance. The module with adaptive capability can automatically adjust according to flight conditions, enhancing the adaptability of the aircraft in a changing environment. At the same time, the system uses historical and real-time data to make intelligent decisions, ensuring rapid response and high reliability.

[0072] (2) In the present invention, the stall monitoring module accurately evaluates the engine stall risk, significantly improves the prediction accuracy, realizes real-time monitoring and early warning, effectively prevents safety hazards, and ensures the safe operation of the engine. Based on accurate risk assessment, the module can safely adjust the engine working state and optimize performance. The system has adaptive capabilities and automatically adjusts the evaluation strategy according to different flight conditions to enhance the environmental adaptability of the aircraft. It uses historical and real-time data to make decisions and ensure rapid response and high reliability.

[0073] (3) In the present invention, a controller decision module is used to comprehensively evaluate multiple parameters, which can fully identify and quickly respond to engine operation risks, thereby improving flight safety. Based on accurate evaluation, the module reasonably adjusts the engine status to ensure safety while optimizing performance. The system automatically makes decisions based on risk levels to enhance response flexibility, and uses multi-source data for reliable evaluation to improve operational efficiency. Risk thresholds are set to achieve refined management, ensure optimal responses at each risk level, and ensure system stability and reliability. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 This is a system block diagram of Embodiment 1 of the present invention;

[0075] Figure 2This is a system block diagram of Embodiment 2 of the present invention;

[0076] Figure 3 This is a logical flow diagram of the second embodiment of the present invention. DETAILED DESCRIPTION

[0077] The following will combine the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all the embodiments. All other embodiments obtained by ordinary technicians in this field without creative work based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0078] Embodiment 1: Figure 1 As shown, an active stability control system based on aircraft engine stability margin estimation proposed by the present invention includes an aviation stability control platform, an inlet flow control module, a surge margin estimation module, a stall monitoring module, a controller decision module and a protection execution module;

[0079] The aviation stability control platform is connected to the surge margin estimation module, the stall monitoring module, and the controller decision module in a two-way communication manner. The aviation stability control platform is connected to the inlet flow control module in a one-way communication manner. The controller decision module is connected to the protection execution module in a one-way communication manner.

[0080] The inlet flow control module is used to collect the inlet flow, engine flow and flight attack angle in real time, calculate the optimal angle of the inclined plate, and obtain the inclined plate adjustment angle value according to the calculation result;

[0081] The specific process of the intake flow control module calculating the optimal inclined plate angle is as follows:

[0082] The intake flow, engine flow, flight angle of attack and current ramp angle are collected in real time through sensors. The intake flow refers to the air flow entering the intake duct, and the intake flow is marked as Q j , engine flow refers to the air flow required by the engine, and the engine flow is marked as Q f , the flight angle of attack refers to the angle of attack of the aircraft relative to the airflow, and the flight angle of attack is marked as β. The ramp angle refers to the angle between the ramp of the inlet duct and the axis of the inlet duct, and the current ramp angle is marked as θ;

[0083] In order to ensure the normal operation of the engine, the intake flow must meet or slightly exceed the engine's demand, that is: Q j ≥Q f ;

[0084] The change of flight angle of attack will directly affect the airflow distribution and flow rate of the inlet. The relationship between the flight angle of attack and the inlet flow rate is expressed as follows:

[0085] Q j (β) = Q j0 f(β);

[0086] Where Q j0 is the inlet flow at zero flight angle of attack, and f(β) is a function related to the flight angle of attack;

[0087] Adjusting the angle of the ramp will change the airflow distribution of the intake duct, thereby affecting the intake duct flow rate. The relationship between the ramp angle and the intake duct flow rate is expressed as follows:

[0088] Q j (θ) = Q j0 g(θ);

[0089] Where Q j0 is the intake flow at zero swash plate angle, and g(θ) is a function related to the swash plate angle;

[0090] In order to ensure that the intake flow meets the needs of the engine, the influence of the flight angle of attack and the angle of the ramp is comprehensively considered. The relationship between the intake flow and the engine flow is expressed as follows:

[0091] Q j (θ,β)=Q f ;

[0092] Substituting the relationship between the flight angle of attack, the angle of the inclined plate and the intake flow rate into the equation, we get:

[0093] Q j0 f(β) g(θ) = Q f ;

[0094] By solving this equation, we can get the optimal inclined plate angle θ * :

[0095]

[0096] where g -1 It is the inverse function of the function g(θ);

[0097] The inclined plate adjustment angle value θ is obtained by the following formula t :θ t =θ * -θ;

[0098] The calculated inclined plate adjustment angle value θ t Send to aviation stabilization platform;

[0099] The inlet flow control module can accurately adjust the angle of the ramp and optimize the inlet flow distribution, thereby significantly improving the engine's operating efficiency and overall performance; it ensures optimal air supply under various flight conditions, enhances the stability and reliability of engine operation, and reduces unstable factors caused by changes in intake conditions; the module has adaptive capabilities and can automatically adjust according to the flight status, allowing the aircraft to adapt to a wider range of operating environments; at the same time, it ensures that the engine has sufficient air supply in different flight phases, avoids safety hazards caused by insufficient air supply, and comprehensively improves the safety and operational flexibility of the aircraft.

[0100] A surge margin estimation module is used to collect historical surge margin estimation parameters, build a surge margin estimation model, and calculate a real-time surge margin estimation value based on the model;

[0101] The specific process of constructing the surge margin estimation model by the surge margin estimation module is as follows:

[0102] Obtain historical surge margin estimation parameters, including flight angle of attack, compressor flow coefficient, engine speed, and compressor inlet total pressure, generate a collection period, and divide the collection period S into multiple collection periods {s1, s2, …, sn}, that is, S = {s1, s2, …, sn};

[0103] The flight angle of attack of the aircraft in multiple collection periods is obtained to construct a set A of the flight angle of attack, and the average of the difference between the maximum subset and the minimum subset in the set A is recorded as the flight angle of attack difference FGC;

[0104] The compressor flow coefficient of the aircraft in multiple collection periods is obtained. The compressor flow coefficient represents the dimensionless ratio of the air mass flow through a certain section of the compressor per unit time to the area of ​​the section and the local sound speed. A set B of compressor flow coefficients is constructed based on this, and the average of the difference between the largest subset and the smallest subset in set B is recorded as the compressor flow coefficient difference YLC;

[0105] Obtain the engine speed of the aircraft in multiple collection periods. The engine speed represents the number of complete rotations of the crankshaft or main shaft of the engine in one minute, thereby constructing a set C of engine speeds, and recording the average of the difference between the maximum subset and the minimum subset in the set C as the engine speed difference FZC;

[0106] Obtain the compressor inlet total pressure of the aircraft in multiple collection periods. The compressor inlet total pressure represents the total pressure of the gas before entering the compressor. The compressor inlet total pressure set D is constructed based on this, and the average of the difference between the maximum subset and the minimum subset in the set D is recorded as the compressor inlet total pressure difference value YYC;

[0107] The flight angle of attack difference FGC, the compressor flow coefficient difference YLC, the engine speed difference FZC and the compressor inlet total pressure difference YYC are obtained, and the flight angle of attack difference FGC, the compressor flow coefficient difference YLC, the engine speed difference FZC and the compressor inlet total pressure difference YYC are used to construct a feature matrix TJ, and the feature matrix TJ is used as the input of the machine learning model, and the surge margin corresponding to each set of feature matrices TJ is used as the output of the machine learning model. The surge margin is used as the estimation target, and the minimum sum of the estimation errors of all training data is used as the training target. The machine learning model is trained until the sum of the estimation errors reaches convergence and the training is stopped. The surge margin estimation model is obtained. The surge margin estimation model is expressed as follows:

[0108] CY=γ0+γ1·FGJ+γ2·YLJ+γ3·FZJ+γ4·YYJ;

[0109] Where CY is the estimated value of surge margin, γ0, γ1, γ2, γ3 and γ4 are regression coefficients;

[0110] The real-time surge margin estimation parameters are obtained, converted into corresponding feature matrices and input into the surge margin estimation model. The real-time surge margin estimation value CY is calculated by the surge margin estimation model. 实时 , the calculated real-time surge margin estimate CY 实时 Send to aviation stabilization platform;

[0111] The surge margin estimation module can accurately estimate the surge margin, which not only improves the prediction accuracy, but also realizes real-time monitoring and dynamic adjustment, effectively preventing surge and ensuring the safe operation of the engine. Based on accurate surge margin estimation, the system can approach the performance limit more safely, thereby optimizing the engine's operating efficiency and performance. The module has adaptive capabilities and can automatically adjust according to different flight conditions, enhancing the aircraft's adaptability in various environments. In addition, the use of historical data and real-time data for decision-making ensures the system's rapid response and high reliability, improves overall operational efficiency, and provides strong support for the aviation stability control platform.

[0112] Stall monitoring module, used to monitor engine operating parameters and flight status parameters in real time, and monitor and evaluate the engine stall risk;

[0113] The specific process of the stall monitoring module monitoring and evaluating the engine stall risk is as follows:

[0114] Obtain historical engine operating parameters and historical flight status parameters. The engine operating parameters include engine speed and compressor inlet total pressure. The flight status parameters include flight speed, flight angle of attack, and flight sideslip angle. Generate a monitoring cycle, divide the monitoring cycle into g consecutive sub-cycles, and mark the midpoint of each sub-cycle to obtain g midpoints.

[0115] Taking g midpoint moments as the base point, expand forward and backward by equal time lengths, mark h-1 expansion moments, and then summarize the midpoint moments and h-1 expansion moments to obtain h detection moments;

[0116] The engine speed values ​​at h detection moments are measured by the sensor respectively to obtain h detection engine speed values, and the h detection engine speed values ​​are accumulated and averaged to obtain g sub-engine speed values;

[0117] The expression of the sub-engine speed value is:

[0118] Where, FZ zg is the sub-engine speed value of the g-th sub-cycle, FZ jcgn is the nth detected engine speed value in the gth sub-cycle;

[0119] Remove the maximum and minimum sub-engine speed values, and add up the remaining g-2 sub-engine speed values ​​and calculate the average to obtain the engine speed mean;

[0120] The expression of the mean engine speed is:

[0121] Where, FZ jz is the mean engine speed, FZ zo is the sub-engine speed value of the oth sub-cycle;

[0122] Using the method of calculating the mean engine speed, the mean compressor inlet total pressure YY can be obtained in the same way. jy , flight speed mean FS js , mean flight angle of attack FG jg And the mean side slip angle FH jh , the average engine speed FZ jz , Average value of total pressure at compressor inlet YY jy , flight speed mean FS js , mean flight angle of attack FG jg And the mean side slip angle FH jh Combine and construct the risk assessment feature matrix FP;

[0123] The constructed risk assessment feature matrix FP is used as the input of the logistic regression model, and the label vector v is used as the output of the logistic regression model. The label vector v indicates whether the engine has a stall risk. The output of the label vector v is 0 or 1, 0 indicates that the engine has no stall risk, and 1 indicates that the engine has a stall risk. The label vector v is used as the prediction target, and the sum of the prediction errors of all training data is minimized as the training target. The logistic regression model is trained until the sum of the prediction errors reaches convergence, and the training is stopped to obtain a logistic regression model that predicts the label vector v.

[0124] The expression formula of the logistic regression model is:

[0125]

[0126] Where P(v=1) represents the probability value of engine stall, μ0 represents the intercept term, which represents the baseline probability of engine stall, and μ0, μ1, μ2, μ3, μ4 and μ5 are all regression coefficients;

[0127] Obtain real-time engine operating parameters and real-time flight status parameters, process them and construct the risk assessment feature matrix FP 实时 , the probability value P of engine stall is calculated by the trained logistic regression model 实时 , the calculated probability value P of engine stall 实时 Send to aviation stabilization platform;

[0128] The stall monitoring module can accurately assess the risk of engine stall, significantly improving prediction accuracy, and realize real-time monitoring and early warning of engine stall risk, effectively preventing potential safety hazards and ensuring the safe operation of the engine; based on accurate risk assessment, the module can more safely adjust the operating state of the engine and optimize its performance; in addition, the system has adaptive capabilities and can automatically adjust the assessment strategy according to different flight conditions to enhance the adaptability of the aircraft in various environments; at the same time, the use of historical data and real-time data for decision-making ensures the system's rapid response and high reliability, improves overall operational efficiency, and provides strong support for the aviation stability control platform.

[0129] Embodiment 2: The technical solution of the embodiment of the present invention is different from that of embodiment 1 in that:

[0130] like Figure 2 and Figure 3 As shown, the controller decision module is used to comprehensively evaluate the engine operating state according to the inclined plate adjustment angle value, the real-time surge margin estimation value and the stall risk evaluation result, and make a control decision according to the evaluation result;

[0131] The specific process of the controller decision module's comprehensive evaluation of the engine operating status is as follows:

[0132] Get the inclined plate adjustment angle value θ t , Real-time surge margin estimation value CY 实时 And the probability value P of engine stall 实时 , calculate the operating status assessment coefficient YZP by the following formula:

[0133]

[0134] Wherein b1, b2 and b3 are all preset proportional factor coefficients, b3>b2>b1>0, the operation state assessment coefficient YZP is compared with the preset first operation state assessment coefficient threshold and the preset second operation state assessment coefficient threshold, and the preset first operation state assessment coefficient threshold is less than the preset second operation state assessment coefficient threshold;

[0135] If the operating state assessment coefficient is less than the preset first operating state assessment coefficient threshold, it indicates that the engine operation is in a low risk state;

[0136] If the operating state assessment coefficient is greater than or equal to the preset first operating state assessment coefficient threshold, and the operating state assessment coefficient is less than the preset second operating state assessment coefficient threshold, it indicates that the engine operation is in a medium risk state;

[0137] If the operating state assessment coefficient is greater than or equal to the preset second operating state assessment coefficient threshold, it indicates that the engine operation is in a high-risk state;

[0138] Make corresponding control decisions based on the evaluation results of the engine operating status and send the control decisions to the protection execution module. The control decision contents are as follows:

[0139] If the engine is running at a low risk state, maintain the current state;

[0140] If the engine is operating at a medium risk, make minor adjustments;

[0141] If the engine is operating at a high risk, make emergency adjustments;

[0142] By comprehensively evaluating multiple parameters through the controller decision module, it can fully identify engine operation risks and respond quickly, effectively improving flight safety. Based on accurate risk assessment, the module reasonably adjusts the engine operating status to optimize performance while ensuring safety. The system automatically makes decisions based on different risk levels, enhancing the flexibility and adaptability to various working conditions. It uses multi-source data for scientific and reliable evaluation, improves operational efficiency, sets different risk thresholds for refined management, ensures the optimal response measures are taken at each risk level, and guarantees the stability and reliability of the system.

[0143] A protection execution module is used to control the corresponding execution agency to execute the control measures according to the control decision;

[0144] The specific process of the protection execution module executing the corresponding control measures is as follows:

[0145] After receiving the control decision, the protection execution module immediately sends the control instruction to the corresponding execution agency, and the execution agency executes the corresponding control measures according to the control instruction. The specific contents of the control measures are as follows:

[0146] If the control decision is to maintain the current state, there is no need to adjust the ramp angle, engine speed, or flight attitude;

[0147] If the control decision is to make a slight adjustment, then the angle of the inclined plate is appropriately increased or decreased to optimize the intake conditions, the engine speed is appropriately increased or decreased to optimize the compressor working state, the flight angle of attack and sideslip angle are appropriately adjusted to improve the intake duct working conditions;

[0148] If the control decision is to make an emergency adjustment, the ramp angle is greatly increased to increase the intake flow, improve the compressor working condition, greatly increase the engine speed, increase the compressor flow, avoid entering the stall area, greatly adjust the flight angle of attack and sideslip angle, improve the intake working conditions, and reduce the risk of stall;

[0149] By protecting the execution module, the reaction speed and control accuracy of the system are significantly improved to ensure the stability of the engine and flight status. It can flexibly adjust parameters according to different control requirements and enhance the adaptability of the system under various working conditions. Especially in emergency situations, the module can quickly make large adjustments to avoid safety hazards and ensure flight safety. At the same time, during fine adjustments, the intake and compressor working conditions are optimized to improve engine performance without affecting safety. Through the comprehensive management of key parameters such as the ramp angle, engine speed and flight attitude, refined control of the engine operating status is achieved, providing reliable support for the aviation stabilization and control platform.

[0150] The working principle of the present invention is as follows: when in use, the surge risk can be accurately assessed through the surge margin estimation module, and the surge phenomenon can be effectively prevented through real-time monitoring and dynamic adjustment, ensuring the safe operation of the engine. The system allows safe operation closer to the performance limit, thereby optimizing work efficiency and performance. The module with adaptive capability can automatically adjust according to flight conditions, enhancing the adaptability of the aircraft in a changing environment. At the same time, the system uses historical and real-time data to make intelligent decisions, ensuring rapid response and high reliability. The stall monitoring module accurately assesses the engine stall risk, significantly improving the prediction accuracy, realizing real-time monitoring and early warning, effectively preventing safety hazards, and ensuring the safe operation of the engine. Based on accurate risk assessment The module can safely adjust the engine operating status and optimize performance. The system has adaptive capabilities and automatically adjusts the evaluation strategy according to different flight conditions to enhance the environmental adaptability of the aircraft. It uses historical and real-time data to make decisions to ensure rapid response and high reliability. The controller decision module conducts a comprehensive evaluation of multiple parameters, which can fully identify and quickly respond to engine operation risks and improve flight safety. Based on accurate evaluation, the module reasonably adjusts the engine status to ensure safety while optimizing performance. The system automatically makes decisions based on risk levels to enhance response flexibility, and uses multi-source data for reliable evaluation to improve operational efficiency. Risk thresholds are set to achieve refined management, ensure the optimal response at each risk level, and ensure system stability and reliability.

[0151] The above are only preferred specific implementation modes of the present invention; however, the protection scope of the present invention is not limited thereto; any technician familiar with the technical field within the technical scope disclosed by the present invention; any equivalent replacement or change based on the technical solution and improved concept of the present invention shall be covered within the protection scope of the present invention.

Claims

1. An active stability control system based on aircraft engine stability margin estimation, characterized in that: It includes aviation stability control platform, inlet flow control module, surge margin estimation module, stall monitoring module, controller decision module and protection execution module; The inlet flow control module is used to collect the inlet flow, engine flow and flight attack angle in real time, calculate the optimal angle of the inclined plate, and obtain the inclined plate adjustment angle value according to the calculation result; A surge margin estimation module is used to collect historical surge margin estimation parameters, build a surge margin estimation model, and calculate a real-time surge margin estimation value based on the model; Stall monitoring module, used to monitor engine operating parameters and flight status parameters in real time, and monitor and evaluate the engine stall risk; A controller decision module is used to comprehensively evaluate the engine operating state according to the swash plate adjustment angle value, the real-time surge margin estimation value and the stall risk assessment result, and make a control decision according to the assessment result; The protection execution module is used to control the corresponding execution agency to execute control measures according to the control decision.

2. The active stability control system based on aircraft engine stability margin estimation according to claim 1, characterized in that: The specific process of the intake flow control module calculating the optimal inclined plate angle is as follows: The intake flow, engine flow, flight angle of attack and current ramp angle are collected in real time through sensors. The intake flow refers to the air flow entering the intake duct, and the intake flow is marked as Q j , engine flow refers to the air flow required by the engine, and the engine flow is marked as Q f , the flight angle of attack refers to the angle of attack of the aircraft relative to the airflow, and the flight angle of attack is marked as β. The ramp angle refers to the angle between the ramp of the inlet duct and the axis of the inlet duct, and the current ramp angle is marked as θ; In order to ensure the normal operation of the engine, the intake flow must meet or slightly exceed the engine's demand, that is: Q j ≥Q f ; The change of flight angle of attack will directly affect the airflow distribution and flow rate of the inlet. The relationship between the flight angle of attack and the inlet flow rate is expressed as follows: Q j (β)=Q j0 ·f(β); Where Q j0 is the inlet flow at zero flight angle of attack, and f(β) is a function related to the flight angle of attack; Adjusting the angle of the ramp will change the airflow distribution of the intake duct, thereby affecting the intake duct flow rate. The relationship between the ramp angle and the intake duct flow rate is expressed as follows: Q j (θ)=Q j0 ·g(θ); Where Q j0 is the intake flow rate at zero ramp angle, and g(θ) is a function related to the ramp angle.

3. The active stability control system based on aircraft engine stability margin estimation according to claim 2, characterized in that: In order to ensure that the intake flow meets the needs of the engine, the influence of the flight angle of attack and the angle of the ramp is comprehensively considered. The relationship between the intake flow and the engine flow is expressed as follows: Q j (θ,β)=Q f ; Substituting the relationship between the flight angle of attack, the angle of the inclined plate and the intake flow rate into the equation, we get: Q j0 ·f(β)·g(θ)=Q f ; By solving this equation, we can get the optimal inclined plate angle θ * : where g -1 It is the inverse function of the function g(θ); The inclined plate adjustment angle value θ is obtained by the following formula t :θ t =θ * -θ; The calculated inclined plate adjustment angle value θ t Sent to the aviation stabilization platform.

4. The active stability control system based on aircraft engine stability margin estimation according to claim 1, characterized in that: The specific process of the surge margin estimation module constructing the surge margin estimation model is as follows: Obtain historical surge margin estimation parameters, including flight angle of attack, compressor flow coefficient, engine speed, and compressor inlet total pressure, generate a collection period, and divide the collection period S into multiple collection periods {s1, s2, …, sn}, that is, S = {s1, s2, …, sn}; The flight angle of attack of the aircraft in multiple collection periods is obtained to construct a set A of the flight angle of attack, and the average of the difference between the maximum subset and the minimum subset in the set A is recorded as the flight angle of attack difference FGC; The compressor flow coefficient of the aircraft in multiple collection periods is obtained. The compressor flow coefficient represents the dimensionless ratio of the air mass flow through a certain section of the compressor per unit time to the area of ​​the section and the local sound speed. A set B of compressor flow coefficients is constructed based on this, and the average of the difference between the largest subset and the smallest subset in set B is recorded as the compressor flow coefficient difference YLC; Obtain the engine speed of the aircraft in multiple collection periods. The engine speed represents the number of complete rotations of the crankshaft or main shaft of the engine in one minute, thereby constructing a set C of engine speeds, and recording the average of the difference between the maximum subset and the minimum subset in the set C as the engine speed difference FZC; The compressor inlet total pressure of the aircraft in multiple collection periods is obtained. The compressor inlet total pressure represents the total pressure of the gas before entering the compressor. The set D of compressor inlet total pressures is constructed based on this, and the average of the difference between the maximum subset and the minimum subset in the set D is recorded as the compressor inlet total pressure difference value YYC.

5. The active stability control system based on aircraft engine stability margin estimation according to claim 4, characterized in that: The flight angle of attack difference FGC, the compressor flow coefficient difference YLC, the engine speed difference FZC and the compressor inlet total pressure difference YYC are obtained, and the flight angle of attack difference FGC, the compressor flow coefficient difference YLC, the engine speed difference FZC and the compressor inlet total pressure difference YYC are used to construct a feature matrix TJ, and the feature matrix TJ is used as the input of the machine learning model, and the surge margin corresponding to each set of feature matrices TJ is used as the output of the machine learning model. The surge margin is used as the estimation target, and the minimum sum of the estimation errors of all training data is used as the training target. The machine learning model is trained until the sum of the estimation errors reaches convergence and the training is stopped. The surge margin estimation model is obtained. The surge margin estimation model is expressed as follows: CY=γ0+γ1·FGJ+γ2·YLJ+γ3·FZJ+γ4·YYJ; Where CY is the estimated value of surge margin, γ0, γ1, γ2, γ3 and γ4 are regression coefficients; The real-time surge margin estimation parameters are obtained, converted into corresponding feature matrices and input into the surge margin estimation model. The real-time surge margin estimation value CY is calculated by the surge margin estimation model. 实时 , the calculated real-time surge margin estimate CY 实时 Sent to the aviation stabilization platform.

6. The active stability control system based on aircraft engine stability margin estimation according to claim 1, characterized in that: The specific process of the stall monitoring module monitoring and evaluating the engine stall risk is as follows: Obtain historical engine operating parameters and historical flight status parameters. The engine operating parameters include engine speed and compressor inlet total pressure. The flight status parameters include flight speed, flight angle of attack, and flight sideslip angle. Generate a monitoring cycle, divide the monitoring cycle into g consecutive sub-cycles, and mark the midpoint of each sub-cycle to obtain g midpoints. Taking g midpoint moments as the base point, expand forward and backward by equal time lengths, mark h-1 expansion moments, and then summarize the midpoint moments and h-1 expansion moments to obtain h detection moments; The engine speed values ​​at h detection moments are measured by the sensor respectively to obtain h detection engine speed values, and the h detection engine speed values ​​are accumulated and averaged to obtain g sub-engine speed values; The expression of the sub-engine speed value is: Where FZ zg is the sub-engine speed value of the g-th sub-cycle, FZ jcgn is the nth detected engine speed value in the gth sub-cycle; Remove the maximum and minimum sub-engine speed values, and add up the remaining g-2 sub-engine speed values ​​and calculate the average to obtain the engine speed mean; The expression of the mean engine speed is: Where FZ jz is the mean engine speed, FZ zo is the sub-engine speed value of the oth sub-cycle.

7. The active stability control system based on aircraft engine stability margin estimation according to claim 6, characterized in that: Using the method of calculating the mean engine speed, the mean compressor inlet total pressure YY can be obtained in the same way. jy , flight speed mean FS js , mean flight angle of attack FG jg And the mean side slip angle FH jh , the average engine speed FZ jz , Average value of total pressure at compressor inlet YY jy , flight speed mean FS js , mean flight angle of attack FG jg And the mean side slip angle FH jh Combine and construct the risk assessment feature matrix FP; The constructed risk assessment feature matrix FP is used as the input of the logistic regression model, and the label vector v is used as the output of the logistic regression model. The label vector v indicates whether the engine has a stall risk. The output of the label vector v is 0 or 1, 0 indicates that the engine has no stall risk, and 1 indicates that the engine has a stall risk. The label vector v is used as the prediction target, and the sum of the prediction errors of all training data is minimized as the training target. The logistic regression model is trained until the sum of the prediction errors converges, and the training is stopped to obtain a logistic regression model that predicts the label vector v.

8. According to the active stability control system based on aircraft engine stability margin estimation according to claim 7, the expression formula of the logistic regression model is: Where P(v=1) represents the probability value of engine stall, μ0 represents the intercept term, which represents the baseline probability of engine stall, and μ0, μ1, μ2, μ3, μ4 and μ5 are all regression coefficients; Obtain real-time engine operating parameters and real-time flight status parameters, process them and construct the risk assessment feature matrix FP 实时 , the probability value P of engine stall is calculated by the trained logistic regression model 实时 , the calculated probability value P of engine stall 实时 Sent to the aviation stabilization platform.

9. The active stability control system based on aircraft engine stability margin estimation according to claim 1, characterized in that: The specific process of the controller decision module performing a comprehensive evaluation on the engine operating status is as follows: Get the inclined plate adjustment angle value θ t , Real-time surge margin estimation value CY 实时 And the probability value P of engine stall 实时 , calculate the operating status assessment coefficient YZP by the following formula: Wherein b1, b2 and b3 are all preset proportional factor coefficients, b3>b2>b1>0, the operation state assessment coefficient YZP is compared with the preset first operation state assessment coefficient threshold and the preset second operation state assessment coefficient threshold, and the preset first operation state assessment coefficient threshold is less than the preset second operation state assessment coefficient threshold; If the operating state assessment coefficient is less than the preset first operating state assessment coefficient threshold, it indicates that the engine operation is in a low risk state; If the operating state assessment coefficient is greater than or equal to the preset first operating state assessment coefficient threshold, and the operating state assessment coefficient is less than the preset second operating state assessment coefficient threshold, it indicates that the engine operation is in a medium risk state; If the operating state assessment coefficient is greater than or equal to the preset second operating state assessment coefficient threshold, it indicates that the engine operation is in a high-risk state; Make corresponding control decisions based on the evaluation results of the engine operating status and send the control decisions to the protection execution module.

10. The active stability control system based on aircraft engine stability margin estimation according to claim 9, characterized in that: The specific process of the protection execution module executing the corresponding control measures is as follows: After receiving the control decision, the protection execution module immediately sends the control instruction to the corresponding execution agency, and the execution agency executes the corresponding control measures according to the control instruction. The specific contents of the control measures are as follows: If the control decision is to maintain the current state, there is no need to adjust the ramp angle, engine speed, or flight attitude; If the control decision is to make a slight adjustment, then the angle of the inclined plate is appropriately increased or decreased to optimize the intake conditions, the engine speed is appropriately increased or decreased to optimize the compressor working state, the flight angle of attack and sideslip angle are appropriately adjusted to improve the intake duct working conditions; If the control decision is to make an emergency adjustment, the ramp angle will be greatly increased, the intake flow will be increased, the compressor working condition will be improved, the engine speed will be greatly increased, the compressor flow will be increased, entering the stall area will be avoided, the flight angle of attack and sideslip angle will be greatly adjusted, the inlet working conditions will be improved, and the stall risk will be reduced.

Images