A method, apparatus, equipment and medium for extracting degradation factors from aero-engines

Abstract

This application discloses a method, apparatus, device, and medium for extracting degradation factors from aero-engines, relating to the field of aero-engine technology. The method establishes a linear guidance system for aero-engines based on engine characteristics. Building upon the traditional particle swarm optimization algorithm, it adds guidance awareness to the particles, proposing to use the linear guidance system to participate in particle velocity correction, thus solving the problem of degradation factor extraction easily getting trapped in local optima and achieving accurate output of degradation factors for rotating components. Compared to existing technologies, this application fully utilizes the multidimensional characteristics of aero-engine degradation problems, simplifying the influence of degradation factors on multidimensional output into a linear influence matrix, and directly using the multidimensional deviation vector multiplied by the matrix to construct guidance awareness. This significantly improves the extraction accuracy of aero-engine degradation factors while having low overall computational cost, requiring no complex calculations or judgments, and ensuring the extraction rate and adaptability of degradation factors.

Description

Technical Field

[0001] This application relates to the field of aero-engine technology, and in particular to a method, apparatus, equipment and medium for extracting aero-engine degradation factors. Background Technology

[0002] High-precision extraction of degradation factors in aero-engines is crucial for ensuring flight safety, enabling predictive maintenance, and reducing operating costs. By quantifying the performance degradation of key components (such as reduced compressor efficiency and turbine wear), potential faults can be predicted in advance, and maintenance strategies can be optimized, thereby avoiding sudden failures, extending component lifespan, and reducing unnecessary disassembly and inspection. In aero-engines, degradation factors are key indicators used to quantify the degree of performance degradation, reflecting the irreversible decline in performance parameters (such as efficiency, thrust, and aerodynamic stability) of critical engine components (such as compressors and turbines) due to wear, corrosion, and fouling.

[0003] The extraction of degradation factors for aero-engines is essentially a multi-objective optimization problem. It aims to inversely infer the degree of performance degradation (performance decline or functional deterioration) of key internal components of the engine (such as compressors, turbines, combustion chambers, etc.) by using sensor data and engine models.

[0004] Existing methods for extracting degradation factors from aero-engines suffer from limitations such as high computational complexity, high parameter sensitivity, and strong subjectivity in fuzzy weights, making them ill-suited to the multidimensional dynamic nonlinear characteristics exhibited during engine degradation. Meanwhile, while optimization methods based on chaos theory improve global search capabilities, they are highly dependent on model accuracy (e.g., CFD models) and lack adaptability to handling dynamic changes in engine operating conditions. These factors restrict the real-time performance and accuracy of degradation factor extraction, impacting the effectiveness of engine fault prediction and maintenance optimization. Therefore, there is an urgent need to develop more efficient and adaptable degradation factor extraction techniques. Summary of the Invention

[0005] This application provides a method for extracting degradation factors from aero-engines, which addresses the technical problems of poor real-time performance, accuracy, and adaptability in existing aero-engine degradation factor extraction technologies.

[0006] This application is achieved through the following solution:

[0007] A method for extracting degradation factors from an aero-engine, comprising the following steps:

[0008] S1. Based on flight data and component-level models, construct a linear influence matrix of engine degradation factors;

[0009] S2, randomly initialize particle population, initialize particle motion inertia, individual consciousness, group consciousness, and guide consciousness, and evaluate the speed and position of each particle to obtain the initial global optimum;

[0010] S3, establish a linear aero-engine guide based on engine characteristics, add guide consciousness calculation on the basis of particle motion inertia, individual consciousness, and group consciousness of the traditional particle swarm algorithm, superimpose the speed and position of each particle, then calculate the output deviation vector and evaluate the function fitness value of each particle;

[0011] S4, update the guide weight coefficient according to the current fitness of the particle, and then calculate the particle guide consciousness according to the linear influence matrix, the output deviation vector, and the guide consciousness weight coefficient;

[0012] S5, update the historical optimal position of each particle based on the function fitness value of each particle, and then update the global optimal position of the group;

[0013] S6, verify whether the global optimal position of the group meets the end condition, if not, continue iteration until the end condition is met and exit.

[0014] Further, the step S1 specifically comprises the steps of:

[0015] S11, respectively disturb the flow and efficiency degradation factors of each rotating component of the engine model, and record the changes of each state quantity after single degradation factor disturbance;

[0016] S12, construct an engine degradation factor linear influence matrix α :

[0017]

[0018] In the formula, Δ η i is the disturbance amount of the first i engine degradation factor, Δ x ji is the first i degradation factor, and the first j engine state quantity change.

[0019] Further, the step S3 has the steps of:

[0020] S31, respectively calculate the particle motion inertia m , individual consciousness k , group consciousness , and guide consciousness of the first particle in the first iteration:

[0021]

[0022] where, w is the inertia weight, controlling the proportion of the original velocity to be reserved, v is the particle velocity; c 1 and c 2 are the individual learning factor constant and the group learning factor constant, respectively; r 1, r 2 is a random number, which is introduced to avoid the algorithm from falling into local optimum; p md and g d are the individual historical optimal position and the group historical optimal position, respectively; x is the current position of the particle; c 3 is the weight coefficient of the guide of the aero-engine, which changes with the fitness value and is used to make the order of magnitude of the guide consciousness consistent with the other three; γ is the degeneration factor adjustment amount, which is related to the linear influence matrix α and the bias vector β ;

[0023] S32, the calculated particle motion inertia, individual consciousness, group consciousness, and guide consciousness are superimposed to obtain the velocity and position of each particle, respectively:

[0024]

[0025] where, is the velocity obtained by the m th particle in the k th iteration, is the position obtained by the m th particle in the k th iteration;

[0026] S33, the position of each particle is taken as the degeneration factor, which is substituted into the component-level model for calculation, and the absolute error of the m th particle is obtained by comparing with the sensor data:

[0027]

[0028] where, e j is the absolute error of the j th state variable; n is the sample number, and the absolute error average of n samples is taken as the absolute error in the case of equivalent degeneration level;

[0029] S34, the fitness value is calculated according to the bias vectorf m :

[0030]

[0031] In the formula, a mj It is the first m The first particle j The weighting coefficients of each state variable e mj It is the first m The first particle j The absolute error of each state variable.

[0032] Furthermore, step S4 specifically includes the following steps:

[0033] S41. Calculate the order-of-magnitude adjustment based on the particle velocity. r m :

[0034]

[0035] In the formula, r m It is the first m The adjustment factor is on the order of magnitude of the number of particles, where maxAcc is the maximum particle velocity. α It is a linear influence matrix. β The deviation vector;

[0036] S42. Adjust the amount according to the order of magnitude. r m Particle fitness value f m Update the guide weight coefficient of the aircraft engine c 3:

[0037]

[0038] In the formula, k 1. b , f 1. f 2 is a non-zero constant; when f m < f At 1 o'clock, cancel the aircraft engine guide; when f 1< f m < f 2. The guide weight coefficient changes with the fitness value; when f m > f At time 2, the guide weight coefficient is a non-zero constant;

[0039] S43. Based on the linear influence matrix α Deviation vector β Updated Guide Awareness Weighting Coefficient c 3. Recalculate the guide's awareness v 4:

[0040] v 4= c 3× α × β .

[0041] This application also provides an apparatus for extracting degradation factors from aircraft engines, comprising:

[0042] The linear influence matrix construction module is used to construct the linear influence matrix of engine degradation factors based on flight data and component-level models.

[0043] The initial global optimum evaluation module is used to randomly initialize the particle population, initialize the particle motion inertia, individual consciousness, group consciousness, and guide consciousness, and evaluate the velocity and position of each particle to obtain the initial global optimum.

[0044] The function fitness value calculation module is used to establish a linear aero-engine guide based on engine characteristics. On the basis of particle motion inertia, individual consciousness and group consciousness in the traditional particle swarm algorithm, the guide consciousness calculation is added. The velocity and position of each particle are obtained by superposition, and then the output deviation vector is calculated and the function fitness value of each particle is evaluated.

[0045] The guide consciousness calculation module is used to update and calculate the guide weight coefficient based on the particle's current fitness, and then calculate the particle's guide consciousness based on the linear influence matrix, the output deviation vector, and the guide consciousness weight coefficient.

[0046] The optimal position update module is used to update the historical optimal position of each particle based on the function fitness value of each particle, and then update the global optimal position of the population.

[0047] The iterative verification module is used to verify whether the global optimal position of the population meets the termination condition. If it does not meet the condition, the iteration continues until the termination condition is met and the module exits.

[0048] Furthermore, the linear influence matrix construction module specifically includes:

[0049] The state quantity recording module is used to perturb the flow rate and efficiency degradation factor of each rotating part of the engine model, and record the changes of each state quantity after a single degradation factor perturbation.

[0050] The matrix construction module is used to construct the linear influence matrix of engine degradation factors. α :

[0051]

[0052] In the formula, Δ η i For the engine i The perturbation of each degradation factor, Δ x ji For the disturbance i The first degradation factor, the... j Changes in engine state.

[0053] Furthermore, the function fitness value calculation module includes:

[0054] The integrated calculation module is used to calculate the first... m The first particle k Particle motion inertia in the next iteration Individual consciousness Group consciousness Guide awareness :

[0055]

[0056] In the formula, w It is the inertial weight, which controls the proportion of the original velocity that is retained. v It is the particle velocity; c 1 and c 2 represents the individual learning factor constant and the group learning factor constant, respectively; r 1. r 2 is a random number, introducing randomness to prevent the algorithm from getting trapped in local optima; p md and g d These are the individual particle's historical best position and the group's historical best position, respectively. x It is the particle's current position; c 3 is the guide weight coefficient for aero-engines, which changes with the fitness value of the function and is used to keep the order of magnitude of the guide consciousness consistent with the other three items; γ It is the degradation factor moderating factor, and the linear influence matrix. α Sum of deviation vectors β related;

[0057] The velocity and position calculation module is used to superimpose the calculated particle motion inertia, individual consciousness, group consciousness, and guide consciousness to obtain the velocity and position of each particle.

[0058]

[0059] In the formula, It is the first mParticle iteration k The speed obtained this time, It is the first m Particle iteration k The position obtained next;

[0060] The deviation vector calculation module is used to take the position of each particle as a degradation factor, substitute it into the component-level model for calculation, and compare it with the sensor data to obtain the first deviation vector. m The deviation vector of each particle :

[0061]

[0062] In the formula, e j It is the first j The absolute error of each state quantity; n It is the sample size, taken under the condition of comparable degradation levels. n The average absolute error of each sample is taken as the absolute error;

[0063] The fitness value calculation module is used to calculate the fitness value based on the bias vector. f m :

[0064]

[0065] In the formula, a mj It is the first m The first particle j The weighting coefficients of each state variable e mj It is the first m The first particle j The absolute error of each state variable.

[0066] Furthermore, the guide awareness calculation module specifically includes:

[0067] The order-of-magnitude adjustment calculation module is used to calculate the order-of-magnitude adjustment based on the particle velocity. r m :

[0068]

[0069] In the formula, r m It is the first m The adjustment factor is on the order of magnitude of the number of particles, where maxAcc is the maximum particle velocity. α It is a linear influence matrix. β The deviation vector;

[0070] The wizard-driven weight coefficient update module is used to adjust the amount based on the order of magnitude.r m Particle fitness value f m Update the guide weight coefficient of the aircraft engine c 3:

[0071]

[0072] In the formula, k 1. b , f 1. f 2 is a non-zero constant; when f m < f At 1 o'clock, cancel the aircraft engine guide; when f 1< f m < f 2. The guide weight coefficient changes with the fitness value; when f m > f At time 2, the guide weight coefficient is a non-zero constant;

[0073] The guide awareness update module is used to update the linear influence matrix. α Deviation vector β Updated Guide Awareness Weighting Coefficient c 3. Recalculate the guide's awareness v 4:

[0074] v 4= c 3× α × β .

[0075] This application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the aero-engine degradation factor extraction method.

[0076] This application also provides a storage medium including a stored program that, when the program is executed, controls the device where the storage medium is located to perform the steps of the aero-engine degradation factor extraction method.

[0077] Compared with the prior art, this application has the following advantages:

[0078] This application proposes a method for extracting degradation factors from aero-engines. This method establishes a linear aero-engine guide based on engine characteristics. Building upon the traditional particle swarm optimization algorithm's considerations of particle motion inertia, individual consciousness, and collective consciousness, it adds a guide consciousness based on engine characteristics. Innovatively, it proposes using a linear guide system to modify particle velocity, solving the problem of degradation factor extraction easily getting trapped in local optima, and achieving accurate output of degradation factors for rotating components. Because the proposed linear aero-engine guide is linear, and linear guides have low computational cost, requiring no complex calculations or judgments, it can guarantee the degradation factor extraction rate. Compared with traditional methods, the degradation factor extraction method of this application not only significantly improves the accuracy and computational efficiency of degradation factor extraction but also has excellent stability and adaptability, and can be widely applied to the performance degradation assessment and life prediction of rotating components in aero-engines, gas turbines, and other systems.

[0079] In addition to the purposes, features, and advantages described above, this application has other purposes, features, and advantages. A further detailed description of this application will be provided below with reference to the figures. Attached Figure Description

[0080] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0081] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort, wherein:

[0082] Figure 1 This is a flowchart illustrating the preferred embodiment of the aero-engine degradation factor extraction method of this application;

[0083] Figure 2 This is a flowchart illustrating another preferred embodiment of the method for extracting degradation factors from an aero-engine.

[0084] Figure 3 This is a schematic diagram of the aircraft engine degradation factor extraction device module according to a preferred embodiment of this application;

[0085] Figure 4 This is a schematic diagram of a submodule of the linear influence matrix construction module in a preferred embodiment of this application;

[0086] Figure 5 This is a schematic diagram of a submodule of the function fitness value calculation module in a preferred embodiment of this application;

[0087] Figure 6This is a schematic diagram of a submodule of the guide awareness calculation module in a preferred embodiment of this application;

[0088] Figure 7 This is a schematic block diagram of an electronic device according to a preferred embodiment of this application;

[0089] Figure 8 This is an internal structural diagram of a computer device according to a preferred embodiment of this application. Detailed Implementation

[0090] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0091] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0092] It should be noted that the executing entity in this embodiment can be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, or mobile phone, or an aircraft engine degradation factor extraction device capable of performing the above functions. The following description uses an aircraft engine degradation factor extraction device as the executing entity to illustrate this embodiment and the subsequent embodiments.

[0093] like Figure 1 As shown, a preferred embodiment of this application provides a method for extracting degradation factors from an aero-engine, including the following steps:

[0094] S1. Based on flight data and component-level models, construct a linear influence matrix of engine degradation factors;

[0095] S2. Randomly initialize the particle population, initialize the particle motion inertia, individual consciousness, group consciousness, and guide consciousness, and evaluate the speed and position of each particle to obtain the initial global optimum;

[0096] S3. Based on engine characteristics, establish a linear aero-engine guide. On the basis of particle motion inertia, individual consciousness and group consciousness in the traditional particle swarm algorithm, add guide consciousness calculation, superimpose to obtain the velocity and position of each particle, then calculate the output deviation vector and evaluate the function fitness value of each particle.

[0097] S4. Calculate the guide weight coefficient based on the particle's current fitness, and then calculate the particle's guide consciousness based on the linear influence matrix, output deviation vector, and guide consciousness weight coefficient.

[0098] S5. Based on the function fitness value of each particle, update the historical best position of each particle, and then update the global best position of the population.

[0099] S6. Verify whether the global optimal position of the population satisfies the termination condition. If not, continue iterating until the termination condition is met and exit.

[0100] This embodiment proposes a method for extracting degradation factors from aero-engines. This method establishes a linear aero-engine guide based on engine characteristics. Building upon the traditional particle swarm optimization algorithm's considerations of particle motion inertia, individual consciousness, and collective consciousness, it adds a guide consciousness based on engine characteristics. Innovatively, it proposes using a linear guide system to modify particle velocity, solving the problem of degradation factor extraction easily getting trapped in local optima, and achieving accurate output of degradation factors for rotating components. Because the proposed linear aero-engine guide is linear, and linear guides have low computational cost, requiring no complex calculations or judgments, it can guarantee the degradation factor extraction rate. Compared with traditional methods, the degradation factor extraction method of this embodiment not only significantly improves the accuracy and computational efficiency of degradation factor extraction but also has excellent stability and adaptability, and can be widely applied to the performance degradation assessment and life prediction of rotating components in aero-engines, gas turbines, and other systems.

[0101] Preferably, step S1 specifically includes the following steps:

[0102] S11. Perturb the flow rate and efficiency degradation factor of each rotating component of the engine model respectively, and record the changes of each state quantity after the single degradation factor perturbation.

[0103] S12. Construct the linear influence matrix of engine degradation factors. α :

[0104]

[0105] In the formula, Δ η i For the engine i The perturbation of each degradation factor, Δ x ji For the disturbance i The first degradation factor, the... j Changes in engine state.

[0106] In this embodiment, steps S11-S12 construct the linear influence matrix of the engine degradation factor by perturbing the flow rate and efficiency degradation factor of each rotating component of the engine model and then changing the state variables. The advantages include directly quantifying the sensitivity of the unit degradation factor to a specific state variable, establishing a direct mapping relationship between the degradation factor and the state variable, providing a physically interpretable mathematical basis for the subsequent reverse extraction of the degradation factor, and realizing linear dimensionality reduction of complex nonlinear systems.

[0107] Preferably, step S3 includes the following steps:

[0108] S31, calculate the first one respectively m The first particle k Particle motion inertia in the next iteration Individual consciousness Group consciousness Guide awareness :

[0109]

[0110] In the formula, w It is the inertial weight, which controls the proportion of the original velocity that is retained. v It is the particle velocity; c 1 and c 2 represents the individual learning factor constant and the group learning factor constant, respectively; r 1. r 2 is a random number, introducing randomness to prevent the algorithm from getting trapped in local optima; p md and g d These are the individual particle's historical best position and the group's historical best position, respectively. x It is the particle's current position; c 3 is the guide weight coefficient for aero-engines, which changes with the fitness value of the function and is used to keep the order of magnitude of the guide consciousness consistent with the other three items; γ It is the degradation factor moderating factor, and the linear influence matrix. α Sum of deviation vectors β related;

[0111] S32. Superimpose the calculated particle inertia, individual consciousness, group consciousness, and guide consciousness to obtain the velocity and position of each particle:

[0112]

[0113] In the formula, It is the first m Particle iteration k The speed obtained this time, It is the first m Particle iteration k The position obtained next;

[0114] S33. Using the position of each particle as a degradation factor, substituting it into the component-level model for calculation, and comparing it with the sensor data to obtain the first... m The deviation vector of each particle :

[0115]

[0116] In the formula, e jIt is the first j The absolute error of each state quantity; n It is the sample size, taken under the condition of comparable degradation levels. n The average absolute error of each sample is taken as the absolute error;

[0117] S34. Calculate the fitness value based on the deviation vector. f m :

[0118]

[0119] In the formula, a mj It is the first m The first particle j The weighting coefficients of each state variable e mj It is the first m The first particle j The absolute error of each state variable.

[0120] This embodiment calculates the particle motion inertia, individual consciousness, group consciousness, and guide consciousness by superimposing them in steps S31-S34. After obtaining the velocity and position of each particle, the position is used as a degradation factor and substituted into the component-level model to calculate the deviation vector. Finally, the fitness value is calculated based on the deviation vector. Its advantages include: directly mapping the particle position to the candidate degradation factor and comparing it with the actual sensor data in the component-level model, ensuring that each particle optimization is based on the actual physical laws of engine operation, solving the problem that the optimization direction of traditional algorithms is divorced from engineering reality; and by guiding the particles to focus in the direction of minimizing deviation through guide consciousness, and combining the deviation vector for comprehensive evaluation of multiple state quantities, the number of algorithm iterations can be reduced.

[0121] Preferably, step S4 specifically includes the following steps:

[0122] S41. Calculate the order-of-magnitude adjustment based on the particle velocity. r m :

[0123]

[0124] In the formula, r m It is the first m The adjustment factor is on the order of magnitude of the number of particles, where maxAcc is the maximum particle velocity. α It is a linear influence matrix. β The deviation vector;

[0125] S42. Adjust the amount according to the order of magnitude. r m Particle fitness value fm Update the guide weight coefficient of the aircraft engine c 3:

[0126]

[0127] In the formula, k 1. b , f 1. f 2 is a non-zero constant; when f m < f At 1 o'clock, cancel the aircraft engine guide; when f 1< f m < f 2. The guide weight coefficient changes with the fitness value; when f m > f At time 2, the guide weight coefficient is a non-zero constant;

[0128] S43. Based on the linear influence matrix α Deviation vector β Updated Guide Awareness Weighting Coefficient c 3. Recalculate the guide's awareness v 4:

[0129] v 4= c 3× α × β .

[0130] In this embodiment, after first calculating the order-of-magnitude adjustment amount in steps S41-S43, the adjustment amount is then... r m Particle fitness value f m Update the guide weight coefficients of the aero-engine, and finally based on the linear influence matrix. α Deviation vector β Updated Guide Awareness Weighting Coefficient c 3. Recalculating the guide consciousness for iterative updates has the following advantages: by adjusting the magnitude, it can ensure that the guide consciousness is consistent with the magnitude of inertial consciousness, individual consciousness, and group consciousness, avoiding the excessive dominance of a certain consciousness item in the optimization process; it can also achieve adaptive adjustment of the guide weight coefficient and intelligently switch strategies at different search stages; at the same time, by using matrix multiplication, the deviation of multiple state variables is compressed into a degradation factor correction direction vector, which can ensure that the guide consciousness accurately points to the true value of the degradation factor.

[0131] Preferably, such as Figure 2As shown, another preferred embodiment of this application provides a method for extracting degradation factors of aero-engines. This method establishes a linear guide matrix for aero-engines and uses the aero-engine guide matrix to assist particle swarm optimization in finding the optimal solution. This solves the problem that traditional particle swarm optimization is prone to getting trapped in local optima when extracting degradation factors, and achieves accurate output of degradation factors of rotating parts and obtains the variation law of degradation factors.

[0132] Preferably, such as Figure 3 As shown, this application also provides an apparatus for extracting degradation factors from an aircraft engine, comprising:

[0133] The linear influence matrix construction module is used to construct the linear influence matrix of engine degradation factors based on flight data and component-level models.

[0134] The initial global optimum evaluation module is used to randomly initialize the particle population, initialize the particle motion inertia, individual consciousness, group consciousness, and guide consciousness, and evaluate the velocity and position of each particle to obtain the initial global optimum.

[0135] The function fitness value calculation module is used to establish a linear aero-engine guide based on engine characteristics. On the basis of particle motion inertia, individual consciousness and group consciousness in the traditional particle swarm algorithm, the guide consciousness calculation is added. The velocity and position of each particle are obtained by superposition, and then the output deviation vector is calculated and the function fitness value of each particle is evaluated.

[0136] The guide consciousness calculation module is used to update and calculate the guide weight coefficient based on the particle's current fitness, and then calculate the particle's guide consciousness based on the linear influence matrix, the output deviation vector, and the guide consciousness weight coefficient.

[0137] The optimal position update module is used to update the historical optimal position of each particle based on the function fitness value of each particle, and then update the global optimal position of the population.

[0138] The iterative verification module is used to verify whether the global optimal position of the population meets the termination condition. If it does not meet the condition, the iteration continues until the termination condition is met and the module exits.

[0139] The aero-engine degradation factor extraction device provided in this embodiment adopts the aero-engine degradation factor extraction method in the above embodiments, solving the technical problems of poor real-time performance, accuracy, and adaptability of existing aero-engine degradation factor extraction technologies. Compared with the prior art, the beneficial effects of the aero-engine degradation factor extraction device provided in this application are the same as those of the aero-engine degradation factor extraction method provided in the above embodiments, and other technical features in the aero-engine degradation factor extraction device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0140] Preferably, such as Figure 4 As shown, the linear influence matrix construction module specifically includes:

[0141] The state quantity recording module is used to perturb the flow rate and efficiency degradation factor of each rotating part of the engine model, and record the changes of each state quantity after a single degradation factor perturbation.

[0142] The matrix construction module is used to construct the linear influence matrix of engine degradation factors. α :

[0143]

[0144] In the formula, Δ η i For the engine i The perturbation of each degradation factor, Δ x ji For the disturbance i The first degradation factor, the... j Changes in engine state.

[0145] Preferably, such as Figure 5 As shown, the function fitness value calculation module includes:

[0146] The integrated calculation module is used to calculate the first... m The first particle k Particle motion inertia in the next iteration Individual consciousness Group consciousness Guide awareness :

[0147]

[0148] In the formula, w It is the inertial weight, which controls the proportion of the original velocity that is retained. v It is the particle velocity; c 1 and c 2 represents the individual learning factor constant and the group learning factor constant, respectively; r 1. r 2 is a random number, introducing randomness to prevent the algorithm from getting trapped in local optima; p md and g d These are the individual particle's historical best position and the group's historical best position, respectively. x It is the particle's current position; c 3 is the guide weight coefficient for aero-engines, which changes with the fitness value of the function and is used to keep the order of magnitude of the guide consciousness consistent with the other three items; γIt is the degradation factor moderating factor, and the linear influence matrix. α Sum of deviation vectors β related;

[0149] The velocity and position calculation module is used to superimpose the calculated particle motion inertia, individual consciousness, group consciousness, and guide consciousness to obtain the velocity and position of each particle.

[0150]

[0151] In the formula, It is the first m Particle iteration k The speed obtained this time, It is the first m Particle iteration k The position obtained next;

[0152] The deviation vector calculation module is used to take the position of each particle as a degradation factor, substitute it into the component-level model for calculation, and compare it with the sensor data to obtain the first deviation vector. m The deviation vector of each particle :

[0153]

[0154] In the formula, e j It is the first j The absolute error of each state quantity; n It is the sample size, taken under the condition of comparable degradation levels. n The average absolute error of each sample is taken as the absolute error;

[0155] The fitness value calculation module is used to calculate the fitness value based on the bias vector. f m :

[0156]

[0157] In the formula, a mj It is the first m The first particle j The weighting coefficients of each state variable e mj It is the first m The first particle j The absolute error of each state variable.

[0158] Preferably, such as Figure 6 As shown, the guide consciousness calculation module specifically includes:

[0159] The order-of-magnitude adjustment calculation module is used to calculate the order-of-magnitude adjustment based on the particle velocity.r m :

[0160]

[0161] In the formula, r m It is the first m The adjustment factor is on the order of magnitude of the number of particles, where maxAcc is the maximum particle velocity. α It is a linear influence matrix. β The deviation vector;

[0162] The wizard-driven weight coefficient update module is used to adjust the amount based on the order of magnitude. r m Particle fitness value f m Update the guide weight coefficient of the aircraft engine c 3:

[0163]

[0164] In the formula, k 1. b , f 1. f 2 is a non-zero constant; when f m < f At 1 o'clock, cancel the aircraft engine guide; when f 1< f m < f 2. The guide weight coefficient changes with the fitness value; when f m > f At time 2, the guide weight coefficient is a non-zero constant;

[0165] The guide awareness update module is used to update the linear influence matrix. α Deviation vector β Updated Guide Awareness Weighting Coefficient c 3. Recalculate the guide's awareness v 4:

[0166] v 4= c 3× α × β .

[0167] like Figure 7 As shown, a preferred embodiment of this application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the aero-engine degradation factor extraction method in the above embodiments.

[0168] This application provides an electronic device that employs the aircraft engine degradation factor extraction method described in the above embodiments, solving the technical problems of poor real-time performance, accuracy, and adaptability in existing aircraft engine degradation factor extraction technologies. Compared with the prior art, the beneficial effects of the electronic device provided in this application are the same as those of the aircraft engine degradation factor extraction method provided in the above embodiments, and other technical features of the electronic device are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0169] like Figure 8 As shown, a preferred embodiment of this application also provides a computer device, which may be a terminal or a liveness detection server, and its internal structure diagram may be as follows. Figure 8 As shown. The computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with other external computer devices via a network connection. When the computer program is executed by the processor, it implements the steps of the aforementioned aero-engine degradation factor extraction method.

[0170] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0171] The computer equipment provided in this application employs the aircraft engine degradation factor extraction method described in the above embodiments, solving the technical problems of poor real-time performance, accuracy, and adaptability of existing aircraft engine degradation factor extraction technologies. Compared with the prior art, the beneficial effects of the computer equipment provided in this application are the same as those of the aircraft engine degradation factor extraction method provided in the above embodiments, and other technical features in the electronic equipment are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0172] A preferred embodiment of this application also provides a storage medium, the storage medium including a stored program, which, when the program is executed, controls the device where the storage medium is located to perform the steps of the aero-engine degradation factor extraction method in the above embodiments.

[0173] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0174] If the functions described in this embodiment are implemented as software functional units and sold or used as independent products, they can be stored in one or more computing device-readable storage media. Based on this understanding, the parts of this application's embodiments that contribute to the prior art or the technical solutions can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a computing device (which may be a personal computer, server, mobile computing device, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage media include: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0175] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of this application can be implemented in various computer languages, such as the object-oriented programming language C++ and the embedded programming language C.

[0176] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0177] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0178] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0179] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described method for extracting aero-engine degradation factors.

[0180] The computer program product provided in this application solves the technical problems of poor real-time performance, accuracy, and adaptability in existing aero-engine degradation factor extraction technologies. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the aero-engine degradation factor extraction method provided in the above embodiments, and will not be repeated here.

[0181] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0182] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. An aeroengine degradation factor extraction method, characterized by, The method comprises the steps of: S1, constructing an engine degradation factor linear influence matrix according to flight data and component-level models; S2, randomly initializing a particle population, initializing particle motion inertia, individual consciousness, group consciousness, and guide consciousness, and evaluating the speed and position of each particle to obtain an initial global optimum; S3, establishing a linear aircraft engine guide based on engine characteristics, adding guide consciousness calculation on the basis of particle motion inertia, individual consciousness, and group consciousness of the traditional particle swarm algorithm, superimposing the speed and position of each particle, then calculating an output deviation vector and evaluating the function fitness value of each particle, specifically comprising the steps of: S31, respectively calculate the first m particle motion inertia of the first k iteration of the particle , individual awareness , group awareness , guide awareness : ； wherein w is an inertial weight that controls the proportion of the original velocity that is preserved, v is the particle velocity; c 1 and c 2 are individual learning factor constant, group learning factor constant, respectively; r 1, r 2 is a random number, which introduces randomness to avoid the algorithm falling into local optimum; p md and g d are the individual historical optimal position of the particle, the group historical optimal position, respectively; x is the current position of the particle; c 3 is the weight coefficient of the aircraft engine guide, which changes with the fitness value of the function, and at the same time is used to make the order of magnitude of the guide consistent with the remaining three; γ is the degeneration factor adjustment quantity, which is related to the linear influence matrix α and the bias vector β ; S32, superimposing the calculated particle motion inertia, individual consciousness, group consciousness, and guide consciousness to obtain the speed and position of each particle respectively: ； In the formula, It is the first m Particle iteration k The speed obtained this time, It is the first m Particle iteration k The position obtained next; S33, the position of each particle is taken as a degradation factor, substituted into the component-level model for calculation, and compared with the sensor data to obtain the deviation vector of the m individual particle : ； In the formula, e j is the absolute error of the first j state quantity; n is the number of samples, and the absolute error of n samples is averaged to obtain the absolute error in the case of equivalent degradation levels. S34, calculating a fitness value from the deviation vector f m : ； In the formula, a mj It is the first m The first particle j The weighting coefficients of each state variable e mj It is the first m The first particle j The absolute error of each state quantity; S4, updating the guide weight coefficient according to the current fitness of the particle, and then calculating the guide consciousness of the particle according to the linear influence matrix, the output deviation vector, and the guide consciousness weight coefficient; S5, updating the historical optimal position of each particle based on the function fitness value of each particle, and then updating the global optimal position of the group; S6, verifying whether the global optimal position of the group meets the end condition, if not, continuing iteration until the end condition is met and exiting.

2. The aeroengine degradation factor extraction method of claim 1, wherein, The step S1 specifically comprises the steps of: S11, respectively perturbing the flow and efficiency degradation factors of each rotating component of the engine model, and recording the changes of each state quantity after perturbation of a single degradation factor; S12, constructing an engine degradation factor linear influence matrix α : ； where Δ η i is the first i degeneracy factor perturbation, Δ x ji is the first i degeneracy factor, and the first j engine state change.

3. The aeroengine degradation factor extraction method of claim 2, wherein, The step S4 specifically comprises the steps of: S41、According to the velocity of the particle, the magnitude adjustment amount is calculated r m : ； In the formula, r m It is the first m The adjustment factor is on the order of magnitude of the number of particles, where maxAcc is the maximum particle velocity. α It is a linear influence matrix. β The deviation vector; S42, adjusting the order of magnitude according to the adjustment amount r m particle fitness value f m updating a guide weight coefficient of an aeroengine c 3: ； wherein k 1, b , f 1, f 2 is a constant other than zero; when f m f 1, the aircraft engine is disengaged; when f 1 f m f 2, the guide weight coefficient varies with the fitness value; when f m f 2, the guide weight coefficient is a constant other than zero;​​​ S43, according to the linear influence matrix α , bias vector β , updated guide awareness weight coefficient c 3 Recalculate guide awareness v 4: v 4= c 3× α × β 。 4. An aeroengine degradation factor extraction apparatus, characterised by, including: a linear influence matrix construction module, configured to construct an engine degradation factor linear influence matrix according to flight data and component-level models; an initial global optimum evaluation module, configured to randomly initialize a particle population, initialize particle motion inertia, individual consciousness, group consciousness, and guide consciousness, and evaluate the speed and position of each particle to obtain an initial global optimum; a function fitness value calculation module, configured to establish a linear aircraft engine guide based on engine characteristics, add guide consciousness calculation on the basis of particle motion inertia, individual consciousness, and group consciousness of the traditional particle swarm algorithm, superimpose the speed and position of each particle, then calculate an output deviation vector and evaluate the function fitness value of each particle, the function fitness value calculation module having: The integrated calculation module is used to calculate the first... m The first particle k Particle motion inertia in the next iteration Individual consciousness Group consciousness Guide awareness : ； wherein, w is the inertia weight, controlling the retention proportion of the original velocity, v is the particle velocity; c 1 and c 2 are respectively the individual learning factor constant and the group learning factor constant; r 1, r 2 is a random number, introducing randomness to avoid the algorithm from falling into local optimum; p md and g d are respectively the particle individual historical optimal position and the group historical optimal position; x is the current position of the particle; c 3 is the weight coefficient of the aero-engine guide, which changes with the fitness value of the function and is used to make the order of magnitude of the guide awareness consistent with the remaining three; γ is the degradation factor adjustment amount, which is related to the linear influence matrix α and the bias vector β ; a speed and position calculation module, configured to superimpose the calculated particle motion inertia, individual consciousness, group consciousness, and guide consciousness to obtain the speed and position of each particle respectively: ； In the formula, It is the first m Particle iteration k The speed obtained this time, It is the first m Particle iteration k The position obtained next; a bias vector calculation module for calculating a bias vector of each particle by substituting the position of each particle as a degeneration factor into the component level model and comparing the sensor data to obtain the bias vector of the particle m :​ ； In the formula, e j is the absolute error of the first j state variable; n is the number of samples, and the absolute error of n samples is averaged to obtain the absolute error in the case of equivalent degradation levels. a fitness value calculation module configured to calculate a fitness value based on the deviation vector f m : ； In the formula, a mj It is the first m The first particle j The weighting coefficients of each state variable e mj It is the first m The first particle j The absolute error of each state quantity; a guide consciousness calculation module, configured to update the guide weight coefficient according to the current fitness of the particle, and then calculate the guide consciousness of the particle according to the linear influence matrix, the output deviation vector, and the guide consciousness weight coefficient; an optimal position updating module, configured to update the historical optimal position of each particle based on the function fitness value of each particle, and then update the global optimal position of the group; an iteration verification module, configured to verify whether the global optimal position of the group meets the end condition, if not, continuing iteration until the end condition is met and exiting.

5. The aircraft engine degradation factor extraction apparatus of claim 4, wherein, The linear influence matrix construction module specifically comprises: The state quantity recording module is configured to respectively disturb the flow and the efficiency degradation factor of each rotating component of the engine model, and record the change of each state quantity after the disturbance of a single degradation factor. a matrix construction module for constructing a linear influence matrix of engine degradation factors α : ； where Δ η i is the first i degeneracy factor perturbation, Δ x ji is the first i degeneracy factor, and the first j engine state change.

6. The aircraft engine degradation factor extraction apparatus of claim 4, wherein, The guide awareness calculation module specifically comprises: An order of magnitude adjustment amount calculation module is configured to calculate an order of magnitude adjustment amount based on the velocity of the particle r m : ； In the formula, r m It is the first m The adjustment factor is on the order of magnitude of the number of particles, where maxAcc is the maximum particle velocity. α It is a linear influence matrix. β The deviation vector; The guide weight coefficient updating module is configured to adjust the guide weight coefficient according to the order of magnitude adjustment amount r m , particle fitness value f m Updating the guide weight coefficient of an aero-engine c 3: ； wherein k 1、 b 、 f 1、 f 2 is a constant other than 0; when f m < f 1, the aircraft engine is guided; when f 1 f m < f 2, the guide weight coefficient changes with the fitness value; when f m > f 2, the guide weight coefficient is a constant other than 0; a guide awareness updating module, configured to update the guide awareness weight coefficient according to a linear influence matrix α , a bias vector β , an updated guide awareness weight coefficient c 3 recalculate guide awareness v 4: v 4= c 3× α × β 。 7. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor, when executing the computer program, implements the steps of the method for extracting the degradation factor of the aero-engine according to any one of claims 1 to 3.

8. A storage medium, the storage medium comprising a stored program, characterized in that The device in which the storage medium is located is controlled to execute the steps of the method for extracting the degradation factor of the aero-engine according to any one of claims 1 to 3 when the program is running.

Images