Engine health status assessment method based on combined weighting method and cloud position evaluation

Abstract

The present invention discloses an engine health status assessment method based on a combined weighting method and cloud position judgment, comprising the following steps: S1. Selecting assessment indicators involved in engine health status assessment, inputting original data of various assessment indicators involved in engine health status assessment; S2. Dividing health levels, determining comment sets and generating standard evaluation clouds; S3. Constructing subjective weighting models and objective weighting models, and determining the comprehensive weights of assessment indicators based on a combined weighting method; S4. Obtaining standard values ​​of assessment indicators, determining ideal cloud positions according to ideal values ​​of assessment indicators; and determining actual cloud positions according to actual data; S5. Calculating weighted deviations and determining the health level of the engine. The present invention establishes an aircraft engine model, and uses the model to simulate aircraft engine operation, obtains full-cycle operation data, and selects engine health status assessment parameters, and realizes effective evaluation of engine health status based on a combined weighting method and cloud position judgment.

Description

Technical Field

[0001] The invention relates to the field of aircraft engine health status assessment, and in particular to an engine health status assessment method based on a combined weighting method and cloud position evaluation. Background Art

[0002] The aviation industry is a strategic industry in the national defense science and technology. As the core of the aviation propulsion system, aircraft engines cover multiple disciplines such as mechanics, pneumatics, combustion, control, materials science, electronic technology and artificial intelligence, and are representatives of the country's comprehensive scientific and technological level. With the development of the aviation industry, aircraft engines have evolved from the original piston engines to new scramjet engines and pulse detonation engines. As the performance of aircraft engines has been greatly improved, their parts have gradually increased, and their structures have become more complex. In addition, they have been operating in harsh environments (high temperature, high pressure, high vibration, strong corrosion, and high energy release) for a long time, and the wear of parts has intensified, which has posed greater challenges to the safety, reliability, and economy of aircraft engines.

[0003] In the operation, the aircraft engine cluster has multiple technical states and large individual dispersion. In today's complex electromagnetic environment, data loss and electronic and electrical failures are prone to occur. And with the gradual development of aircraft engines, there is an obvious contradiction between the method of fast and efficient cluster detection of the fleet and the growing operation tasks, which will seriously restrict aircraft operation and mission execution. Improving the reliability and stability of aircraft engines in the field and achieving high-quality technical support capabilities have gradually become the key.

[0004] Aiming at the problems of low operating efficiency caused by multiple states, large dispersion and difficulty in fleet cluster detection during operation of in-service aircraft engines, as well as data loss and frequent faults in complex electromagnetic environments, a quality control standard for safe operation of aircraft engine health parameters based on a dual-model of "aircraft engine model + actual operation data" is established. Aiming at the problem of lack of health level assessment during the use of aircraft engines, a method for establishing a comprehensive system for advanced health status assessment is proposed, which will help with the health status assessment of aircraft engines, thereby improving the field autonomous support capability of aviation power equipment.

[0005] The health status of an aircraft engine is an assessment of the deviation between the current state of an aircraft engine and the expected state, reflecting the ability of an aircraft engine to complete its mission well. The health status evaluation of an aircraft engine needs to solve three problems: the construction of a healthy parameter set of an aircraft engine, the construction of an evaluation index system for the health status of an aircraft engine, and the construction of a comprehensive evaluation model for the health status. The health evaluation index system should truly and comprehensively reflect the health status of the equipment. Therefore, the construction of the health evaluation index system for equipment should follow certain principles and fully consider the health management purpose of the equipment, the functional characteristics, safety, and stability of the aircraft engine. It can not only cover the requirements for the expression of the health status of the aircraft engine, but also reflect the "five qualities" (reliability, maintainability, security, testability, and safety) of the aircraft engine to a certain extent. The health status parameters of equipment have different formats, characteristics, and sampling periods. The heterogeneity of the parameters causes the amount of information contained in the parameters to be different, and at the same time increases the difficulty of constructing a comprehensive health evaluation model. Heterogeneous data fusion methods include expert scoring method, mathematical operations research solution, multi-objective decision-making method, data envelopment analysis method, and gray management analysis method. The expert scoring method contains too much subjective and arbitrary elements and cannot overcome the problems of lack of comprehensiveness and logic, while the complete description of the state space required by other methods is difficult to achieve in a short period of time. Summary of the invention

[0006] The purpose of the present invention is to overcome the shortcomings of the prior art and provide an engine health status assessment method based on a combined weighting method and cloud position judgment, establish an aircraft engine model and use the model to simulate the operation of the aircraft engine, obtain full-cycle operation data, and select engine health status assessment parameters, so as to achieve an effective assessment of the engine health status based on the combined weighting method and cloud position judgment.

[0007] The object of the present invention is achieved through the following technical solution: an engine health status assessment method based on a combined weighting method and cloud position evaluation comprises the following steps:

[0008] S1. Select the evaluation indicators involved in the engine health status evaluation, and input the original data of the evaluation indicators involved in the engine health status evaluation;

[0009] S2. Divide the health level, determine the comment set and generate a standard evaluation cloud;

[0010] S3. Construct subjective weighting model and objective weighting model, and determine the comprehensive weight of evaluation indicators based on combined weighting method;

[0011] S4. Obtain standard values ​​of evaluation indicators, determine ideal cloud locations based on ideal values ​​of evaluation indicators, and determine actual cloud locations based on actual data;

[0012] S5. Calculate the weighted deviation and determine the health level of the engine.

[0013] The beneficial effects of the present invention are as follows: the present invention establishes an aircraft engine model and uses the model to simulate the operation of the aircraft engine, obtains full-cycle operation data, and selects engine health status assessment parameters, and realizes effective evaluation of the engine health status based on the combined weighting method and cloud position judgment, which can provide a basis for the health status assessment of the aircraft engine, and solve the problems existing in the full-cycle operation of traditional aircraft engines, such as the difficulty in predicting the health status, long maintenance cycle, high maintenance cost, insufficient real-time performance and reliability, so as to guide the acquisition of the full-cycle operation health status of the aircraft engine, assist in the formulation of maintenance decisions, improve the reliability of aircraft engine operation, and the real-time performance of maintenance, so as to ensure the safe operation of the aircraft and avoid accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 Schematic diagram of aero-engine modeling based on component method and cavity effect;

[0015] Figure 2 To solve the parameter matrix flow chart;

[0016] Figure 3 Construct a flow chart for the evaluation system;

[0017] Figure 4 It is a schematic diagram of the digital characteristic curve of the normal distribution model;

[0018] Figure 5 This is a schematic diagram of the normal cloud model;

[0019] Figure 6 This is a schematic diagram of the principle of the forward cloud generator;

[0020] Figure 7 This is a schematic diagram of the principle of the reverse cloud generator;

[0021] Figure 8 Schematic diagram of the cloud generator for evaluation;

[0022] Fig. 9 Flowchart of engine health status assessment based on cloud position judgment method. DETAILED DESCRIPTION

[0023] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings, but the protection scope of the present invention is not limited to the following.

[0024] like Figure 1 As shown, the engine health status assessment method based on the combined weighting method and cloud position judgment includes the following steps:

[0025] S1. Construct an aircraft engine model, select engine health status assessment parameters, and obtain the original data of the engine health status assessment parameters by simulating the full cycle operation of a real aircraft engine;

[0026] S2. Determine the review set and generate a standard review cloud;

[0027] S3. Construct subjective weighting model and objective weighting model, and determine the comprehensive weight of evaluation indicators based on combined weighting method;

[0028] S4. Obtain standard values ​​of evaluation indicators, determine ideal cloud locations based on ideal values ​​of evaluation indicators, and determine actual cloud locations based on actual data;

[0029] S5. Calculate the weighted deviation and determine the health level of the engine.

[0030] 1.Engine parameter matrix establishment

[0031] In the embodiments of the present application, in order to understand the various parameters that affect the healthy state of the aircraft engine throughout its entire operating cycle, it is necessary to conduct a systematic study of the aircraft engine system. However, obtaining aircraft engine operating parameters through experimental methods is costly and time-consuming, which is not conducive to further in-depth research. Therefore, it is necessary to establish a suitable aircraft engine model to obtain the parameters involved in the operation of the aircraft engine and the related parameter matrix from the model. The aircraft engine model provides an economical and efficient tool that can better understand the operating mechanism of the aircraft engine and help identify the key factors that affect the healthy state of the engine. By establishing such a model, the present invention can effectively reduce research costs, shorten research cycles, and provide a reliable basis for the health status evaluation system and health monitoring of aircraft engines.

[0032] Establishment of aircraft engine model: Based on the volumetric method and component characteristics, a dynamic mathematical model of a certain type of high bypass ratio turbofan engine is established, which can describe the real dynamic characteristics of the aircraft engine. The turbofan aircraft engine object selects a certain type of high bypass ratio dual-shaft separate exhaust turbofan engine. The establishment of the dynamic model of the engine object adopts a modeling approach based on component characteristics and the volumetric method. The engine object components include atmospheric conditions, inlet duct components, fan components, external duct components, low-pressure compressor, compressor components, combustion chamber components, high-pressure turbine components, low-pressure turbine components, mixing chamber, tail nozzle (including internal nozzle and external duct nozzle), high-pressure rotor components, and low-pressure rotor components. The aircraft engine construction process based on component characteristics and cavity effects can be found in Figure 1 The entire process uses a series of gas path, aerodynamic thermodynamics and rotor dynamics calculation methods to establish an aircraft engine model.

[0033] Linearized parameter matrix: The engine model is the basis for establishing the engine parameter matrix. Corresponding to each environmental parameter point and operating condition, the linearized parameters under this condition are solved by linearization. In this way, a linearized parameter matrix set is established. The specific process of solving the parameter matrix is ​​as follows: Figure 2 .

[0034] Design point parameters such as N1, N2 speed and design point fuel supply rate enter the engine model through the linearization module. At the same time, external environmental parameters (altitude, Mach number, temperature) also enter the engine model. After the engine model runs through a series of inputs, all dependent variables are output and enter the Newton-Raphson solver at the same time, by configuring the initial conditions and parameter selection conditions of the solver. Through a series of iterative cycles, when the error is less than the error set by the solver, all independent variables are output and enter the engine model. At the same time, this process converts the nonlinear engine model into a linear model. At the same time, the module composed of the engine model and the solver inputs data into the linearization module. The linearization module outputs a series of parameters related to the health status of the engine, including temperature, pressure, speed, stall margin, and fuel parameters. The parameters are processed to form a parameter matrix.

[0035] The aircraft engine component-level model obtained by the component method and the volume method has high accuracy, but the aircraft engine it represents is essentially a system with strong nonlinearity. In order to obtain the linearized parameter matrix of the aircraft engine, it is necessary to use a solver to obtain a specific matrix. Here, the widely used Newton-Raphson theory is used to solve the parameter matrix.

[0036] The Newton-Raphson method is an iterative numerical method for solving nonlinear equations with numerical approximation. The basic idea is to approximate the root of the equation through continuous iteration. Assume that the equation to be solved is f(x) = 0, select an initial approximate solution x0, and then iterate to make f(x i ) approaches 0. In each iteration, by i The tangent is used to update the approximate solution until the convergence condition is met. The Newton-Raphson method has quadratic convergence, and the error at each step decreases at a quadratic rate. The convergence speed depends on the choice of the initial approximate solution and the properties of the equation f(x). In some cases, the convergence speed may be slow or non-convergence may occur, and adjustments or other methods may be required.

[0037] In fact, in this application, as long as the evaluation indicators involved in the engine health status evaluation can be given in advance as input data, the evaluation indicator data can be measured, simulated, or obtained according to the method in 1. The specific acquisition method is not limited. The key lies in the selection of the evaluation indicators and the specific evaluation process:

[0038] 2. Determination of aircraft engine health parameter set

[0039] According to the establishment of the above-mentioned aircraft engine parameter matrix, by establishing a suitable aircraft engine model, the present invention can obtain the parameters involved in the full-cycle operation of the aircraft engine from the model, and can simulate the full-cycle operation of the real aircraft engine by changing the input conditions of the model, and obtain the required related parameters by the method of linearizing the parameter matrix. The aircraft engine model and related parameters provide a reliable basis for the aircraft engine health status assessment method. Next, the present invention constructs an aircraft engine health parameter set for monitoring and evaluating the performance and health status of the aircraft engine, and makes auxiliary strategies for the next step of operation, maintenance, and decision-making.

[0040] Aircraft engine health parameters are key indicators used to evaluate and monitor engine status and performance. They provide important information about the engine's operating conditions, helping to identify potential problems in a timely manner and take preventive or repair measures to ensure safe, reliable and efficient operation of the engine. The aircraft engine health parameter set is determined by defining the following health parameters:

[0041] (1) Temperature health parameters

[0042] There are many temperature parameters in aircraft engines, including turbine inlet temperature (TIT), turbine outlet temperature (TOT), combustion chamber temperature, etc. These parameters can reflect the operating temperature of various components inside the engine and are important indicators for evaluating the performance of aircraft engines. Temperature parameters reflect the thermal state of the gas flow after the turbine and directly affect the power output and efficiency of the engine. At the same time, temperature parameters have a direct impact on the life and reliability of the engine.

[0043] Excessive temperature will increase thermal stress, accelerate the wear and aging of engine parts, and thus reduce the life of the engine. At the same time, excessive temperature may cause engine failure or even cause an accident, so timely detection and handling of temperature anomalies is an important part of ensuring aviation safety.

[0044] Among them, the temperature parameter that can directly reflect the combustion efficiency of aircraft engines is the temperature after the combustion chamber. However, due to the high temperature after the combustion chamber, the requirements for temperature sensors are high. Usually, the outlet temperature of the turbine is selected as the temperature monitoring parameter. The control of the temperature after the turbine is also closely related to fuel efficiency. By reasonably controlling the temperature after the turbine, the combustion efficiency can be improved, thereby reducing fuel consumption and reducing aviation operating costs. By monitoring and controlling the temperature after the turbine, the performance of the engine can be optimized and ensured to operate within the design parameter range. In the present invention, the exhaust temperature T after the turbine is selected. 45 As a health parameter of aircraft engines.

[0045] (2) Stress health parameters

[0046] Aircraft engine pressure parameters are important parameters for evaluating the health status of aircraft engines. There are many pressure parameters in aircraft engines, such as low-pressure compressor outlet pressure (LPCOP), high-pressure compressor outlet pressure (HPCOP), turbine inlet pressure (TIP), turbine outlet pressure (TOP), etc. These parameters reflect the air pressure conditions in various components of the engine and have an important impact on the performance and efficiency of the engine.

[0047] The high-pressure compressor after-pressure can directly reflect the health of the engine air path, engine performance and efficiency. Appropriate high-pressure compressor after-pressure can ensure that the compressor works near the design point, thereby ensuring the performance and efficiency of the engine. At the same time, by maintaining an appropriate after-pressure level, the workload of the compressor can be reduced and the fuel consumption of the engine can be reduced. This is of great significance for reducing aviation operating costs and reducing the impact on the environment.

[0048] Reasonable control of the compressor after-pressure can reduce the wear and fatigue of the compressor components and extend the service life of the engine. Too high a pressure may cause excessive stress on the components and accelerate wear, while too low a pressure may cause unstable operation of the components and affect their service life. At the same time, appropriate high-pressure compressor after-pressure can ensure the stable operation of the compressor under various operating conditions. Too high or too low pressure may cause problems such as compressor stall or overheating, affecting the stability and reliability of the engine. Effective monitoring and control of the compressor after-pressure is one of the keys to ensure the safe operation of the engine. By monitoring the high-pressure compressor after-pressure, the health status of the aircraft engine can be directly detected. In the present invention, the high-pressure compressor outlet pressure Ps3 is selected as the health parameter of the aircraft engine.

[0049] (3) Speed ​​parameters

[0050] The speed of an aircraft engine is one of the important indicators to measure the operating status of the engine, such as the high-pressure shaft speed, low-pressure shaft speed, fan speed, etc. The change in speed can reflect the changes in engine load, power output and working status. The speed is directly related to the performance of the engine. The appropriate set point speed can ensure that components such as the compressor and turbine operate near the designed working point, thereby maximizing the efficiency and performance of the engine. By adjusting the speed, the engine's thrust output, fuel efficiency and response speed can be optimized to meet the needs of different flight phases.

[0051] The stability and balance of the high-pressure shaft speed is crucial to the operating stability of the engine. Excessive speed fluctuations will cause increased engine vibration and may cause equipment damage or system failure. Abnormal changes in the high-pressure shaft speed may cause serious engine failures or even cause aircraft failure. Therefore, continuous monitoring and control of the high-pressure shaft speed is one of the important measures to ensure aviation safety. By timely detecting and handling speed abnormalities, safety issues such as engine stall and excessive wear can be prevented, ensuring flight safety.

[0052] At the same time, the high-pressure shaft speed has an important impact on the life of each key component of the engine. Too high or too low speed will lead to increased wear of components, thereby shortening their service life. By reasonably controlling the high-pressure shaft speed, the wear and fatigue of components can be reduced, the service life of the engine can be extended, and the maintenance cost can be reduced. In the present invention, the high-pressure shaft speed N2 is selected as the health parameter of the aircraft engine.

[0053] (4) Stall margin parameters

[0054] Aircraft engine stall margin is an important parameter for evaluating engine performance and safety, including fan stall margin (SM Fan ), low pressure compressor stall margin (SM LPC ), high pressure compressor stall margin (SM HPC ) and so on. Stall is a serious engine failure that may cause the engine to be unable to provide sufficient thrust or completely lose thrust. Ensuring sufficient stall margin is one of the keys to ensuring safe aircraft operation. The adequacy of stall margin directly affects the engine's ability to respond to emergencies and improves flight safety.

[0055] Secondly, the stall margin reflects the stability and reliability of the aircraft engine in the face of external disturbances. A larger stall margin means that the engine is more stable and can better cope with changes in external conditions, thereby improving the performance of the engine. By ensuring sufficient stall margin, the engine's thrust output, fuel efficiency and response speed can be optimized.

[0056] Stall margin is also related to the engine's adaptability to different environmental conditions. In special environments such as extreme climates or high altitudes, aircraft engines may be subject to more severe external airflow disturbances, so a larger stall margin is required to ensure stable engine operation. Sufficient stall margin can improve the engine's environmental adaptability and ensure that it can operate reliably under various operating conditions.

[0057] A larger stall margin can reduce fatigue and stress on the blades and extend their service life. At the same time, the adequacy of the stall margin can also reduce the engine failure rate and reduce maintenance costs. Therefore, reasonable design and guarantee of the stall margin are of great significance to the maintenance and life management of the engine. In the present invention, the fan stall margin (SM Fan ), low pressure compressor stall margin (SM LPC ), high pressure compressor stall margin (SM HPC )Three stall margins as health parameters of aircraft engines.

[0058] (5) Fuel parameters

[0059] (a) Specific fuel consumption (T sfc )

[0060] Aircraft engine specific fuel consumption (T sfc , Thrust Specific Fuel Consumption) refers to the amount of fuel consumed by the engine to produce unit thrust, usually in pounds / hour or kilograms / Newton (lb / hr or kg / N). sfc It is of great significance to the performance and operation of aircraft engines. sfc It is one of the important indicators for evaluating engine economy. sfc This means that the engine consumes less fuel to produce a certain amount of thrust.

[0061] Engine T sfc Directly affects the range and endurance of the aircraft. sfc The engine can provide a longer range with a given fuel capacity, or consume less fuel with the same range, thereby increasing the aircraft's range. sfc The engine consumes less fuel per unit thrust, which correspondingly reduces the emission of carbon dioxide (CO2) and other emissions generated by fuel combustion, which helps to reduce the impact of aircraft on the environment and meets environmental protection requirements. sfc The change of can directly reflect the health status of the aircraft engine, so the present invention selects T sfc As a health parameter of aircraft engines.

[0062] (b) Fuel consumption ratio

[0063] Aviation engine fuel flow refers to the amount of fuel consumed by the engine while it is running, usually expressed as fuel mass or volume per unit time. Fuel flow is of great significance to the performance and operation of aircraft engines, and fuel flow directly affects the range and endurance of the aircraft. With a given fuel capacity, lower fuel flow means that the aircraft can fly longer distances or longer. The study and optimization of fuel flow helps to improve the design and manufacture of engines and enhance their performance.

[0064] During the operation cycle of an aircraft engine, the health status of the aircraft engine can be monitored by comparing its fuel consumption ratio under a certain operating state. In this paper, a fuel consumption ratio is defined as a health parameter of the aircraft engine, as shown in Formula 1.

[0065]

[0066] Where η is the fuel consumption ratio of the aircraft engine, W f-PLA1 、N 2-PLA1 The fuel flow and low pressure shaft speed in PLA1 state; W f-PLA2 、N 2-PLA2 It is the fuel flow and low pressure shaft speed in PLA2 state. PLA is the abbreviation of Power Lever Angle. PLA1 refers to the angle when the throttle lever angle is in the first state position. For general research on aircraft engines, it is usually 40°; PLA2 refers to the angle when the throttle lever angle is in the second state position. For general research on aircraft engines, it is usually 80°; other angles can also be used to study some other operating states.

[0067] The monitoring and analysis of aircraft engine health parameters are usually performed through flight data recording systems or ground test equipment. Continuous monitoring and analysis of these parameters can help predict potential failures, optimize maintenance plans, and improve the reliability and safety of aircraft engines.

[0068] Based on the aircraft engine performance calculation, determine the parameters that need to be used as input. These parameters include engine operating status (such as speed, temperature, pressure, etc.), external environmental conditions (such as altitude, Mach number, air density, etc.), fuel characteristics, etc. Define the health parameters to be monitored and evaluated. These parameters should be able to reflect the performance, status and health of the engine, such as temperature gradient, pressure loss, vibration amplitude, fuel efficiency, etc. Collect data and ensure the quality and reliability of the data, and perform preprocessing to eliminate noise and outliers. Predict output parameters based on input parameters and use a validation data set to evaluate the accuracy and generalization ability of the model. Perform model tuning and improvement as needed. Extract health parameters using real-time or historical data. Embed the model into a real-time monitoring system to calculate health parameters in real time at runtime, or apply the model to historical data to obtain previously unknown health information.

[0069] The health parameter set is optimized according to actual needs and application scenarios to ensure that the health parameter set can accurately reflect the working status and health status of the engine. The established health parameter set is applied to the real-time monitoring system to monitor the engine status in real time and provide timely feedback and alarms. At the same time, the collected real-time data is used to continuously optimize and improve the health parameter set.

[0070] Such a health parameter set based on aircraft engine performance calculation is established to monitor and evaluate the performance and health of the engine, providing support for maintenance and preventive maintenance.

[0071] 3. Classification of health status and establishment of evaluation index system

[0072] 3.1 Basic principles for constructing an engine health status assessment index system

[0073] The realization basis of the research on the health status assessment technology of aircraft engines is the construction of the engine status parameter assessment index system. A reasonable assessment index system is an important condition to ensure the safe operation of the engine, which makes the principle research on the construction of the health status assessment index system the first priority of health status assessment. In the actual process of constructing the engine health status assessment index system, due to the large number of monitoring parameters that affect the engine health status, if all monitoring parameters are included in the system evaluation index system, the entire evaluation system will be very large, and in view of the strong correlation between some monitoring parameters, it is not necessary to use all monitoring parameters as evaluation indicators, resulting in redundancy and duplication of evaluation information. In addition, because the engine has a very complex structure, it is difficult to take all influencing factors into account, and it is not necessary to take all of them into account in actual engineering applications. Therefore, in order to achieve the ideal evaluation effect, the establishment of the evaluation index system should follow the following principles.

[0074] 1) Scientific principle

[0075] In the aircraft engine health status assessment index system, representative typical indicators should be selected. These indicators should have a certain physical meaning and ensure the measurability, independence and integrity of the assessment indicators. For example, the engine exhaust temperature, this assessment indicator can specifically characterize the health status of the gas path system and has a certain scientific connotation. Indicators that do not have a certain physical meaning and cannot objectively reflect the health status of the engine should be discarded. In addition, when constructing the engine health status assessment index system, the interference of subjective factors should be avoided as much as possible. Only in this way can the scientific nature of the assessment system be guaranteed.

[0076] 2) Feasibility principle

[0077] The establishment of an aircraft engine health status assessment index system should follow the principle of feasibility, that is, the selected assessment indicators should be able to collect data through existing monitoring technologies, because the assessment indicator monitoring data obtained using immature monitoring technologies contains more "impurities", resulting in large errors in the assessment results.

[0078] 3) Principle of consistency

[0079] The establishment of the aircraft engine health status assessment index system should follow the principle of consistency. The consistency here refers to the consistency of various assessment indicators and assessment purposes. The selected assessment indicators can objectively and comprehensively reflect the assessment objectives. In addition, consistency also refers to ensuring the consistency of various assessment indicators, that is, contradictory assessment indicators cannot be listed in the assessment index system.

[0080] 4) Principle of Independence

[0081] The principle of independence aims to remove the strong correlation between the evaluation indicators in the evaluation indicator system. It is necessary to ensure that each evaluation indicator exists independently. If there is a strong correlation between the evaluation indicators, too many evaluation indicators will make the evaluation model too complicated. In addition, the principle of independence also requires that each evaluation indicator has a unique physical meaning and there is no causal relationship between the indicators.

[0082] 5) Principle of simplicity

[0083] The principle of simplicity requires that the evaluation index system should be clearly structured, and the levels should not be too many or too complicated, which would make the index system too large. In addition, the evaluation model should also be simple and easy to operate. It is not advisable to conduct evaluation based on a particularly complex evaluation model, which lacks operability and practicality.

[0084] 3.2 Main factors affecting engine health level

[0085] 1) Failure probability: The probability of the engine being in different failure modes is obtained through the intelligent classification and recognition algorithm. The probability of this failure is the main factor in evaluating the health status of the engine. The smaller the probability of being in a failure state, the better the engine working state, and the higher the health status level safety; otherwise, the opposite is true.

[0086] 2) Fault severity: If the vibration severity is used to describe the degree of engine structural fault, the larger the vibration amplitude, the higher the risk of the corresponding healthy state of the engine; the smaller the vibration amplitude, the higher the safety of the corresponding healthy state of the engine. Since different types of engines implement different vibration standards, the relative vibration amplitude will be obtained by dividing the difference between the absolute vibration amplitude and the vibration alarm value at the measuring point of the engine by the vibration alarm value. Using relative vibration amplitude to express the degree of fault will eliminate the influence of engine model, sensor type and sensor installation position.

[0087] 3) Risk of loss: Different failure modes will cause different consequences and losses. For example, under the same vibration amplitude, the consequences may be different when the engine is in an unbalanced state or in a blade falling failure state. The imbalance of the engine rotor is absolute, and the balance is relative. In a certain range of imbalance, the engine can sometimes even complete the operation; but if a blade falls, it is likely to cause a major accident with the destruction of the machine and the loss of people. Therefore, different failure modes will bring different loss risks, which is a factor that must be considered in the engine health status assessment.

[0088] 3.3 Classification of health status

[0089] In the past, the "yes or no" classification method was often used to divide the health level, that is, the health status was divided into two health levels: qualified and unqualified. It was considered that the data of each monitoring parameter was qualified within the allowable range, and unqualified outside the allowable range. This classification may take the same maintenance measures for the two states of good engine status and near failure, which cannot well achieve the goal of condition-based maintenance and has no practical engineering significance. Therefore, the concept of "health level" is introduced to describe the health status of the engine.

[0090] The number of health status levels should be appropriately selected, and the commonly used scale is 1 to 9. Different levels contain two physical meanings: one is "safety". As the status level decreases, the engine safety decreases; the other is "danger". As the status level decreases, the engine danger increases. An odd number of levels can ensure the symmetry and complementary properties of "safety" and "danger". An odd number should be selected as the number of engine health levels. Dividing the engine health status into 5 levels is too rough, and dividing it into 9 levels is too cumbersome and does not conform to actual engineering practice habits; therefore, the status of aircraft engines is divided into 7 levels.

[0091] The present invention divides the health status into 7 levels based on the actual operating status of the engine: healthy, sub-healthy, good, qualified, degraded, abnormal, and faulty. The description corresponding to each health level is shown in Table 1.

[0092] As engine components change continuously from healthy to faulty, their safety gradually decreases, the possibility of failure increases, and the maintenance cycle is greatly shortened. These seven levels of health directly reflect the health status assessment results and describe the engine's status change process.

[0093] Table 1 Engine health status classification and level description

[0094]

[0095]

[0096] 4. Construction of a comprehensive system for aircraft engine health status assessment

[0097] The construction of a comprehensive health status assessment system is a complex and scientific task. The health status assessment results depend not only on whether the assessment indicators can fully characterize the health status of the subject to be assessed, but also on whether the relative importance of the assessment indicators of the subject to be assessed can be correctly judged, that is, whether the determination of the assessment indicator weights is close to the actual situation. At present, the principle research on the determination of assessment indicators is relatively clear. As long as the principles of assessment indicator selection are strictly followed, the assessment indicators that fully characterize the health status of the subject to be assessed can be determined, and the credibility of the assessment results can be maximized.

[0098] The comprehensive system for evaluating the health status of aircraft engines proposed in this invention is constructed as follows: Figure 3 ,The construction of the system is mainly divided into two parts, one is the ,combination empowerment process, and the other is the process of building the ,cloud model, among which the combination empowerment process is the basis of ,the construction of the cloud model.

[0099] According to the principle, the weighting method is divided into subjective weighting method and objective weighting method. The former is completely dependent on the subjective experience of experts, which is greatly affected by people's cognitive level and prejudice, and has poor objectivity; the latter relies on data support and is not affected by people's subjective experience. The weight calculation depends only on data indicators, and the evaluation is more objective, but it cannot express the degree of importance that decision makers attach to different indicators. The calculated weights may not conform to the actual situation. A single weighting method has certain limitations. The combined weighting method can combine the subjectivity of expert experience and the scientific nature of objective data to make the results of weight calculation more real and reliable.

[0100] Combining the improved AHP method with the entropy weight method, a compromised combination weight is obtained between the subjective weight and the objective weight, which can be regarded as the optimal balance solution. The subjective weighting method in the present invention adopts the improved APH method, firstly determines the order relationship between the indicators, further determines the relative importance of the indicators, and finally obtains the subjective weight coefficient of each indicator by calculation. The objective weighting is mainly obtained from the original data sample of the aircraft engine operation, which can objectively reflect the operation of the aircraft engine. The original data is normalized to form a data sample matrix, and the entropy weight of each indicator is obtained by calculation, so as to determine the corresponding objective weight. The subjective weight and the objective weight together form a combined weight and are input into the cloud model.

[0101] To build a cloud model, it is necessary to determine the health comment set, and form a health evaluation standard cloud by calculating its standard cloud parameters. At the same time, the underlying indicators further form the first-level indicator cloud parameters by calculating the cloud parameters. The comprehensive health evaluation cloud map is formed with reference to this cloud parameter. The health evaluation standard cloud map and the comprehensive health evaluation cloud map are compared and analyzed to obtain the evaluation results, which further guides the auxiliary formulation of maintenance decisions and improves the reliability of aircraft engine operation and the real-time maintenance, ensuring the safe operation of aircraft and avoiding accidents.

[0102] 4.1 Evaluation Index Weighting Method

[0103] The determination of the weight of the evaluation indicators is a key issue to be solved in the process of building a comprehensive health status evaluation system. Weight is a relative concept and a measure of the degree of influence on the health status of the object to be evaluated. The larger the weight of an evaluation indicator, the greater the influence of this indicator on the health status of the object to be evaluated, and vice versa.

[0104] In the objective weighting process, the entropy weight method is a comprehensive calculation method that comprehensively considers the monitoring information of the object to be evaluated. It is mainly weighted according to the amount of information transmitted by each evaluation indicator of the object to be evaluated. The weighting result reflects the degree of disorder of the monitoring information of the object to be evaluated and can measure the amount of information. The entropy weight method weights each evaluation indicator of the aircraft engine to ensure the objectivity of the obtained weight and improve the reliability of the aircraft engine health status assessment results.

[0105] The entropy weight method is as follows: if there are n aircraft engine evaluation samples, each evaluation sample has m indicators, forming the original data matrix, as shown in Formula 2.

[0106]

[0107] (1) Raw data preprocessing

[0108] Since the value range of the variable in "entropy" is [0, 1], in order to meet the requirements, the monitoring data of various evaluation indicators involved in health status assessment need to be standardized and preprocessed according to the following formula, and the preprocessed matrix P = (P ij ) n×m .

[0109]

[0110] In the formula, is the maximum value of the monitoring data of the jth evaluation indicator; is the minimum value of the monitoring data of the j-th evaluation indicator.

[0111] (2) Calculate information entropy E j

[0112] According to the above formula, P ij , calculate the information entropy E of the jth evaluation index j for

[0113]

[0114] (3) Determine the entropy weight of the indicator

[0115] The weight of the jth evaluation metric for

[0116]

[0117] and According to the above formula, the weight of the jth evaluation indicator in the evaluation process is obtained

[0118] In the process of subjective weighting method, the improved AHP method is adopted. Specifically, the three-scale method is used to quantitatively express the relative importance of indicators. At the same time, the concept of optimal transfer matrix is ​​introduced to establish the judgment matrix. The principle of determining weights by the improved AHP is as follows.

[0119] (1) Establish the judgment matrix B based on the three-scale method

[0120] The three-scale method establishes the judgment matrix, which greatly reduces the probability of misjudgment when comparing matrix elements, weakens the impact of human subjective factors on the evaluation results, and improves the accuracy of the weight determination process. The specific steps are as follows.

[0121] (a) Each aircraft engine has m evaluation indicators. The three-scaling method is introduced to quantitatively express the relative importance of each aircraft engine evaluation indicator, and the corresponding comparison matrix A is obtained. gh ) m×m for:

[0122]

[0123] Among them, a g represents the gth index of the aircraft engine; a h represents the hth index of the aircraft engine;

[0124] Based on the three-scaling method, the element a gh Quantitative expression, its value and corresponding content are as follows:

[0125] Set the scale value If a gh =0,a g Than a h Important; if a gh =1, a g with a h Equally important; if a gh =2, a g Than a h important;

[0126] (b) Based on the comparison matrix A, calculate the ranking index according to Formula 7.

[0127]

[0128] (c) According to the ranking index r i Construct judgment matrix B gh , whose element b gh By for.

[0129]

[0130] Among them, k m =r max / r min

[0131] (2) Adjust the judgment matrix

[0132] The concept of optimal transfer matrix is ​​introduced to establish the judgment matrix and obtain the matrix that satisfies the consistency check. Based on this matrix, the weights of various evaluation indicators can be directly calculated, which greatly simplifies the calculation process and further improves the calculation efficiency. The quasi-optimal consistent matrix B of the judgment matrix can be calculated according to formula 9. gh ′.

[0133]

[0134] In the formula, c gh =logb gh .

[0135] (3) Weight determination

[0136] According to B gh′, normalize the matrix by column, and get the matrix T gh , whose elements are

[0137]

[0138] Then use formula 11 to calculate the weight value of each evaluation index

[0139]

[0140] The improved AHP method is effectively combined with the entropy weight method to improve the accuracy and credibility of the weighting results of various engine evaluation indicators in a way of mutual integration and mutual correction, retain the information of the original monitoring data to the greatest extent, and obtain weights with subjective and objective significance.

[0141] The weighting results based on a single weighting method, such as the entropy weight method, are overly dependent on monitoring data. Once the monitoring data changes, the weights of the evaluation indicators will also change accordingly. The entropy weight method is to maximize the mining of system laws through the existing monitoring information. In the case of limited sample data, the weighting results based on the entropy weight method are only approximate values, and do not consider the relative importance of the evaluation indicators. Although the improved AHP method has some improvements over the conventional AHP method, subjectivity still exists, and the intrinsic information of the monitoring sample data is not considered, resulting in the loss of monitoring information. The improved AHP method is effectively combined with the entropy weight method to improve the accuracy and credibility of the weighting results of various evaluation indicators of the engine in a way of mutual integration and mutual correction, and the information of the original monitoring data is retained to the maximum extent, and the subjective opinions of the evaluators are appropriately reflected to obtain weights with subjective and objective significance. The basic principle of determining weights by the combined weighting method is shown in Formula 12.

[0142]

[0143] In the formula, θ is the proportion of weight determined by improved AHP;

[0144] ω j ′——improve the weight determined by AHP;

[0145] ——Weights determined by entropy weight method;

[0146] ω j ——Combination weight.

[0147] 4.2 Normal distribution model construction

[0148] The normal distribution model is a new method for analysis, decision-making and evaluation developed on the basis of normal distribution theory. It is a conversion model that forms qualitative concepts and quantitative expressions by constructing specific operators based on the cross-penetration of probability theory and fuzzy theory.

[0149] Assume that Q is a qualitative concept in the numerical quantitative domain U, set the value x∈U, and x is a random realization of the qualitative concept Q, and the certainty of x with respect to Q μ(x)∈[0,1] is a random number with a stable tendency.

[0150]

[0151] Then the distribution of x on the domain U is called the normal distribution model. The normal distribution model is also called the membership cloud. The μ(x) of each cloud droplet x on the cloud can reflect its membership to Q.

[0152] The cloud is characterized as a whole by three numerical features: expectation Ex (expect value), entropy En (entropy) and hyper entropy He (hyper entropy).

[0153] Expected Ex: represents the expected distribution of cloud droplets on the domain U. It is a point of the most quantifiable concept. The closer to Ex, the more concentrated the cloud droplets, and vice versa.

[0154] Entropy En: A measure of uncertainty of a qualitative concept, reflecting the number of elements in the domain that can be accepted by the concept. The larger En is, the larger the acceptable range of values ​​is and the more elements are, and vice versa.

[0155] Super entropy He: He is the entropy of entropy En, reflecting the cohesion of each numerical value representing the membership of a qualitative concept.

[0156] The normal distribution model combines fuzziness and randomness by simultaneously expressing the deterministic measurement expectation Ex of Q, the uncertainty measurement entropy En, and the uncertainty measurement super entropy He of En, thus realizing the mutual conversion between quantitative and qualitative concepts. Its digital characteristic curve is as follows: Figure 4 shown.

[0157] 4.2.1 Normal cloud model

[0158] The normal cloud model is the most basic normal distribution model and the basis for operating other normal distribution models. It can effectively explain the basic language values ​​in natural language. The normal distribution is the basic distribution in probability theory, has universal applicability, and is a powerful tool for expressing fuzzy concepts.

[0159] The mathematical expectation curve of the normal cloud model is shown in Formula 13.

[0160]

[0161] A normal cloud model can be formed by a generation algorithm, and the algorithm is as follows:

[0162] (1) Eni' = NORM (En, He2), we get the normal random number Eni', the expectation is En, the variance is He2 ;

[0163] (2) xi = NORM (Ex, Eni'), and a normal random number xi is obtained, whose expectation is Ex and variance is Eni';

[0164] (3) Taking (xi, μi) as the cloud droplet, calculate value;

[0165] (4) Repeat the above steps until N cloud droplets are generated.

[0166] Through the above algorithm, the normal cloud model can be generated by setting the three digital features of the normal cloud model. For example, if Ex = 0, En = 1, He = 0.1, N = 3000, the generated normal cloud model is as follows Figure 5 shown.

[0167] 5.2.2 Cloud Generator

[0168] Cloud generators are divided into forward cloud generators and reverse cloud generators. Among them, the forward cloud generator converts a specific concept into its corresponding quantitative representation, such as Figure 6 shown.

[0169] The forward cloud generator generates a specific number of cloud droplets based on the three digital features of the cloud. The specific steps are as follows:

[0170] Input: (Ex, En, He, N)

[0171] Output: ((Drop(x1, μ(x1)), Drop(x2, μ(x2)), Λ, Drop(xN, μ(xN)))

[0172] (1) Generate a normal random number En', where En' conforms to a normal distribution with En as the expectation and He as the standard deviation;

[0173] (2) Generate a normal random number x, which conforms to the normal distribution with Ex as the expectation and En′ as the standard deviation;

[0174] (3) According to (1) and (2), calculate μ(x) = exp[-(x-Ex) 2 / 2 (En') 2 ];

[0175] (4) Generate cloud droplets (x, μ(x));

[0176] (5) Repeat (1) to (4) until the required N cloud droplets are generated.

[0177] Backward Cloud Generator (BCG) is a tool that converts quantitative values ​​into qualitative concepts, such as Figure 7Shown:

[0178] Input: The exact numerical values ​​of N cloud droplets and the qualitative concept membership (x, μ(x)) represented by each cloud droplet.

[0179] Output: 3 digital features of the cloud model corresponding to N cloud droplets.

[0180] (1) Mean variance

[0181] (2)

[0182] (3)

[0183] (4)

[0184] The correctness of the inverse cloud generator algorithm is proved as follows:

[0185] According to the forward cloud generator algorithm, the cloud obeys a Gaussian distribution with Ex as the expectation and En as the standard deviation, and its probability density function is shown in Equation 14.

[0186]

[0187] but

[0188]

[0189] make but

[0190]

[0191] therefore

[0192]

[0193] When there are N cloud droplets

[0194]

[0195] Therefore, the calculation formula of entropy En is as shown in Formula 19.

[0196]

[0197] The variance of the cloud model is as shown in Equation 20.

[0198]

[0199] Also because Therefore, the calculation of super entropy He is as shown in Equation 21.

[0200]

[0201] 4.2.2 Normal distribution position vector

[0202] The aircraft engine represented by n indicators can be described by an n-dimensional comprehensive normal distribution cloud. When the system state changes, the shape of the comprehensive cloud also changes, and its position also changes accordingly. The normal distribution position vector T can be expressed as

[0203] T=a×b (22)

[0204] Among them, "a" represents the cloud position, which is the expectation of one of the three digital features of the cloud model; "b" is the height of the cloud position, which represents the weight of a certain evaluation indicator relative to the object to be evaluated. If the weight changes, the final evaluation result will also be different. Under normal circumstances, the general cloud position height is 0.371. When clouds with the same expectations appear, the importance of the cloud can be judged by comparing the cloud position heights.

[0205] 5. Health status assessment steps

[0206] The specific steps of engine health status assessment based on combined weighting method and cloud position evaluation are as follows.

[0207] S1. Select the evaluation indicators involved in the engine health status evaluation, and input the original data of the evaluation indicators involved in the engine health status evaluation;

[0208] S2. Divide the health level, determine the comment set and generate a standard evaluation cloud;

[0209] S3. Construct subjective weighting model and objective weighting model, and determine the comprehensive weight of evaluation indicators based on combined weighting method;

[0210] S4. Obtain standard values ​​of evaluation indicators, determine ideal cloud locations based on ideal values ​​of evaluation indicators, and determine actual cloud locations based on actual data;

[0211] S401. Obtain the standard value of the evaluation indicator, and determine the ideal cloud location based on the ideal value of the evaluation indicator:

[0212] Suppose the position G of the m-dimensional normal distribution comprehensive cloud in the ideal state is 0 Represented as an m-dimensional vector:

[0213]

[0214] In the formula, is the ideal cloud center of gravity position, and its value is the expectation of one of the three digital features in the healthy cloud model in the ideal state, that is, it is 1; is the ideal cloud center of gravity height, which is 0.371, where j = 1, 2, ..., m

[0215] S402. Determine the actual cloud location based on the actual data:

[0216] (1): Evaluation index cloudification: For each index, select Z sample data x1, x2, ..., x z , calculate the expectation Ex in the digital features of the normal distribution cloud, recorded as:

[0217]

[0218] Since there are m evaluation indicators in total, the expectation of m evaluation indicators is obtained;

[0219] (2) Calculate the weighted integrated cloud position vector

[0220] The system state reflected by the m evaluation indicators is described by an m-dimensional comprehensive normal distribution cloud. When the system state changes, the position of the m-dimensional comprehensive normal distribution cloud also changes accordingly.

[0221] The position G of the m-dimensional normal distribution integrated cloud is represented as an m-dimensional vector:

[0222] G=(G1,G2,...,G m )

[0223] In the formula, G j =a j ×b j , b j =w j ×0.371,j=1,2,...,m,a j is the actual cloud center of gravity position, which is equal to the expectation of the jth evaluation index; b j is the actual cloud position height, indicating the weight of the evaluation index relative to the object to be evaluated in the actual state; w j is the weight of the corresponding indicator.

[0224] S5. Calculate the weighted deviation and determine the health level of the engine.

[0225] S501. The comprehensive cloud position vector G in the actual state is processed as follows to obtain a set of new vectors G i ′:

[0226] G′=(G′1,G′2,...,G′ m ),in:

[0227]

[0228] Calculate the weighted deviation σ(0<σ<1) as

[0229]

[0230] S502. Evaluate the engine health status based on σ:

[0231] (1) The qualitative concept membership of σ (x, μ(x)) is calculated and input into the reverse cloud generator to obtain its digital features Ex, En, and He;

[0232] x=σ+1

[0233]

[0234] Eni'=NORM(0.0125,0.005 2 )

[0235] NORM(0.0125,0.005 2 ) means the expected value is 0.0125 and the variance is 0.005 2 is a normal random number;

[0236] The principle of the reverse cloud generator is as follows:

[0237] Input: The exact value of N cloud droplets and the membership of the qualitative concept represented by each cloud droplet (x, μ(x));

[0238] Output: 3 digital features of the cloud model corresponding to N cloud droplets;

[0239] Mean variance

[0240]

[0241] (2) Input the obtained digital features Ex, En, and He into the forward cloud generator to obtain its evaluation cloud;

[0242] (3) Compare the obtained evaluation cloud with the standard evaluation clouds of the seven health levels in the review set to determine the normal distribution model that the evaluation cloud can activate. When the overlap between the evaluation cloud and the standard evaluation cloud of any health level exceeds a preset percentage, it is considered that the evaluation cloud can activate the normal distribution model of the health level;

[0243] If there is only one normal distribution model activated by the evaluation cloud, the health level corresponding to the normal distribution model is recorded as the health assessment result of the engine;

[0244] If there are two normal distribution models activated by the evaluation cloud, proceed to step (4);

[0245] (4) Recalculate the expected values ​​Ex′, En′, He′ based on the two activated normal distribution models and their digital features Ex1, En1, He1; Ex2, En2, He2, where:

[0246]

[0247] The digital features composed of Ex′, En′, and He′ are input into the forward cloud generator to obtain a new evaluation cloud, and then step (3) is performed.

[0248] In summary, the engine health status assessment flow chart based on cloud position judgment method and combined weight method is obtained, as shown in Fig. 9 shown.

[0249] Table 3 shows the engine evaluation results of the aircraft engine health status evaluation comprehensive system construction method proposed in the present invention for aircraft engine operation data samples with different health levels. The evaluation results are consistent with the actual health status of the engine model.

[0250] Table 3 Evaluation results of the engine status to be evaluated

[0251]

[0252] According to the method proposed in the present invention, an actual aircraft engine is modeled, and the original data can be obtained through the engine model. These data do not need to be obtained through actual aircraft engine tests, and the credibility is high enough. After preprocessing the original data, the engine health status assessment result is obtained through the system, model and algorithm proposed in the present invention. Thereby solving the shortcomings of the existing aircraft engine health status assessment, providing a method for constructing an aircraft engine health status assessment comprehensive system, solving the problems of difficult health status prediction, long maintenance cycle, high maintenance cost, insufficient real-time and reliability in the full-cycle operation of traditional aircraft engines, so as to guide the acquisition of the full-cycle operation health status of aircraft engines, the auxiliary formulation of maintenance decisions, and improve the reliability of aircraft engine operation, the real-time maintenance, ensure the safe operation of aircraft, and avoid accidents. Therefore, this method has certain advantages in aircraft engine status prediction, aircraft engine health status assessment, auxiliary formulation of maintenance strategies, and reducing maintenance costs.

[0253] The following describes an embodiment of the present invention in combination with different health conditions simulated by an aircraft engine model. For a certain type of high bypass ratio turbofan engine, a corresponding aircraft engine model is established according to its component characteristics and cavity effect, simulating the full flight state of the aircraft from ground slow, maximum takeoff, air slow, air cruising, ground approach, landing, and parking, and using its flight cycle number to simulate its health state, and obtaining its operating data when the flight cycle number is 0 cycle, 3000 cycles, 4500 cycles, and 6000 cycles, respectively, as a sample of the embodiment of the present invention.

[0254] Select the high-pressure rotor speed N2, the exhaust temperature after the turbine T 45 , Fan stall margin SM Fan , High pressure compressor stall margin SM HPC , unit fuel consumption rate T sfc , fuel consumption ratio W f / N2, 6 parameters are used as evaluation indicators for health status assessment to evaluate the health status of the engine.

[0255] The corresponding relationship of system performance parameters is shown in the following table, where the number of performance indicators is m (i = 1…, m), and the original data of performance indicators corresponding to x1-x6 are N2, T 45 , SM Fan , SM HPC , T sfc , W f / N2, the number of engine samples is n (j=1...,n), and the original data in the present invention uses x ij describe.

[0256]

[0257]

[0258] The corresponding relationship of system performance parameters is shown in the following table, where the number of performance indicators is m (i = 1…, m), and the standardized data of performance indicators corresponding to p1-p6 are N2, T 45 , SM Fan , SM HPC , T sfc , W f / N2, the number of engine samples is n (j=1...,n), and the standardized data in the present invention uses p ij describe.

[0259] The numerical features of formulas (23) and (24) also use the standardized data p ij Calculate, where x i Corresponding to p in the standardized data i .

[0260]

[0261] Set the acceleration process of the aircraft engine from the slow state to the maximum thrust state, and record the time series data of the above six parameters with a sampling frequency of 1 Hz.

[0262] First, the above 6 parameters are normalized and preprocessed. The preprocessing results are shown in Table 4-7.

[0263] Table 4 Normalized data of aircraft engine health status assessment indicators (sample 1-0 cycles)

[0264]

[0265] Table 5 Normalized data of aircraft engine health status assessment indicators (sample 2—3000 cycles)

[0266]

[0267] Table 6 Normalized data of aircraft engine health status assessment indicators (sample 3—4500 cycles)

[0268]

[0269]

[0270] Table 7 Normalized data of aircraft engine health status assessment indicators (sample 4—6000 cycles)

[0271]

[0272] according to Figure 3 The evaluation system construction flow chart given is used to build an evaluation system for this aircraft engine. Fig. 9 The engine health status assessment process of the cloud position judgment method is given, and the health status is assessed using a certain section of non-fault data collected from 0, 3000, 4500 and 6000 flight cycles of a certain type of high bypass ratio turbofan engine.

[0273] (1) Evaluation indicators in the cloud

[0274] Use the data in Table 4-7 as the decision matrix, and use Formula 23 and Formula 24 to obtain the expected Ex and entropy En of the four sample evaluation indicators, as shown in Table 8-11.

[0275] Table 8 Expected and entropy values ​​of evaluation indicators of a certain type of engine (sample 1)

[0276]

[0277] Table 9 Expected and entropy values ​​of evaluation indicators of a certain type of engine (sample 2)

[0278]

[0279] S1. Select the evaluation indicators involved in the engine health status evaluation, and input the original data of the evaluation indicators involved in the engine health status evaluation;

[0280] S2. Divide the health level, determine the comment set and generate a standard evaluation cloud;

[0281] S3. Construct subjective weighting model and objective weighting model, and determine the comprehensive weight of evaluation indicators based on combined weighting method;

[0282] S4. Obtain standard values ​​of evaluation indicators, determine ideal cloud locations based on ideal values ​​of evaluation indicators, and determine actual cloud locations based on actual data;

[0283] S5. Calculate the weighted deviation and determine the health level of the engine.

[0284] Table 10 Expected and entropy values ​​of evaluation indicators of a certain type of engine (sample 3)

[0285]

[0286]

[0287] Table 11 Expected and entropy values ​​of evaluation indicators of a certain type of engine (sample 4)

[0288]

[0289] (2) Determination of evaluation index weights

[0290] (a) Determine weights using entropy weight method

[0291] According to the normalized data of aircraft engine health status assessment indicators obtained in Table 4-7, the information entropy of each state is calculated by substituting it into Formula 4. The results are as follows:

[0292] E1={0.2615,0.2713,0.2069,0.5618,0.4753,0.1647}

[0293] E2={0.3524,0.6259,0.8196,0.6922,0.7239,0.6629}

[0294] E3={0.5069,0.7523,0.7689,0.6741,0.7777,0.6412}

[0295] E4={0.7424,0.8055,0.5892,0.7714,0.6896,0.6829}

[0296] Using the standardized values ​​of each evaluation index, the entropy weight ratio of each engine health evaluation index is obtained according to Formula 5:

[0297] ω1={0.1820,0.1792,0.1955,0.1080,0.1293,0.2059}

[0298] ω2={0.3050,0.1762,0.0849,0.1449,0.1299,0.1588}

[0299] ω3={0.2626,0.1319,0.1226,0.1736,0.1184,0.1910}

[0300] ω4={0.1499,0.1131,0.2389,0.1330,0.1806,0.1844}

[0301] (b) Improved AHP method to determine weights

[0302] According to the relative importance of each engine evaluation index and the meaning of the scale values ​​in Table 3, the comparison matrix is ​​obtained as follows:

[0303]

[0304] According to formula 8, the judgment matrix is ​​constructed as follows:

[0305]

[0306] According to Formula 9, the quasi-optimal consistent matrix B' of the judgment matrix B is:

[0307]

[0308] The weight ratio obtained by the combined weight method is both subjective and objective, reflecting the relative importance of each indicator in the study of engine health status assessment. Substituting the weights obtained by the entropy weight method and the improved analytic hierarchy process into formula 12, the weights with subjective and objective significance are obtained:

[0309] ω1={0.1831,0.1375,0.2173,0.1520,0.1625,0.1476}

[0310] ω2={0.2454,0.1372,0.1606,0.1695,0.1619,0.1254}

[0311] ω3={0.2232,0.1144,0.1807,0.1842,0.1567,0.1408}

[0312] ω4={0.1672,0.1049,0.2387,0.1642,0.1877,0.1372}

[0313] (3) Determine the comprehensive cloud location

[0314] The ideal state of a certain type of engine is healthy. It is known that the state of sample 1 is healthy, and the values ​​of its various evaluation indicators are all 1. Then the weighted comprehensive cloud position vector under the ideal state condition is:

[0315] G 0 ={0.0355,0.0292,0.0499,0.0203,0.0147,0.0506}

[0316] According to formula 25 and combined with the obtained weight W, the comprehensive cloud position vectors of sample 2, sample 3 and sample 4 in the actual state are obtained as follows:

[0317] G 2 ={0.0752,0.0330,0.0217,0.0122,0.0335,0.0119}

[0318] G 3 ={0.0602,0.0219,0.0327,0.0295,0.0247,0.0232}

[0319] G 4 ={0.0355,0.0143,0.0587,0.0155,0.0137,0.0121}

[0320] The actual integrated cloud gravity center vector is standardized according to formula 26, and the new cloud position vector is obtained as follows:

[0321] G 2′ ={0.5286,0.1159,-0.5662,-0.3995,0.5621,-0.7653}

[0322] G 3′ ={0.4112,-0.2499,-0.3457,0.3126,0.4054,-0.5409}

[0323] G 4′ ={-0.1489,-0.5101,0.1495,-0.2351,-0.0664,-0.7616}

[0324] Here, “-” indicates the negative direction of deviation from the ideal state value.

[0325] (4) Calculate weighted deviation

[0326] Substitute the obtained weights W of each engine evaluation index and the new cloud position vector G' into formula 27 to calculate the weighted deviation σ, that is, the distance between the current evaluation state of the engine and the ideal state, σ2 = -0.09265, σ3 = -0.06193, σ4 = -0.22554.

[0327] (5) Obtain health status assessment results

[0328] The calculated weighted comprehensive deviation σ is imported into the generator of the normal cloud evaluation, and the cloud state object corresponding to the health state is activated. If two state objects are activated at the same time but the degree of activation of one state object is much greater than that of the other state object, the evaluation conclusion cloud corresponding to the model is the final result. The health level of the four groups of samples can be determined as shown in the following table.

[0329] Table 12 Evaluation results of the engine status to be evaluated

[0330]

[0331] The above is only a preferred embodiment of the present invention, and the scope of the rights of the present invention cannot be limited by this. Unless otherwise mentioned, the elements or features may be considered as optional. Each element or feature may be practiced without being combined with other elements or features. The order of operations described in the embodiments of the present invention may be rearranged. Some structures of any embodiment may be included in another embodiment, and may be replaced by the corresponding structure of another embodiment. For those of ordinary skill in the art, without departing from the principles of the present invention, several improvements and changes may also be made, and these improvements and changes are also considered as the scope of protection of the present invention.

Claims

1. An engine health status assessment method based on a combined weighting method and cloud position judgment, characterized by: The following steps are involved: S1. Select the evaluation indicators involved in the engine health status evaluation, and input the original data of the evaluation indicators involved in the engine health status evaluation; The evaluation indicators selected in step S1 for engine health status evaluation include: (1) Temperature health parameter: The exhaust temperature after the turbine of the aircraft engine is selected. 45 ; (2) Pressure health parameter: The high pressure compressor outlet pressure Ps3 of the aircraft engine is selected; (3) Speed ​​parameter: select the high pressure shaft speed N2 of the aircraft engine; (4) Stall margin parameter: Use the aircraft engine fan stall margin SM Fan , low pressure compressor stall margin SM LPC , High pressure compressor stall margin SM HPC Three stall margins; (5) Fuel parameters: Select the specific fuel consumption rate T of the aircraft engine. sfc and fuel consumption ratio η; where, W f-PLA1 、N 2-PLA1 The fuel flow and low pressure shaft speed in PLA1 state; W f-PLA2 、N 2-PLA2 The fuel flow and low pressure shaft speed in PLA2 state; S2. Divide the health level, determine the comment set and generate a standard evaluation cloud; S3. Construct subjective weighting model and objective weighting model, and determine the comprehensive weight of evaluation indicators based on combined weighting method; S4. Obtain standard values ​​of evaluation indicators, determine ideal cloud locations based on ideal values ​​of evaluation indicators, and determine actual cloud locations based on actual data; The step S4 comprises: S401. Obtain the standard value of the evaluation indicator, and determine the ideal cloud location based on the ideal value of the evaluation indicator: Suppose the position of the m-dimensional normal distribution integrated cloud in the ideal state, that is, the ideal cloud position G 0 Represented as an m-dimensional vector: In the formula, is the ideal cloud center of gravity position, and its value is the expectation of one of the three digital features in the healthy cloud model in the ideal state, that is, it is 1; is the ideal cloud center of gravity height, which is 0.371, where j = 1, 2, ..., m S402. Determine the actual cloud location based on the actual data: (1): Evaluation index cloudification: For each index, select Z sample data x1, x2, ..., x z , calculate the expectation Ex in the digital features of the normal distribution cloud, recorded as: Since there are m evaluation indicators in total, the expectations of m evaluation indicators are obtained; (2) Calculate the weighted integrated cloud position vector The system state reflected by the m evaluation indicators is described by an m-dimensional comprehensive normal distribution cloud. When the system state changes, the position of the m-dimensional comprehensive normal distribution cloud also changes accordingly. The position of the m-dimensional normal distribution integrated cloud, that is, the actual cloud position G is expressed as an m-dimensional vector: G=(G1,G2,...,G m ) In the formula, G j =a j ×b j , b j =w j ×0.371,j=1,2,...,m,a j is the actual cloud center of gravity position, which is equal to the expectation of the jth evaluation index; b j is the actual cloud position height, indicating the weight of the evaluation index relative to the object to be evaluated in the actual state; w j is the weight of the corresponding indicator; S5. Calculate the weighted deviation and determine the health level of the engine; The step S5 comprises: S501. The comprehensive cloud position vector G in the actual state is processed as follows to obtain a set of new vectors G i ′:G′=(G1′,G2′,...,G m '),in: Calculate the weighted deviation σ(0<σ<1) as S502. Evaluate the engine health status based on σ: (1) The qualitative concept membership of σ (x, μ(x)) is calculated and input into the reverse cloud generator to obtain its digital features Ex, En, and He; x=σ+1 Eni'=NORM(0.0125,0.005 2 ) NORM(0.0125,0.005 2 ) means the expected value is 0.0125 and the variance is 0.005 2 is a normal random number; The principle of the reverse cloud generator is as follows: Input: The exact value of N cloud droplets and the membership of the qualitative concept represented by each cloud droplet (x, μ(x)); Output: 3 digital features of the cloud model corresponding to N cloud droplets; Mean variance (2) Input the obtained digital features Ex, En, and He into the forward cloud generator to obtain its evaluation cloud; (3) Compare the obtained evaluation cloud with the standard evaluation clouds of the seven health levels in the review set to determine the normal distribution model that the evaluation cloud can activate. When the overlap between the evaluation cloud and the standard evaluation cloud of any health level exceeds a preset percentage, it is considered that the evaluation cloud can activate the normal distribution model of the health level; If there is only one normal distribution model activated by the evaluation cloud, the health level corresponding to the normal distribution model is recorded as the health assessment result of the engine; If there are two normal distribution models activated by the evaluation cloud, proceed to step (4); (4) According to the two activated normal distribution models and their digital features E x1 、E n1 、He1;E x2 、E n2 , H e2 Recalculate the expected values ​​Ex′, En′, He′ where: The digital features composed of Ex′, En′, and He′ are input into the forward cloud generator to obtain a new evaluation cloud, and then step (3) is performed.

2. The engine health status assessment method based on combined weighting method and cloud position judgment according to claim 1 is characterized in that: The step S2 comprises: S201. The engine health status is divided into 7 health levels, namely, failure, abnormality, degradation, qualified, good, sub-healthy, and healthy, and a comment set V consisting of 7 health levels is formed, namely, {V1, V2, V3, V4, V5, V6, V7} = {healthy, sub-healthy, good, qualified, degradation, abnormal, failure}; S202. Place the comment set V on a continuous language scale and use a normal distribution model to represent the comment set. The expected vector of the normal distribution model of the comment set is (0, 0.167, 0.333, 0.501, 0.668, 0.835, 1.0), and its normal distribution cloud digital features are: The expected value of the fault is Ex = 0, the entropy is En = 0.017, and the excess entropy is He = 0.005; Abnormal expectation Ex = 0.167, entropy En = 0.033, excess entropy He = 0.005; Degraded expectation Ex = 0.333, entropy En = 0.033, excess entropy He = 0.005; Qualified expectation Ex = 0.501, entropy En = 0.033, excess entropy He = 0.005; Good expectation Ex = 0.668, entropy En = 0.0417, excess entropy He = 0.005; Sub-health expectation Ex=0.835, entropy En=0.033, excess entropy He=0.005; Healthy expectation Ex = 1.0, entropy En = 0.0125, excess entropy He = 0.005; S203. Generate a standard evaluation cloud based on the aircraft engine health status rating evaluation set: Input the digital features of the normal distribution cloud of each health level in the comment set into the cloud generator to obtain the standard evaluation cloud of each health level; The forward cloud generator generates a specific number of cloud droplets based on the three digital features of the cloud. The specific steps are as follows: Input: (Ex, En, He, N) Output:((Drop(x1, μ(x1)), Drop(x2, μ(x2)), Λ, Drop(x N ,μ(x N ))) (1) Generate a normal random number En', where En' conforms to a normal distribution with En as the expectation and He as the standard deviation; (2) Generate a normal random number x, which conforms to the normal distribution with Ex as the expectation and En' as the standard deviation; (3) According to (1) and (2), calculate μ(x) = exp[-(x-Ex) 2 / 2(En') 2 ]; (4) Generate cloud droplets (x, μ(x)); (5) Repeat (1) to (4) until the required N cloud droplets are generated.

3. The engine health status assessment method based on combined weighting method and cloud position judgment according to claim 1 is characterized in that: In step S3, an objective weighting module is constructed by using an entropy weight method, including: (1) Assume that n aircraft engine evaluation samples are input in step 1, and each evaluation sample has m indicators, forming the original data matrix X: Among them, x ij represents the jth index of the i-th aircraft engine; (2) Perform standardization preprocessing on each element of the original data matrix to obtain the preprocessed matrix P = (p ij ) n×m : In the formula, is the maximum value of the monitoring data of the jth evaluation indicator; is the minimum value of the monitoring data of the jth evaluation indicator; p ij Indicates x ij The normalized value obtained by standardization preprocessing; (3 Calculate the information entropy E j : Calculate the information entropy E of the jth evaluation indicator j for: (4) Determine the indicator weights: Calculate the weight of the jth evaluation indicator for and According to the above formula, the weight of the jth evaluation indicator in the evaluation process is obtained 4. The engine health status assessment method based on combined weighting method and cloud position judgment according to claim 1 is characterized in that: In step S3, a subjective weighting module is constructed by improving the AHP method, including: (1) Establish the judgment matrix B according to the three-scale method. The specific steps are as follows: (a) Each aircraft engine has m evaluation indicators. The three-scaling method is introduced to quantitatively express the relative importance of each aircraft engine evaluation indicator, and the corresponding comparison matrix A is obtained. gh ) m×m for: Among them, a g Indicates the gth index of the aircraft engine; a h Indicates the hth index of the aircraft engine; g = 1, 2, .., m; h = 1, 2, …, m; Based on the three-scaling method, the element a gh Quantitative expression, its value and corresponding content are as follows: Set the scale value If a gh =0,a g Than a h Important; if a gh =1, a g with a h Equally important; if a gh =2, a h Than a g important; (b) According to the comparison matrix A, find the ranking index; (c) According to the ranking index r i Construct judgment matrix B gh , the element b in the gth row and hth column gh for: Among them, k m =r max / r min ;g=1,2,..,m;h=1,2,…,m; (2) Adjust the judgment matrix Find the quasi-optimal consistent matrix B of the judgment matrix gh ′; In the formula, c gh =logb gh ; (3) Weight determination According to B gh ′, normalize the matrix by column, and get the matrix T gh , whose elements are Calculate the weight of each evaluation index 5. The engine health status assessment method based on combined weighting method and cloud position judgment according to claim 1 is characterized in that: In step S3, determining the comprehensive weight of the evaluation index based on the combined weighting method includes: In the formula, θ represents the proportion of weights determined by improved AHP; ω′ j represents the weight determined by the improved AHP; represents the weight determined by the entropy weight method; ω j Represents the combined weight.

Images