A method for predicting performance trends of a turbofan engine component and an overall engine

Abstract

The application discloses a kind of turbofan engine component and whole machine performance trend prediction method, comprising the following steps: obtaining the component performance estimation historical data of engine;The data is obtained from engine test data, including the performance degradation coefficient of each gas path component of engine test;Load engine model running in specified working condition, input component performance estimation historical data into engine model, start specified working condition, obtain component performance estimation current data, component performance estimation prediction data of engine in specified working condition by engine model;Obtain the whole machine normalized performance degradation estimation parameter.According to the above technical scheme, the performance degradation of the gas path components and the whole machine of the engine can be evaluated under multiple operating conditions, and the evaluation results are normalized to the same evaluation standard. The future engine performance trend is predicted through historical estimation results.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of aero-engine health management, in particular to a method for predicting performance trend of a turbofan engine component and whole machine. BACKGROUND

[0002] For an aircraft, performance management of an aero-engine is very important. Especially for turbojet and turbofan engines, key components such as fans, compressors, turbines and the like work in harsh environments of high temperature, high pressure and high speed, and are prone to damage such as fatigue and wear, resulting in performance degradation. Accurate and effective performance prediction of each component can help develop a maintenance plan to avoid unnecessary over-maintenance or insufficient maintenance; through performance trend prediction of the whole engine, the performance change of the engine can be predicted in advance, such as thrust decline, fuel consumption rate increase and the like.

[0003] However, the operation of the engine has varying working conditions, such as take-off stage, climbing stage, landing stage and the like, and the engine speed has different requirements in different states, making the performance degradation characteristics of the components more complex; at the same time, the performance prediction method based on data has high requirements for data volume and data sources, and the original analysis data also has interference, for example, control system degradation will interfere with the state data representing engine degradation.

[0004] Therefore, a method for predicting performance trend of a turbofan engine component and whole machine is needed, which can isolate the influence of control system degradation on engine degradation and evaluate the performance of the engine in the full envelope domain and under multiple working conditions. SUMMARY

[0005] To achieve the above-mentioned purpose, the present application provides a method for predicting performance trend of a turbofan engine component and whole machine, comprising the following steps:

[0006] Obtaining component performance estimation historical data of the engine; the component performance estimation historical data is obtained from engine test data, including performance degradation coefficients of each gas path component of the engine test;

[0007] Loading an engine model, the engine model runs under a specified working condition, calculates component performance estimation current data based on the specified working condition, and generates component performance prediction data and whole machine performance prediction data;

[0008] Inputting the component performance estimation historical data into the engine model, starting the specified working condition, and obtaining component performance estimation current data and component performance estimation prediction data of the engine under the specified working condition through the engine model;

[0009] Obtaining whole machine normalized performance degradation estimation parameters.

[0010] The engine model generates current data based on the component performance estimation under the specified working condition, and the process comprises:

[0011] Starting the engine and running to the ground intermediate state, comprising: initializing the engine and the control system, performing a loop iteration to realize the engine starting and running, and making the engine run to the ground intermediate state;

[0012] Adjusting the nozzle area A8 and the main fuel flow Wf to make the engine run to the specified working condition; wherein, when the nozzle area A8 and the main fuel flow Wf are adjusted, the engine control system is abandoned, the guide vane angle and in the engine input parameter structure are set as the fan guide vane angle target value and the compressor guide vane angle target value, the fuel flow Wf and the nozzle area A8 are modified through the PID control algorithm, the engine speed reaches the specified target value, and the high pressure power difference is 0.

[0013] The engine starting and running to the ground intermediate state is realized by the control system in the engine model, and the functions involved include: the engine initialization function CreateEngine, the control system initialization function ControlSym_Init, the engine single-step running function EngineStepGo, the parameter passing function Get_Sensor_Para_Model, and the control system single-step running function ControlSym_Go.

[0014] Further, the loop iteration is performed to realize the engine starting and running, which comprises: in the loop iteration process, the throttle lever angle PLA is gradually modified to make the engine gradually run to the ground intermediate state.

[0015] Further, the method for obtaining the component performance estimation prediction data comprises:

[0016] Filtering the component performance estimation historical data and the component performance estimation current data to generate the data to be analyzed;

[0017] According to the trend analysis, the step number is selected to select the analysis method, and the analysis method is called to obtain the component performance degradation coefficient;

[0018] The component performance degradation prediction value and the component performance estimation current data are added to the component performance estimation historical data for the next round of prediction.

[0019] The analysis method is selected according to the trend analysis and the step number, and the analysis method is called to obtain the component performance degradation coefficient.

[0020] If the output engine component performance degradation prediction value in the component performance estimation history data is greater than three times the forward prediction step number, trend prediction is performed using the LSTM-AFFINE prediction network, otherwise linear interpolation is used to generate the component performance degradation prediction value.

[0021] Further, the acquisition of the whole machine normalized performance degradation estimation parameter comprises: the engine model calling a whole machine normalized performance degradation estimation method to acquire the whole machine normalized performance degradation estimation parameter representing the whole machine performance trend according to the component performance estimation history data and the component performance degradation prediction value.

[0022] The acquisition of the whole machine normalized performance degradation estimation parameter further comprises: acquiring the thrust, the turbine rear temperature and the specific fuel consumption when the engine speed reaches a specified target value and the high pressure power difference is 0, performing uniform unit conversion and normalization processing on the thrust, the turbine rear temperature and the specific fuel consumption to generate the normalized standard thrust, the normalized standard turbine rear temperature and the normalized standard specific fuel consumption.

[0023] According to the present application, the performance degradation of the engine air path components and the whole machine can be evaluated under multiple working conditions, and the evaluation results are normalized to the same evaluation standard, and the future engine performance trend is predicted through the historical estimation results. The application of this method can effectively solve the problem that turbojet and turbofan engines have variable working conditions, wide operating envelope and are difficult to find similar working conditions for performance evaluation. BRIEF DESCRIPTION OF DRAWINGS

[0024] Figure 1 is a step diagram of a turbofan engine component and whole machine performance trend prediction method according to an embodiment of the present application;

[0025] Figure 2 is a flowchart of a turbofan engine performance degradation information self-correction mode according to an embodiment of the present application;

[0026] Figure 3 is a flowchart of a turbofan engine performance degradation prediction mode according to an embodiment of the present application;

[0027] Figure 4 is a flowchart of a turbofan engine starting and running to an intermediate state control according to an embodiment of the present application;

[0028] Figure 5 is a flowchart of a turbofan engine running to a specified working state according to an embodiment of the present application;

[0029] Figure 6 is a flowchart of a turbofan engine introducing performance degradation and adjusting fuel according to an embodiment of the present application;

[0030] Figure 7A performance trend prediction network architecture diagram is provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0031] The method can estimate the performance degradation of the engine and the whole engine under multiple working conditions, normalize the estimation results to the same evaluation standard, and integrate the estimation data to predict the performance trend of the future engine.

[0032] The specific implementation of the present application will be described in detail below with reference to the accompanying drawings.

[0033] As shown in Figure 1 The method for predicting the performance trend of the components and the whole engine of the turbofan engine comprises the following steps:

[0034] Step S100: Obtain component performance estimation historical data of the engine;

[0035] The process of extracting the component performance estimation historical data in this step is to extract the performance degradation information in the self-correction mode, and the specific process is as shown in Figure 2 First, parameters are selected from a group of engine test data, and the data of different standards are unit-converted and unified to the input standard of the program.

[0036] Secondly, the test data meeting the input standard of the program are extracted in the steady state to obtain steady state test data; during the extraction process, the relative speed of the compressor in the steady state data is judged, if the relative speed of the compressor is greater than 0.9, the program continues to run, otherwise it is determined that the performance degradation estimation of the test data is not applicable, and it is directly skipped.

[0037] According to the steady state test data, the component performance degradation coefficients of each gas path component are estimated, including: fan efficiency degradation coefficient, fan flow degradation coefficient, compressor efficiency degradation coefficient, compressor flow degradation coefficient, high pressure turbine efficiency degradation coefficient, high pressure turbine flow degradation coefficient, low pressure turbine efficiency degradation coefficient, and low pressure turbine flow degradation coefficient.

[0038] After the estimation and calculation are completed, the performance degradation coefficients estimated this time are saved to constitute the component performance estimation historical data.

[0039] Step S110: Load the engine model, which runs under a specified working condition, calculates the component performance estimation current data based on the specified working condition, and generates component performance prediction data and whole engine performance prediction data.

[0040] In the present application, as Figure 3As shown, the performance degradation information extracted in the self-repairing mode is combined to realize the turbofan engine performance degradation prediction mode through iterative calculation of the engine model, as shown in step S120.

[0041] Step S120: input the component performance estimation history data into the engine model, start the specified working state, obtain the component performance estimation current data of the engine in the specified working state through the engine model, and output the engine component performance estimation current data and the component performance estimation prediction data.

[0042] The process of generating component performance estimation current data based on the specified working state by the engine model includes:

[0043] 1) Start the engine and run to the ground intermediate state; realize through the control system in the engine model, as shown in Figure 4 As shown, it includes: initializing the engine through the engine initialization function CreateEngine, initializing the control system through the control system initialization function ControlSym_Init, executing loop iteration to realize engine starting and running through the engine single-step running function EngineStepGo, the parameter passing function Get_Sensor_Para_Model and the control system single-step running function ControlSym_Go, and gradually modifying the throttle lever angle PLA to make the engine gradually run to the ground intermediate state. This process takes very little time to calculate, and the loop iteration number is generally controlled within 10000 times;

[0044] 2) Adjust the nozzle area A8 and the main fuel flow Wf to make the engine run to the specified working state; the process is as shown in Figure 5 As shown: the engine single-step running function EngineStepGo integrates the current adjusted nozzle area A8, the main fuel flow Wf, the fan guide vane angle target value Aim_a1 and the compressor guide vane angle target value Aim_a2 to calculate and judge whether the engine high-speed target value and the engine low-speed target value reach the specified control threshold. If not, adjust the nozzle area A8 and the main fuel flow Wf through PID until the engine high-speed target value and the engine low-speed target value reach the target value, at which time the main fuel flow Wf makes the high-pressure power difference 0.

[0045] In the process of adjusting the nozzle area A8 and the main fuel flow Wf through PID, the engine runs to the specified working state (specified T6, N1), and the flow is as shown in Figure 6As shown, in the adjustment process, the engine control system is abandoned, the specified performance degradation value (such as Power_Dat_Compress+) is input, the fan vane angle Angle_FanVane and the compressor vane angle Angle_CompressVane in the engine input parameter structure are set as the fan vane angle target value Aim_a1 and the compressor vane angle target value Aim_a2, and the fuel flow Wf and the nozzle area A8 are modified through the PID control algorithm, so that the engine speed reaches the specified target value, and the high-pressure power difference is 0.

[0046] The test data in the specified working state is extracted to estimate the current data, including: selecting parameters from the engine test data, converting units and unifying rules for different standard data to make them meet the input standard of the program; extracting the steady-state section of the processed test data to obtain steady-state test data; during the extraction process, the relative speed of the compressor in the steady-state section data is judged, if the relative speed of the compressor > 0.8, the program continues to run, otherwise it is determined that the test data is not suitable for performance degradation estimation, and directly jumps out; at this time, the performance degradation coefficient of the component is extracted, which is the same as in step S100, including: fan efficiency degradation coefficient, fan flow degradation coefficient, compressor efficiency degradation coefficient, compressor flow degradation coefficient, high-pressure turbine efficiency degradation coefficient, high-pressure turbine flow degradation coefficient, low-pressure turbine efficiency degradation coefficient and low-pressure turbine flow degradation coefficient.

[0047] The engine model also generates engine component performance degradation prediction values by estimating historical data and current data of component performance of the engine, and the prediction model for generating engine component performance degradation prediction values is as follows: Figure 7 As shown, the prediction process includes:

[0048] 1) Filter the historical data and current data of component performance estimation to generate data to be analyzed;

[0049] 2) According to the trend analysis prediction step number selection analysis method, call the analysis method to obtain the component performance degradation coefficient; wherein the trend analysis prediction step number is determined based on the time step of the existing data to be analyzed;

[0050] The step of selecting the analysis method according to the trend analysis prediction step number comprises: if the output engine component performance degradation prediction value in the component performance estimation history data is greater than three times the forward prediction step number, then a trend prediction is performed using an LSTM-AFFINE prediction network, otherwise a linear interpolation is used to perform prediction to generate a component performance degradation prediction value; the content of the component performance degradation prediction value is the same as that of the component performance estimation history data and the component performance estimation current data, and comprises: a fan efficiency degradation coefficient, a fan flow degradation coefficient, a compressor efficiency degradation coefficient, a compressor flow degradation coefficient, a high-pressure turbine efficiency degradation coefficient, a high-pressure turbine flow degradation coefficient, a low-pressure turbine efficiency degradation coefficient and a low-pressure turbine flow degradation coefficient.

[0051] 3) The component performance degradation prediction value and the component performance estimation current data are added to the component performance estimation history data, and are used for the next round of prediction.

[0052] Step S130: Obtain the normalized overall performance degradation estimation parameter;

[0053] In this step, the engine model calls the overall normalized performance degradation estimation method to obtain the overall normalized performance degradation estimation parameter representing the overall performance trend according to the component performance estimation history data and the component performance degradation prediction value;

[0054] On the other hand, according to the thrust, the turbine rear temperature and the specific fuel consumption under the specified working state, i.e., the engine speed reaches a specified target value and the high-pressure power difference is 0, the thrust, the turbine rear temperature and the specific fuel consumption are further converted into a unified unit and normalized to generate a normalized standard thrust, a normalized standard turbine rear temperature and a normalized standard specific fuel consumption.

[0055] Further, the overall normalized performance degradation estimation parameter is also added to the overall normalized performance degradation estimation history data, and is used for subsequent prediction.

[0056] In the overall process, the present application performs multiple data phase analysis on the degradation trends of the engine components and the overall engine. Different stages of data extraction have different requirements, for example, the data obtained when estimating the initial degradation value requires n2r to reach 0.9, and the data obtained when analyzing the current running state stage requires n2r to reach 0.9. In actual application, the component performance estimation value can realize the prediction of the overall engine performance; the overall engine performance estimation value can also realize the prediction of the component performance.

[0057] Through the application, the performance estimation of the engine can be realized in the full envelope domain and under multiple working conditions; in the adjustment process of running the engine to the specified working state, the engine control system is abandoned, the influence of the control system degradation on the engine degradation can be isolated, and the whole engine degradation information of the engine body is obtained; meanwhile, the performance prediction of the engine air path components and the whole engine within a certain time in the future is realized according to the historical engine degradation estimation results.

[0058] The above disclosed are only several specific embodiments of the present application, but the present application is not limited thereto, and any variation that can be thought of by any person skilled in the art shall fall within the protection scope of the present application.

Claims

1. A method for predicting the performance trends of turbofan engine components and the overall engine, characterized in that, Includes the following steps: Obtain historical data on the performance estimation of engine components; the historical data on the performance estimation of components is obtained from engine test data, including the performance degradation coefficients of each air passage component during engine test. Load the engine model, which runs under a specified operating condition, calculate the current data of component performance estimation based on the specified operating condition, and generate component performance prediction data and overall engine performance prediction data; Input the historical data of component performance estimation into the engine model, start the specified working state, and obtain the current data of component performance estimation and the predicted data of component performance estimation of the engine in the specified working state through the engine model; Obtaining normalized performance degradation estimation parameters for the entire engine includes: the engine model uses historical data on component performance estimation and predicted data on component performance degradation to call the normalized performance degradation estimation method for the entire engine to obtain normalized performance degradation estimation parameters that characterize the performance trend of the entire engine; specifically, it includes: obtaining the thrust, turbine after-temperature, and fuel consumption rate when the engine speed reaches the specified target value and the high-pressure power difference is 0, and performing unified unit conversion and normalization on the thrust, turbine after-temperature, and fuel consumption rate to generate normalized standard thrust, normalized standard turbine after-temperature, and normalized standard fuel consumption rate; The process by which the engine model generates current data for estimating component performance under specified operating conditions includes: Starting the engine and running it to the intermediate ground state includes: initializing the engine and control system, executing iterative cycles to start and run the engine, and running the engine to the intermediate ground state. Adjust the nozzle area A8 and the main fuel flow rate Wf to bring the engine to the specified operating state; wherein, when adjusting the nozzle area A8 and the main fuel flow rate Wf, the engine control system is discarded, and the target values ​​of the guide vane angle, fan guide vane angle and compressor guide vane angle in the engine input parameter structure are set. The fuel flow rate Wf and nozzle area A8 are modified by the PID control algorithm so that the engine speed reaches the specified target value and the high pressure power difference is 0.

2. The prediction method according to claim 1, characterized in that, The engine is started and run to the intermediate ground state through the control system built into the engine model. The functions involved include: engine initialization function CreateEngine, control system initialization function ControlSym_Init, engine single-step operation function EngineStepGo, parameter passing function Get_Sensor_Para_Model, and control system single-step operation function ControlSym_Go. The engine initialization function CreateEngine is used to create and initialize an engine model instance. The control system initialization function ControlSym_Init is used to initialize the control system. The EngineStepGo function is used to integrate and adjust the nozzle area A8, main fuel flow Wf, fan guide vane angle target value Aim_a1 and compressor guide vane angle target value Aim_a2, and calculate and determine whether the engine high-pressure speed target value and engine low-speed target value have reached the specified control threshold. The parameter passing function Get_Sensor_Para_Model is used to obtain sensor parameters and pass them to the single-step execution function ControlSym_Go of the control system. The single-step operation function ControlSym_Go of the control system executes the single-step operation of the control system based on sensor parameters and PLA.

3. The prediction method according to claim 1, characterized in that, The process of executing the cyclic iteration to start and run the engine includes: gradually modifying the throttle lever angle PLA during the cyclic iteration process, so that the engine gradually runs to the intermediate state on the ground.

4. The prediction method according to claim 1, characterized in that, The method for obtaining the component performance estimation and prediction data includes: Filter the historical and current component performance estimation data to generate data to be analyzed. Based on the trend analysis and prediction steps, select the analysis method and call the analysis method to obtain the component performance degradation coefficient; The predicted value of component performance degradation and the current data of component performance estimation are added to the historical data of component performance estimation for the next round of prediction.

5. The prediction method according to claim 4, characterized in that, The method for selecting the number of steps based on trend analysis and prediction includes: If the predicted value of engine component performance degradation in the historical data of component performance estimation is greater than three times the number of forward prediction steps, then the LSTM-AFFINE prediction network is used for trend prediction; otherwise, linear interpolation is used for prediction to generate the predicted value of component performance degradation.

Images