An Optimization Method for Aircraft Engine Warm-up Process

Abstract

This invention discloses an optimization method for the warm-up process of an aero-engine. First, the minimum tip clearance δ1 of the high-pressure turbine, the minimum tip clearance δ2 of the high-pressure compressor, and the minimum thrust F during takeoff are obtained during the engine's history. m Total fuel consumption (TFC) throughout the entire process is related to warm-up time (Δt) and warm-up speed (N). H The corresponding samples; then, based on the above samples, Δt and N are established through an artificial neural network. H For δ1, δ2, F m And the prediction model of TFC. Finally, based on the δ1, δ2, F required for practical use. m The minimum value is used as a constraint. The ε-constraint method is used to select the combination of the minimum required warm-up time and warm-up speed. If the combination is not unique, the combination with the minimum corresponding TFC is selected from the results to complete the optimization of the warm-up process. This invention uses an artificial neural network to establish the relationship between relevant variables and warm-up time and warm-up speed. Under multiple constraints, the ε-constraint method is used to select the minimum required warm-up time, thus scientifically optimizing the engine warm-up process.

Description

Technical Field

[0001] This invention relates to an optimization method for the warm-up process of an aero-engine, belonging to the technical field of aero-engine warm-up process optimization. Background Technology

[0002] Many aircraft engine user manuals stipulate that when operating in low-temperature environments, the engine needs to be kept at a certain speed for a period of time after a successful start to warm it up. In actual use, if the aircraft engine is not warmed up during a cold start, it may cause a decrease in thrust during takeoff, which in turn affects the payload that can be carried during takeoff and may even affect the safety of the takeoff process. The existence of a warm-up process directly increases the time the aircraft spends on the ground or on the deck, thus restricting the aircraft's sortie efficiency.

[0003] my country's existing warm-up regulations are based on foreign engine warm-up regulations, and there is currently no standardized and procedural method for determining the warm-up process for aero engines. Therefore, optimizing the warm-up procedure and shortening the warm-up time are of great practical significance. Summary of the Invention

[0004] The technical problem to be solved by this invention is to provide an optimization method for the warm-up process of an aero-engine, which scientifically formulates the warm-up process of an aero-engine by using artificial neural networks and the ε-constraint method.

[0005] To solve the above-mentioned technical problems, the present invention adopts the following technical solution:

[0006] An optimized method for the warm-up process of an aircraft engine includes the following steps:

[0007] Step 1: Combine the engine warm-up time and warm-up speed as a combination, and obtain the minimum tip clearance of the high-pressure turbine, the minimum tip clearance of the high-pressure compressor, the minimum thrust during takeoff, and the total fuel consumption of the engine throughout its entire life cycle under different combinations, i.e., different warm-up times and warm-up speeds, as training samples.

[0008] Step 2: Set constraints during the warm-up process;

[0009] Step 3: Using warm-up time and warm-up speed as independent variables, and minimum tip clearance of high-pressure turbine, minimum tip clearance of high-pressure compressor, minimum thrust during takeoff and total fuel consumption during the engine's entire lifespan as dependent variables, an artificial neural network is used to establish a predictive model of the dependent variables with respect to the independent variables. The training samples from Step 1 are then used for training to obtain a well-trained predictive model.

[0010] Step 4: With the minimum warm-up time as the optimization objective and the constraints set in Step 2 as constraints, the ε-constraint method is used to solve the prediction model trained in Step 3 to obtain several combined solutions of warm-up time and warm-up speed.

[0011] Step 5: If the combined solution of warm-up time and warm-up speed obtained in Step 4 exists, proceed to Step 6; otherwise, return to Step 2 to modify the constraints.

[0012] Step 6: If the combination of warm-up time and warm-up speed obtained in Step 4 is unique, proceed to Step 7; otherwise, select the combination of warm-up time and warm-up speed corresponding to the minimum total fuel consumption during the entire engine life and proceed to Step 7.

[0013] Step 7: Use the warm-up time and warm-up speed obtained in Step 6 to verify the results, and obtain the verification results of the minimum tip clearance of the high-pressure turbine, the minimum tip clearance of the high-pressure compressor, and the minimum thrust during takeoff. Determine whether the verification results are within the constraints set in Step 2. If so, use the warm-up time and warm-up speed obtained in Step 6 as the final optimization results; otherwise, put the verification results into the training samples in Step 1 and return to Step 3 to continue training.

[0014] As a preferred embodiment of the present invention, in step 1, the engine's entire lifecycle refers to the entire process from the start of engine startup to the end of flight.

[0015] As a preferred embodiment of the present invention, in step 2, the constraints include the minimum tip clearance of the high-pressure turbine, the minimum tip clearance of the high-pressure compressor, and the minimum acceptable value of the minimum thrust during takeoff.

[0016] As a preferred embodiment of the present invention, the training samples in step 1 are obtained in the following manner:

[0017] 1) Determine the ground idle speed N idle And the maximum permissible speed N during the warm-up process. max ;

[0018] 2) Determine the maximum allowable warm-up time t max ;

[0019] 3) Increase the warm-up speed from N idle To N max Divide into several equal parts;

[0020] 4) Set the warm-up time from 0 to t max Divide into 5 equal parts;

[0021] 5) Select any warm-up speed from 3) and any warm-up time from 4) as a combination, conduct experiments or calculations, and obtain the corresponding minimum tip clearance of the high-pressure turbine, minimum tip clearance of the high-pressure compressor, minimum thrust during takeoff, and total fuel consumption of the engine throughout its entire lifespan under different combinations.

[0022] A computer device includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the computer program to implement the steps of the optimized method for the aircraft engine warm-up process.

[0023] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the optimized method for the aircraft engine warm-up process.

[0024] Compared with the prior art, the present invention, employing the above technical solution, has the following technical effects:

[0025] This invention, based on the actual operating requirements of engines, utilizes an Artificial Neural Network (ANN) to establish the relationship between relevant parameters and warm-up time and warm-up speed. It then employs the ε-constraint method for multi-objective optimization to obtain the minimum required combination of warm-up time and warm-up speed. If this combination is not unique, the warm-up process with the lowest total fuel consumption is selected, thereby scientifically formulating or optimizing the engine warm-up process. This provides a standardized and streamlined warm-up method for aero-engines. Attached Figure Description

[0026] Figure 1 This is a flowchart of an optimized method for the warm-up process of an aero-engine according to the present invention;

[0027] Figure 2 It is a sample of the relationship between warm-up speed, warm-up time and minimum tip clearance of the compressor;

[0028] Figure 3 It is a sample of the relationship between warm-up speed, warm-up time and minimum tip clearance of high-pressure turbine;

[0029] Figure 4 It is a sample of the relationship between warm-up time, warm-up speed and minimum thrust during takeoff;

[0030] Figure 5 This is a sample of the relationship between warm-up time, warm-up speed, and total fuel consumption. Detailed Implementation

[0031] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0032] During a cold start of an aircraft engine, failure to warm up may result in a decrease in thrust during takeoff. Currently, there is no standardized and streamlined method for determining the aircraft engine warm-up procedure. This invention optimizes the aircraft engine warm-up process based on experimental or calculation results, and establishes an optimal warm-up procedure for the engine, such as... Figure 1 As shown, the specific process is as follows:

[0033] 1) Obtain the minimum tip clearance δ1 of the high-pressure turbine, the minimum tip clearance δ2 of the high-pressure compressor, and the minimum thrust F during takeoff in different processes. m Based on the TFC test results or calculation results of total fuel consumption throughout the entire process, set the constraints in the optimization process: the minimum acceptable values ​​of δ1 and δ2, F m The minimum acceptable value.

[0034] 2) Based on existing engine test results or calculation results, artificial neural networks are used to establish high-pressure δ1, δ2, and F respectively. m Total fuel consumption (TFC) throughout the entire process is related to warm-up time (Δt) and warm-up speed (N). H The relationship is as follows:

[0035] a. Determine the ground idle speed N idle And the maximum permissible speed N during the warm-up process. max ;

[0036] b. Determine the maximum allowable warm-up time t max ;

[0037] c. Change the warm-up time from 0 to t max Divide into 5 equal parts;

[0038] d. Increase the warm-up speed from N idle To N max Divide into several equal parts;

[0039] e. Combine the warm-up speed and warm-up time from c and d to form a warm-up process, and conduct experiments or calculations to obtain F. m δ1, δ2 and TFC in different N H The result under the combination of Δt;

[0040] f, with N H And Δt are independent variables, F m δ1, δ2, and TFC are the dependent variables, and F is obtained by training an artificial intelligence neural network. m δ1, δ2 and TFC with respect to N H The prediction model for Δt.

[0041] 3) Taking the shortest Δt as the optimization objective and the constraints established in step 1) as constraints, use the ε-constraint method to find the values ​​that satisfy Δt and N.H The combination of .

[0042] 4) If Δt and N are obtained in 3) H If a combination exists, proceed to step 5); otherwise, return to step 1) to modify the constraints.

[0043] 5) If the obtained Δt and N H If the combination is unique, proceed to step 7; otherwise, proceed to step 6.

[0044] 6) Select the result with the smallest TFC from the results given in 5), and then proceed to step 7).

[0045] 7) Reuse calculations or experiments to verify the current Δt and N. H If the warm-up effect is within the constraints, input the optimization result and end the process; if it fails to meet the constraints, return to step 1) and use the current calculation result or experimental result as a training sample for the artificial neural network again.

[0046] Example

[0047] First, the minimum tip clearance δ1 of different high-pressure turbines, the minimum tip clearance δ2 of different high-pressure compressors, and the minimum thrust F during takeoff are obtained through calculation or experimental methods. m TFC with different total fuel consumption, warm-up time Δt, and warm-up speed N H The corresponding sample points; such as Figures 2-5 As shown.

[0048] Optimize the warm-up process using the current sample:

[0049] 1) Employ an artificial neural network (ANN) with Δt and N H Using δ1, δ2, and F as independent variables, fit the values. m And the prediction model of TFC.

[0050] 2) Set the constraints during the warm-up process: δ1 is not less than 0.19mm, δ2 is not less than 0.19mm.

[0051] 3) Set F m The minimum values ​​are 120kN, 120.5kN, 121kN, 121.5kN and 122kN respectively.

[0052] 4) Using δ1, δ2, F m Given the constraints, with the goal of minimizing Δt, the ε-constraint method is used for optimization.

[0053] The optimization results are shown in the table below:

[0054] Table 1 Optimization Results

[0055] <![CDATA[F m / kN]]> <![CDATA[N H / %]]> Δt / min 120 86.94 2.33 120.5 87.26 2.85 121 87.15 3.45 121.5 89.03 3.64 122 87.98 4.54

[0056] In summary, the warm-up process optimized using the warm-up process optimization method of the present invention can systematically and procedurally formulate the warm-up process. The optimized warm-up time is reduced by more than 20% compared with the traditional warm-up process, and the fuel consumption is reduced by more than 20%. It has important engineering reference value for the formulation of the warm-up process of aero-engines.

[0057] Based on the same inventive concept, this application provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the aforementioned optimization method for the aircraft engine warm-up process.

[0058] Based on the same inventive concept, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the aforementioned optimized method for the aircraft engine warm-up process.

[0059] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0060] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0061] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0062] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0063] The above embodiments are merely illustrative of the technical concept of the present invention and should not be construed as limiting the scope of protection of the present invention. Any modifications made to the technical solutions based on the technical concept proposed in this invention shall fall within the scope of protection of this invention.

Claims

1. An optimized method for the warm-up process of an aircraft engine, characterized in that, Includes the following steps: Step 1: Combine the engine warm-up time and warm-up speed as a combination, and obtain the minimum tip clearance of the high-pressure turbine, the minimum tip clearance of the high-pressure compressor, the minimum thrust during takeoff, and the total fuel consumption of the engine throughout its entire life cycle under different combinations, i.e., different warm-up times and warm-up speeds, as training samples. Step 2: Set constraints during the warm-up process; Step 3: Using warm-up time and warm-up speed as independent variables, and minimum tip clearance of high-pressure turbine, minimum tip clearance of high-pressure compressor, minimum thrust during takeoff and total fuel consumption during the engine's entire lifespan as dependent variables, an artificial neural network is used to establish a predictive model of the dependent variables with respect to the independent variables. The training samples from Step 1 are then used for training to obtain a well-trained predictive model. Step 4: With the minimum warm-up time as the optimization objective and the constraints set in Step 2 as constraints, the ε-constraint method is used to solve the prediction model trained in Step 3 to obtain several combined solutions of warm-up time and warm-up speed. Step 5: If the combined solution of warm-up time and warm-up speed obtained in Step 4 exists, proceed to Step 6; otherwise, return to Step 2 to modify the constraints. Step 6: If the combination of warm-up time and warm-up speed obtained in Step 4 is unique, proceed to Step 7; otherwise, select the combination of warm-up time and warm-up speed corresponding to the minimum total fuel consumption during the entire engine life and proceed to Step 7. Step 7: Use the warm-up time and warm-up speed obtained in Step 6 to verify the results, and obtain the verification results of the minimum tip clearance of the high-pressure turbine, the minimum tip clearance of the high-pressure compressor, and the minimum thrust during takeoff. Determine whether the verification results are within the constraints set in Step 2. If so, use the warm-up time and warm-up speed obtained in Step 6 as the final optimization results; otherwise, put the verification results into the training samples in Step 1 and return to Step 3 to continue training.

2. The method for optimizing the warm-up process of an aero-engine according to claim 1, characterized in that, In step 1, the engine's entire lifecycle refers to the entire process from the start of engine startup to the end of flight.

3. The optimized method for the warm-up process of an aero-engine according to claim 1, characterized in that, In step 2, the constraints include the minimum tip clearance of the high-pressure turbine, the minimum tip clearance of the high-pressure compressor, and the minimum acceptable thrust during takeoff.

4. The optimized method for the warm-up process of an aero-engine according to claim 1, characterized in that, The training samples in step 1 are obtained through the following methods: 1) Determine the ground idle speed N idle And the maximum permissible speed N during the warm-up process. max ; 2) Determine the maximum allowable warm-up time t max ; 3) Increase the warm-up speed from N idle To N max Divide into several equal parts; 4) Set the warm-up time from 0 to t max Divide into 5 equal parts; 5) Select any warm-up speed from 3) and any warm-up time from 4) as a combination, conduct experiments or calculations, and obtain the corresponding minimum tip clearance of the high-pressure turbine, minimum tip clearance of the high-pressure compressor, minimum thrust during takeoff, and total fuel consumption of the engine throughout its entire lifespan under different combinations.

5. A computer device comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the optimized method for the aircraft engine warm-up process as described in any one of claims 1 to 4.

6. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the optimized method for the warm-up process of an aircraft engine as described in any one of claims 1 to 4.

Images