An adaptive control method for aircraft thermal management system

Abstract

The present invention belongs to the technical field of aircraft thermal management system control, and proposes an adaptive control method for aircraft thermal management system. The method comprises the following steps: Step S1: acquiring flight parameters and heat load power in real time during the flight of the aircraft; Step S2: selecting the optimal heat transfer path of the thermal management system using a heat transfer path selection model according to the flight parameters and heat load power; Step S3: determining the heat sink flow rate using a heat sink flow prediction model according to the flight parameters, heat load power and the optimal heat transfer path; Step S4: performing real-time heat sink control on the thermal management system according to the heat sink flow rate. The adaptive control method of the present invention can achieve real-time matching of the heat sink heat dissipation capacity, ensure the real-time heat dissipation capacity of the thermal management system, improve the utilization rate of the heat sink, and achieve optimization of heat control.

Description

Technical Field

[0001] The invention belongs to the technical field of aircraft thermal management system control, and in particular relates to an adaptive control method for an aircraft thermal management system. Background Art

[0002] The thermal management system is one of the important subsystems of modern aircraft. Its design purpose is to ensure that all types of aircraft structures and onboard equipment operate within a safe and efficient temperature range. With the increase in the flight speed of the next generation of aircraft and the increase in onboard electronic equipment, aircraft face severe heat dissipation and thermal control problems. At the same time, the aircraft's requirements for aerodynamics and stealth, as well as high flight speeds and high cruising altitudes, make it difficult to use ram air heat sinks. Therefore, it is necessary to formulate adaptive planning and intelligent control thermal management strategies based on the thermal load distribution characteristics of the aircraft at different flight stages to reduce aircraft compensation losses and improve energy utilization efficiency.

[0003] The existing thermal management system control methods mainly use fuel and ram air as the main heat sinks, and the aircraft heat dissipation demand limit as the design target. The control technology is mostly based on PID control method, which controls the fuel heat sink flow according to the key node temperature or temperature change trend. The structure is single and cannot adapt to complex working conditions. It is unable to optimize the system heat transfer path in real time to achieve intelligent scheduling and adaptive dynamic control of multiple heat sinks such as the thermal management system fuel heat sink, ram air heat sink and consumable heat sink, resulting in low energy utilization efficiency of the thermal management system. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention proposes an adaptive control method for an aircraft thermal management system.

[0005] The adaptive control method fully considers the urgent needs of external aerodynamic thermal cooling and integrated electronic equipment cooling of the next generation aircraft. Taking into account the multiple heat sinks and multiple heat transfer paths of the thermal management system, an adaptive real-time control method for the aircraft thermal management system is proposed, which selects the optimal heat transfer path based on a random forest algorithm, optimizes the multi-heat sink flow based on a genetic algorithm, and performs online prediction based on a BP neural network. The method can realize real-time matching of the heat sink heat dissipation capacity, ensure the real-time heat dissipation capacity of the thermal management system, improve the utilization rate of the heat sink, and achieve optimization of heat control.

[0006] The technical solution of the present invention is as follows:

[0007] An adaptive control method for an aircraft thermal management system comprises the following steps:

[0008] Step S1: acquiring flight parameters and heat load power in real time during the flight of the aircraft;

[0009] Step S2: selecting an optimal heat transfer path of the thermal management system using a heat transfer path selection model according to flight parameters and heat load power;

[0010] Step S3: Determine the heat sink flow rate using a heat sink flow rate prediction model according to flight parameters, heat load power and optimal heat transfer path;

[0011] Step S4: According to the heat sink flow rate, the heat management system is controlled in real time.

[0012] Preferably, the flight parameters include flight altitude, flight Mach number and fuel consumption rate.

[0013] Preferably, the heat load power includes the heat load power of the avionics thermal management subsystem and the heat load power of the hydraulic thermal management subsystem.

[0014] Preferably, the heat transfer path selection model in step S2 is obtained by the following method:

[0015] (1) Based on the thermal management system benchmark architecture and typical flight envelope, calculate the heat sink utilization rate of each heat transfer path of the aircraft in each flight phase, compare the heat sink utilization rates of each heat transfer path in the same flight phase, and select the heat transfer path with the highest heat sink utilization rate as the optimal heat transfer path, thereby obtaining the optimal heat transfer path for each flight phase;

[0016] (2) Establish a random forest model with flight parameters and heat load power in a typical flight envelope as input and the optimal heat transfer path as output;

[0017] (3) Taking the flight parameters and heat load power in a typical flight envelope and the optimal heat transfer path in each flight phase as samples, the random forest model is trained to obtain a heat transfer path selection model.

[0018] Preferably, the heat sink flow prediction model in step S3 is obtained by the following method:

[0019] (1) Based on the optimal heat transfer path in each flight phase, a genetic algorithm is used to match the optimal heat sink flow in each flight phase. The constraints of the genetic algorithm include that the fuel tank supply flow meets the engine fuel consumption flow and the temperature of each key node does not exceed the limit temperature. The optimization goal of the genetic algorithm is to maximize the heat sink utilization rate of the optimal heat transfer path;

[0020] (2) A BP neural network is established, with the optimal heat transfer path in each flight phase, the flight parameters and the heat load power in the typical flight envelope as input, and the optimal heat sink flow rate in each flight phase as output. The BP neural network is trained to obtain a heat sink flow rate prediction model.

[0021] Preferably, the optimal heat sink flow rate is one or more of an optimal fuel heat sink flow rate, an optimal ram air heat sink flow rate and an optimal consumable heat sink flow rate.

[0022] Preferably, the expression of the heat sink utilization is as follows:

[0023]

[0024] in, Indicates the flight phase s Heat sink utilization of heat transfer paths, arrive For the flight phase s duration, Indicates the flight phase s The heat transfer path is the heat sink that actually transfers the heat. Indicates the flight phase s The maximum amount of heat that the total heat sink can theoretically transfer. represents the specific heat capacity of the heat sink, represents the heat sink mass flow rate, represents the inlet temperature of the heat sink, Indicates the actual outlet temperature of the heat sink; Indicates the theoretical limit temperature after the heat sink absorbs heat.

[0025] Preferably, the constraint condition expression of the genetic algorithm is as follows:

[0026]

[0027] in, Indicates the oil supply flow rate of the fuel tank; Indicates the engine fuel consumption flow; Indicates the actual fuel temperature at the tank outlet; Indicates the maximum limit temperature of fuel at the tank outlet; Indicates the thermal management system The actual fuel temperature at the inlet of each subsystem, , is the number of subsystems in the thermal management system; Indicates the thermal management system Maximum limit temperature of fuel inlet of each subsystem; Indicates the thermal management system Actual fuel temperature at the outlet of each subsystem; Indicates the thermal management system Maximum limit temperature of fuel at the outlet of each subsystem; Indicates the actual fuel temperature at the engine inlet; Indicates the maximum limit temperature of the engine inlet fuel.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] 1. The adaptive control method of the aircraft thermal management system proposed in the present invention can well perform adaptive real-time control of different flight phases and heat load distribution conditions under the typical flight envelope of the aircraft thermal management system.

[0030] 2. Compared with the existing single control strategy, the adaptive control method of the aircraft thermal management system proposed in the present invention can achieve real-time matching of the heat sink's heat dissipation capacity, ensure the real-time heat dissipation capacity of the thermal management system, improve the heat sink utilization rate of the thermal management system, and achieve optimal heat control, which plays an important role in the fine control of the thermal management system. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. The features and advantages of the present invention can be more clearly understood by referring to the drawings. The drawings are schematic and should not be understood as limiting the present invention in any way. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0032] Figure 1 It is a flow chart of the adaptive control method of the aircraft thermal management system proposed by the present invention.

[0033] Figure 2 It is a technical principle diagram of the adaptive control method of the aircraft thermal management system proposed by the present invention.

[0034] Figure 3 It is a structural diagram of the thermal management system benchmark architecture in Example 1.

[0035] Figure 4 This is the heat sink flow diagram during the full flight phase in Example 1.

[0036] Figure 5 It is a schematic diagram of the temperatures of key nodes under the real-time heat sink regulation of the thermal management system in Example 1.

[0037] Figure 6 It is a schematic diagram of the heat sink utilization rate of the thermal management system in the whole flight stage in Example 1.

[0038] Among them, 1-fuel thermal management subsystem, 2-fuel tank, 3-air-fuel heat exchanger, 4-engine, 5-avionics thermal management subsystem, 6-electronic equipment thermal load, 7-fuel-liquid heat exchanger, 8-first liquid storage tank, 9-air-liquid heat exchanger, 10-liquid-hydraulic heat exchanger, 11-hydraulic thermal management subsystem, 12-fuel-hydraulic heat exchanger, 13-second liquid storage tank, 14-hydraulic action thermal load. DETAILED DESCRIPTION

[0039] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present invention and the features in the embodiments can be combined with each other without conflict.

[0040] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0041] like Figure 1 As shown, the adaptive control method of the aircraft thermal management system proposed in the present invention mainly includes four steps: real-time acquisition of flight parameters and heat load power; selection of the optimal heat transfer path; optimization of heat sink flow; and real-time heat sink control.

[0042] Figure 2 The main technical principles of the adaptive control method of the aircraft thermal management system proposed in the present invention are shown. When selecting the optimal heat transfer path, the heat transfer path is selected based on the random forest algorithm. On the basis of the known thermal management system benchmark architecture, the optimal heat transfer path for each flight stage under the flight envelope is obtained according to the heat sink utilization optimization. The random forest algorithm is used to establish a mapping relationship between flight parameters (flight altitude, flight Mach number and fuel consumption rate, etc.), thermal load power (thermal load power of avionics thermal management subsystem and thermal load power of hydraulic thermal management subsystem, etc.) and the optimal heat transfer path, so that the random forest algorithm can select the optimal heat transfer path.

[0043] When optimizing the heat sink flow, the genetic algorithm is used to match the corresponding optimal heat sink flow (fuel heat sink flow, ram air heat sink flow, and consumable heat sink flow) based on the optimal heat transfer path. The constraints of the genetic algorithm include that the fuel tank supply flow meets the engine fuel consumption flow and the temperature of each key node does not exceed the limit temperature. The optimization goal of the genetic algorithm is to maximize the heat sink utilization rate of the optimal heat transfer path.

[0044] In the actual flight mission execution, since the genetic algorithm takes a long time to calculate and is difficult to meet the real-time requirements, the genetic algorithm is optimized in the offline process to obtain samples, train the BP neural network, and use the BP neural network instead of the genetic algorithm for online prediction. The BP neural network input parameters include flight parameters and heat load power, and the output parameter is the optimal heat sink flow, which realizes the real-time adaptive scheduling of the aircraft thermal management system.

[0045] Example 1

[0046] In order to verify the effectiveness of the adaptive control method of the aircraft thermal management system proposed in this invention, an Amesim simulation system of a typical aircraft thermal management system is built. The aircraft thermal management system benchmark architecture is as follows: Figure 3 shown.

[0047] In the aircraft thermal management system, the fuel is used as a heat sink in the cooling circuit of the fuel thermal management subsystem 1. The fuel absorbs the heat from the refrigeration circuits of the avionics thermal management subsystem 5 and the hydraulic thermal management subsystem 11. A portion of the high-temperature fuel flows into the engine 4 for combustion, and the other portion is cooled by the ram air and flows to the fuel tank 2 to enter the next cycle. In the cooling circuit of the avionics thermal management subsystem 5, the refrigerant starts from the first liquid storage tank 8, flows through the electronic equipment heat load 6 through the pump to cool it, and then transfers the heat to the fuel through the fuel-liquid heat exchanger 7 to dissipate the heat, and then dissipates the heat through the air-liquid heat exchanger 9, and finally flows back to the first liquid storage tank 8. In the cooling circuit of the hydraulic thermal management subsystem 11, there are two system architectures. In the first, the low-temperature refrigerant starts from the second liquid storage tank 13, first dissipates the heat 14 to the hydraulic action heat load, and then the high-temperature refrigerant flows through the fuel-hydraulic heat exchanger 12, and the refrigerant is cooled by the fuel thermal management subsystem 1, and finally flows back to the second liquid storage tank 13. The second method is that the low-temperature refrigerant starts from the second liquid storage tank 13 and first dissipates heat to the hydraulic action heat load 14. Then, the high-temperature refrigerant passes through the liquid-hydraulic heat exchanger 10, and the avionics thermal management subsystem 5 dissipates heat to the high-temperature refrigerant. Then, it flows through the fuel-hydraulic heat exchanger 12, and the fuel thermal management subsystem 1 dissipates heat to the refrigerant for the second time. Finally, the low-temperature refrigerant flows back to the second liquid storage tank 13.

[0048] This embodiment selects a typical flight envelope to implement the adaptive control method of the aircraft thermal management system. The performance description of each flight phase of the typical flight envelope is shown in Table 1.

[0049] Table 1

[0050]

[0051] Under this flight condition, the thermal load range of the thermal management system in each flight phase is shown in Table 2.

[0052] Table 2

[0053]

[0054] Step 1. First, based on the thermal management system benchmark architecture and typical flight envelope, calculate the heat sink utilization of each heat transfer path under each flight phase. This thermal management system has two benchmark architectures, namely, the avionics thermal management subsystem and the hydraulic thermal management subsystem independently exchange heat with the fuel thermal management subsystem, which is defined as heat transfer path 1; and the avionics thermal management subsystem performs additional cooling on the hydraulic thermal management subsystem, which is named heat transfer path 2. The heat sink utilization of the heat transfer path is defined as:

[0055]

[0056] in, Indicates the flight phase s Heat sink utilization of heat transfer paths, arrive For the flight phase s duration, Indicates the flight phase s The heat transfer path is the heat sink that actually transfers the heat. Indicates the flight phase s The maximum amount of heat that the total heat sink can theoretically transfer. represents the specific heat capacity of the heat sink, represents the heat sink mass flow rate, represents the inlet temperature of the heat sink, Indicates the actual outlet temperature of the heat sink; Indicates the theoretical limit temperature after the heat sink absorbs heat.

[0057] The heat sink utilization rates of the two heat transfer paths in each flight stage are compared to obtain the optimal heat transfer path in each flight stage, as shown in Table 3.

[0058] Table 3

[0059]

[0060] Subsequently, the flight altitude, flight Mach number, fuel consumption rate and heat load power (thermal load power of avionics thermal management subsystem and thermal load power of hydraulic thermal management subsystem) of the typical flight envelope were used as input parameters of the random forest algorithm, and the corresponding number of the heat transfer path was used as the output parameter. The random forest algorithm was built in the MATLAB neural network toolbox for training. The implementation of the random forest algorithm uses the TreeBagger random forest training function in MATLAB, the number of decision trees is set to 100, the minimum number of leaves is set to 1, and the training method is set to Classification. After the training is completed, the heat transfer path selection model is obtained, and the samples are input into the heat transfer path selection model. The results are shown in Figure 4, and the selection accuracy rate reaches 100%, which verifies the effectiveness of the heat transfer path selection model in selecting the optimal heat transfer path.

[0061] Table 4

[0062]

[0063] The second step is to use genetic algorithms to match the optimal heat sink flow rate based on the optimal heat transfer path in each flight phase, including the optimal fuel heat sink flow rate and the optimal ram air heat sink flow rate (in this embodiment, since the heat load is relatively small, the fuel heat sink and the ram air heat sink can already match the heat load, so the consumable heat sink is not used). This includes ensuring that the fuel tank supply flow rate meets the engine fuel consumption flow rate and that the temperature of each key node does not exceed the limit temperature. The optimization goal of the genetic algorithm is to maximize the heat sink utilization rate of the thermal management system.

[0064] In this example, the genetic algorithm is built using the Amesim parameter optimization toolbox. The parameters to be optimized in the genetic algorithm are the fuel heat sink flow rate and the ram air flow rate; the optimization goal is to maximize the heat sink utilization rate of the thermal management system. The genetic algorithm training parameter settings are shown in Table 5.

[0065] Table 5

[0066]

[0067] After optimizing the optimal heat sink flow rate in each flight phase under the typical flight envelope, the following can be obtained: Figure 4 The heat sink flow rate during the whole flight stage is shown. Among them, (a) is the fuel heat sink flow rate, (b) is the ram air heat sink flow rate of the avionics thermal management subsystem, and (c) is the ram air heat sink flow rate of the hydraulic thermal management subsystem.

[0068] In the third step, a variety of heat load distribution combinations are used in the offline process of the first and second steps to obtain samples by selecting the optimal heat transfer path and matching the optimal heat sink flow, and the BP neural network is trained to obtain a heat sink flow prediction model.

[0069] The input parameters of the BP neural network include flight parameters and heat load power, and the output parameter is the optimal heat sink flow rate. Matlab / Simulink is used to train the BP neural network model, and the BP neural network hyperparameter selection is shown in Table 6.

[0070] Table 6

[0071]

[0072] Under the adaptive control strategy, the temperature of each key node of the thermal management system is Figure 5As shown, (a) is the outlet temperature of the heat exchanger of the avionics thermal management subsystem, (b) is the outlet temperature of the heat exchanger of the hydraulic thermal management subsystem, and (c) is the outlet temperature of the heat exchanger of the fuel thermal management subsystem. The results show that none of them exceeds the limit temperature, ensuring the heat dissipation capacity and heat utilization efficiency of the thermal management system.

[0073] Step 4: The thermal management system is regulated during the entire flight phase using the existing typical thermal management system PID control method and the adaptive control method of the aircraft thermal management system of this embodiment. The results are as follows: Figure 6 As shown in the figure, the final heat sink utilization rates are 25.8% and 41.0% respectively. The adaptive control method of this embodiment improves the heat sink utilization rate by 15.2%, which plays an important role in improving the heat sink utilization rate and fine control of the thermal management system.

[0074] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An adaptive control method for an aircraft thermal management system, characterized in that: The following steps are involved: Step S1: acquiring flight parameters and heat load power in real time during the flight of the aircraft; Step S2: selecting an optimal heat transfer path of the thermal management system using a heat transfer path selection model according to flight parameters and heat load power; Step S3: Determine the heat sink flow rate using a heat sink flow rate prediction model according to flight parameters, heat load power and optimal heat transfer path; Step S4: According to the heat sink flow rate, the heat management system is controlled in real time; The flight parameters include flight altitude, flight Mach number and fuel consumption rate; The thermal load power includes the thermal load power of the avionics thermal management subsystem and the thermal load power of the hydraulic thermal management subsystem; The heat transfer path selection model in step S2 is obtained by the following method: (1) Based on the thermal management system benchmark architecture and typical flight envelope, calculate the heat sink utilization rate of each heat transfer path of the aircraft in each flight phase, compare the heat sink utilization rates of each heat transfer path in the same flight phase, and select the heat transfer path with the highest heat sink utilization rate as the optimal heat transfer path, thereby obtaining the optimal heat transfer path for each flight phase; (2) Establish a random forest model with flight parameters and heat load power in a typical flight envelope as input and the optimal heat transfer path as output; (3) Taking the flight parameters and heat load power in a typical flight envelope and the optimal heat transfer path in each flight phase as samples, the random forest model is trained to obtain a heat transfer path selection model.

2. The adaptive control method according to claim 1, characterized in that: The heat sink flow prediction model in step S3 is obtained by the following method: (1) Based on the optimal heat transfer path in each flight phase, a genetic algorithm is used to match the optimal heat sink flow in each flight phase. The constraints of the genetic algorithm include that the fuel tank supply flow meets the engine fuel consumption flow and the temperature of each key node does not exceed the limit temperature. The optimization goal of the genetic algorithm is to maximize the heat sink utilization rate of the optimal heat transfer path; (2) A BP neural network is established, with the optimal heat transfer path in each flight phase, the flight parameters and the heat load power in the typical flight envelope as input, and the optimal heat sink flow rate in each flight phase as output. The BP neural network is trained to obtain a heat sink flow rate prediction model.

3. The adaptive control method according to claim 2, characterized in that: The optimal heat sink flow rate is one or more of an optimal fuel heat sink flow rate, an optimal ram air heat sink flow rate, and an optimal consumable heat sink flow rate.

4. The adaptive control method according to claim 3, characterized in that: The expression of the heat sink utilization is as follows: in, Indicates the flight phase s Heat sink utilization of heat transfer paths, arrive For the flight phase s duration, Indicates the flight phase s The heat transfer path is the heat sink that actually transfers the heat. Indicates the flight phase s The maximum amount of heat that the total heat sink can theoretically transfer. represents the specific heat capacity of the heat sink, represents the heat sink mass flow rate, represents the inlet temperature of the heat sink, Indicates the actual outlet temperature of the heat sink; Indicates the theoretical limit temperature after the heat sink absorbs heat.

5. The adaptive control method according to claim 4, characterized in that: The constraint expression of the genetic algorithm is as follows: in, Indicates the oil supply flow rate of the fuel tank; Indicates the engine fuel consumption flow; Indicates the actual fuel temperature at the tank outlet; Indicates the maximum limit temperature of fuel at the tank outlet; Indicates the thermal management system The actual fuel temperature at the inlet of each subsystem, , is the number of subsystems in the thermal management system; Indicates the thermal management system Maximum limit temperature of fuel inlet of each subsystem; Indicates the thermal management system Actual fuel temperature at the outlet of each subsystem; Indicates the thermal management system Maximum limit temperature of fuel at the outlet of each subsystem; Indicates the actual fuel temperature at the engine inlet; Indicates the maximum limit temperature of the engine inlet fuel.

Images