Intake duct adaptive control method, device and equipment based on deformation bulge

Abstract

The present invention relates to an adaptive control method, device and equipment for an intake duct based on a deformable bulge. The method comprises: obtaining the configuration of the intake duct and determining the position of the bulge in the intake duct; constructing a bulge deformation mapping model according to the relationship between the applied force and the deformation of the bulge; constructing a flow field mapping model according to the relationship between the deformation of the bulge and the flow field characteristics; identifying the working mode of the intake duct and judging whether the intake duct is in a starting state. If the intake duct is in a non-starting state, the bulge shape is regulated and controlled according to the preset target pressure value and the monitored pressure value through the bulge deformation mapping model and the flow field mapping model to optimize the flow field characteristics of the intake duct. The present invention can quickly and efficiently predict from the applied force to the bulge profile, and then from the bulge profile to the flow field characteristics through the constructed bulge deformation mapping model and flow field mapping model, shortening the analysis and optimization cycle and meeting the real-time application requirements.

Description

Technical Field

[0001] The present invention relates to the technical field of bulge intake duct control, and in particular to an intake duct adaptive control method, device and equipment based on a deformable bulge. Background Art

[0002] In the field of modern aviation, aircraft engines are the core power components of aircraft, and the performance of their air intakes is directly related to the overall flight performance, efficiency and safety of the aircraft. With the rapid development of aviation technology, the shape of the air intake needs to be flexibly adjusted. Facing the flow fields under different flight conditions, the traditional fixed geometry air intakes lack the ability to adjust and are difficult to meet various flight conditions at the same time.

[0003] In the prior art, although mechanical adjustment devices have been introduced to achieve wear adjustment of the intake duct shape, such devices often have complex structures and delayed responses, making it difficult to meet the needs of rapidly changing flow fields and unable to achieve real-time optimization of the flow fields. Therefore, traditional mechanical adjustment devices have obvious deficiencies in dynamic response and real-time response.

[0004] At present, engineers need to rely on experience to reduce the geometric adjustment of the inlet bulge. There is a lack of systematic and refined design methods, and it is difficult to achieve precise control of the bulge surface. In addition, the existing inlet adjustment technology is mainly based on preset geometric schemes, lacks the ability of real-time monitoring and dynamic optimization, and cannot make adaptive adjustments according to the actual changes in the flow field state. This makes it difficult for the inlet to achieve optimal performance under flight conditions.

[0005] In addition, the existing technology has deficiencies in the working state of the inlet, and cannot achieve real-time dynamic optimization control of the inlet flow field characteristics. Therefore, under complex and changeable flight conditions, the shape of the inlet cannot be adaptively adjusted according to the actual flow field state, limiting the further improvement of the overall performance of the aircraft engine. Summary of the invention

[0006] Based on this, it is necessary to provide an adaptive control method, device and equipment for the air inlet based on a deformable bulge, which can efficiently and accurately control the bulge profile and improve the restart performance of the air inlet under complex flight conditions, in order to address the above technical problems.

[0007] An adaptive control method for an air intake duct based on a deformable bulge, the method comprising:

[0008] Acquire the air intake duct configuration and determine the position of the bulge in the air intake duct;

[0009] A bulge deformation mapping model is constructed according to the relationship between the applied force and the deformation of the bulge; a flow field mapping model is constructed according to the relationship between the deformation of the bulge and the flow field characteristics;

[0010] The working mode of the intake duct is identified to determine whether the intake duct is in a starting state. If the intake duct is in a non-starting state, the bulge shape is regulated according to the preset target pressure value and the monitored pressure value through the bulge deformation mapping model and the flow field mapping model to optimize the flow field characteristics of the intake duct.

[0011] An adaptive control device for an air intake duct based on a deformable bulge, the device comprising:

[0012] A configuration determination module, used to obtain the configuration of the air inlet and determine the position of the bulge in the air inlet;

[0013] A model building module, used to build a bulge deformation mapping model according to the relationship between the applied force and the deformation of the bulge; and to build a flow field mapping model according to the relationship between the deformation of the bulge and flow field characteristics;

[0014] The control and optimization module is used to identify the working mode of the intake duct and determine whether the intake duct is in a starting state. If the intake duct is in a non-starting state, the bulge shape is controlled according to the preset target pressure value and the monitored pressure value through the bulge deformation mapping model and the flow field mapping model to optimize the flow field characteristics of the intake duct.

[0015] A computer device includes a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the adaptive control method of an air intake duct based on a deformable bulge when executing the computer program.

[0016] The above-mentioned adaptive control method, device and equipment of the intake duct based on deformable bulge determine the position of the bulge in the intake duct by acquiring the intake duct configuration; then, a bulge deformation mapping model is constructed according to the relationship between the applied force and the deformation of the bulge; a flow field mapping model is constructed according to the relationship between the deformation of the bulge and the flow field characteristics; finally, the working mode of the intake duct is identified to determine whether the intake duct is in a starting state. If the intake duct is in a non-starting state, the bulge shape is regulated according to the preset target pressure value and the monitored pressure value through the bulge deformation mapping model and the flow field mapping model to optimize the flow field characteristics of the intake duct.

[0017] The present invention constructs a bulge deformation mapping model according to the relationship between the applied force and the deformation of the bulge, thereby realizing the accurate prediction of the bulge surface under different applied forces, which can greatly improve the efficiency and accuracy of bulge shape control; constructs a flow field mapping model according to the relationship between the bulge deformation and the flow field characteristics, which can intuitively display the influence of different bulge surfaces on the inlet flow field characteristics, and realizes the rapid prediction from the bulge surface to the flow field characteristics; the present invention can realize the rapid and efficient prediction from the applied force to the bulge surface, and then from the bulge surface to the flow field characteristics through the constructed bulge deformation mapping model and flow field mapping model, thereby shortening the analysis and optimization cycle and meeting the real-time application needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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 or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0019] Figure 1 It is a flowchart of an adaptive control method of an air intake duct based on a deformable bulge in one embodiment;

[0020] Figure 2 A flowchart of an adaptive control method for an air intake duct based on a deformable bulge in one embodiment;

[0021] Figure 3 A schematic diagram of the position of a bulge in an embodiment;

[0022] Figure 4 A schematic diagram of the deformation of a bulge under stress in one embodiment;

[0023] Figure 5 A schematic diagram of the arrangement of a pressure sensor in one embodiment;

[0024] Figure 6 Schematic diagram of the wall pressure distribution corresponding to the working mode of the inlet duct in an embodiment; wherein, Figure 6 (a) is a schematic diagram of the wall pressure distribution corresponding to the starting state. Figure 6 (b) is a schematic diagram of the wall pressure distribution corresponding to the small separation state on the fuselage side. Figure 6 (c) is a schematic diagram of the wall pressure distribution corresponding to the large separation state on the fuselage side. Figure 6 (d) is a schematic diagram of the wall pressure distribution corresponding to the double separation state on the lip side of the body;

[0025] Figure 7 is a structural block diagram of an air intake adaptive control device based on a deformable bulge in one embodiment;

[0026] Figure 8 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment.

[0027] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0028] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0029] It should be noted that the technical solutions between the various embodiments of the present invention can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0030] The following will describe the implementation of the present invention in detail with reference to the accompanying drawings in the embodiment diagram of the present invention.

[0031] Example 1

[0032] This embodiment discloses an adaptive control method for an air intake based on a deformable bulge. By establishing a mapping relationship between the force and the bulge profile, a bulge deformation mapping model is constructed using neural network technology to achieve accurate prediction of various bulge profiles under various forces, greatly improving the efficiency and accuracy of bulge shape control. At the same time, according to the influence of different bulge profiles on the flow field characteristics of the air intake, a flow field mapping model is constructed to achieve rapid prediction from the bulge profile to the flow field characteristics (such as wall pressure distribution).

[0033] like Figure 1 and 2 As shown, a method for adaptive control of an air intake duct based on a deformable bulge is provided, comprising the following steps:

[0034] Step 201, obtaining the configuration of the air intake duct and determining the position of the bulge in the air intake duct.

[0035] Step 202: construct a bulge deformation mapping model according to the relationship between the applied force and the bulge deformation; and construct a flow field mapping model according to the relationship between the bulge deformation and the flow field characteristics.

[0036] Step 203, identifies the working mode of the intake duct to determine whether the intake duct is in a starting state. If the intake duct is in a non-starting state, the bulge shape is regulated according to the preset target pressure value and the monitored pressure value through the bulge deformation mapping model and the flow field mapping model to optimize the flow field characteristics of the intake duct.

[0037] In the specific implementation process of step 201, the configuration of the air intake duct is as follows: Figure 3 As shown, the bulge is located near the throat of the air inlet, and points A and B are the two end points of the bulge. The flow field distribution characteristics of the air inlet are controlled by changing the shape of the bulge.

[0038] In the specific implementation process of step 202, the relationship between the applied force and the bulge deformation is first determined. Specifically, Figure 4 As shown, after the positions of the two end points of the bulge are determined in step 201, the bulge is simplified into an elastic beam, the two ends of which are fixedly connected and the length is , the elastic modulus of the material is , the width is , thickness is . Using the bulge shape function To describe the simplified deformation curve of the elastic beam, it satisfies the basic deflection equation of the elastic beam as follows:

[0039] ;

[0040] In the formula, represents the moment of inertia of the section; It represents the distributed force function on the bulge, and the unit is force / length; represents the differential symbol; Represents the length of the force interval, and its value range is .

[0041] It can be understood that the applied force can be roughly divided into concentrated force and distributed force. The distributed force includes but is not limited to uniformly distributed load, linearly decreasing load, trapezoidal distributed load, parabolic distributed load, etc. Figure 4 The distributed force in the figure is an indication of uniformly distributed load.

[0042] For concentration ,use Expressed as an equivalent distributed force, assuming a concentrated force Acting on the bulge length Some point inside Then the deflection equation under the concentrated force is:

[0043] ;

[0044] The shape function of the bulge is obtained by piecewise integration :

[0045] ;

[0046] in, and Fixed, ensure , satisfying the boundary conditions.

[0047] For distribution force , assuming the distributed force is an arbitrary function form, then the deflection equation under the distributed force is:

[0048] ;

[0049] Distributed forces for general forms , the analytical solution is obtained through successive integration and boundary conditions.

[0050] Then, according to the deflection equation under concentrated force and the deflection equation under distributed force, the relationship between applied force and bulge deformation in different situations is determined; according to the relationship between applied force and bulge deformation, a bulge deformation mapping model is constructed. The bulge deformation mapping model is a fully connected neural network model, and its key structure includes input layer, hidden layer and output layer. The input layer inputs applied force information, where concentrated force The key information includes the input force magnitude and force location, distributed force The key information of includes the sampling points of discrete distribution force. The hidden layer adopts a multi-layer fully connected structure with ReLU as the activation function to capture the complex relationship between nonlinear force and shape function. The output of the output layer is a discrete shape function, i.e., the shape function of the bulge The constructed bulge deformation mapping model is trained by pre-selecting the constructed loss function to obtain a trained bulge deformation mapping model. The loss function is expressed as:

[0051] ;

[0052] In the formula, Indicates the number of discrete sampling points of pressure distribution; Represents the loss function for predicting bulge shape; Represents the real bulge shape loss function; Indicates the sequence number of each sampling point.

[0053] During training, the Adam optimizer is used to achieve dynamic adjustment of the learning rate.

[0054] Through the trained bulge deformation mapping model, the bulge shape function under different applied force conditions can be generated for different bulge initial configurations to obtain more sample data. The samples include various force distributions (such as uniform load, linear decreasing load, concentrated force) and their corresponding deflection functions.

[0055] Then, determine the relationship between the bulge deformation and the flow field characteristics. Specifically, based on the bulge deformation mapping model, the corresponding bulge shape is generated by applying force, and the complete structure of the entire intake duct is constructed with A and B as the two end points. Subsequently, the flow field simulation of the intake duct is performed, and the stable solution of the flow field is obtained through meshing and steady-state solution, so as to extract the key characteristics of the flow field; then, a flow field mapping model is constructed according to the generated bulge shape and the flow field characteristics corresponding to the bulge shape. It also uses a fully connected neural network model, and the structure of the neural network is the same as that of the bulge deformation mapping model; the difference is that the input of the flow field mapping model is the shape function of the bulge output by the bulge deformation mapping model. , the output is the flow field characteristic distribution.

[0056] The constructed flow field mapping model is trained by pre-selecting the constructed loss function to obtain a trained flow field mapping model. The loss function is expressed as:

[0057] ;

[0058] In the formula, represents the predicted flow field characteristic distribution; Represents the actual flow field characteristics distribution.

[0059] In the specific implementation process of step 203, the working mode of the air intake duct includes a start state (Start) and a non-start state. The start state is an ideal working mode that the air intake duct is expected to maintain at all times, while the non-start state is an abnormal working state that needs to be avoided. Among them, the non-start state includes a small separation state (SSB) on the body side, a large separation state (LSB) on the body side, and a double separation state (DSBL) on the body lip side.

[0060] During flight, pressure signals are the easiest to obtain, fastest responding, and most reliable information source. The pressure distribution of each operating mode on the fuselage side and the lip side will show completely different characteristics. Specifically, Figure 6 As shown in (a), when the inlet is in the starting working mode, the internal flow is dominated by supersonic flow, and the internal and external wave systems remain stable. Figure 6 As shown in (b), when the air inlet is in the small separation working mode, the separation area is concentrated on the fuselage side, and the separation area is relatively small. Figure 6As shown in (c), when the inlet is in the large separation mode, the flow field becomes more complicated. This is because under the combined effect of strong lip shock waves and downstream blockage, a significant separation phenomenon occurs on the fuselage side, resulting in a significant increase in the pressure on the inlet wall. Therefore, the large separation state on the fuselage side has a significant negative impact on the inlet performance. When the inlet is in the double separation state on the fuselage lip side, the main feature is that significant separation areas appear on both sides of the lip and the fuselage, and are maintained by mutual reinforcement. Due to this separation state, a large flow loss is caused, a large area of ​​separation area is generated inside the inlet, and the total pressure recovery coefficient and mass capture ratio are much lower than the level under the large separation mode on the fuselage side. This shows that the performance of the inlet is most negatively affected in the double separation state on the fuselage lip side.

[0061] Therefore, by monitoring the inlet state in real time through the wall pressure measurement point, the flow field characteristics corresponding to different working modes are significantly different, which reflects the obvious difference in pressure distribution. Analyzing the pressure data to classify whether the inlet is started or not is one of the most effective and rapid criteria.

[0062] Based on this, for the intake duct designed based on the deformable bulge, several pressure sensors are arranged near the intake duct. The pressure sensors are used to monitor the wall pressure changes of the intake duct in real time to obtain the monitored pressure values.

[0063] Specifically, Figure 5 As shown, a total of 14 pressure measuring points S1-S14 are arranged at different positions to monitor the wall pressure changes of the air inlet duct. Among them, S1-S7 are located on the body side, S9-S14 are located on the lip side, and S8 is arranged in the isolation section to capture the pressure change characteristics at different positions. By monitoring the pressure changes at each measuring point, effective identification of multiple working modes of the air inlet duct can be achieved. It is worth noting that if the model of the air inlet duct is different, the shape or position of the bulge may change. Therefore, the number and position of the pressure sensor will also change accordingly, and are not limited to the number and position of the arrangement provided in this embodiment.

[0064] Then, the monitored pressure value is feature extracted by dimensionality reduction method, and the working mode of the intake duct under the current state is determined by clustering and classification algorithm. Dimensionality reduction methods include but are not limited to ISOMAP, PCA, MDS, etc., which are selected according to the specific situation, and ISOMAP is preferred.

[0065] In addition, a pressure modal coupling model between the pressure distribution and the intake duct working mode can be constructed based on the monitored pressure value distribution data; the intake duct working mode in the current state can be determined based on the pressure modal coupling model to achieve rapid identification of the intake duct working mode. The pressure modal coupling model can also use a fully connected neural network model. The structure of its neural network is the same as that of the bulge deformation mapping model. The difference is that the input is the pressure distribution data and the output is the intake duct working mode. It is worth noting that the output intake duct working mode is presented in the form of one-hot encoding, and the corresponding relationship is shown in Table 1. Table 1 only shows one of the one-hot encoding forms, which can also be modified according to needs.

[0066] Table 1

[0067]

[0068] Furthermore, a PID controller is provided. For the non-starting state, the PID controller is used to generate control instructions based on the error between the current pressure value and the set target pressure value. The PID controller includes: proportional control (P), integral control (I) and differential control (D). The proportional control quickly responds to the current error and calculates the direct force of the adjustment; the integral control accumulates the error to eliminate the steady-state deviation caused by environmental interference or nonlinearity of the bulge; the differential control predicts the error change trend to avoid overshoot or oscillation during the control process.

[0069] During operation, the pressure value is continuously acquired through the pressure sensor installed on the wall of the air inlet duct, and then transmitted to the control center in real time to meet the real-time requirements of the data acquisition frequency.

[0070] The wall pressure data is used to determine whether the air inlet is in a starting state under the current flow field. If it is in a starting state, the bulge shape is kept unchanged; if it is in a non-starting state, the bulge deformation control process is triggered.

[0071] Specifically, the pressure error is calculated based on the preset target pressure value and the monitored pressure value, and the pressure error is obtained by subtracting the monitored pressure value from the preset target pressure value. According to the pressure error, the input applied force is adjusted, and the adjusted applied force is input into the bulge deformation mapping model, and then the bulge size to be deformed is output; the bulge size to be deformed is input into the flow field mapping model, and the flow field characteristics under the bulge size to be deformed are output to determine whether the flow field characteristics under the bulge size to be deformed meet the starting state requirements; if so, based on the bulge size to be deformed, a control signal is output through the PID controller, and the control signal is transmitted to the actuator, and the actuator converts the control signal into a force signal to adjust the bulge shape, optimize the flow field characteristics of the inlet duct, and realize the transition from the non-starting working mode to the starting working mode.

[0072] After the control is completed, the feedback signal needs to be judged. Specifically, according to the control signal output by the PID controller, the actuator records the actual applied force and / or the bulge shape change and other parameters, and feeds these parameters back to the control system. The control system compares the feedback parameters with the expected parameters. If there is an error, the control signal output by the PID controller is adjusted to further optimize the working process of the actuator and reduce the error.

[0073] After the control is completed, it is also necessary to calibrate whether the start is successful. The pressure sensor collects the pressure value monitored after the control, and sends the pressure value monitored after the control to the control system. The control system compares the pressure value monitored after the control with the preset target pressure value to determine whether the intake duct has returned to the starting state; if so, the shape of the bulge after the control is kept unchanged; if not, based on the adjusted applied force and / or the bulge shape under the deformation size of the bulge fed back by the actuator, the pressure error is recalculated, and then the control signal output by the PID controller is corrected, and the bulge shape is iteratively adjusted until the intake duct starts successfully.

[0074] It can be seen that the adaptive control method of the air intake duct based on the deformable bulge provided by the present invention continuously collects pressure data through the pressure sensor and uploads it to the control system in real time during the entire flight process. The control system makes judgments based on the real-time uploaded pressure data, and dynamically controls the bulge shape through the PID controller to form a closed-loop control loop; at the same time, the adaptive bulge deformation control technology combining the bulge deformation mapping model and the flow field mapping model realizes the precise control of the flow field characteristics, and can greatly improve the restart performance of the air intake duct through real-time feedback adjustment under complex and changeable flight conditions, and significantly improve the stability and reliability of the air intake duct. The present invention can control the control error within 1% through the bulge deformation mapping model and the flow field mapping model, and can achieve 100% prediction accuracy under the condition of high initial pressure data dimension.

[0075] Although this embodiment Figure 1 The steps in the process are shown in sequence as indicated by the arrows, but the steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of the steps, and the steps can be executed in other orders. Figure 1 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0076] Example 2

[0077] Based on the adaptive control method of the air intake duct based on the deformable bulge in Example 1, this embodiment discloses an adaptive control device of the air intake duct based on the deformable bulge, such as Figure 7 As shown, the adaptive control device for the air intake based on the deformable bulge includes: a configuration determination module 401, a model building module 402 and a control optimization module 403, wherein:

[0078] The configuration determination module 401 is used to obtain the configuration of the air intake duct and determine the position of the bulge in the air intake duct.

[0079] The model building module 402 is used to build a bulge deformation mapping model according to the relationship between the applied force and the bulge deformation; and to build a flow field mapping model according to the relationship between the bulge deformation and the flow field characteristics.

[0080] The control optimization module 403 is used to identify the working mode of the intake duct and determine whether the intake duct is in a starting state. If the intake duct is in a non-starting state, the bulge shape is controlled according to the preset target pressure value and the monitored pressure value through the bulge deformation mapping model and the flow field mapping model to optimize the flow field characteristics of the intake duct.

[0081] In this embodiment, the specific working process and working principle of the configuration determination module 401, the model construction module 402 and the control optimization module 403 are the same as those in the method of embodiment 1, so they are not described in detail in this embodiment. Each unit module can be implemented in whole or in part by software, hardware and a combination thereof, and each unit module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above unit modules.

[0082] Example 3

[0083] like Figure 8 The terminal device disclosed in this embodiment includes a transmitter, a receiver, a memory, and a processor. The transmitter is used to send instructions and data, the receiver is used to receive instructions and data, the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions stored in the memory to implement the method in the above-mentioned embodiment 1.

[0084] It should be noted that the above memory can be independent or integrated with the processor. When the memory is independently provided, the terminal device further includes a bus for connecting the memory and the processor.

[0085] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0086] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0087] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the invention. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the attached claims.

Claims

1. An adaptive control method for an air intake based on a deformable bulge, characterized in that: The method comprises: Acquire the air intake duct configuration and determine the position of the bulge in the air intake duct; A bulge deformation mapping model is constructed according to the relationship between the applied force and the deformation of the bulge; a flow field mapping model is constructed according to the relationship between the deformation of the bulge and the flow field characteristics; Identify the working mode of the intake duct to determine whether the intake duct is in a starting state. If the intake duct is in a non-starting state, adjust the shape of the bulge according to the preset target pressure value and the monitored pressure value through the bulge deformation mapping model and the flow field mapping model to optimize the flow field characteristics of the intake duct; According to the preset target pressure value and the monitored pressure value, the bulge shape is regulated by the bulge deformation mapping model and the flow field mapping model to optimize the flow field characteristics of the inlet duct, including: Calculate the pressure error based on the preset target pressure value and the monitored pressure value; Adjusting the applied force according to the pressure error, inputting the adjusted applied force into the bulge deformation mapping model, and outputting the bulge size to be deformed; Input the size of the bulge to be deformed into the flow field mapping model, and output the flow field characteristics under the size of the bulge to be deformed; determine whether the flow field characteristics under the size of the bulge to be deformed meet the starting state requirements; If so, based on the size of the bulge to be deformed, a control signal is output through the PID controller, and the control signal is transmitted to the actuator, which converts the control signal into a force signal to adjust the shape of the bulge and optimize the flow field characteristics of the inlet duct.

2. The adaptive control method of the air intake duct based on the deformable bulge according to claim 1 is characterized in that: A bulge deformation mapping model is constructed according to the relationship between the applied force and the deformation of the bulge, including: Determine the positions of the two end points of the bulge, simplify the bulge into an elastic beam, and determine the basic deflection equation of the elastic beam; Based on the basic deflection equation, a concentrated force and a distributed force are applied to the elastic beam to obtain a deflection equation under the concentrated force and a deflection equation under the distributed force; According to the deflection equation under the concentrated force and the deflection equation under the distributed force, the relationship between the applied force and the bulge deformation is determined; and according to the relationship between the applied force and the bulge deformation, a bulge deformation mapping model is constructed.

3. The adaptive control method of the air intake duct based on the deformable bulge according to claim 2 is characterized in that: A flow field mapping model is constructed according to the relationship between the deformation of the bulge and the flow field characteristics, including: Perform flow field simulation on the inlet duct and obtain a stable solution of the flow field through meshing and steady-state solution; Based on the bulge deformation mapping model, a bulge shape is generated; and a flow field mapping model is constructed according to the bulge shape and flow field characteristics corresponding to the bulge shape.

4. The adaptive control method of the air intake duct based on the deformable bulge according to any one of claims 1 to 3, characterized in that: The working modes of the air intake duct include a starting state and a non-starting state; The non-starting state includes a small separation state on the body side, a large separation state on the body side, and a double separation state on the body lip side.

5. The adaptive control method of the air intake based on the deformable bulge according to claim 4 is characterized in that: Identify the working mode of the air intake duct, including: A plurality of pressure sensors are arranged near the air inlet duct, wherein the pressure sensors monitor the wall pressure change of the air inlet duct in real time and obtain the monitored pressure value; The monitored pressure values ​​are feature extracted through dimensionality reduction method, and then the working mode of the intake duct under the current state is determined through clustering and classification algorithms.

6. The adaptive control method of the air intake based on the deformable bulge according to claim 4 is characterized in that: Identify the working mode of the air intake duct, including: A plurality of pressure sensors are arranged near the air inlet duct, wherein the pressure sensors monitor the wall pressure change of the air inlet duct in real time and obtain the monitored pressure value; According to the monitored pressure value distribution data, a pressure mode coupling model between the pressure distribution and the intake duct working mode is constructed; The operating mode of the intake duct in the current state is determined according to the pressure mode coupling model.

7. The adaptive control method of the air intake duct based on the deformable bulge according to claim 1 is characterized in that: According to the preset target pressure value and the monitored pressure value, the bulge shape is regulated by the bulge deformation mapping model and the flow field mapping model to optimize the flow field characteristics of the inlet duct, and further includes: After the control is completed, the pressure value monitored after the control is compared with the preset target pressure value to determine whether the intake duct has returned to the starting state; If not, the pressure error is recalculated based on the applied force and bulge shape fed back by the actuator, and then the control signal output by the PID controller is corrected, and the bulge shape is iteratively adjusted until the intake duct is successfully started.

8. An adaptive control device for an air intake based on a deformable bulge, characterized in that: The adaptive control method of the air intake duct based on the deformable bulge according to any one of claims 1 to 7 is adopted, and the device comprises: A configuration determination module, used to obtain the configuration of the air inlet and determine the position of the bulge in the air inlet; A model building module, used to build a bulge deformation mapping model according to the relationship between the applied force and the deformation of the bulge; and to build a flow field mapping model according to the relationship between the deformation of the bulge and flow field characteristics; The control and optimization module is used to identify the working mode of the intake duct and determine whether the intake duct is in a starting state. If the intake duct is in a non-starting state, the bulge shape is controlled according to the preset target pressure value and the monitored pressure value through the bulge deformation mapping model and the flow field mapping model to optimize the flow field characteristics of the intake duct.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the adaptive control method of the air intake duct based on the deformable bulge according to any one of claims 1 to 7 are implemented.

Images