Pressure adjusting method and system of pressure air gun for drying

Abstract

The invention discloses a pressure adjusting method and system for a pressure air gun for drying, and relates to the technical field of pressure air gun adjusting.The method comprises the steps that pressure distribution data and drying effect parameters of the surface of a dried object are collected in real time; the drying effect parameters are input into a reinforcement learning and quantum annealing collaborative decision model, a dynamic pressure adjusting strategy is generated, and the dynamic pressure adjusting strategy comprises control parameters of a pressure value, a waveform frequency and a nozzle direction; an air gun is controlled to output a target pressure waveform according to the dynamic pressure adjusting strategy, the target pressure waveform is generated based on the 3D geometrical characteristics of the drying object, and the impedance of an internal flow channel of the air gun is adjusted in real time through a magnetorheological fluid strategy; in the drying process, three-section mode switching is triggered according to the real-time water content and surface roughness data, chaos frequency modulation pulse waves are output in the initial stage to peel off water, fractal diffusion waves are switched in the middle stage to achieve uniform coverage, and nanometer resonance waves are adopted in the final stage to complete drying.

Description

Technical Field

[0001] The present application relates to the technical field of pressure air gun regulation, and in particular to a pressure regulation method and system for a pressure air gun for drying. Background Art

[0002] As a commonly used drying tool, air guns primarily deliver compressed air in a specific waveform by adjusting the air pressure and nozzle direction, thereby rapidly stripping moisture from the surface of the object being dried and ensuring uniform coverage. The flexibility and adaptability of air guns have led to their widespread use in various drying scenarios, particularly where controlled drying performance is crucial.

[0003] Existing pressure air gun drying methods mainly use fixed pressure mode control. However, the fixed pressure mode lacks flexibility and cannot be adjusted in real time according to the characteristics of the drying object (such as surface roughness). This can easily lead to uneven drying effects and even problems such as overdrying or surface damage.

[0004] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0005] The embodiments of the present application provide a pressure regulation method and system for a pressure air gun for drying to solve the above-mentioned technical problems.

[0006] The present application provides a method for regulating the pressure of a pressure air gun for drying, comprising:

[0007] Real-time collection of pressure distribution data and drying effect parameters on the surface of the drying object, including drying speed, uniformity, energy consumption and damage risk index;

[0008] Inputting the drying effect parameters into a reinforcement learning and quantum annealing collaborative decision-making model to generate a dynamic pressure regulation strategy, wherein the dynamic pressure regulation strategy includes control parameters of pressure value, waveform frequency, and nozzle direction;

[0009] controlling the airgun to output a target pressure waveform according to the dynamic pressure regulation strategy, wherein the target pressure waveform is generated based on the 3D geometric features of the drying object, and adjusting the flow channel impedance inside the airgun in real time through a magnetorheological fluid strategy;

[0010] During the drying process, three-stage mode switching is triggered according to real-time moisture content and surface roughness data: in the initial stage, chaotic frequency-modulated pulse waves are output to remove moisture, in the middle stage, fractal diffusion waves are switched to achieve uniform coverage, and in the final stage, nano-resonance waves are used to complete drying.

[0011] Furthermore, the operations of the reinforcement learning and quantum annealing collaborative decision-making model include:

[0012] Constructing a state space for reinforcement learning, including Young's modulus of the material of the drying object, surface curvature radius, and real-time thermal imaging data;

[0013] Design a quantum annealing optimization module: Map drying speed, energy consumption, uniformity, and damage risk to spin interaction energy; traverse the solution space through the quantum tunneling effect to select a low-energy state solution set that meets the constraints;

[0014] Generate a reinforcement learning strategy: Use the low-energy state solution set output by the quantum annealing optimization module as the initial strategy to fine-tune the pressure parameters in the continuous action space; increase rewards when the entropy ratio of drying speed to uniformity improves, and trigger a penalty mechanism when the local pressure gradient exceeds the yield strength of the material;

[0015] After each drying cycle is completed, the coupling weight coefficient of quantum annealing is updated.

[0016] Furthermore, the magnetorheological fluid strategy for regulating flow channel impedance includes:

[0017] The air gun flow channel is filled with magnetorheological fluid, and an electromagnetic coil array is arranged on the outer wall of the flow channel;

[0018] Generate a magnetic field control signal based on the target pressure waveform; calculate the optimal magnetic flux distribution of each cross-section of the flow channel through finite element simulation based on the 3D geometric characteristics of the drying object; and adopt a hybrid drive strategy of pulse width modulation and space vector modulation to control the amplitude and phase of the coil current;

[0019] Dynamically adjust the flow channel impedance: Real-time monitoring of magnetic induction intensity and feedback to the magnetic field control loop; when particle deposition is detected in the flow channel, the high-frequency alternating magnetic field cleaning mode is automatically triggered.

[0020] Furthermore, the generation of chaotic frequency-modulated pulse waves in the initial stage includes: acquiring the surface microstructure characteristics of the dry object through a laser speckle imaging strategy to generate frequency-modulated parameters of an initial chaotic sequence; dynamically adjusting the pulse interval to make the pulse frequency chaotically jump within the range of 10 to 100 kHz;

[0021] The fractal diffusion wave control in the intermediate stage includes: dividing the dry surface into fractal grids, assigning an independent pressure amplitude to each subgrid; controlling the diffusion path of the pressure wave through an iterative function system, so that the high-pressure area migrates along the fractal dimension gradient.

[0022] Furthermore, the quantum annealing optimization module also includes:

[0023] Using quantum bits to characterize the dynamic deformation constraints of dry objects;

[0024] Optimizing annealing rate via adiabatic quantum evolution pathway;

[0025] The interaction matrix is ​​updated in real time during the drying process, and the damage risk data fed back by the sensor is encoded as the coupling strength between quantum bits.

[0026] Furthermore, before the magnetic field control signal is generated, a pre-calibration step is also included:

[0027] When the air gun is started, a suspension of magnetic nanoparticles for calibration is injected into the flow channel;

[0028] The particles are driven by a gradient magnetic field to form a reference impedance distribution, and the current and impedance response curves of each coil are recorded;

[0029] The constitutive equation of magnetorheological fluid is constructed based on the response curve for real-time impedance prediction.

[0030] Furthermore, the fractal diffusion wave control further includes:

[0031] The charge distribution on the surface of the dry object is detected by a dielectrophoretic force sensor, and the potential gradient of the fractal grid is dynamically adjusted;

[0032] The electrowetting effect is superimposed on the migration path in the high-pressure area to guide the water to flow in a directional manner towards the low-pressure area.

[0033] Furthermore, the method also includes a self-repair drying mode:

[0034] When the acoustic emission sensor detects a microcrack signal, it immediately switches to repair mode;

[0035] The air gun outputs vibration waves of a specific frequency to form a local thermal gradient in the crack area, inducing surface atoms to migrate and fill the defects;

[0036] After the repair is complete, a low-energy helium ion beam is used to scan the surface to restore optical flatness.

[0037] Furthermore, the method further comprises:

[0038] After drying is completed, a knowledge graph of the drying process is constructed to associate pressure parameters with drying quality indicators; the adversarial distillation algorithm is used to compress the reinforcement learning and quantum annealing collaborative decision-making model.

[0039] The present application provides a pressure regulating system for a pressure air gun for drying, comprising:

[0040] A drying object data acquisition module is used to collect pressure distribution data and drying effect parameters on the surface of the drying object in real time. The drying effect parameters include drying speed, uniformity, energy consumption and damage risk index;

[0041] a pressure regulation strategy generation module, configured to input the drying effect parameters into a reinforcement learning and quantum annealing collaborative decision-making model to generate a dynamic pressure regulation strategy, wherein the dynamic pressure regulation strategy includes control parameters of pressure value, waveform frequency, and nozzle direction;

[0042] a pressure waveform adjustment module, configured to control the airgun to output a target pressure waveform according to the dynamic pressure adjustment strategy, wherein the target pressure waveform is generated based on the 3D geometric features of the drying object and to adjust the flow channel impedance inside the airgun in real time through a magnetorheological fluid strategy;

[0043] The drying mode switching module is used to trigger three-stage mode switching during the drying process based on real-time moisture content and surface roughness data: in the initial stage, chaotic frequency-modulated pulse waves are output to remove moisture; in the middle stage, fractal diffusion waves are switched to achieve uniform coverage; and in the final stage, nano-resonance waves are used to complete drying.

[0044] Based on the embodiments provided in this application, through the collaborative decision-making of reinforcement learning and quantum annealing, the four-dimensional target simultaneous optimization of drying speed, energy consumption, uniformity and damage risk is achieved, breaking through the limitations of traditional fixed pressure mode or single PID control. Customized pressure waveforms are generated based on 3D geometric features, combined with real-time impedance adjustment of magnetorheological fluids, which can accurately adapt to complex shapes such as lumens and porous structures to solve the problems of uneven drying and residual water film. Through the staged control of chaotic frequency-modulated pulse waves (rapid peeling), fractal diffusion waves (uniform coverage), and nano-resonance waves (fine drying), efficiency and safety are taken into account, which is especially suitable for fragile precision instruments. Real-time monitoring of surface roughness and damage index, dynamic constraint of pressure parameters, to avoid over-drying or material yield caused by empirical adjustment of traditional methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings described herein are used to provide a further understanding of the embodiments of the present invention and constitute a part of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation of this application. In the drawings:

[0046] Figure 1 This is a flow chart of an optional method for adjusting the pressure of a pressure air gun for drying according to an embodiment of the present application;

[0047] Figure 2 Flowchart of another optional pressure regulation method for a pressure air gun for drying according to an embodiment of the present application;

[0048] Figure 3 This is a structural diagram of a pressure regulating system of an optional pressure air gun for drying according to an embodiment of the present application.

[0049] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0051] Alternatively, as Figure 1 As shown, the present application provides a method for regulating the pressure of a pressure air gun for drying, comprising:

[0052] S101, collecting pressure distribution data and drying effect parameters on the surface of the drying object in real time, the drying effect parameters including drying speed, uniformity, energy consumption and damage risk index;

[0053] S102, inputting the drying effect parameters into a reinforcement learning and quantum annealing collaborative decision-making model to generate a dynamic pressure adjustment strategy, which includes control parameters of pressure value, waveform frequency, and nozzle direction;

[0054] S103, controlling the airgun to output a target pressure waveform according to a dynamic pressure regulation strategy, wherein the target pressure waveform is generated based on the 3D geometric features of the drying object, and adjusting the flow channel impedance inside the airgun in real time through a magnetorheological fluid strategy;

[0055] S104, during the drying process, triggers a three-stage mode switch based on real-time moisture content and surface roughness data: in the initial stage, chaotic frequency-modulated pulse waves are output to remove moisture, in the middle stage, fractal diffusion waves are switched to achieve uniform coverage, and in the final stage, nano-resonance waves are used to complete drying.

[0056] In the embodiment of the present application, the pressure regulation method of the drying pressure air gun is applied to the drying of semiconductor wafers:

[0057] A topological insulator coating is used in the initial stage to suppress surface electrostatic adsorption;

[0058] Photoacoustic imaging is used to monitor capillary residue at the wafer edge and generate circular contraction waves for targeted removal.

[0059] In the final drying stage, the air gun temperature was controlled below the Debye temperature to avoid surface roughening caused by lattice thermal vibration.

[0060] Based on the embodiments provided in this application, through the collaborative decision-making of reinforcement learning and quantum annealing, the four-dimensional target simultaneous optimization of drying speed, energy consumption, uniformity and damage risk is achieved, breaking through the limitations of traditional fixed pressure mode or single PID control. Customized pressure waveforms are generated based on 3D geometric features, combined with real-time impedance adjustment of magnetorheological fluids, which can accurately adapt to complex shapes such as lumens and porous structures to solve the problems of uneven drying and residual water film. Through the staged control of chaotic frequency-modulated pulse waves (rapid peeling), fractal diffusion waves (uniform coverage), and nano-resonance waves (fine drying), efficiency and safety are taken into account, which is especially suitable for fragile precision instruments. Real-time monitoring of surface roughness and damage index, dynamic constraint of pressure parameters, to avoid over-drying or material yield caused by empirical adjustment of traditional methods.

[0061] Furthermore, if Figure 2 As shown in Figure 2, the operations of the reinforcement learning and quantum annealing collaborative decision-making model include:

[0062] S201, constructing a state space for reinforcement learning, including the Young's modulus of the material of the drying object, the surface curvature radius, and real-time thermal imaging data;

[0063] S202, designing a quantum annealing optimization module: mapping drying speed, energy consumption, uniformity, and damage risk to spin interaction energy; traversing the solution space through the quantum tunneling effect to select a low-energy state solution set that meets the constraints;

[0064] S203, generating a reinforcement learning strategy: using the low-energy state solution set output by the quantum annealing optimization module as the initial strategy to fine-tune the pressure parameters in the continuous action space; increasing rewards when the entropy ratio of drying speed to uniformity improves, and triggering a penalty mechanism when the local pressure gradient exceeds the material yield strength;

[0065] S204, after each drying cycle is completed, updating the coupling weight coefficient of quantum annealing.

[0066] The examples presented in this application combine the global search capabilities of quantum annealing with fine-tuning strategies using reinforcement learning to address the "curse of dimensionality" problem in multi-objective optimization and accelerate drying strategy convergence. By combining a dynamic reward function with a hard constraint mechanism, this approach ensures rapid drying while strictly controlling damage risk below the material's yield strength, making it suitable for drying precision aerospace components.

[0067] Furthermore, the magnetorheological fluid strategy adjusts the flow channel impedance, including:

[0068] The air gun flow channel is filled with magnetorheological fluid, and an electromagnetic coil array is arranged on the outer wall of the flow channel;

[0069] Generate magnetic field control signals based on the target pressure waveform: Based on the 3D geometric characteristics of the drying object, the optimal magnetic flux distribution of each flow channel section is calculated through finite element simulation. A hybrid drive strategy of pulse width modulation and space vector modulation is used to control the amplitude and phase of the coil current.

[0070] Dynamically adjust the flow channel impedance: The magnetic induction intensity is monitored in real time through the Hall sensor and fed back to the magnetic field control loop; when particle deposition is detected in the flow channel, the high-frequency alternating magnetic field cleaning mode is automatically triggered to prevent impedance drift.

[0071] Based on the embodiments provided in this application, a PWM-SVM hybrid drive strategy and high-frequency alternating magnetic field cleaning are adopted to achieve long-term stability of the flow channel impedance; it is suitable for continuous drying operations of medical devices in high humidity environments to avoid pressure fluctuations caused by particle deposition.

[0072] Furthermore, the chaotic frequency-modulated pulse wave generation in the initial stage includes: obtaining the surface microstructure characteristics of the dry object through a laser speckle imaging strategy to generate the frequency modulation parameters of the initial chaotic sequence; based on the Lorentz attractor model, dynamically adjusting the pulse interval to make the pulse frequency chaotically jump within the range of 10 to 100 kHz;

[0073] The fractal diffusion wave control in the intermediate stage includes: dividing the dry surface into fractal grids, assigning an independent pressure amplitude to each subgrid; controlling the diffusion path of the pressure wave through an iterative function system, so that the high-pressure area migrates along the fractal dimension gradient.

[0074] Based on the embodiments provided in this application, an iterative function system generates a Sierpinski carpet-like fractal grid, enabling pressure waves to migrate along the fractal dimension gradient, thereby improving drying coverage. This method, specifically designed for drying porous fuel cell electrodes, can remove moisture from the pores, avoiding the "surface encrustation" problem associated with traditional uniform spraying.

[0075] Furthermore, the quantum annealing optimization module also includes:

[0076] Using quantum bits to characterize the dynamic deformation constraints of dry objects;

[0077] Optimize the annealing rate through adiabatic quantum evolution path to avoid local optimal solution trap;

[0078] The interaction matrix is ​​updated in real time during the drying process, and the damage risk data fed back by the sensor is encoded as the coupling strength between quantum bits.

[0079] In the embodiment of the present application, the quantum annealing energy mapping equation is:

[0080]

[0081] in, is the coupling strength between drying speed and energy consumption, 、 These are numbers for dry areas. Characterization The dry area and The synergistic effect between the drying areas ( , For the The dry area and The spatial angle between the drying areas, It means proportional to; For the The pressure decision mode of each drying area is +1 (high pressure fast drying) or −1 (low pressure protection mode); For the Pressure decision-making model in a dry area; is the uniformity weight factor ( ); is the damage risk penalty coefficient (dynamically adjusted through Bayesian optimization, with the initial value set to 10); is the microcrack energy release rate detected in real time by the acoustic emission sensor (unit: J / m 2 ); is the material yield strength threshold (unit: J / m 2 ), determined based on the fracture toughness and elastic modulus of the material;

[0082] For example, for aluminum alloy, the elastic modulus is 70GPa, Approximately 12.8 J / m 2 .

[0083] Based on the above equation, the drying target is mapped to the interaction energy between quantum bits. Through the quantum tunneling effect, the global optimal solution is quickly locked, preventing traditional optimization algorithms from falling into local optimality. Combined with hard constraints on damage risk, the pressure parameters are ensured to always be within safe boundaries, significantly reducing the probability of damage to precision instruments.

[0084] Based on the examples provided in this application, virtual qubits are introduced to represent dynamic deformation constraints. Using adiabatic quantum evolution paths, the annealing rate is optimized to avoid premature convergence and improve solution quality. This approach is suitable for drying flexible materials (such as medical silicone catheters) to prevent pressure distribution distortion caused by deformation.

[0085] Furthermore, before the magnetic field control signal is generated, a pre-calibration step is also included:

[0086] When the air gun is activated, a suspension of magnetic nanoparticles for calibration is injected into the flow channel;

[0087] The particles are driven by a gradient magnetic field to form a reference impedance distribution, and the current and impedance response curves of each coil are recorded;

[0088] The constitutive equation of magnetorheological fluid is constructed based on the response curve for real-time impedance prediction.

[0089] Based on the embodiments provided in this application, a gradient magnetic field is used to drive nanoparticles to form a reference impedance distribution, construct a high-precision constitutive equation, and shorten initial calibration time. This significantly reduces equipment commissioning time in scenarios such as automotive spray painting lines where air guns require frequent replacement.

[0090] In the embodiment of the present application, the magnetorheological fluid impedance control equation is:

[0091]

[0092] in, is the vacuum permeability (constant); is the number of turns of the electromagnetic coil (designed to be 50 to 200 turns according to the cross-sectional dimensions of the flow channel); is the effective magnetic induction intensity (controlled by hybrid drive strategy); is the flow channel geometric distortion factor (determined based on the actual flow channel cross-sectional area / nominal cross-sectional area); is the temperature correction coefficient of magnetorheological fluid viscosity; is the magnetorheological fluid temperature; is the particle deposition compensation factor (calibrated to 0.1 to 0.3 through pre-calibration experiments); is the average spacing between magnetic particles (controlled by the concentration of the nanoparticle suspension); is the characteristic dimension of the flow channel section; is the average distance between magnetic particles.

[0093] Based on the above formula, the flow channel impedance is precisely controlled by the magnetic field, combined with real-time compensation of temperature and particle deposition to achieve high-precision output of the pressure waveform.

[0094] Furthermore, the fractal diffusion wave control further includes:

[0095] The charge distribution on the surface of the dry object is detected by a dielectrophoretic force sensor, and the potential gradient of the fractal grid is dynamically adjusted;

[0096] The electrowetting effect is superimposed on the migration path in the high-pressure area to guide the water to flow in a directional manner towards the low-pressure area.

[0097] Based on the embodiments provided in this application, the dielectrophoretic force and electrowetting effect are combined to actively control the moisture migration path and reduce drying energy consumption. This is suitable for rapid drying of printed circuit boards, avoiding the risk of short circuits caused by residual moisture.

[0098] In the embodiment of the present application, the fractal diffusion wave pressure distribution equation is:

[0099]

[0100] in, is the basic pressure amplitude (output by the quantum annealing module); is the fractal attenuation factor, ; is the index of the iteration number; is the number of iterations, according to the fractal dimension Dynamic adjustment; Fractal coordinate mapping generated for iterated function systems; is the dry surface coordinate; is the characteristic length (take the maximum inscribed circle diameter of the dry object).

[0101] Based on the above formula, the diffusion path of the pressure wave is controlled by fractal dimension gradients, allowing the high-pressure zone to migrate along the pore edges, resolving the industry challenge of uneven drying of porous materials. Combined with dielectrophoresis potential gradient regulation, this actively guides water flow and improves drying uniformity.

[0102] Furthermore, the method also includes a self-repairing drying mode:

[0103] When the acoustic emission sensor detects a microcrack signal, it immediately switches to repair mode;

[0104] Vibration waves of a specific frequency are output through an air gun to form a local thermal gradient in the crack area, inducing surface atomic migration to fill the defects; the specific frequency range is between 4 to 6 Hz or 8 to 10 Hz.

[0105] After the repair is complete, a low-energy helium ion beam is used to scan the surface to restore optical flatness.

[0106] Based on the embodiments provided in this application, surface atomic migration is induced to achieve in-situ repair of microcracks, restoring surface strength after repair. For high-value, vulnerable parts such as optical lenses, processing defects can be repaired simultaneously during the drying process.

[0107] Furthermore, the method further comprises:

[0108] After drying is completed, a knowledge graph of the drying process is constructed to associate pressure parameters with drying quality indicators; the adversarial distillation algorithm is used to compress the reinforcement learning and quantum annealing collaborative decision-making model.

[0109] Based on the embodiments provided in this application, by constructing a knowledge graph of the drying process, the interpretable transfer of empirical knowledge is achieved, which is suitable for the collaborative control of distributed drying equipment in the industrial Internet of Things environment.

[0110] Alternatively, as Figure 3 As shown, the present application provides a pressure regulating system for a pressure air gun for drying, comprising:

[0111] Drying object data acquisition module 301, for real-time acquisition of pressure distribution data and drying effect parameters on the surface of the drying object, including drying speed, uniformity, energy consumption and damage risk index;

[0112] The pressure regulation strategy generation module 302 is used to input the drying effect parameters into the reinforcement learning and quantum annealing collaborative decision model to generate a dynamic pressure regulation strategy, which includes control parameters of pressure value, waveform frequency and nozzle direction;

[0113] The pressure waveform adjustment module 303 is used to control the airgun to output a target pressure waveform according to a dynamic pressure adjustment strategy. The target pressure waveform is generated based on the 3D geometric characteristics of the drying object and the internal flow channel impedance of the airgun is adjusted in real time through a magnetorheological fluid strategy.

[0114] The drying mode switching module 304 is used to trigger a three-stage mode switch during the drying process based on the real-time moisture content and surface roughness data: in the initial stage, chaotic frequency-modulated pulse waves are output to remove moisture; in the middle stage, fractal diffusion waves are switched to achieve uniform coverage; and in the final stage, nano-resonance waves are used to complete drying.

[0115] It should be noted that, in the present application, the embodiments implemented on the pressure regulating system side of the drying pressure air gun can be referenced with the embodiments implemented on the pressure regulating method side of the drying pressure air gun, and this application will not describe them one by one.

[0116] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for regulating the pressure of a pressure air gun for drying, characterized in that: include: Real-time collection of pressure distribution data and drying effect parameters on the surface of the drying object, including drying speed, uniformity, energy consumption and damage risk index; Inputting the drying effect parameters into a reinforcement learning and quantum annealing collaborative decision-making model to generate a dynamic pressure regulation strategy, wherein the dynamic pressure regulation strategy includes control parameters of pressure value, waveform frequency, and nozzle direction; controlling the airgun to output a target pressure waveform according to the dynamic pressure regulation strategy, wherein the target pressure waveform is generated based on the 3D geometric features of the drying object, and adjusting the flow channel impedance inside the airgun in real time through a magnetorheological fluid strategy; During the drying process, three-stage mode switching is triggered according to real-time moisture content and surface roughness data: in the initial stage, chaotic frequency-modulated pulse waves are output to remove moisture, in the middle stage, fractal diffusion waves are switched to achieve uniform coverage, and in the final stage, nano-resonance waves are used to complete drying.

2. The pressure regulating method of a pressure air gun for drying according to claim 1, characterized in that: The operations of the reinforcement learning and quantum annealing collaborative decision-making model include: Constructing a state space for reinforcement learning, including Young's modulus of the material of the drying object, surface curvature radius, and real-time thermal imaging data; Design a quantum annealing optimization module: Map drying speed, energy consumption, uniformity, and damage risk to spin interaction energy; traverse the solution space through the quantum tunneling effect to select a low-energy state solution set that meets the constraints; Generate a reinforcement learning strategy: Use the low-energy state solution set output by the quantum annealing optimization module as the initial strategy to fine-tune the pressure parameters in the continuous action space; increase rewards when the entropy ratio of drying speed to uniformity improves, and trigger a penalty mechanism when the local pressure gradient exceeds the yield strength of the material; After each drying cycle is completed, the coupling weight coefficient of quantum annealing is updated.

3. The pressure regulating method of a pressure air gun for drying according to claim 1, characterized in that: The magnetorheological fluid strategy for adjusting flow channel impedance includes: The air gun flow channel is filled with magnetorheological fluid, and an electromagnetic coil array is arranged on the outer wall of the flow channel; Generate a magnetic field control signal based on the target pressure waveform; calculate the optimal magnetic flux distribution of each cross-section of the flow channel through finite element simulation based on the 3D geometric characteristics of the drying object; and adopt a hybrid drive strategy of pulse width modulation and space vector modulation to control the amplitude and phase of the coil current; Dynamically adjust the flow channel impedance: Real-time monitoring of magnetic induction intensity and feedback to the magnetic field control loop; when particle deposition is detected in the flow channel, the high-frequency alternating magnetic field cleaning mode is automatically triggered.

4. The pressure regulating method of a pressure air gun for drying according to claim 1, characterized in that: The chaotic frequency-modulated pulse wave generation in the initial stage includes: obtaining the surface microstructure characteristics of the dry object through a laser speckle imaging strategy to generate the frequency modulation parameters of the initial chaotic sequence; dynamically adjusting the pulse interval to make the pulse frequency chaotically jump within the range of 10 to 100 kHz; The fractal diffusion wave control in the intermediate stage includes: dividing the dry surface into fractal grids, assigning an independent pressure amplitude to each subgrid; controlling the diffusion path of the pressure wave through an iterative function system, so that the high-pressure area migrates along the fractal dimension gradient.

5. The pressure regulating method of a pressure air gun for drying according to claim 2, characterized in that: The quantum annealing optimization module also includes: Using quantum bits to characterize the dynamic deformation constraints of dry objects; Optimizing annealing rate via adiabatic quantum evolution pathway; The interaction matrix is ​​updated in real time during the drying process, and the damage risk data fed back by the sensor is encoded as the coupling strength between quantum bits.

6. The pressure regulating method of a pressure air gun for drying according to claim 3, characterized in that: Before the magnetic field control signal is generated, a pre-calibration step is also included: When the air gun is started, a suspension of magnetic nanoparticles for calibration is injected into the flow channel; The particles are driven by a gradient magnetic field to form a reference impedance distribution, and the current and impedance response curves of each coil are recorded; The constitutive equation of magnetorheological fluid is constructed based on the response curve for real-time impedance prediction.

7. The pressure regulating method of a pressure air gun for drying according to claim 4, characterized in that: The fractal diffusion wave control further includes: The charge distribution on the surface of the dry object is detected by a dielectrophoretic force sensor, and the potential gradient of the fractal grid is dynamically adjusted; The electrowetting effect is superimposed on the migration path in the high-pressure area to guide the water to flow in a directional manner towards the low-pressure area.

8. The pressure regulating method of a pressure air gun for drying according to claim 1, characterized in that: The method also includes a self-healing drying mode: When the acoustic emission sensor detects a microcrack signal, it immediately switches to repair mode; The air gun outputs vibration waves of a specific frequency to form a local thermal gradient in the crack area, inducing surface atoms to migrate and fill the defects; After the repair is complete, a low-energy helium ion beam is used to scan the surface to restore optical flatness.

9. The pressure regulating method of a pressure air gun for drying according to claim 1, characterized in that: The method further comprises: After drying is completed, a knowledge graph of the drying process is constructed to associate pressure parameters with drying quality indicators; the adversarial distillation algorithm is used to compress the reinforcement learning and quantum annealing collaborative decision-making model.

10. A pressure regulating system for a pressure air gun for drying, characterized in that: include: A drying object data acquisition module is used to collect pressure distribution data and drying effect parameters on the surface of the drying object in real time. The drying effect parameters include drying speed, uniformity, energy consumption and damage risk index; a pressure regulation strategy generation module, configured to input the drying effect parameters into a reinforcement learning and quantum annealing collaborative decision-making model to generate a dynamic pressure regulation strategy, wherein the dynamic pressure regulation strategy includes control parameters of pressure value, waveform frequency, and nozzle direction; a pressure waveform adjustment module, configured to control the airgun to output a target pressure waveform according to the dynamic pressure adjustment strategy, wherein the target pressure waveform is generated based on the 3D geometric features of the drying object and to adjust the flow channel impedance inside the airgun in real time through a magnetorheological fluid strategy; The drying mode switching module is used to trigger three-stage mode switching during the drying process based on real-time moisture content and surface roughness data: in the initial stage, chaotic frequency-modulated pulse waves are output to remove moisture; in the middle stage, fractal diffusion waves are switched to achieve uniform coverage; and in the final stage, nano-resonance waves are used to complete drying.

Images