Multi-stage particle degradation and anti-blocking micro-nano paraffin atomization method and system

Abstract

The invention discloses a multi-stage particle degradation and anti-blocking micro-nano paraffin atomization method and system, and relates to the technical field of atomization engineering.The method comprises the steps that a fatty acid salt dispersing agent is injected into a solid paraffin raw material, electric heat tracing melting is conducted, and paraffin constant-temperature dispersion liquid is obtained; performing three-stage synergistic degradation on the paraffin constant-temperature dispersion liquid to form a paraffin micro-nano suspension, and performing light scattering analysis on the paraffin micro-nano suspension to obtain particle size distribution of the suspension; and performing sound pressure dynamic tuning on the particle size distribution of the suspension through a PID control algorithm, and outputting parameters of the anti-blocking paraffin purification liquid. Through a three-stage synergistic degradation mechanism and a digital twin atomization model, the particle size uniformity and stability of the paraffin micro-nano suspension are improved, and efficient and stable production of a paraffin atomized finished product is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of atomization engineering technology, and in particular to a micro-nano paraffin atomization method and system for multi-stage particle degradation and anti-clogging. Background Technology

[0002] In recent years, the application of micro and nanomaterials has become increasingly widespread, especially in chemical products such as coatings and lubricants. Micro and nano paraffin wax, as an important raw material, has also attracted considerable attention regarding its atomization methods. Traditional paraffin wax atomization methods mainly rely on a single physical process, achieving simple phase transitions and atomization. In recent years, researchers have begun to explore more precise multi-stage synergistic degradation methods, such as using ultrasonic-assisted dissolution and high-pressure homogenizers to improve the dispersibility and particle size distribution of paraffin wax, thereby enhancing the quality and efficiency of paraffin wax atomization to some extent.

[0003] Existing micro / nano paraffin atomization methods still face several challenges in practical applications. Firstly, current technologies often neglect the multi-stage synergistic control of paraffin particles during degradation, typically employing single or two-stage treatment methods. This leads to insufficient particle degradation, uneven particle size distribution, and agglomeration, affecting the stability and droplet uniformity of paraffin atomization. Secondly, existing atomization control methods largely rely on manual experience for parameter adjustment, resulting in low automation and difficulty in dynamically optimizing atomization parameters according to changing operating conditions. This leads to high energy consumption, poor adaptability, and hinders the continuous and efficient production capacity of atomized paraffin products. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a micro / nano paraffin atomization method with multi-stage particle degradation and anti-clogging to solve the problems of poor atomization uniformity and lack of intelligent control mechanism.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, the present invention provides a multi-stage particle degradation and anti-clogging micro-nano paraffin atomization method, which includes injecting a fatty acid salt dispersant into a solid paraffin raw material and performing electric heating melting to obtain a paraffin isothermal dispersion; and performing a three-stage synergistic degradation on the paraffin isothermal dispersion to form a paraffin micro-nano suspension.

[0008] Light scattering analysis was performed on the paraffin micro-nano suspension to obtain the particle size distribution of the suspension; the particle size distribution of the suspension was dynamically tuned by sound pressure through a PID control algorithm to output the parameters of the anti-clogging paraffin purification liquid.

[0009] Input the parameters of the anti-clogging paraffin purification liquid into the digital twin atomization model; the feature coupling layer performs multi-physics feature fusion, and the decision optimization layer performs multi-objective optimization of energy consumption and coverage, and outputs paraffin atomization instructions;

[0010] According to the paraffin atomization command, the paraffin micro-nano suspension is dynamically atomized through a dual-fluid nozzle array, and the atomized particle size distribution and the surface coverage of the wood shavings are collected. Based on the atomized particle size distribution and the surface coverage of the wood shavings, the paraffin atomization scheme is dynamically adjusted, and the optimal atomization process parameters are output.

[0011] As a preferred embodiment of the multi-stage particle degradation and anti-clogging micro / nano paraffin atomization method of the present invention, the specific steps for obtaining the homogeneous molten liquid are as follows:

[0012] Solid paraffin raw material is put into a high-temperature resistant reactor, and fatty acid salt dispersant is added and mechanically stirred to obtain a preliminary mixture.

[0013] The initial mixture is heated and melted, and then dynamically turbulently premixed to generate a homogeneous melt. The homogeneous melt is then kept at a constant temperature to form a paraffin isothermal dispersion.

[0014] As a preferred embodiment of the multi-stage particle degradation and anti-clogging micro / nano paraffin atomization method of the present invention, the specific steps for forming the paraffin micro / nano suspension are as follows:

[0015] Paraffin isothermal dispersion is introduced into the guide cavity for turbulent shearing to obtain primary degradation liquid;

[0016] The primary degradation liquid is transferred to a cavitation reactor for cavitation explosion to generate a secondary degradation liquid.

[0017] The secondary degradation solution was introduced into the eddy current resonant cavity to perform eddy current resonance, thereby obtaining a paraffin micro-nano suspension.

[0018] As a preferred embodiment of the multi-stage particle degradation and anti-clogging micro / nano paraffin atomization method of the present invention, the specific steps for obtaining the particle size distribution of the suspension are as follows:

[0019] Dynamic light scattering signals of paraffin micro-nano suspensions were collected, and autocorrelation functions were calculated to generate light intensity autocorrelation attenuation curves.

[0020] The diffusion coefficient is inverted from the autocorrelation decay curve of light intensity to generate the particle size distribution of the suspension.

[0021] As a preferred embodiment of the multi-stage particle degradation and anti-clogging micro / nano paraffin atomization method of the present invention, the specific steps for outputting the anti-clogging paraffin purification liquid parameters are as follows:

[0022] The PID control algorithm is used to perform proportional-integral-derivative coordinated control of the particle size distribution of the suspension to generate sound pressure tuning parameters.

[0023] Based on the sound pressure tuning parameters, an orthogonal standing wave field of sound pressure is applied to the paraffin micro-nano suspension to obtain the anti-clogging paraffin purification liquid. Parameters are recorded simultaneously and output as parameters of the anti-clogging paraffin purification liquid.

[0024] As a preferred embodiment of the multi-stage particle degradation and anti-clogging micro / nano paraffin atomization method of the present invention, the digital twin atomization model is constructed as follows:

[0025] A feature coupling layer is built using a convolutional neural network, and a decision optimization layer is built using the U-Net architecture.

[0026] By using skip connections to perform cross-level feature fusion and residual stacking on the feature coupling layer and decision optimization layer, a digital twin fogging model is constructed.

[0027] As a preferred embodiment of the multi-stage particle degradation and anti-clogging micro / nano paraffin atomization method of the present invention, the specific steps for outputting the paraffin atomization command are as follows:

[0028] The parameters of the anti-clogging paraffin purification liquid are input into the digital twin atomization model. The feature coupling layer uses three-dimensional convolution to perform multi-physics field feature fusion on the parameters of the anti-clogging paraffin purification liquid to generate atomization coupling features.

[0029] The decision optimization layer performs multi-objective optimization of energy consumption and coverage using the NSGA-II algorithm to form Pareto optimal parameters;

[0030] The atomization coupling features and Pareto optimal parameters are tensor-joined and nonlinearly activated to output paraffin atomization commands.

[0031] As a preferred embodiment of the multi-stage particle degradation and anti-clogging micro / nano paraffin atomization method of the present invention, the specific steps for obtaining the atomized particle size distribution and the surface coverage of the wood shavings are as follows:

[0032] Extract the atomization control parameters of the paraffin atomization command, and use a dual-fluid nozzle array to dynamically atomize the anti-clogging paraffin purification liquid according to the atomization control parameters to obtain the finished paraffin atomization product;

[0033] The particle size distribution and shaving surface coverage of the paraffin atomized product were collected using a laser particle size analyzer and a near-infrared moisture analyzer, respectively.

[0034] As a preferred embodiment of the multi-stage particle degradation and anti-clogging micro / nano paraffin atomization method of the present invention, the specific steps for outputting the optimal atomization process parameters are as follows:

[0035] The cumulative volume distribution of the atomized particle size distribution is calculated to obtain the particle size uniformity index; at the same time, the thickness change of the shaving surface coverage is calculated to generate the thickness expansion uniformity coefficient.

[0036] Based on the particle size uniformity index and thickness expansion uniformity coefficient, the compressed air pressure and atomization cone angle parameters of the paraffin atomization scheme are adjusted to output the optimal atomization process parameters.

[0037] Secondly, the present invention provides a multi-stage particle degradation and anti-clogging micro-nano paraffin atomization system, comprising: a melting and dispersion module for injecting fatty acid salt dispersant into solid paraffin raw material and performing electric heating melting to obtain paraffin isothermal dispersion; and performing three-stage synergistic degradation on the paraffin isothermal dispersion to form paraffin micro-nano suspension.

[0038] The particle size control module is used to perform light scattering analysis on paraffin micro-nano suspensions to obtain the particle size distribution of the suspensions; and to perform dynamic acoustic pressure tuning on the particle size distribution of the suspensions through a PID control algorithm to output parameters for the anti-clogging paraffin purification solution.

[0039] The atomization decision module is used to input the parameters of the anti-clogging paraffin purification liquid into the digital twin atomization model; the feature coupling layer performs multi-physics feature fusion, and the decision optimization layer performs energy consumption-coverage multi-objective optimization and outputs paraffin atomization instructions;

[0040] The atomization execution module is used to dynamically atomize the paraffin micro-nano suspension through a dual-fluid nozzle array according to the paraffin atomization command, and to collect the atomized particle size distribution and the surface coverage of the wood shavings; based on the atomized particle size distribution and the surface coverage of the wood shavings, it performs dynamic adjustment of the paraffin atomization scheme and outputs the optimal atomization process parameters.

[0041] The beneficial effects of this invention are as follows: By employing a three-stage synergistic degradation mechanism that sequentially performs turbulent shearing, cavitation explosion, and vortex resonance, the paraffin particles are progressively refined and uniformly dispersed, significantly improving the particle size uniformity and stability of the paraffin micro / nano suspension, thereby alleviating the problem of uneven droplet distribution during atomization. Simultaneously, by using a digital twin atomization model for multi-physics feature fusion and energy consumption-coverage multi-objective optimization, the autonomous generation and dynamic adjustment of atomization parameters are achieved. This not only reduces energy consumption but also enhances anti-clogging capabilities, ensuring efficient and stable production of the atomized paraffin product. Attached Figure Description

[0042] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0043] Figure 1 A flowchart of a micro / nano paraffin atomization method for multi-stage particle degradation and anti-clogging.

[0044] Figure 2 A schematic diagram of a micro / nano paraffin atomization system for multi-stage particle degradation and anti-clogging.

[0045] Figure 3 This is a flowchart of the three-stage synergistic degradation process.

[0046] Figure 4 A flowchart for building a digital twin atomization model. Detailed Implementation

[0047] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0048] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0049] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0050] Reference Figures 1-4 This is one embodiment of the present invention, which provides a multi-stage particle degradation and anti-clogging micro / nano paraffin atomization method, comprising the following steps:

[0051] S1. Inject fatty acid salt dispersant into solid paraffin raw material and melt it with electric heating to obtain paraffin isothermal dispersion; perform three-stage synergistic degradation on paraffin isothermal dispersion to form paraffin micro-nano suspension.

[0052] S1.1. Solid paraffin raw material is put into a high-temperature resistant reactor, and fatty acid salt dispersant is added for mechanical stirring to obtain a preliminary mixture.

[0053] In specific operations,

[0054] Solid paraffin raw material is fed into a high-temperature resistant reactor, and a quantitative amount (e.g., 1.5-2.5% of the mass of solid paraffin raw material) of fatty acid salt dispersant is added to the high-temperature resistant reactor; the solid paraffin raw material and fatty acid salt dispersant are subjected to high-speed shear dispersion and mixing using a mechanical stirring paddle until a homogeneous mixture without obvious particles is formed, thus obtaining a pre-dispersed paraffin mixture.

[0055] The pre-dispersed paraffin mixture was monitored in real time using a temperature sensor and a viscometer to obtain temperature fluctuations and viscosity changes. When both temperature fluctuations and viscosity changes were within the target range, the preliminary preparation was deemed complete, and the preliminary mixture was output.

[0056] It should be noted that the target range is defined based on the melting characteristics and dispersion stability of the historical preliminary mixture; the exemplary value for the temperature fluctuation target range is ±2℃, and the exemplary value for the viscosity change target range is 150-200mPa·s.

[0057] S1.2. The preliminary mixture is heated and melted and dynamically turbulently premixed to generate a homogeneous melt; the homogeneous melt is then kept at a constant temperature to form a paraffin isothermal dispersion.

[0058] In specific operations,

[0059] The high-temperature resistant reactor is heated at a constant rate (e.g., 2-3℃ / min) to raise its temperature from room temperature to the paraffin melting temperature range, causing the initial mixture to completely melt and obtain a liquid paraffin mixture. Next, the liquid paraffin mixture is subjected to dynamic turbulent premixing. Further, a high-speed dispersion disc is activated to rotate the liquid paraffin mixture using a sawtooth turbine, obtaining a primary dispersion slurry. The primary dispersion slurry is then subjected to ultrasonic homogenization to obtain a homogenized mixed liquid. Finally, the homogenized mixed liquid is subjected to isothermal static degassing to generate a homogenized melt.

[0060] It should be noted that the melting temperature range of paraffin is defined based on the synergistic melting characteristics of paraffin and fatty acid salt dispersants, with an exemplary value of 85-90℃; ultrasonic homogenization refers to the process of high-frequency mechanical oscillation and acoustic stirring of the primary dispersion slurry; the specific process of constant-temperature static degassing of the homogenized mixed liquid is as follows: the homogenized mixed liquid is placed in a sealed container and kept at constant pressure and temperature, so that the bubbles naturally rise and precipitate out, thereby removing the entrained gas in the intermediate dispersion liquid.

[0061] Once the temperature of the homogeneous melt reaches the high-temperature threshold, it is kept at a constant temperature. Then, the homogeneous melt is rapidly cooled using a plate heat exchanger to obtain a cooled intermediate phase. The cooled intermediate phase is then pressurized and filtered to generate a paraffin isothermal dispersion precursor. An anchor stirrer is used to stir the dispersion precursor at a low speed (e.g., 50 rpm) to prevent stratification, ultimately forming a paraffin isothermal dispersion.

[0062] It should be noted that the high temperature threshold is defined based on the correlation between viscosity and temperature of historical homogeneous melts, with an exemplary range of 85-87℃.

[0063] S1.3. The paraffin isothermal dispersion is subjected to three-stage synergistic degradation to form a paraffin micro-nano suspension.

[0064] In specific operations,

[0065] The paraffin isothermal dispersion is fed into the guide cavity via a high-pressure pump for turbulent shearing. Further, guide vanes are installed inside the guide cavity. The shearing force generated by the vortex of the guide vanes is used to break up the paraffin isothermal dispersion and disperse the particles, resulting in a pretreated suspension. Multi-stage shearing forces (e.g., shear rate 800-1500 s⁻¹) are applied to the pretreated suspension until it is broken down to the primary target particle size (e.g., 50 μm), at which point the primary degradation liquid is output.

[0066] Next, the primary degradation liquid is transferred to a cavitation reactor for cavitation explosion. Further, a piezoelectric ceramic array is installed in the cavitation reactor, and the piezoelectric ceramic array is subjected to high-frequency inverse piezoelectric oscillation to generate local cavitation collapse high pressure. Based on the local cavitation collapse high pressure, the primary degradation liquid is subjected to micro-jet impact to obtain cavitation treatment liquid. The cavitation treatment liquid is subjected to multiple rounds of micro-jet impact (e.g., 3-5 cycles) until the cavitation treatment liquid is broken down to the secondary target particle size (e.g., 10 μm), generating secondary degradation liquid.

[0067] It should be noted that the specific process of high-frequency inverse piezoelectric oscillation of the piezoelectric ceramic array is as follows: the piezoelectric ceramic array is excited by an electric field through a high-voltage pulse power supply to induce the piezoelectric crystals in the piezoelectric ceramic array to deform and vibrate, thereby obtaining a mechanical oscillation wave; the mechanical oscillation wave is coupled and transmitted through a liquid medium to generate a local cavitation collapse high voltage.

[0068] The secondary degradation liquid is introduced into an eddy current resonant cavity for eddy current resonance. Further, an eddy current generator is placed in the eddy current resonant cavity and activated to perform high-frequency mechanical oscillation, generating acoustic radiation force. Based on the acoustic radiation force, the secondary degradation liquid is subjected to eddy current induced resonance to obtain a resonant treated liquid. The acoustic radiation force of the resonant treated liquid is enhanced (e.g., the acoustic radiation force is in the range of 0.05-0.2μN) until the resonant treated liquid is broken down to the tertiary target particle size (e.g., 5μm) to obtain a tertiary degradation liquid. The tertiary degradation liquid is finely filtered to remove undegraded impurities, and a paraffin micro-nano suspension is output.

[0069] It should be noted that the target particle size is defined based on the deposition efficiency requirements of paraffin atomization applications.

[0070] S2. Perform light scattering analysis on the paraffin micro-nano suspension to obtain the particle size distribution of the suspension; use a PID control algorithm to perform dynamic sound pressure tuning on the particle size distribution of the suspension and output parameters for the anti-clogging paraffin purification liquid.

[0071] S2.1 Collect the dynamic light scattering signal of the paraffin micro-nano suspension and calculate the autocorrelation function to form the light intensity autocorrelation attenuation curve.

[0072] In specific operations,

[0073] The paraffin micro-nano suspension was diluted to avoid multiple scattering interference, and a suspension sample was obtained. The suspension sample was then irradiated with a monochromatic laser using a laser particle size analyzer, and a photomultiplier tube was used simultaneously to capture the dynamic light scattering signal at a fixed sampling frequency (e.g., 100kHz). The dynamic light scattering signal was then high-pass filtered to eliminate environmental noise and obtain a purified light intensity signal.

[0074] The autocorrelation function of the purified light intensity signal is calculated to generate a constant decay time value. The specific mathematical formula is as follows.

[0075] ;

[0076] in, This represents a constant value for the decay time. Indicates the attenuation linewidth. Indicates the delay time. Indicates delay time The autocorrelation function value, Indicates the baseline constant. Indicates the contrast ratio;

[0077] It should be noted that the attenuation linewidth is defined based on the autocorrelation attenuation rate of the purified light intensity signal, and the exemplary value range is 1×10³~1×10 6 Hz; Delay time is obtained by multi-channel delay line sampling of the purified light intensity signal; Baseline constant is defined based on the long-term stable average value of the purified light intensity signal, with an exemplary value range of 0.8~1.2; Contrast coefficient is defined based on the ratio of the fluctuation amplitude of the purified light intensity signal to the baseline, with an exemplary value range of 0.1~0.9.

[0078] Next, least-squares fitting is performed on the constant decay time value. Further, the amplitude of the constant decay time value is scaled to obtain a normalized decay sequence. The normalized decay sequence is then discretized to obtain initial fitting parameters. Nonlinear fitting is performed on the initial fitting parameters to generate an autocorrelation decay curve of light intensity. S2.2, Diffusion coefficient inversion is performed on the autocorrelation decay curve of light intensity to generate the particle size distribution of the suspension.

[0079] In specific operations,

[0080] The attenuation rate parameter of the light intensity autocorrelation attenuation curve is extracted and multimodal separation is performed to obtain the light intensity attenuation component. The Stokes-Einstein equation is used to perform diffusion dynamics inversion and weighted integral calculation on the light intensity attenuation component to generate a multi-peaked diffusion coefficient. The specific mathematical formula is as follows.

[0081] ;

[0082] in, Indicates the diffusion coefficient of a multimodal distribution. Indicates the magnitude of the scattering vector. This represents the total number of light intensity attenuation components. The index representing the light intensity attenuation component. Indicates the first The weighting coefficients of each light intensity attenuation component. Indicates the first Attenuation rate of each light intensity attenuation component;

[0083] It should be noted that the scattering vector magnitude is obtained by performing angle calibration and wavelength matching on the light intensity autocorrelation attenuation curve; the weighting coefficient is defined based on the relative amplitude intensity of the light intensity attenuation component, and the exemplary value range is 0.1~0.9; the attenuation rate is obtained by performing exponential fitting and residual optimization on the light intensity attenuation component.

[0084] The probability density mapping of the diffusion coefficient of the multi-peak distribution is performed to generate the initial probability of particle size; Gaussian kernel smoothing is performed on the initial probability of particle size to obtain the particle size probability distribution; peak boundary identification is performed on the particle size probability distribution to obtain the characteristic peak region; area integration is performed on the characteristic peak region to generate the initial area of ​​each peak; Min-Max scaling is performed on the initial area of ​​each peak to generate the suspension particle size distribution.

[0085] It should be noted that the specific process of peak boundary identification for particle size probability distribution is as follows: the first derivative of the particle size probability distribution is calculated to generate a gradient change sequence; zero-point detection is performed on the gradient change sequence to obtain the boundary coordinate points; the boundary coordinate points are merged into intervals to obtain the characteristic peak region.

[0086] S2.3. The particle size distribution of the suspension is controlled by proportional-integral-derivative coordinated regulation through PID control algorithm to generate sound pressure tuning parameters.

[0087] In specific operations,

[0088] The particle size distribution of the suspension is differentially compared with the target particle size setpoint to generate the instantaneous particle size deviation. A PID control algorithm is applied to perform proportional-integral-derivative coordinated control of the instantaneous particle size deviation. Furthermore, the proportional term linearly amplifies and adjusts the gain of the instantaneous particle size deviation to quickly respond to errors and obtain a proportional output signal. The integral term accumulates the instantaneous particle size deviation over time and eliminates steady-state errors to form an integral compensation signal. The derivative term tracks the deviation slope and performs lead correction on the instantaneous particle size deviation to suppress process oscillations and generate a derivative correction signal.

[0089] It should be noted that the target particle size setting is defined based on the process requirements of the specific application scenario of paraffin atomization; deviation slope tracking refers to the process of monitoring the rate of change and identifying the trend of instantaneous particle size deviation; and advance correction refers to the process of phase compensation and damping adjustment of instantaneous particle size deviation.

[0090] Finally, the proportional output signal, integral compensation signal, and derivative correction signal are superimposed to obtain the original PID control signal; the original PID control signal is then level-converted and limited (e.g., the limiting range is 0-10V) using a signal conditioning circuit to generate a standard drive level.

[0091] The standard driving level is mapped to sound pressure intensity. Then, an inverse piezoelectric converter is used to perform inverse piezoelectric conversion on the standard driving level to obtain the basic sound pressure value. The basic sound pressure value is linearly amplified to generate the sound wave vibration intensity. The sound wave vibration intensity is normalized to obtain the sound pressure tuning parameters.

[0092] S2.4. Based on the sound pressure tuning parameters, apply an orthogonal standing wave field of sound pressure to the paraffin micro-nano suspension to obtain the anti-clogging paraffin purification liquid. Simultaneously record and store the parameters, and output the parameters of the anti-clogging paraffin purification liquid.

[0093] In specific operations,

[0094] Based on the sound pressure tuning parameters, the array-type electric transducer is driven to perform phase synchronization and amplitude modulation to obtain a coherent sound beam. The coherent sound beam is then reflected and superimposed to generate a standing wave interference field. Energy density focusing is performed on the standing wave interference field to obtain a sound pressure orthogonal standing wave field. The sound pressure orthogonal standing wave is applied to the closed reaction chamber of the paraffin micro-nano suspension, and the paraffin micro-nano suspension is subjected to particle resonance crushing and dispersion stabilization to prevent the nozzle and pipe from clogging during atomization, thus obtaining an anti-clogging paraffin purification liquid.

[0095] It should be noted that the specific process of energy density focusing on the standing wave interferometer field is as follows: the acoustic energy gradient of the standing wave interferometer field is controlled to obtain the energy convergence point; focus enhancement and phase interpolation are performed on the energy convergence point to generate a high energy density region; waveform superposition is performed on the high energy density region to obtain an orthogonal standing wave field of sound pressure.

[0096] The sound pressure intensity, duration of action, and particle size distribution of the paraffin micro-nano suspension were recorded and stored in a structured manner to obtain the original parameter records. The original parameter records were then filtered and noise-reduced to generate parameters for the anti-clogging paraffin purification liquid.

[0097] S3. Input the parameters of the anti-clogging paraffin purification liquid into the digital twin atomization model; the feature coupling layer performs multi-physics feature fusion, the decision optimization layer performs energy consumption-coverage multi-objective optimization, and outputs paraffin atomization instructions.

[0098] S3.1 Build and train a digital twin atomization model.

[0099] In specific operations,

[0100] In the TensorFlow framework, a convolutional neural network is invoked through the Conv3D parameter and initialized. For example, the number of convolutional kernels is set to 64, the kernel size is set to 3×3×3, and the activation function is set to ReLU. A three-dimensional convolution is embedded in the convolutional neural network to extract multi-physics features in order to capture spatial correlation characteristics. The features are then normalized through BatchNormalization to complete the construction of the feature coupling layer.

[0101] The U-Net (encoder-decoder) architecture is invoked through the UpSampling3D parameters and initialized. For example, the downsampling factor is set to 2×2×2, the dropout rate is set to 0.2, and the upsampling method is set to transposed convolution. The NSGA-II algorithm is then applied to the U-Net architecture to perform multi-objective optimization operations to balance energy consumption and coverage metrics. The Sigmoid function is used for non-linear activation to complete the construction of the decision optimization layer.

[0102] Skip connections are used to perform cross-level feature fusion on the feature coupling layer and the decision optimization layer to obtain multi-scale fogging features. The multi-scale fogging features are then concatenated by channel dimension to generate fogging process coupling features. 1×1 convolution is used to compress the dimensions of the fogging process coupling features to generate fogging control vectors. Fully connected layer mapping is performed on the fogging control vectors to obtain layer-based weights. Based on the layer-based weights, residual stacking is performed on the feature coupling layer and the decision optimization layer to complete the construction of the digital twin fogging model.

[0103] Next, the digital twin atomization model is trained. Further, the historical anti-clogging paraffin purification fluid parameters are divided into a sample set, a training set, and a validation set. On the sample set, the MinMaxScaler (minimum-maximum normalizer) is used for data normalization to form preprocessed samples. On the training set, the Adam optimizer is used to perform gradient backpropagation on the preprocessed samples, and an early stopping mechanism is simultaneously applied to suppress overfitting, obtaining optimized digital twin atomization model parameters. On the validation set, the mean squared error loss function is used to measure the loss of the optimized digital twin atomization model parameters, obtaining the validation loss value. When the validation loss value exceeds the convergence threshold for several consecutive rounds (e.g., 5 times), training terminates, and the trained digital twin atomization model is output simultaneously.

[0104] It should be noted that the convergence threshold is defined based on the dynamic volatility of historical validation loss values, with an exemplary range of 0.001 to 0.005.

[0105] S3.2 The feature coupling layer uses three-dimensional convolution to fuse multi-physics field features of the anti-clogging paraffin purification liquid parameters to generate atomization coupling features.

[0106] In specific operations,

[0107] The parameters of the anti-clogging paraffin purification fluid were input into the digital twin atomization model through the OPC UA industrial data interface. The feature coupling layer applied 3D convolution to reconstruct the spatiotemporal dimensions of the anti-clogging paraffin purification fluid parameters, resulting in a four-dimensional structured tensor. Subsequently, multi-physics feature extraction was performed on the four-dimensional structured tensor through three layers of 3D convolution kernels. Furthermore, the first layer performed Gaussian difference filtering and LeakyReLU activation on the four-dimensional structured tensor to capture local correlation features; the second layer performed cross-channel convolution and batch normalization on the four-dimensional structured tensor to obtain cross-field collaborative features; and the third layer performed global convolution and pooling dimensionality reduction on the four-dimensional structured tensor to obtain global interactive features.

[0108] An attention weight is obtained by calculating the importance of local correlation features, cross-field collaborative features, and global interaction features using a multi-head attention mechanism. The specific mathematical formula is as follows.

[0109] ;

[0110] in, Indicates attention weights, This indicates a query for projection coefficients. Represents the local correlation feature matrix. Represents the weights of the linear transformation. Represents the cross-field collaborative feature matrix. This indicates the transpose operation. Indicates the scaling factor. Represents the global interaction feature matrix;

[0111] It should be noted that the local correlation feature matrix is ​​obtained by performing a moving exponential average on the local correlation features; the cross-field collaboration feature matrix is ​​obtained by performing dimensionality compression on the cross-field collaboration features; and the global interaction feature matrix is ​​obtained by performing a fully connected transformation on the global interaction features.

[0112] The query projection coefficient is defined based on the normal distribution of the query vector in the multi-head attention mechanism, with an exemplary value range of [-1.0, 1.0]; the linear transformation weight is defined based on the variance balance contribution rate of local association features, cross-field collaborative features, and global interaction features, with an exemplary value range of [-0.02, 0.02]; the scaling factor is defined based on the dimensionality balance requirement of the multi-head attention mechanism, with an exemplary value range of 8~32.

[0113] Based on attention weights, weighted fusion is performed on local correlation features, cross-field collaborative features, and global interaction features to generate a multi-field coupled feature map; channel dimension compression and nonlinear transformation are performed on the multi-field coupled feature map to generate fogged coupled features.

[0114] S3.3 The decision optimization layer performs energy consumption-coverage multi-objective optimization through the NSGA-II algorithm to form Pareto optimal parameters.

[0115] In specific operations,

[0116] A bidirectional U-Net architecture is used to perform multi-scale feature parsing of fog coupling features. Furthermore, the forward U-Net architecture downsamples and extracts features from the fog coupling features through the encoder to obtain high-dimensional semantic features; the backward U-Net architecture applies the decoder to upsample and reconstruct the high-dimensional semantic features to obtain the reconstructed feature tensor; and a fully connected mapping is performed on the reconstructed feature tensor to obtain the fogging process feature vector.

[0117] The NSGA-II algorithm is used to perform multi-objective optimization of the atomization process feature vector, considering energy consumption and coverage. Furthermore, atomization control parameters are extracted from the feature vector and used as initial population individuals. Subsequently, non-dominated sorting is performed on the initial population individuals: first, the objective function value for each initial population individual is calculated, using the following mathematical formula.

[0118] ;

[0119] in, Represents the objective function value. This represents the energy consumption weighting coefficient. This represents the energy consumption index value. This represents the coverage weighting coefficient. Indicates the theoretical maximum coverage. Indicates actual coverage rate;

[0120] It should be noted that the energy consumption weighting coefficient is based on the energy consumption sensitivity definition of the atomization control parameters, and the exemplary value range is 0.5~0.8; the energy consumption index value is obtained by performing power integration on the atomization control parameters; the theoretical maximum coverage is defined based on the ideal hydrodynamic conditions of paraffin atomization; the actual coverage is obtained by performing surface imaging detection on the atomization control parameters; the coverage weighting coefficient is defined based on the ratio of the theoretical maximum coverage to the actual coverage, and the exemplary value range is 0.2~0.5.

[0121] The initial population individuals are ranked according to the frontier level based on the objective function value. For example, the level interval is defined based on the statistical distribution of historical objective function values. When the objective function value is in the optimal interval (e.g., 0 to 85), the initial population individuals are ranked as the first level. When the objective function value is in the suboptimal interval (e.g., 85 to 120), the initial population individuals are ranked as the second level. When the objective function value is in the non-optimal interval (e.g., 120 to 200), the initial population individuals are ranked as the third level, and the non-dominated ranking result is output.

[0122] Simulated binary crossover and polynomial mutation are performed on the non-dominated sorting results to generate offspring individuals; the offspring individuals are merged with the initial population in equal proportions to obtain a merged population; the merged population is subjected to multiple (e.g., 200) genetic iterations to obtain a Pareto solution set; parameter extraction is performed on the Pareto solution set to output the Pareto optimal parameters; each solution in the Pareto optimal parameters represents the best trade-off between energy consumption and coverage, which can meet the engineering requirements of multi-objective collaborative optimization.

[0123] S3.4. Perform tensor splicing and nonlinear activation on the atomization coupling features and Pareto optimal parameters to output the paraffin atomization command.

[0124] In specific operations,

[0125] The Pareto optimal parameters are expanded in dimension and reshaped into tensors by a fully connected function to obtain the parameter feature tensor. The parameter feature tensor and the fog coupling feature are concatenated in the channel dimension to form the enhanced feature tensor. Then, the enhanced feature tensor is compressed by a 1×1 convolution kernel, and the LeakyReLU activation function is applied to preserve the nonlinear relationship, outputting the optimized fog control vector.

[0126] The optimized atomization control vector is mapped to paraffin atomization instructions. Further, the optimized atomization control vector is linearly transformed to obtain normalized control parameters. Engineering dimension conversion is performed on the normalized control parameters to generate physical quantity control instructions. The physical quantity control instructions are format-encapsulated to obtain paraffin atomization instructions.

[0127] It should be noted that engineering dimension conversion refers to the process of mapping the range of normalized control parameters and adding units.

[0128] S4. According to the paraffin atomization command, the paraffin micro-nano suspension is dynamically atomized through a dual-fluid nozzle array, and the atomized particle size distribution and the surface coverage of the wood shavings are collected. Based on the atomized particle size distribution and the surface coverage of the wood shavings, the paraffin atomization scheme is dynamically adjusted, and the optimal atomization process parameters are output.

[0129] S4.1 Extract the atomization control parameters of the paraffin atomization command. The dual-fluid nozzle array dynamically atomizes the anti-clogging paraffin purification liquid according to the atomization control parameters to obtain the finished paraffin atomization product.

[0130] In specific operations,

[0131] The air pressure setting parameters, flow range, and atomization angle in the paraffin atomization command are extracted as atomization control parameters. Based on the atomization control parameters, the air path solenoid valve of the dual-fluid nozzle array is driven to regulate the pressure and stabilize the airflow. At the same time, a servo motor is used for precise flow control to obtain a stable gas-liquid input flow.

[0132] The anti-clogging paraffin purification liquid is sheared, mixed, and vortex-atomized by a stable gas-liquid input flow to obtain preliminary atomized products. At the same time, a high-speed camera is used to detect the atomization cone angle of the preliminary atomized products. When the atomization cone angle reaches the qualified range, the preliminary atomized products are judged to meet the finished product requirements, and the paraffin atomized finished product is output.

[0133] It should be noted that the acceptable range is defined based on the actual process requirements of paraffin atomization.

[0134] S4.2. The particle size distribution and shaving surface coverage of the paraffin atomized product were collected using a laser particle size analyzer and a near-infrared moisture analyzer, respectively.

[0135] In specific operations,

[0136] The atomized paraffin wax product is introduced into a wet sample cell at a constant flow rate (e.g., 1.5 mL / s), and the atomized paraffin wax product is irradiated with dual light sources of red and blue light. Simultaneously, the atomized particle size distribution is collected by a laser particle size analyzer. Then, the atomized paraffin wax product is placed on a rotating sample stage, and the surface is scanned with near-infrared light at a fixed wavelength (e.g., 1450 nm). The surface coverage of the wood shavings is detected by a near-infrared moisture analyzer.

[0137] S4.3 Calculate the cumulative volume distribution of the atomized particle size distribution to obtain the particle size uniformity index; at the same time, calculate the thickness change of the shaving surface coverage to generate the thickness expansion uniformity coefficient.

[0138] In specific operations,

[0139] The cumulative volume distribution of the atomized particle size is calculated to obtain the particle size uniformity index. The specific mathematical formula is as follows.

[0140] ;

[0141] in, Indicates the particle size uniformity index. The standard deviation of the atomized particle size distribution is represented by the standard deviation of the atomized particle size distribution. This represents the mean value of the atomized particle size distribution;

[0142] It should be noted that the standard deviation and mean of the atomized particle size distribution are obtained by performing a sliding window statistical operation on the atomized particle size distribution.

[0143] The thickness variation of the wood shavings surface coverage is calculated to generate a thickness expansion uniformity coefficient. The specific mathematical formula is as follows.

[0144] ;

[0145] in, This represents the coefficient of thickness expansion uniformity. Indicates the surface coverage of wood shavings. Indicates the maximum thickness variation deviation;

[0146] It should be noted that the maximum thickness variation deviation was obtained by performing a regional range integral operation on the surface coverage of the wood shavings.

[0147] S4.4. Based on the particle size uniformity index and thickness expansion uniformity coefficient, adjust the compressed air pressure and atomization cone angle parameters of the paraffin atomization scheme to output the optimal atomization process parameters.

[0148] In specific operations,

[0149] Extract the compressed air pressure and atomization cone angle parameters of the paraffin atomization scheme; based on the particle size uniformity index, adjust the compressed air pressure stepwise using a PID controller, and simultaneously adjust the atomization cone angle direction using a fuzzy controller based on the thickness expansion uniformity coefficient, obtaining the adjusted compressed air pressure and atomization cone angle; perform parameter combination tests on the adjusted compressed air pressure and atomization cone angle, and observe the actual atomization state; when the actual atomization shape meets the standard atomization state range, lock the adjusted compressed air pressure and atomization cone angle as the optimal parameters, encapsulate them in JSON format, and output the optimal atomization process parameters;

[0150] It should be noted that the standard atomization state range is defined based on the uniformity of particle size distribution and the density of the deposited layer of the paraffin atomized product.

[0151] This embodiment also provides a multi-stage particle degradation and anti-clogging micro-nano paraffin atomization system, including: a melt dispersion module, used to inject fatty acid salt dispersant into solid paraffin raw material and perform electric heating melting to obtain paraffin isothermal dispersion; and to perform three-stage synergistic degradation on the paraffin isothermal dispersion to form paraffin micro-nano suspension;

[0152] The particle size control module is used to perform light scattering analysis on paraffin micro-nano suspensions to obtain the particle size distribution of the suspensions; and to perform dynamic acoustic pressure tuning on the particle size distribution of the suspensions through a PID control algorithm to output parameters for the anti-clogging paraffin purification solution.

[0153] The atomization decision module is used to input the parameters of the anti-clogging paraffin purification liquid into the digital twin atomization model; the feature coupling layer performs multi-physics feature fusion, and the decision optimization layer performs energy consumption-coverage multi-objective optimization and outputs paraffin atomization instructions;

[0154] The atomization execution module is used to dynamically atomize the paraffin micro-nano suspension through a dual-fluid nozzle array according to the paraffin atomization command, and to collect the atomized particle size distribution and the surface coverage of the wood shavings; based on the atomized particle size distribution and the surface coverage of the wood shavings, it performs dynamic adjustment of the paraffin atomization scheme and outputs the optimal atomization process parameters.

[0155] This embodiment also provides a computer device applicable to the micro / nano paraffin atomization method for multi-stage particle degradation and anti-clogging, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the micro / nano paraffin atomization method for multi-stage particle degradation and anti-clogging as proposed in the above embodiment.

[0156] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0157] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements the micro / nano paraffin atomization method for achieving multi-level particle degradation and anti-clogging as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0158] In summary, this invention achieves progressive refinement and uniform dispersion of paraffin particles through a three-stage synergistic degradation mechanism involving turbulent shearing, cavitation bursting, and vortex resonance. This significantly improves the particle size uniformity and stability of the paraffin micro / nano suspension, thereby mitigating the problem of uneven droplet distribution during atomization. Simultaneously, the use of a digital twin atomization model for multi-physics feature fusion and energy consumption-coverage multi-objective optimization enables the autonomous generation and dynamic adjustment of atomization parameters. This not only reduces energy consumption but also enhances anti-clogging capabilities, ensuring efficient and stable production of atomized paraffin products.

[0159] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A multi-stage particle degradation and anti-blocking micro-nano paraffin atomization method, characterized by: Comprising, Injecting a fatty acid salt dispersant into a solid paraffin raw material, and performing electric heat tracing melting to obtain a paraffin constant-temperature dispersion liquid; performing three-stage synergistic degradation on the paraffin constant-temperature dispersion liquid to form a paraffin micro-nano suspension liquid; Performing light scattering analysis on the paraffin micro-nano suspension liquid to obtain a suspension particle size distribution; performing sound pressure dynamic tuning on the suspension particle size distribution by a PID control algorithm to output anti-blocking paraffin purification liquid parameters; Inputting the anti-blocking paraffin purification liquid parameters into a digital twin atomization model; performing multi-physics field feature fusion by a feature coupling layer, and performing energy consumption-coverage rate multi-objective optimization by a decision optimization layer to output paraffin atomization instructions; According to the paraffin atomization instructions, performing dynamic atomization on the paraffin micro-nano suspension liquid by a two-fluid nozzle array, and collecting atomized particle size distribution and shaving surface coverage rate; performing dynamic adjustment on the paraffin atomization scheme according to the atomized particle size distribution and the shaving surface coverage rate to output optimal atomization process parameters.

2. The multi-stage particle degradation and anti-blocking micro-nano paraffin wax atomization method of claim 1, wherein: The specific steps of obtaining the paraffin constant-temperature dispersion liquid are as follows, Put the solid paraffin raw material into a high-temperature resistant reactor, and add a fatty acid salt dispersant for mechanical stirring to obtain a preliminary mixed material; Performing temperature rising melting and dynamic turbulent premixing on the preliminary mixed material to generate a homogeneous molten liquid; performing constant temperature adjustment on the homogeneous molten liquid to form a paraffin constant-temperature dispersion liquid.

3. The multi-stage particle degradation and anti-blocking micro-nano paraffin wax atomization method of claim 2, wherein: The specific steps of forming the paraffin micro-nano suspension liquid are as follows, Input the paraffin constant-temperature dispersion liquid into a flow guide cavity for turbulent shear to obtain a primary degradation liquid; Transfer the primary degradation liquid into a cavitation reactor for cavitation explosion to generate a secondary degradation liquid; Guide the secondary degradation liquid into a vortex resonance cavity for vortex resonance to obtain a paraffin micro-nano suspension liquid.

4. The multi-stage particle degradation and anti-blocking micro-nano paraffin wax atomization method of claim 1, wherein: The specific steps of obtaining the suspension particle size distribution are as follows, Collect the dynamic light scattering signal of the paraffin micro-nano suspension liquid, and perform autocorrelation function calculation to form a light intensity autocorrelation decay curve; Performing diffusion coefficient inversion on the light intensity autocorrelation decay curve to generate a suspension particle size distribution.

5. The multi-stage particle degradation and anti-blocking micro-nano paraffin wax atomization method of claim 4, wherein: The specific steps of outputting the anti-blocking paraffin purification liquid parameters are as follows, Performing proportional-integral-derivative synergistic control on the suspension particle size distribution by a PID control algorithm to generate sound pressure tuning parameters; According to the sound pressure tuning parameters, apply a sound pressure orthogonal standing wave field to the paraffin micro-nano suspension liquid to obtain an anti-blocking paraffin purification liquid, record the parameters synchronously, and output the anti-blocking paraffin purification liquid parameters.

6. The multi-stage particle degradation and anti-blocking micro-nano paraffin wax atomization method of claim 1, wherein: The specific construction process of the digital twin atomization model is as follows, Build a feature coupling layer by a convolutional neural network, and build a decision optimization layer by a U-Net architecture; Use skip connection to perform cross-level feature fusion and residual stacking on the feature coupling layer and the decision optimization layer to build a digital twin atomization model.

7. The multi-stage particle degradation and anti-blocking micro-nano paraffin wax atomization method of claim 1, wherein: The specific steps of outputting the paraffin atomization instructions are as follows, Input the anti-blocking paraffin purification liquid parameters into the digital twin atomization model, and apply three-dimensional convolution to the anti-blocking paraffin purification liquid parameters by the feature coupling layer to generate atomization coupling features; The decision optimization layer performs energy consumption-coverage rate multi-objective optimization by an NSGA-II algorithm to form Pareto optimal parameters; Perform tensor splicing and nonlinear activation on the atomization coupling features and the Pareto optimal parameters to output paraffin atomization instructions.

8. The multi-stage particle degradation and anti-blocking micro-nano paraffin wax atomization method of claim 7, wherein: The collection of atomized particle size distribution and shaving surface coverage is specifically as follows, The atomization control parameters of the paraffin atomization instruction are extracted, and the double-fluid nozzle array performs dynamic atomization on the anti-blocking paraffin purification liquid according to the atomization control parameters to obtain paraffin atomized products; The atomized particle size distribution and the shaving surface coverage of the paraffin atomized products are collected by a laser particle size analyzer and a near-infrared moisture meter, respectively.

9. The multi-stage particle degradation and anti-blocking micro-nano paraffin wax atomization method of claim 1, wherein: The optimal atomization process parameters are output, and the specific steps are as follows, The cumulative volume distribution of the atomized particle size distribution is calculated to obtain a particle size uniformity index; and the thickness change of the shaving surface coverage is calculated to generate a thickness expansion uniformity coefficient; According to the particle size uniformity index and the thickness expansion uniformity coefficient, the compressed air pressure and the atomization cone angle parameters of the paraffin atomization scheme are adjusted, and the optimal atomization process parameters are output.

10. A multi-stage particle degradation and anti-blocking micro-nano paraffin atomization system based on the multi-stage particle degradation and anti-blocking micro-nano paraffin atomization method of any one of claims 1-9, characterized in that: It comprises, The melting and dispersion module is used for injecting a fatty acid salt dispersant into solid paraffin raw materials and performing electric heat tracing melting to obtain a paraffin constant-temperature dispersion liquid; the paraffin constant-temperature dispersion liquid is subjected to three-stage synergistic degradation to form a paraffin micro-nano suspension liquid; The particle size control module is used for performing light scattering analysis on the paraffin micro-nano suspension liquid to obtain a suspension liquid particle size distribution; a PID control algorithm is used to perform sound pressure dynamic tuning on the suspension liquid particle size distribution to output anti-blocking paraffin purification liquid parameters; The atomization decision module is used for inputting the anti-blocking paraffin purification liquid parameters into a digital twin atomization model; a feature coupling layer performs multi-physical field feature fusion, and a decision optimization layer performs energy consumption-coverage multi-objective optimization to output paraffin atomization instructions; The atomization execution module is used for performing dynamic atomization on the paraffin micro-nano suspension liquid through a double-fluid nozzle array according to the paraffin atomization instructions, and collecting atomized particle size distribution and shaving surface coverage; and the paraffin atomization scheme is dynamically adjusted according to the atomized particle size distribution and the shaving surface coverage to output optimal atomization process parameters.

Images