Dynamic temperature field collaborative optimization method for water-based ink dispersion process

Abstract

The invention relates to the technical field of water-based ink dispersion control, in particular to a dynamic temperature field collaborative optimization method for a water-based ink dispersion process, which comprises the following steps: synchronously acquiring temperature field distribution data and shear field distribution data through a distributed fiber grating temperature sensor and an ultrasonic Doppler velocimeter; and constructing multi-dimensional field data with a unified timestamp and space coordinates. Calculating temperature field intensity gradient data and shear field intensity gradient data based on the multi-dimensional field data, analyzing and identifying a mismatch region through a field cooperation angle, establishing a dynamic coupling relation model in combination with a deep neural network, generating field cooperation optimization parameters, and performing field cooperation optimization. And forming a regional temperature compensation strategy by adopting rule engine analysis, a multi-objective optimization algorithm and a feasibility verification mechanism, and converting the regional temperature compensation strategy into a control instruction sequence of the multi-channel temperature control system. Through real-time monitoring and fuzzy PID dynamic adjustment, continuous cooperation of a temperature field and a shear field is realized, and the dispersion efficiency and the product stability are improved.

Description

Technical Field

[0001] This invention relates to the field of water-based ink dispersion control technology, and in particular to a dynamic temperature field co-optimization method for water-based ink dispersion processes. Background Technology

[0002] The dispersion process of water-based inks is a crucial step in industries such as coatings, printing, and surface treatment. Its dispersion quality directly determines the product's color intensity, stability, gloss, and long-term storage performance. This process is essentially a complex dynamic system driven by the evolution of thermal, flow, and material microstructures. The temperature field influences the actual effect of shear force by adjusting local fluid viscosity, while the shear field affects dispersion efficiency by driving particle breakage, deagglomeration, and migration. Therefore, the degree of synergy between the temperature and shear fields has a decisive impact on the final dispersion effect.

[0003] Existing technologies suffer from the following main problems: First, traditional dispersion processes often monitor only single indicators such as temperature or torque, lacking simultaneous high-resolution acquisition methods for temperature and shear field distribution data. This makes it difficult to obtain truly effective multi-dimensional field data, resulting in an inability to accurately determine local field mismatch issues. Second, existing research relies heavily on empirical judgments regarding the correlation between temperature and shear fields, lacking systematic evaluation methods based on gradient analysis and field synergy theory. It also fails to handle the coupling changes at different stages of the dispersion process, causing optimization strategies to be unable to adapt to the dynamic evolution of the process. Third, traditional compensation strategies typically employ fixed temperature control modes or simple linear adjustment methods, lacking intelligent decision-making systems based on deep learning models, rule engines, and multi-objective optimization algorithms, making it difficult to balance synergy, energy consumption, and stability. Finally, existing temperature control systems are mostly based on overall control or low-dimensional adjustment, unable to achieve independent and precise temperature control in multiple regions, and lacking real-time field synergy feedback and dynamic correction capabilities. This makes it difficult to achieve effective compensation at the execution level even when problem areas are identified. Summary of the Invention

[0004] This invention provides a dynamic temperature field collaborative optimization method for the dispersion process of water-based inks, which realizes a comprehensive method of multi-dimensional field data acquisition, field collaborative analysis, intelligent optimization decision-making and regional independent control, significantly improving the collaborative efficiency and dispersion quality of the dispersion process of water-based inks.

[0005] A dynamic temperature field co-optimization method for the dispersion process of water-based inks includes the following steps:

[0006] S1: Simultaneously collect multi-dimensional field data during the dispersion process of water-based inks, including temperature field distribution data and shear field distribution data;

[0007] S2: Based on the multi-dimensional field data, identify the mismatch region between the temperature field and the shear field, establish a dynamic coupling relationship model, and output the field collaborative optimization parameters through the dynamic coupling relationship model;

[0008] S3: Generate a regional temperature compensation strategy based on the field collaborative optimization parameters. The regional temperature compensation strategy includes a differentiated temperature control scheme for the mismatched region.

[0009] S4: Based on the aforementioned regional temperature compensation strategy, the dispersed equipment is independently controlled in different regions through a multi-channel temperature control system to achieve dynamic coordination between the temperature field and the shear field.

[0010] Optionally, S1 includes:

[0011] S11: Raw temperature data is collected by an array of temperature sensors deployed within the distributed equipment, and raw shear data is collected by an ultrasonic Doppler velocimeter.

[0012] S12: Perform spatial interpolation on the original temperature data to generate temperature field distribution data, and perform vector calculation on the original shear data to generate shear field distribution data;

[0013] S13: The temperature field distribution data and the shear field distribution data are spatiotemporally aligned and integrated to form the multidimensional field data.

[0014] Optionally, the temperature sensor array employs a distributed fiber Bragg grating temperature sensor to synchronously acquire the raw temperature data at a sampling frequency of 0.1 seconds; the ultrasonic Doppler velocimeter acquires the raw shear data at the same sampling frequency and simultaneously records the velocity vector and turbulence intensity parameters at each measurement point.

[0015] Optionally, the spatiotemporal alignment and integration includes: adding unified timestamps and spatial coordinate identifiers to the temperature field distribution data and the shear field distribution data respectively, and mapping the two to the same three-dimensional spatial coordinate system through a data fusion algorithm to form multi-dimensional field data with spatiotemporal consistency.

[0016] Optionally, S2 includes:

[0017] S21: Based on the multi-dimensional field data, calculate the temperature field intensity gradient data and the shear field intensity gradient data respectively;

[0018] S22: Based on the temperature field intensity gradient data and the shear field intensity gradient data, identify the mismatch region through field synergy angle analysis and extract the characteristic parameters of the mismatch region;

[0019] S23: Input the feature parameters of the mismatched region into a pre-trained deep neural network to establish a dynamic coupling relationship model;

[0020] S24: Calculate and output field collaborative optimization parameters through the dynamic coupling relationship model, the field collaborative optimization parameters including the compensation priority and optimal temperature compensation amount of each mismatch region.

[0021] Optionally, the field coordination angle analysis specifically involves: calculating the cosine value of the angle between the temperature field intensity gradient data and the shear field intensity gradient data at each spatial point; when the cosine value is less than 0.7, the spatial point is determined to belong to the mismatch region, and the feature parameters of the mismatch region are extracted, including the mismatch area, average mismatch intensity, and spatial distribution pattern.

[0022] Optionally, S3 includes:

[0023] S31: Analyze the compensation priority and optimal temperature compensation amount in the field cooperative optimization parameters to generate an initial regional temperature compensation strategy;

[0024] S32: The initial regional temperature compensation strategy is globally optimized based on a multi-objective optimization algorithm to generate an optimized regional temperature compensation strategy.

[0025] S33: Perform feasibility verification and conflict resolution on the optimized regional temperature compensation strategy to generate a feasible regional temperature compensation strategy.

[0026] S34: Based on the feasible regional temperature compensation strategy, formulate a differentiated temperature control scheme including specific control parameters and execution timing.

[0027] Optionally, the specific steps of parsing the compensation priority and optimal temperature compensation amount in the field collaborative optimization parameters are as follows: using a rule engine-based parsing method, sorting each mismatched region according to the compensation priority, and converting the optimal temperature compensation amount into the initial temperature setting value of each region, thereby generating an initial sub-regional temperature compensation strategy that includes the temperature setting value of each region and the execution order.

[0028] Optionally, S4 includes:

[0029] S41: Analyze the regional temperature compensation strategy and convert it into an independent control command sequence for each channel of the multi-channel temperature control system;

[0030] S42: Send the control command sequence to each execution unit of the multi-channel temperature control system to start the regional independent control process;

[0031] S43: Monitor the changes in temperature and shear fields during the execution of independent regional control in real time, verify the dynamic synergistic effect of temperature and shear fields, and dynamically adjust the control command sequence based on the verification results.

[0032] Optionally, the analytical regional temperature compensation strategy is implemented through an instruction compilation module. The instruction compilation module converts the temperature setpoint, control timing, and change rate parameters in the regional temperature compensation strategy into independent control instruction sequences for each channel of the multi-channel temperature control system. The control instruction sequences include the target temperature value, heating / cooling rate, and holding time parameters for each channel.

[0033] The beneficial effects of this invention are:

[0034] 1. This invention employs a combined deployment of a distributed fiber optic grating temperature sensor matrix and a multi-probe ultrasonic Doppler velocimeter to achieve a one-to-one spatial correspondence acquisition of temperature and shear field distribution data, and ensures high accuracy of the raw data through a dynamic calibration mechanism. Furthermore, based on Kriging interpolation, vector calculation (including vorticity and shear rate calculation), spatiotemporal alignment integration, and wavelet transform-based data compression, this invention constructs multi-dimensional field data of temperature and shear fields with unified timestamps, a unified three-dimensional spatial coordinate system, and high confidence weights, which can be directly used for dynamic collaborative analysis. Compared to traditional monitoring methods that rely solely on single-field or low-frequency sampling, this invention significantly improves the refinement of multi-field coupling analysis of dispersed processes, providing a high-resolution, low-noise, and continuously updated basic data system for dynamically identifying field mismatch problems.

[0035] 2. This invention achieves accurate identification of mismatch regions through field coordination angle analysis of temperature field intensity gradient data and shear field intensity gradient data. It also distinguishes different physical characteristics in the early, middle, and late stages of dispersion through a dynamic threshold mechanism, gradually adjusting the threshold from 0.6 to 0.8 to implement a layered monitoring strategy of "macroscopic stability control—refined optimization—microscopic refinement" at different stages. Simultaneously, this invention extracts feature parameters of the mismatch region and inputs them into a graph convolutional neural network with an attention mechanism to construct a dynamic coupling relationship model. Based on an online adaptive mechanism, the network model is continuously updated to improve the real-time performance and relevance of strategy generation. Through rule engine parsing, multi-objective global optimization based on a non-dominated sorting genetic algorithm, feasibility verification, and conflict resolution mechanisms, this invention achieves a fully intelligent decision-making chain from "mismatch identification" to "compensation optimization strategy generation," enabling the temperature compensation strategy to achieve a dynamic balance between field coordination, energy consumption, and stability, significantly improving the uniformity of dispersion results and energy utilization efficiency.

[0036] 3. This invention transforms the regional temperature compensation strategy into a control command sequence for a multi-channel temperature control system through an instruction compilation module, and achieves microsecond-level synchronous transmission via the EtherCAT industrial communication network, enabling the entire system to possess high real-time performance and high consistency at the execution level. During the control execution phase, each execution unit performs heating, cooling, and steady-state maintenance operations in parallel according to an independent control command sequence, forming a truly regional independent control structure. Simultaneously, this invention collects real-time temperature and shear field change data, calculates the current field coordination degree, and uses fuzzy PID for dynamic correction, forming a closed-loop temperature control system. Combined with abnormal fluctuation detection and safety protection mechanisms, it ensures steady-state controllability under any operating condition. Compared to traditional methods that only perform single-point temperature control or fixed strategy regulation, this invention can achieve precise linkage control across multiple regions, dimensions, and time sequences, maintaining the dynamic coordination degree of the entire dispersion process at its optimal state, ultimately significantly improving the dispersion efficiency, fineness, stability, and product consistency of water-based inks. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a schematic diagram of the method flow according to an embodiment of the present invention;

[0039] Figure 2 This is a schematic diagram of the S2 process in an embodiment of the present invention. Detailed Implementation

[0040] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. It should also be noted that, to make the embodiments more comprehensive, the following embodiments are the best and preferred embodiments, and those skilled in the art can use other alternative methods to implement some well-known technologies; moreover, the accompanying drawings are only for more specific description of the embodiments and are not intended to specifically limit the present invention.

[0041] It should be noted that the use of terms such as "an embodiment," "an embodiment," "an exemplary embodiment," and "some embodiments" in the specification indicates that the described embodiment may include a specific feature, structure, or characteristic, but not every embodiment necessarily includes that specific feature, structure, or characteristic. Furthermore, when a specific feature, structure, or characteristic is described in connection with an embodiment, implementing such a feature, structure, or characteristic in conjunction with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the art.

[0042] Generally, terms can be understood at least partly from their use in context. For example, depending at least partly on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in a singular sense, or a combination of features, structures, or characteristics in a plural sense. Additionally, the term "based on" can be understood not necessarily to convey an exclusive set of factors, but rather, alternatively, depending at least partly on the context, to allow for the presence of other factors that are not necessarily explicitly described.

[0043] like Figures 1-2 As shown, the dynamic temperature field co-optimization method for the dispersion process of water-based inks includes the following steps:

[0044] S1: Synchronously collect multi-dimensional field data during the dispersion process of water-based inks. The multi-dimensional field data includes temperature field distribution data and shear field distribution data, specifically:

[0045] S11: Raw temperature data is acquired through a temperature sensor array deployed within the distributed equipment, and raw shear data is acquired through an ultrasonic Doppler velocimeter. A dynamic calibration process is performed before each acquisition to ensure data accuracy and repeatability. The steps are as follows:

[0046] 1. A temperature sensor array is installed on the inner wall of the dispersion vessel and the surface of the agitator. The temperature sensor array adopts distributed fiber optic grating temperature sensors, which are arranged in a regular matrix on the inner wall of the dispersion vessel according to the preset axial and radial spacing, and also in a regular matrix along the length and width of the agitator blade, so that the distributed fiber optic grating temperature sensors form a three-dimensional temperature measurement network, covering the key spatial locations in the dispersion area.

[0047] 2. The distributed fiber optic temperature sensor synchronously collects raw temperature data at a sampling frequency of 0.1 seconds and transmits the raw temperature data corresponding to each deployment node to the data acquisition system in real time. The data acquisition system accurately marks the sampling time of each sensing node to ensure the time accuracy of subsequent spatiotemporal alignment and integration.

[0048] 3. An ultrasonic Doppler velocimeter is installed inside the distributed equipment, employing a multi-probe configuration to ensure that each measurement point of the ultrasonic Doppler velocimeter corresponds one-to-one with a node of the three-dimensional temperature measurement network in spatial location. Each probe acquires raw shear data at a sampling frequency of 0.1 seconds, and simultaneously records the velocity vector and turbulence intensity parameters at each measurement point. The raw shear data, including the velocity vector and turbulence intensity parameters, is then sent to the data acquisition system.

[0049] 4. Perform dynamic calibration: Before each acquisition begins, inject standard temperature field fluid and standard shear fluid into the dispersion device.

[0050] Using a standard temperature field fluid, under known temperature distribution conditions, response data from a distributed fiber Bragg grating temperature sensor is collected. The collected temperature response is compared with the standard temperature value, and the calibration coefficients of the temperature sensor array are adjusted online based on the deviation to ensure the accuracy of the original temperature data.

[0051] Using a standard shear fluid under known shear field conditions, the velocity vector and turbulence intensity parameters of an ultrasonic Doppler velocimeter are collected. The collected raw shear data are compared with the standard shear field data, and the measurement sensitivity and zero-point offset of the ultrasonic Doppler velocimeter are corrected online based on the deviation to ensure the accuracy of the raw shear data.

[0052] The above methods enable the synchronous acquisition and dynamic calibration of raw temperature and raw shear data, providing a reliable data foundation for subsequent spatial interpolation and vector calculation.

[0053] S12: Spatial interpolation is performed on the raw temperature data to generate temperature field distribution data, and vector calculations are performed on the raw shear data to generate shear field distribution data. The vector calculations include vorticity calculation and shear rate calculation. The specific steps are as follows:

[0054] 1. Spatial interpolation processing of raw temperature data: Based on the actual placement of distributed fiber optic temperature sensors on the inner wall of the dispersion vessel and the surface of the stirring paddle, a set of spatial coordinates of temperature measuring points is constructed, and the corresponding raw temperature data is used as input samples for the Kriging interpolation algorithm.

[0055] A regular grid was constructed inside the dispersion vessel using the Kriging interpolation algorithm. The dispersion area was divided into grid cells with a spatial resolution of 1 cm × 1 cm. Temperature estimates were calculated at the center of each grid cell using the Kriging interpolation algorithm. The temperature estimates of all grid cells were combined to form gridded temperature field distribution data.

[0056] 2. Perform data verification steps for spatial interpolation: Compare the grid temperature values ​​in the interpolated temperature field distribution data with the measured original temperature data at the corresponding spatial locations, calculate the residual for each measured point, and construct the residual distribution based on the residuals of all measured points.

[0057] When the maximum residual in the residual distribution exceeds the preset allowable value, the interpolation parameters in the Kriging interpolation algorithm are automatically adjusted, including the semi-variogram model parameters and the relevant distance parameters. Spatial interpolation processing is then performed on the original temperature data again to regenerate the temperature field distribution data until the maximum residual of all measured points does not exceed the allowable value.

[0058] 3. Perform vector calculations on the original shear data to generate shear field distribution data: First, based on the velocity vectors recorded in the original shear data, construct a velocity vector field on a grid with the same spatial resolution of 1cm×1cm as the temperature field distribution data. Then, interpolate or project the original shear data to map the velocity vectors of each measurement point to the center of the corresponding grid cell.

[0059] Based on the constructed velocity vector field, vorticity calculation is performed. The velocity gradient information of each grid cell is used to calculate the local vorticity value of that grid cell, and the vorticity value is stored as part of the vector calculation result.

[0060] Based on the same velocity vector field, shear rate calculation is performed. By differentiating the changes of the velocity vector in different directions, the shear rate value of each grid cell is calculated, and the shear rate value is stored as another part of the vector calculation result.

[0061] The vector calculation output, which includes the vorticity calculation results and the shear rate calculation results, is organized into a grid with a spatial resolution of 1cm×1cm to generate shear field distribution data with the same spatial resolution, so that the shear field distribution data is consistent with the temperature field distribution data in terms of spatial resolution.

[0062] Through the above spatial interpolation and vector calculation, temperature field distribution data and shear field distribution data that meet the requirements of subsequent analysis are obtained.

[0063] S13: Spatiotemporally align and integrate the temperature field distribution data and shear field distribution data to form multi-dimensional field data. The specific steps are as follows:

[0064] 1. Add unified timestamps and spatial coordinate identifiers to the temperature field distribution data and shear field distribution data respectively:

[0065] The time information corresponding to the raw temperature data and raw shear data collected in S11 at a sampling frequency of 0.1 seconds will be inherited into the temperature field distribution data and shear field distribution data. When generating each frame of temperature field distribution data and shear field distribution data, a unified timestamp will be assigned to each frame of data.

[0066] Based on the geometry of the dispersion vessel, a unified three-dimensional spatial coordinate system is established. The spatial position of each grid cell in the temperature field distribution data and the spatial position of each grid cell in the shear field distribution data are represented by spatial coordinates, so that the two types of data have a unified reference system in space.

[0067] 2. By using a data fusion algorithm, temperature field distribution data and shear field distribution data are mapped to the same three-dimensional spatial coordinate system, forming multi-dimensional field data with spatiotemporal consistency:

[0068] In a unified three-dimensional spatial coordinate system, temperature field distribution data and shear field distribution data at the same spatial location are paired according to the spatial coordinate identifier of each grid cell to form composite data points containing temperature and shear information.

[0069] By arranging composite data points with different timestamps from multiple frames in chronological order, a multi-dimensional field data sequence with spatiotemporal consistency is formed, so that each data point simultaneously contains temperature field distribution data, shear field distribution data, and timestamp information.

[0070] 3. In the data fusion algorithm, a data quality assessment module is set up to assign confidence weights to each data point in the multi-dimensional field data based on the signal-to-noise ratio and integrity indices of the temperature field distribution data and the shear field distribution data.

[0071] By analyzing the signal-to-noise ratio of the raw temperature data and raw shear data, the signal-to-noise ratio index of each grid cell at the corresponding timestamp is calculated.

[0072] Based on whether there are missing sampling records during the data collection process, calculate the integrity index of each grid unit at the corresponding timestamp.

[0073] By combining signal-to-noise ratio (SNR) and data integrity metrics, a confidence weight is assigned to each data point in the multi-dimensional field data. Data points with high SNR and complete data are assigned higher confidence weights, while data points with low SNR or missing data are assigned lower confidence weights.

[0074] 4. Perform data compression on the formed multidimensional field data: Use a wavelet transform-based compression algorithm to decompose the multidimensional field data into multiple layers of wavelet coefficients, retaining the key wavelet coefficients that characterize the spatiotemporal variation features of the temperature field and shear field.

[0075] While retaining all key wavelet coefficients, redundant wavelet coefficients that contribute little to the overall spatiotemporal characteristics are removed, thus achieving lossless compression of multidimensional field data.

[0076] By comparing the data volume before and after compression, the data volume is reduced by more than 60%, while ensuring that the original spatiotemporal characteristics and confidence weight information of the multi-dimensional field data can be fully restored after decompression.

[0077] Through the above steps, S13 generates multi-dimensional field data with unified timestamps, unified spatial coordinate identifiers, confidence weights, and lossless compression, providing a complete data foundation for subsequent identification of mismatch regions between temperature and shear fields and the establishment of dynamic coupling relationship models.

[0078] S2: Based on multi-dimensional field data, identify the mismatch region between the temperature field and the shear field, and establish a dynamic coupling relationship model. The model then outputs field co-optimization parameters, specifically:

[0079] S21: Calculate the temperature field intensity gradient data and the shear field intensity gradient data based on multi-dimensional field data. The temperature field intensity gradient data is calculated using the central difference method, and the shear field intensity gradient data is calculated using the magnitude of the velocity gradient tensor. Both gradient data are calculated in the same spatial coordinate system. The specific steps are as follows:

[0080] 1. Read temperature field distribution data and shear field distribution data: Extract temperature field distribution data and shear field distribution data from the multi-dimensional field data formed by S13 according to the corresponding timestamp, ensuring that the input data is completely aligned in time and space.

[0081] 2. Calculate the temperature field intensity gradient data: In a unified three-dimensional spatial coordinate system, the temperature field distribution data is arranged in a grid. Using the central difference method, the temperature value of each grid cell is differentially calculated in the x, y, and z directions to calculate the three components of the temperature gradient.

[0082] The temperature field intensity gradient data is calculated by squaring and taking the square root of the gradient components in the three directions, so that the temperature field intensity gradient data strictly corresponds to each grid cell.

[0083] The temperature field gradient data are calculated as follows:

[0084] ;

[0085] in, This represents the corresponding grid cell in the temperature field intensity gradient data. gradient strength, Represents the grid cells in the temperature field distribution data Temperature value, , , These represent the grid spacing of the temperature field distribution data in the x, y, and z directions, respectively.

[0086] 3. Calculate shear field intensity gradient data: Based on the velocity vector and vorticity information contained in the shear field distribution data, construct the velocity gradient tensor of the velocity field. By calculating the magnitude of the velocity gradient tensor, obtain the shear field intensity gradient data of each grid cell.

[0087] The position of the shear field intensity gradient data is calibrated in a unified three-dimensional spatial coordinate system so that it has the same spatial position as the temperature field intensity gradient data.

[0088] The temperature field intensity gradient data and shear field intensity gradient data obtained through the above steps provide basic data for subsequent mismatch region identification.

[0089] S22: Based on the temperature field intensity gradient data and shear field intensity gradient data, the mismatch region is identified through field synergy angle analysis, and the characteristic parameters of the mismatch region are extracted. The specific steps are as follows:

[0090] 1. Perform field coordination angle analysis to identify mismatched regions: In a unified three-dimensional spatial coordinate system, calculate the cosine value of the angle between the temperature field intensity gradient data and the shear field intensity gradient data for each spatial point. When the cosine value of the angle is less than 0.7, the spatial point is determined to belong to the mismatched region.

[0091] Clustering of grid points identified as mismatched regions in a continuous space yields the overall spatial extent of the mismatched regions.

[0092] The cosine of the included angle is calculated as follows:

[0093] ;

[0094] in, Represents the corresponding spatial point The cosine value of the included angle, Indicates a point in space The gradient vector corresponding to the temperature field intensity gradient data at that location. Indicates a point in space The gradient vector corresponding to the shear field strength gradient data at that location. This represents the vector dot product of the two. and These represent the magnitudes of the two vectors, respectively.

[0095] 2. Extracting feature parameters of mismatched regions: For each identified mismatched region, extract the feature parameters of the mismatched region, including mismatched area, average mismatched intensity, spatial distribution pattern and temporal evolution characteristics.

[0096] Mismatch area: The actual area or volume of all grid cells within the mismatch area;

[0097] Average mismatch intensity: Calculates the average degree to which the cosine of the included angle of all spatial points within the mismatch region deviates from the standard cooperative state;

[0098] Spatial distribution pattern: Analyze the geometry of the mismatched region and extract parameters showing strip-like, block-like, or locally concentrated distribution patterns;

[0099] Temporal evolution characteristics: Based on the spatial location changes of the mismatched region obtained from multiple consecutive sampling periods, the moving speed of the mismatched region is calculated, and the expansion trend or contraction trend parameter is extracted based on the changing trend of the mismatched region area in consecutive sampling periods.

[0100] 3. Dynamic threshold adjustment: Field synergy angle analysis also includes dynamic threshold adjustment, including:

[0101] In the early stage of dispersion, a threshold value of 0.6 for the cosine of the included angle is used; in the middle stage of dispersion, a threshold value of 0.7 for the cosine of the included angle is used; and in the later stage of dispersion, a threshold value of 0.8 for the cosine of the included angle is used.

[0102] Reassess the mismatch regions based on the current dispersion stage to improve the dynamic adaptability of mismatch region identification.

[0103] The threshold of 0.7 is based on the field synergy theory, which states that the more aligned the gradient directions of the velocity field and the scalar field (temperature field) are, the stronger their synergistic effect. When the included angle... When the cosine value is 0° (cosine value = 1), mass transfer, shear coupling and energy utilization reach their optimal levels.

[0104] During the dispersion of water-based inks, the temperature field modulates the effective direction of the shear field by affecting the regional viscosity; when the gradient directions of the two deviate, the effective utilization of local shear energy will be directly reduced.

[0105] Theoretical analysis shows that when the cosine of the included angle is less than 0.7 (corresponding to...) At temperatures above 45°C, the direction of the temperature gradient is significantly inconsistent with the direction of the shear gradient. This leads to a mismatch between the direction of temperature-induced viscosity control and the direction of shear force action, a lack of coordination between momentum transfer and thermal action, and the formation of a "dynamic dead zone," resulting in insufficient dispersion of local particles and a decrease in actual energy utilization.

[0106] Simultaneous experiments using particle image velocimetry (PIV) and infrared thermal imaging confirmed the following:

[0107] When the cosine value is below 0.7, the particle trajectory deviates significantly from the mainstream shear flow, and the uniformity of particle distribution decreases significantly. Therefore, setting the threshold to 0.7 can accurately capture the key mismatch region that has a substantial adverse impact on the dispersion process, and is the critical criterion between field synergy effectiveness and dispersion failure.

[0108] The rationale for adjusting the dynamic threshold in stages is as follows: The dispersion process of water-based inks is a typical time-varying process, and its macroscopic flow field stability, shear transfer characteristics, and microscopic particle behavior all change significantly with each dispersion stage. Therefore, using a fixed threshold cannot adapt to the dynamic characteristics of a time-varying system.

[0109] To improve the accuracy of mismatch region identification and the stability of control strategies, this invention proposes a phased dynamic threshold adjustment to accurately adapt to different physical characteristics in the early, middle and late stages of dispersion.

[0110] The initial stage of dispersion is characterized by macroscopic fragmentation, rapid disintegration of large aggregates, intense turbulence and extremely unstable flow field, and both temperature and shear fields are in the process of rapid establishment.

[0111] If an excessively high threshold (such as 0.8) is used at this stage, a large number of instantaneous fluctuations will be misidentified as "pseudo-mismatch regions". If the control system over-responds, it will interfere with the main macroscopic crushing process, causing energy waste and unnecessary temperature fluctuations. Therefore, the threshold is relaxed to 0.6, focusing only on the most severe and persistent structured mismatch regions, thereby ensuring control stability.

[0112] The dispersion tends to stabilize in the middle stage, the particle refinement process enters a critical period, the shear chain structure is formed, and the dispersion uniformity has a significant impact on the overall quality.

[0113] Under relatively stable flow field conditions, it is necessary to more accurately identify the local "micro-mismatch regions" that affect the refinement efficiency. Using a threshold of 0.7 can effectively eliminate non-critical disturbances and accurately locate the regions that hinder further particle refinement.

[0114] In the later stages of dispersion, the goal is to achieve high uniformity and avoid re-agglomeration. At this stage, any slight field mismatch may induce secondary agglomeration of particles. Raising the threshold to 0.8 can provide fine compensation for small mismatches and prevent potential instability factors from emerging.

[0115] S23: Input the extracted feature parameters of the mismatch region into a pre-trained deep neural network to establish a dynamic coupling relationship model. The specific steps are as follows:

[0116] 1. Deep Neural Network Structure: The pre-trained deep neural network is a graph convolutional neural network with an attention mechanism. The number of nodes in its input layer is consistent with the dimension of the feature parameters of the mismatched region, and the number of nodes in its output layer is consistent with the dimension of the field co-optimization parameters.

[0117] The mapping relationship in a deep neural network is represented as follows: ;

[0118] in, This represents the set of input feature vectors composed of feature parameters of the mismatched regions. This represents the set of output vectors composed of field collaborative optimization parameters. This represents a pre-trained graph convolutional neural network with an attention mechanism. This represents the set of weight parameters for the convolutional neural network in the graph.

[0119] 2. Training process of deep neural networks: The training process of deep neural networks includes an online adaptive mechanism. After each dispersion process, the measured dispersion effect data is collected; the dispersion effect data is compared with the output of the deep neural network, and the weight parameters of the deep neural network are automatically adjusted according to the deviation between the two to update the model and adapt it to the dynamic characteristics of the next dispersion process.

[0120] 3. Establishment of dynamic coupling relationship model: Input the feature parameters of the mismatch region into the deep neural network, and calculate the output of the deep neural network using the forward propagation method to form a dynamic coupling relationship model, which is used for subsequent field co-optimization parameter calculation.

[0121] S24: Calculate and output the field co-optimization parameters through a dynamic coupling relationship model. The field co-optimization parameters include the compensation priority and optimal temperature compensation amount for each mismatch region. The specific steps are as follows:

[0122] 1. Calculation of compensation priority: The compensation priority is calculated based on the average mismatch intensity and spatial distribution pattern in the characteristic parameters of the mismatch region. The greater the average mismatch intensity, the higher the compensation priority. If the mismatch region has a centralized spatial distribution pattern, the priority is higher than that of a fragmented or dispersed distribution pattern.

[0123] 2. Calculation of the optimal temperature compensation amount: The optimal temperature compensation amount takes into account the following factors:

[0124] Current temperature field gradient data;

[0125] Historical compensation effect data;

[0126] Energy-saving constraints are introduced, and under the premise of ensuring field synergy, the temperature control scheme with lower energy consumption is given priority.

[0127] The energy-saving constraints are embedded into the optimization objective of the dynamic coupling relationship model using the Lagrange multiplier method, so that the optimization result simultaneously satisfies the synergistic effect and the energy consumption balance.

[0128] The optimization objective after introducing the Lagrange multiplier method is expressed as:

[0129] ;

[0130] in, This represents the Lagrangian objective function after introducing energy-saving constraints. This represents the vector of optimal temperature compensation for each mismatch region. This represents the field synergy evaluation function constructed based on the current temperature field intensity gradient data and historical compensation effect data. Indicates the amount of compensation at the optimal temperature. Energy consumption function of multi-channel temperature control system This indicates the upper limit of energy consumption corresponding to the energy-saving constraint. This represents the Lagrange multiplier used in the Lagrange multiplier method to balance the synergistic effect evaluation function and the energy-saving constraint.

[0131] 3. Output verification: Input the field co-optimization parameters into the simulation system for verification. The simulation system evaluates the expected performance of the field co-optimization parameters on the improvement of the temperature field and shear field.

[0132] When the verification results show that the expected improvement effect is not met, the calculation process of steps S21 to S24 is repeated to ensure that the final output field co-optimization parameters are optimal and reliable.

[0133] S3: Based on the field-coordinated optimization parameters, generate a regional temperature compensation strategy. The regional temperature compensation strategy includes differentiated temperature control schemes for mismatched regions, specifically:

[0134] S31: By analyzing the compensation priority and optimal temperature compensation amount in the field collaborative optimization parameters, an initial sub-regional temperature compensation strategy containing regional temperature setpoints and execution order is generated. The steps are as follows:

[0135] 1. Rule-based parsing method: Read the compensation priority and optimal temperature compensation amount from the field collaborative optimization parameters, call the rule-based parsing method, sort all mismatched regions according to compensation priority, convert the optimal temperature compensation amount into the initial temperature setpoint for each region, form the compensation temperature target corresponding to the region, combine the sorted region sequence with the temperature setpoint to generate the initial sub-regional temperature compensation strategy containing the execution order and temperature setpoint.

[0136] 2. Dynamic Correction of Expert Experience Rule Base: The rule engine has a pre-built expert experience rule base, which includes priority adjustment rules for different ink formulations and dispersion stages. It adjusts the execution order of regional compensation according to the viscosity characteristics of the ink system and dynamically adjusts the priority sorting according to the dispersion stage to enhance the adaptability of the strategy to process changes. It also performs slight offset correction on the compensation amount of low-priority but temperature-sensitive areas.

[0137] The above steps generate an initial regional temperature compensation strategy that meets the process characteristics.

[0138] S32: Based on the initial regional temperature compensation strategy, the temperature setpoint and execution timing are globally optimized through a multi-objective optimization algorithm to generate the optimized regional temperature compensation strategy.

[0139] 1. Optimization Algorithm: A non-dominated sorting genetic algorithm with an elitist strategy is adopted, with the three objective functions of maximizing the overall field synergy, minimizing the total system energy consumption, and minimizing the temperature overshoot as the optimization objectives.

[0140] During the optimization process, the algorithm performs non-dominated analysis on the performance of each candidate strategy on the three objectives mentioned above, forming a Pareto optimal solution set.

[0141] 2. Introduction of Process Stability Constraints: To ensure a smooth transition in the decentralized process, multi-objective optimization algorithms incorporate process stability constraints, including:

[0142] The temperature setpoint variation during adjacent control cycles does not exceed a preset threshold.

[0143] Ensure that the compensation action does not cause sudden changes or overshoot in local temperature.

[0144] Under the above constraints, the algorithm performs a global search on the initial temperature setpoint and execution timing, and finally outputs the optimized regional temperature compensation strategy.

[0145] S33: Perform equipment feasibility review, inter-regional temperature gradient verification, and dynamic resource allocation verification on the optimized regional temperature compensation strategy, and generate a feasible regional temperature compensation strategy through a conflict resolution mechanism.

[0146] 1. Feasibility verification: Feasibility verification includes:

[0147] Equipment temperature control range verification: Check whether the temperature setpoint of each area is within the equipment's allowable temperature control range;

[0148] Temperature gradient verification between regions: Calculate the temperature setpoint difference between adjacent regions and ensure that the difference does not exceed the material's tolerance threshold;

[0149] Dynamic resource allocation verification: When multiple areas request heating or cooling at the same time, assess whether the total power capacity of the system is sufficient. If it exceeds the capacity, dynamically allocate power according to compensation priority and adjust the actual temperature compensation amount that each area can provide.

[0150] The above steps ensure that the optimization strategy can be executed under actual equipment conditions.

[0151] 2. Conflict Resolution: When a conflict is detected in temperature setpoints or resource allocation, a priority-based negotiation mechanism is employed, including:

[0152] Always maintain the temperature setpoint for areas with higher compensation priority;

[0153] The temperature setpoints for low-priority areas are reduced proportionally or their execution is delayed.

[0154] Recalculate the resource allocation results to ensure that the final strategy satisfies all constraints.

[0155] After feasibility verification and conflict resolution, a feasible regional temperature compensation strategy was formed.

[0156] S34: Develop differentiated temperature control schemes that include specific control parameters and execution timing based on feasible regional temperature compensation strategies.

[0157] 1. Generate independent temperature control channel control commands: Convert the temperature setpoints in feasible zone temperature compensation strategies into specific control commands for each independent temperature control channel;

[0158] Each temperature control channel corresponds to a zone, and the command includes the target temperature, adjustment mode, and response time information.

[0159] 2. Generate time synchronization control sequence: Generate time synchronization control sequence based on execution timing, including: start and stop time of each temperature control channel, temperature change rate setting, and the sequence of staged compensation instructions.

[0160] Through the above steps, a complete differentiated temperature control scheme is finally formed, providing a precise command basis for the regional independent temperature control actions in S4.

[0161] S4: Based on a regional temperature compensation strategy, a multi-channel temperature control system is used to independently control the distributed equipment in different regions, achieving dynamic coordination between the temperature field and the shear field. Specifically:

[0162] S41: By analyzing the zoned temperature compensation strategy, it is transformed into an independent control command sequence executable by the multi-channel temperature control system. The steps are as follows:

[0163] 1. The instruction compilation module performs the following operations:

[0164] Extract temperature setpoints: Read the temperature setpoints for each region from the regional temperature compensation strategy and map them to the corresponding temperature control channels.

[0165] Analysis of control timing and rate of change parameters: The execution order, start and stop time and temperature change rate contained in the strategy are analyzed item by item to generate the execution time reference for each temperature control channel.

[0166] Generate independent control command sequences: Generate independent control command sequences in a structured format from the temperature setpoint, heating rate, cooling rate, and holding time parameters, so that each temperature control channel has complete target temperature value, heating / cooling rate, and holding time parameters.

[0167] 2. Feedforward Compensation Optimization Function: The instruction compilation module also includes an instruction optimization function, used to perform feedforward compensation optimization based on the actual response characteristics of the actuators in the multi-channel temperature control system, including:

[0168] Collect the inertia, delay, and response curve parameters of each temperature control channel actuator;

[0169] The control command sequence is feedforwarded based on the actuator inertia to ensure that the actual behavior of temperature changes is consistent with the control commands.

[0170] By optimizing the algorithm to adjust the timing of heating or cooling power release, control lag caused by actuator inertia is eliminated, thereby improving temperature control accuracy.

[0171] After being processed by the instruction compilation module, a complete sequence of control instructions is formed that can be directly used for actual execution.

[0172] S42: Synchronously send the control command sequence generated in S41 to the multi-channel temperature control system, enabling each execution unit to execute the regional independent control process in parallel. The steps are as follows:

[0173] 1. Issuance of control command sequence: The control command sequence is synchronously issued to each execution unit of the multi-channel temperature control system via the industrial Ethernet bus. The industrial Ethernet bus adopts the EtherCAT protocol to ensure that the issuance process has millisecond-level real-time performance and high synchronization accuracy. The control system confirms the transmission status of each command to ensure that all execution units receive the control command sequence synchronously.

[0174] 2. Parallel execution of each execution unit: Each execution unit independently executes heating, cooling or holding actions according to the corresponding control command sequence. All execution units operate in parallel to ensure the synchronization and accuracy of temperature regulation in different zones. Each execution unit reports status feedback data in real time during execution, including actual temperature, current power and execution progress.

[0175] 3. Acquisition of status feedback data: Status feedback data from all execution units are uploaded to the control system via the same EtherCAT bus, enabling real-time monitoring of the entire independent control process in different areas.

[0176] S43: By monitoring the changes in the temperature field and shear field in real time, the dynamic synergistic effect of the temperature field and shear field is verified, and the dynamic adjustment of the control command sequence is executed based on the verification results.

[0177] 1. Real-time monitoring of temperature and shear fields: Temperature monitoring is achieved through an array of temperature sensors deployed in the distributed equipment to continuously collect temperature field change data. Shear field monitoring is achieved through an ultrasonic Doppler velocimeter to record real-time changes in velocity vector and turbulence intensity.

[0178] The collected temperature and shear field change data are mapped to a unified three-dimensional spatial coordinate system to form real-time multi-dimensional field change data.

[0179] 2. Calculate the current field synergy degree and verify the dynamic synergy effect: Calculate the current field synergy degree based on the real-time temperature field intensity gradient data and shear field intensity gradient data, compare the current field synergy degree with the target field synergy degree to obtain the field synergy degree deviation, and start the dynamic adjustment process when the deviation exceeds the allowable range.

[0180] 3. Dynamic adjustment mechanism based on fuzzy PID: The dynamic adjustment of the control command sequence adopts the fuzzy PID control algorithm. The control correction amount is calculated based on the field coordination degree deviation and its rate of change. The target temperature value and change rate parameter in the control command sequence are corrected in real time. The corrected command sequence is updated to the corresponding execution unit in an instant, so that the control behavior forms a closed-loop adjustment structure.

[0181] 4. Anomaly detection function: When abnormal fluctuations (such as sudden changes, instability, or abnormal oscillations) are detected in any area of ​​the temperature field or shear field, the safety protection mechanism is immediately triggered. The safety protection mechanism includes suspending the independent control process of each area, switching all channels to safety mode, and issuing an alarm to the control system. The control system records the abnormal data to provide a basis for subsequent diagnosis.

[0182] This invention encompasses any substitutions, modifications, equivalent methods, and solutions made within the spirit and scope of this invention. To provide the public with a thorough understanding of this invention, specific details are described in detail in the following preferred embodiments; however, those skilled in the art will fully understand the invention even without these details. Furthermore, to avoid unnecessary misunderstanding of the essence of this invention, well-known methods, processes, procedures, components, and circuits are not described in detail.

[0183] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for synergistic optimization of dynamic temperature field in the dispersion process of water-based inks, characterized in that, Includes the following steps: Simultaneously collect multi-dimensional field data during the dispersion process of water-based inks, including temperature field distribution data and shear field distribution data; Based on the multi-dimensional field data, the mismatch region between the temperature field and the shear field is identified, and a dynamic coupling relationship model is established. The field collaborative optimization parameters are output through the dynamic coupling relationship model. Based on the field-coordinated optimization parameters, a regional temperature compensation strategy is generated, which includes a differentiated temperature control scheme for the mismatched region. Based on the aforementioned regional temperature compensation strategy, a multi-channel temperature control system is used to independently control the dispersed equipment in different regions, thereby achieving dynamic coordination between the temperature field and the shear field.

2. The dynamic temperature field co-optimization method for the dispersion process of water-based inks according to claim 1, characterized in that, The synchronous acquisition of multi-dimensional field data during the dispersion process of water-based inks includes: Raw temperature data is collected by an array of temperature sensors deployed within the distributed equipment, and raw shear data is collected by an ultrasonic Doppler velocimeter. Spatial interpolation is performed on the original temperature data to generate temperature field distribution data, and vector calculation is performed on the original shear data to generate shear field distribution data. The temperature field distribution data and the shear field distribution data are spatiotemporally aligned and integrated to form the multidimensional field data.

3. The dynamic temperature field synergistic optimization method for the dispersion process of water-based inks according to claim 2, characterized in that, The temperature sensor array uses a distributed fiber optic temperature sensor to synchronously acquire the raw temperature data at a sampling frequency of 0.1 seconds; the ultrasonic Doppler velocimeter acquires the raw shear data at the same sampling frequency and simultaneously records the velocity vector and turbulence intensity parameters at each measurement point.

4. The dynamic temperature field co-optimization method for the dispersion process of water-based inks according to claim 2, characterized in that, The spatiotemporal alignment and integration includes: adding unified timestamps and spatial coordinate identifiers to the temperature field distribution data and the shear field distribution data respectively, and mapping the two to the same three-dimensional spatial coordinate system through a data fusion algorithm to form multi-dimensional field data with spatiotemporal consistency.

5. The dynamic temperature field co-optimization method for the dispersion process of water-based inks according to claim 2, characterized in that, The process involves identifying the mismatch region between the temperature field and the shear field, establishing a dynamic coupling relationship model, and outputting field co-optimization parameters through this model, including: Based on the multi-dimensional field data, temperature field intensity gradient data and shear field intensity gradient data are calculated respectively. Based on the temperature field intensity gradient data and the shear field intensity gradient data, mismatch regions are identified through field synergy angle analysis, and characteristic parameters of the mismatch regions are extracted. The feature parameters of the mismatched region are input into a pre-trained deep neural network to establish a dynamic coupling relationship model; The field collaborative optimization parameters are calculated and output through the dynamic coupling relationship model. The field collaborative optimization parameters include the compensation priority and the optimal temperature compensation amount for each mismatch region.

6. The dynamic temperature field co-optimization method for the dispersion process of water-based inks according to claim 5, characterized in that, The field coordination angle analysis specifically involves: calculating the cosine value of the angle between the temperature field intensity gradient data and the shear field intensity gradient data at each spatial point; when the cosine value is less than 0.7, the spatial point is determined to belong to the mismatch region, and the characteristic parameters of the mismatch region are extracted, including the mismatch area, average mismatch intensity, and spatial distribution pattern.

7. The dynamic temperature field co-optimization method for the dispersion process of water-based inks according to claim 5, characterized in that, The regional temperature compensation strategy includes: The compensation priority and optimal temperature compensation amount in the field collaborative optimization parameters are analyzed to generate an initial regional temperature compensation strategy. The initial regional temperature compensation strategy is globally optimized based on a multi-objective optimization algorithm to generate an optimized regional temperature compensation strategy. The optimized regional temperature compensation strategy is subjected to feasibility verification and conflict resolution to generate a feasible regional temperature compensation strategy. Based on the feasible regional temperature compensation strategy, a differentiated temperature control scheme including specific control parameters and execution timing is formulated.

8. The dynamic temperature field co-optimization method for the dispersion process of water-based inks according to claim 7, characterized in that, The specific steps for parsing the compensation priority and optimal temperature compensation amount in the field collaborative optimization parameters are as follows: using a rule engine-based parsing method, sorting each mismatched region according to the compensation priority, and converting the optimal temperature compensation amount into the initial temperature setting value of each region, thereby generating an initial sub-regional temperature compensation strategy that includes the temperature setting value of each region and the execution order.

9. The dynamic temperature field co-optimization method for the dispersion process of water-based inks according to claim 7, characterized in that, The dynamic coordination of the temperature field and the shear field includes: The regional temperature compensation strategy is analyzed and converted into an independent control command sequence for each channel of the multi-channel temperature control system. The control command sequence is sent to each execution unit of the multi-channel temperature control system to initiate the regional independent control process; The temperature and shear field changes during the execution of independent regional control are monitored in real time to verify the dynamic synergistic effect of the temperature and shear fields, and the control command sequence is dynamically adjusted based on the verification results.

10. The dynamic temperature field co-optimization method for the dispersion process of water-based inks according to claim 9, characterized in that, The analytical regional temperature compensation strategy is implemented through an instruction compilation module. The instruction compilation module converts the temperature setpoint, control timing, and change rate parameters in the regional temperature compensation strategy into independent control instruction sequences for each channel of the multi-channel temperature control system. The control instruction sequence includes the target temperature value, heating / cooling rate, and holding time parameters for each channel.

Images