A microcapsule image intelligent control system and method for printing

Abstract

The present invention relates to the technical field of industrial control systems, specifically a microcapsule image intelligent control system and method for printing, comprising an input module that receives input data, intelligently calculates control parameters, and generates execution commands and control signals; an execution module that receives the execution commands and input data, combines them with real-time status information, and outputs a printed material and related execution data; an intelligent control module that receives the printed material, control parameters, and execution commands, monitors color development characteristics in real time, dynamically optimizes and adjusts control parameters for different regions using an adaptive control algorithm, and ultimately outputs the color-developed printed material and detailed execution data; and an optimization module that aggregates the full-process execution data and quality indicators of each module for evaluation, obtains optimization commands, and deploys and updates the modules in the system based on the optimization commands. The present invention discloses a corresponding method that achieves adaptive and precise control through intelligent linkage of multiple modules.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial control systems, and in particular to an intelligent control system and method for microcapsule images used in printing. Background Art

[0002] In industrial manufacturing, advanced imaging materials, such as printing microcapsules, require subsequent, precisely programmed stimulation to reveal their final color and predetermined functionality. The formation of these materials' key properties relies heavily on precise program control of this stimulation process.

[0003] The automation of these production processes is typically managed by industrial control systems. Existing industrial control systems often rely on pre-set, fixed programs and parameter sets to perform excitation tasks, and generally lack the ability to dynamically perceive the real-time state of the material and the dynamic changes in the processing environment, as well as adaptive adjustment mechanisms. When faced with inherent differences between material batches, subtle fluctuations in environmental conditions, and the refined and spatially differentiated excitation requirements of complex images, these fixed-program control systems struggle to achieve high-precision, highly flexible, real-time optimized program control. Therefore, ensuring the final imaging and functional characteristics and achieving precise control have become a key technical bottleneck in the industrial production of these advanced materials.

[0004] Therefore, an intelligent control system and method for microcapsule images for printing are proposed. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent control system and method for microcapsule images for printing, which realizes adaptive and precise control through multi-module intelligent linkage.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A microcapsule image intelligent control system for printing, comprising:

[0008] Input module: Receives input digital image files as basic program settings, integrates the inherent characteristic parameters of the selected material and historical operation data, intelligently calculates relevant control parameters, and generates execution commands and control signals;

[0009] Execution module: Receives execution commands and image setting data, combines real-time status information monitored by online sensors, dynamically adjusts key process operating parameters, and outputs substrates and related execution data for controlling microcapsule deposition according to instructions;

[0010] Intelligent control module: Receives the substrate after deposition processing, target characteristic parameters and execution commands, monitors the output color characteristics in real time according to the program through the online monitoring system, determines the deviation between the real-time monitored color characteristics and the target requirements defined by the target characteristic parameters through the adaptive control algorithm, dynamically optimizes and adjusts the relevant control parameters of the divisible areas, and finally outputs the substrate that meets the set requirements and detailed execution data;

[0011] Optimization module: collects the full-process execution data and performance indicators of each module for evaluation, obtains optimization commands, and deploys and updates modules in the system according to the optimization commands.

[0012] Preferably, the control parameters related to the intelligent calculation are control parameters, and the specific acquisition process is:

[0013] The basic program settings, the inherent color gamut capability data of the selected materials, and the historical production data are processed by the gradient boosting decision tree model to generate preliminary control parameters. The preliminary control parameters are used as the initial solution and judged based on the color quality optimization goal and the process feasibility constraints. If no further optimization is required, the preliminary control parameters are used as the final control parameters after verification and correction. If further optimization is required, the adaptive perturbation exploration optimization algorithm is used for iterative refinement to output the final control parameters.

[0014] Preferably, the adaptive perturbation exploration optimization algorithm includes intelligently selecting parameters to be adjusted and perturbation directions based on a heuristic rule set; dynamically and adaptively setting the perturbation amplitude of control parameters, iteratively generating candidate parameter combinations, and updating the optimal parameter set after verification and evaluation until the termination condition is met.

[0015] Preferably, the dynamic adjustment of key process operating parameters includes: continuously acquiring and analyzing feedback data reflecting the current real-time application state of the microcapsule material from an online sensor; instantly comparing the acquired real-time application state feedback data with the desired deposition target state received from the control instruction, and determining the deviation between the actual application state and the desired deposition target state;

[0016] Based on the deviation, the required adjustment amount of the key deposition parameter is calculated in real time, and the adjustment amount is automatically applied to the corresponding key deposition parameter to continuously reduce the deviation so that the actual application state of the microcapsule material dynamically approaches and is maintained at the desired deposition target state.

[0017] Preferably, the real-time calculation of the adjustment amount required for the key deposition parameters includes:

[0018] Analyzing historical adjustment instruction data for the key deposition parameters and corresponding real-time material application state feedback data provided by online sensors, and continuously estimating and updating key dynamic characteristic parameters of the microcapsule deposition process online using a recursive estimation algorithm;

[0019] Based on key dynamic characteristic parameters and according to preset PID parameter tuning rules, the proportional, integral and differential gain parameters of the PID control algorithm are automatically and periodically calculated and set.

[0020] Preferably, the color rendering characteristics of the output are monitored in real time according to a program by an online monitoring system, and the color rendering characteristics are specifically color rendering characteristics including:

[0021] During the color development process, the image data of each separable area on the substrate is captured in real time and processed to locate the target area and calculate the quantitative color parameters and color uniformity from it, which are used as real-time monitoring output of the color development characteristics to feed back to the adaptive control algorithm.

[0022] Preferably, the adaptive control algorithm is used to dynamically optimize and adjust relevant control parameters of the separable areas, and the relevant control parameters are excitation parameters. The specific processing flow is: for each separable area, the adaptive control algorithm calculates and generates a set of corrected excitation unit parameters aimed at minimizing the deviation quantification result and making the color rendering characteristics approach the target based on the deviation quantification result between the current color rendering characteristics of the separable area monitored in real time by machine vision and the preset target color rendering characteristics, combined with the dynamic process response model, and then applies the corrected excitation unit parameters to the excitation unit of the corresponding separable area to adjust its working state in real time.

[0023] Preferably, the collection of full-process execution data and quality indicators of each module for evaluation includes:

[0024] The deployment decision model is used to process execution data and quality indicators, output risk assessment indicators and deployment gains, and the decision model is used to combine historical deployment cases to process risk assessment indicators and deployment gains to obtain optimization commands.

[0025] A method for intelligently controlling microcapsule images for printing, comprising:

[0026] Receive the input digital image file as the basic program setting, integrate the inherent characteristic parameters of the selected material and historical operation data, intelligently calculate the relevant control parameters, and generate execution commands and control signals; receive execution commands and image setting data, combine with the real-time status information monitored by online sensors, dynamically adjust key process operation parameters, and output the substrate and related execution data for microcapsule deposition controlled by instructions; receive the substrate after deposition treatment, target characteristic parameters and execution commands, monitor the output color characteristics in real time according to the program through the online monitoring system, determine the deviation between the real-time monitored color characteristics and the target requirements defined by the target characteristic parameters through the adaptive control algorithm, dynamically optimize and adjust the relevant control parameters of the divisible areas, and finally output the substrate that meets the set requirements and detailed execution data; collect the full-process execution data and performance indicators of each module for evaluation, obtain optimization commands, and deploy and update the modules in the system according to the optimization commands.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] 1. By integrating digital images, the inherent color gamut capabilities of the material, and historical production data, intelligent algorithms are used to calculate and optimize initial color rendering parameters, providing a highly optimized and task-specific initial set point for the entire precision control process. This ensures that subsequent physical execution and color development processes are guided by ideal parameters, significantly reducing initial errors and laying a high-quality, preset foundation for achieving ultimate precision imaging and functional characteristics. This is the key to achieving forward-looking, precise control.

[0029] 2. The actual state of the microcapsule deposition process is monitored in real time by online sensors. Key process operation parameters are dynamically adjusted in combination with intelligent control algorithms such as parameter self-tuning PID, thus achieving real-time, closed-loop precise control of the microcapsule physical deposition process and ensuring that the actual deposition results of the microcapsules are consistent with the requirements in the execution command.

[0030] 3. Utilizing machine vision, the color development characteristics of the substrate after deposition are monitored in real time and quantitatively online. Adaptive control algorithms dynamically adjust the excitation parameters for each region, enabling refined, closed-loop adaptive, and precise control of microcapsule color development activation, a critical functional development stage. This ensures that the final color development is precisely guided to the target characteristics, even in the presence of accumulated deviations from previous processes and uncertainties in material response.

[0031] 4. By collecting and deeply analyzing the execution data and final quality indicators of the entire system process, and utilizing online learning mechanisms to generate optimization commands to update the control models and strategy parameters of each module, we establish system-level continuous learning and self-optimization capabilities, thereby ensuring and continuously improving the long-term precise control performance and adaptability of the entire system to changes. This overcomes the problem of reduced precise control capabilities in traditional systems caused by aging models and suboptimal parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of the structure of an intelligent microcapsule image control system for printing provided by an embodiment of the present invention;

[0033] Figure 2 A schematic diagram of the input module flow provided by an embodiment of the present invention;

[0034] Figure 3 A schematic flow chart of a method for intelligently controlling microcapsule images for printing provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0035] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0036] See also Figures 1 to 3 The present invention provides a microcapsule image intelligent control system and method for printing, and the technical solution is as follows:

[0037] Example 1: In order to achieve intelligent and precise control of microcapsule images, Company A introduced a printing microcapsule image intelligent control system provided by the present invention. The system structure diagram is as follows Figure 1 The specific process is as follows:

[0038] Input module: Receives input digital image files as basic program settings, integrates the inherent characteristic parameters of the selected material and historical operation data, intelligently calculates related control parameters, and generates execution commands and control signals. The flow chart of the input module is as follows Figure 2 shown.

[0039] The operator inputs the digital image file to be printed into the system through an interactive interface. The input module receives the input digital image file and parses its content (pixel data, dimensions, color profile, etc.) into basic program settings that define the content and basic requirements of subsequent printing operations. These basic program settings encapsulate all the necessary information to accurately define and guide the core process steps of subsequent microcapsule image printing. In this embodiment, these basic program settings specifically consist of pixel-level color data, spatial dimensions and resolution parameters, color space definition information, and additional structure and metadata information. These additional structure and metadata information include alpha channel data used to define the transparency of each part of the image, layer structure information present in specific file formats (such as layered TIFF or PSD files), and descriptive metadata such as image title or identifier, creation date, author information, copyright notice, etc., which facilitate task identification, content verification, and production traceability.

[0040] Furthermore, based on the microcapsule material and substrate type selected by the operator through the interactive interface when initiating a print job, the input module retrieves the intrinsic color gamut capability data corresponding to this specific combination from the system's built-in, calibrated material database. It then acquires historical production data, identifies and addresses potential missing items, anomalous data points due to various reasons, and common noise interference in sensor data. It then normalizes various numerical features and effectively digitizes categorical information. Variance analysis is used to eliminate features with minimal variation. Based on this, the input module proceeds to the data fusion step. This step combines the previously acquired and processed key features of the current digital image, the quantitative intrinsic color gamut data of the selected material, and pre-processed valid historical production experience data into a unified, multi-dimensional high-dimensional feature vector according to a predetermined structure using feature vector concatenation. This constructed high-dimensional feature vector serves as direct, standardized input to the subsequent gradient boosting decision tree algorithm.

[0041] Furthermore, after the data fusion step is completed, the input module directly submits this high-dimensional feature vector, which integrates the current image analysis features, the inherent color gamut capability data of the selected material, and preprocessed historical production data, as input to a pre-trained gradient boosted decision tree (GBDT) model. Upon receiving the high-dimensional feature vector, the GBDT model performs a predictive processing operation. The core of this predictive processing lies in the model's application of complex decision-making logic learned and solidified from a large amount of historical production data during the training phase. The input high-dimensional feature vector is then routed through the numerous decision trees integrated within the model, selecting and transmitting paths layer by layer based on the learned feature judgment rules at each tree node. The analysis results of each tree are integrated through an integration mechanism to jointly infer the output parameters that best match the current input features. Finally, the GBDT model generates a set of structured preliminary control parameters, specifically color development parameters. This parameter set specifies the initial microcapsule material deposition quantification settings and preliminary color development process excitation conditions for each pre-defined analysis area of the current input digital image, serving as the starting input for the subsequent optimization and refinement process.

[0042] After obtaining the preliminary control parameters, the input module initiates the optimization and refinement process. This process uses these preliminary parameters as the initial solution and, in strict accordance with the color quality optimization goals and various process feasibility constraints set for the specific printing task at hand, first conducts a rigorous process feasibility check on this preliminary parameter set. If any parameter value is detected to violate a key pre-set hard constraint, such as the upper and lower limits of material usage or the safe range of color excitation energy, the algorithm prioritizes initiating an efficient constraint correction procedure. This procedure utilizes a targeted, minimally impacting parameter adjustment strategy to directly correct out-of-bounds parameter values to the nearest permissible bound, thereby rapidly correcting the entire parameter set to be completely within the process feasibility domain, ensuring a valid and executable foundation for subsequent optimization iterations.

[0043] Furthermore, for the preliminary parameter set that ensures compliance with hard constraints, the system performs a lightweight performance estimation and pattern comparison, invoking a simplified color difference prediction function module based on core color science theory. The core of this module is a pre-defined, non-iterative color space forward conversion model; specifically, the microcapsule channel deposition and corresponding preliminary excitation energy values within the current parameter set are mapped to the CIELAB color space. To achieve high computational speed, this conversion model utilizes a small three-dimensional lookup table. Subsequently, the module utilizes a fast evaluation algorithm optimized for standard color difference calculation formulas to compare the estimated color values output by the color space forward conversion model with the target color values represented by the average color features of several key regions extracted from the input digital image file. Through this precise and efficient computational process, the function module ultimately calculates and outputs a quantitative indicator of the expected color difference for the key image regions. The overall algorithm logic of this prediction function module and all required conversion parameters are fixed in the system.

[0044] Furthermore, the system compares the values of the key parameters of the current preliminary parameter set with a pre-established and maintained historical robust parameter pattern library for consistency. This pattern library is constructed through in-depth offline statistical analysis of a large amount of accumulated historical successful production case data. This pattern library specifically and clearly defines the dynamic matching of preset conditions such as material type, substrate characteristics and classification features extracted from image content under similar printing conditions, and is capable of continuously and stably producing high-quality printed output. The effective value range of control parameters, their statistical central trends and common parameter combination patterns. The comparison process is achieved by calculating the statistical distance metric between the current preliminary parameter set and these historical robust patterns. This metric can be specifically used to determine whether the current parameter values fall within the high-frequency confidence interval corresponding to the historical data, in order to evaluate the regularity of the current parameter set and potential process stability risks.

[0045] The system will comprehensively output the expected color difference quantitative indicators and conformity and distance measurement results of each key image area, and execute the final optimization trigger decision. If the expected color difference quantitative indicators of all key image areas have met the core color accuracy indicator requirements set by the task, and the overall pattern of the current preliminary parameter set shows a high degree of conformity with the corresponding pattern in the historical robust parameter pattern library, the system will comprehensively determine that the preliminary parameter set no longer needs further iterative optimization. In this particular case, the preliminary parameter set will be directly adopted as the final control parameter and prepared to be output to the subsequent related processing modules. On the contrary, if the expected color difference indicators fail to fully meet the standards or the current parameter pattern significantly deviates from the robust area indicated by historical experience or these two unfavorable situations exist at the same time, the system will determine that the current initial control parameters have the necessity and feasible space to further optimize to improve the final printing quality, and it is necessary to reduce the potential production risks. It will trigger and start the adaptive perturbation exploration optimization algorithm for optimization.

[0046] Built-in, prioritized hard constraint checking and real-time correction ensure that all preliminary parameters meet basic process feasibility. A lightweight performance estimation module then compares and analyzes historical robust parameter patterns to quickly and intelligently assess parameter quality. This enables the system to identify and directly adopt sufficiently good parameters, avoiding unnecessary, deep, iterative optimization of all parameters. This significantly reduces average processing time and quickly provides high-quality initial working set points for subsequent modules.

[0047] Furthermore, initiating the adaptive perturbation exploration optimization algorithm involves intelligently selecting a set of control parameters from the current parameter set that have the most significant impact on overall print quality, based on a pre-defined heuristic rule set based on the microcapsule printing process and the deviation characteristics between the color rendering effect predicted by the current parameter set and the color rendering quality optimization target. These control parameters are then used as the adjustment targets for this iteration. Simultaneously, the heuristic rule set provides perturbation directions with clear improvement intent for adjusting these selected parameters. When the algorithm evaluates and finds a specific deviation between the color rendering effect predicted by the current preliminary parameters and the target, the algorithm invokes the rule set to guide parameter adjustment.

[0048] Table 1 Example of APEO algorithm heuristic rule set fragment

[0049]

[0050] Table 1 shows a sample snippet of the APEO algorithm's heuristic rule set. These rules, based on process laws and color science principles, guide the algorithm in intelligently selecting adjustment parameters and their direction based on current deviations when optimizing control parameters. For example, if the estimated color brightness is significantly lower than the target value, the rules will direct the algorithm to prioritize and attempt to increase those control parameters (such as a key excitation energy or the dosage of a specific microcapsule) that have the most direct positive impact on overall brightness. Similarly, for specific hue or saturation deviations, the rule set will guide the algorithm to adjust the most relevant color channel parameters, specifying the direction of adjustment (increase or decrease) to most effectively correct the deviation. Furthermore, the rules will also consider the distance between the current parameter value and the process constraint boundary to influence the priority and direction of adjustment, ensuring the safety of the adjustment.

[0051] Furthermore, for the selected parameters and their determined perturbation directions, the algorithm uses a dynamic adaptive mechanism to set the specific value of the parameter to be adjusted in this iteration, that is, the perturbation amplitude. This dynamic adaptive mechanism will first evaluate the current stage of the overall optimization: if it is judged that it is in the early stage of optimization or the current solution is still significantly different from the preset quality target, it tends to set a relatively large baseline perturbation amplitude to encourage broader exploration in the parameter space. At the same time, the mechanism will closely track and analyze the actual feedback of recent iterations: if continuous perturbations can bring about more significant quality improvements, the perturbation amplitude may be maintained or moderately increased to accelerate the optimization; on the contrary, if the improvement effect is not obvious or stagnates, it will clearly indicate to significantly reduce the perturbation amplitude, guiding the algorithm to switch to a more refined local search and fine-tuning mode. In addition, for each parameter selected for perturbation, the mechanism will strictly consider the distance between its current value and the upper and lower limits defined by its process feasibility constraints. When the parameter value is very close to any constraint boundary, the rules will forcibly significantly reduce the perturbation amplitude that may point to or exceed that boundary. In extreme cases, it will even be set to zero to ensure that all perturbation attempts are prioritized to remain within the feasible region or its immediate edge. Through this set of adaptive rules that integrate the optimization stage, recent results, and constraint boundary considerations, the algorithm determines a precise and dynamically changing perturbation amplitude for each selected parameter in the established perturbation direction.

[0052] Based on the specific perturbation amplitude adaptively determined for each selected parameter and its perturbation direction, the algorithm applies these calculated adjustments with clear directions and adaptive amplitudes to the corresponding selected parameters based on the currently recorded optimal parameter set, while other unselected parameters remain unchanged. Through this operation, the algorithm generates new candidate parameter combinations. Each newly generated candidate parameter combination must immediately pass the verification of all preset process feasibility constraints. Any candidate solution that fails to fully meet all hard constraints will be judged as infeasible and directly discarded without entering the subsequent quality assessment step.

[0053] Furthermore, for all valid candidate solutions that pass the constraint check, the system will optimize the objective function based on the preset color rendering quality. The core is to calculate the standard color difference (ΔE value) between the estimated color and the target color, and comprehensively consider other key visual characteristics such as color uniformity and saturation to output a comprehensive performance evaluation value to guide the iterative selection of the optimization algorithm. The algorithm compares the performance evaluation values of all valid candidate solutions with the evaluation value of the currently recorded global optimal solution. If there is a valid candidate solution with better performance, the algorithm adopts the candidate solution that leads to the most significant improvement in the quality objective function value to update and replace the currently recorded global optimal parameter set. If all tentative perturbations in this round of iteration fail to produce a valid new solution that is better than the current optimal solution, the current optimal parameter set remains unchanged in this round. This iterative process including the above steps will continue until a clear algorithm termination condition is met. These termination conditions are specifically defined as follows: the algorithm has reached the maximum number of allowed iterations set for the current printing task; in several consecutive iterations, the quality objective function value of the optimal solution has failed to produce a meaningful improvement greater than the preset threshold, indicating that the optimization process may have converged; the cumulative execution time of the entire APEO optimization process has reached the specific time budget allocated for this step.

[0054] When the APEO algorithm ends its optimization process due to any termination condition, its final output is a set of final control parameters that have been fully refined through this adaptive perturbation exploration optimization process and have maximized the achievement of the preset color quality target while satisfying all process constraints.

[0055] Based on the final control parameters determined, combined with the image geometry information, necessary area division data, and relevant image content features obtained from the basic program settings for the printing task, this multi-source information is compiled, calculated, and integrated. Through this process, the module constructs a structured, machine-readable execution command. To ensure the coordinated operation of various parts of the system, the input module is also responsible for generating and distributing control signals. The main function of these signals is to activate subsequent execution modules and intelligent control modules according to preset logic, notifying them that the relevant execution commands and necessary image data are prepared and available for use, and guiding them to initiate the precise deposition process of microcapsules and subsequent color development control and monitoring tasks according to the established operation process.

[0056] By deeply embedding heuristic rules based on printing process laws and color science principles, it achieves intelligent guidance on the direction and objects of parameter adjustment, and combines dynamic adaptive mechanisms to accurately control the amplitude of disturbances. This design enables efficient and targeted optimization searches in complex parameter spaces, ensuring that the final control parameters output not only strictly meet all process feasibility constraints, but also achieve significant improvements in multiple key visual quality dimensions such as color difference, color uniformity, and saturation. Importantly, the algorithm's core optimization logic does not rely on additional online machine learning model training, but is based on preset intelligent rules and adaptive adjustments. Therefore, APEO can provide a significantly optimized, high-quality initial working set point for the subsequent real-time closed-loop control module within a reasonable computing time, which is crucial for improving the response speed, stability, and consistency and quality of the entire system and the final product.

[0057] Execution module: Receives execution commands and image setting data, combines real-time status information monitored by online sensors, dynamically adjusts key process operating parameters, and outputs substrates and related execution data for controlling microcapsule deposition according to instructions.

[0058] The execution module receives the instruction portion of the previously generated execution command directly related to the microcapsule deposition operation, and also receives the necessary, processed image data. The execution command specifies in detail the target deposition amount, spatial positioning coordinates, and deposition order of each color microcapsule for each image area in the current printing task. The image data provides a positional reference for the visual content of the deposition process. The execution module integrates and controls a group of piezoelectric nozzle arrays that can spray micro-capsule materials on demand, with a specific nozzle group responsible for microcapsules of a specific color. At the same time, the execution module also controls the precision conveying and positioning subsystem of the printing material to ensure that the relative position between the printing material and the deposition unit is precisely controllable. After receiving the execution program, the execution module first drives the deposition unit according to the initial instructions in the program to begin depositing the calculated target amount of microcapsule material on the specified micro-area of the printing material.

[0059] Furthermore, to achieve dynamic closed-loop control of the deposition process, the execution module incorporates online sensors. These sensors continuously monitor the real-time application status of the microcapsule material onto the substrate. These sensors include high-speed, high-resolution visual sensors installed near the deposition unit, which capture, in real time, the geometry, positional accuracy, and coverage density or uniformity within specific microregions of the newly deposited microcapsule array. These sensors then directly output preliminarily processed or calibrated quantitative physical data representing key deposition states to the execution module. Upon receiving these quantitative data streams from various sensors, the execution module primarily performs a numerical scaling process. This process aims to eliminate numerical scaling discrepancies caused by varying physical dimensions in the sensor data, ensuring that all state information has consistent and comparable magnitudes before entering the subsequent control algorithm. After this scaling process, the various state parameters are then integrated and dynamically updated into a structured data record, which constitutes the real-time state information, accurately and consistently representing the actual microcapsule deposition status, for direct use by the subsequent closed-loop control algorithm.

[0060] Furthermore, the acquired, structured real-time status information (which includes quantitative feedback data such as the actual microcapsule application amount, position coordinates, and coverage uniformity of each micro-area) is compared region by region with the desired deposition target state extracted from the corresponding instruction part of the currently executed execution command (i.e., the target application amount, target position coordinates, target uniformity, etc. set for the same micro-area in the program instructions). Through this comparison, the system accurately calculates the deviation vector between the actual application state and the desired deposition target state.

[0061] Precise program instructions define the deposition target, and standardized online sensors provide real-time feedback to accurately quantify the specific deviation between the actual deposition state and the desired target. This clear, quantified deviation vector is the key prerequisite and direct driving force for the subsequent intelligent control algorithm to make effective and precise adjustments to ensure high quality and consistency in the final deposition. It also accumulates important data for overall system learning and optimization.

[0062] The PID controller uses the received deviation vector as its core error input. For each key process parameter currently being controlled, the controller multiplies the current error, the integral term of the error over time, and the rate of change of the error over time by the corresponding proportional (Kp), integral (Ki), and differential (Kd) gain parameters. The controller then linearly superimposes these three individually calculated control action terms to calculate a specific adjustment for that key process parameter in real time. These adjustments calculated by the PID controller directly affect the key process parameters: the adjustable characteristics of the precise electrical pulse waveform driving the microcapsule ejection unit that directly influence the physical deposition behavior of the microcapsules; the setpoints controlling the microcapsule material supply flow rate; and the fine-tuning instructions for the servo motor system responsible for the relative motion and precise positioning of the substrate and deposition nozzle.

[0063] Furthermore, to ensure optimal control performance in the face of dynamic changes in process conditions that may occur during the printing process, the system incorporates a parameter auto-tuning function. This parameter auto-tuning function primarily consists of two core sub-processes that work in concert. The system continuously monitors and records the historical sequence of adjustment commands applied to key process parameters, along with the synchronized sequence of precise feedback data on the real-time microcapsule deposition status provided by the online sensor system. Based on the latest input and output data, the system uses a recursive least squares method to estimate and update a set of key dynamic parameters describing the microcapsule deposition process. These dynamic parameters effectively characterize the process model's equivalent gain, primary time constants, pure lag times, and discrete model coefficients under the current operating conditions. Based on this updated set of dynamic parameters, the internal model control (IMC) automatically calculates and sets the three core gain parameters of the PID control algorithm: proportional (Kp), integral (Ki), and derivative (Kd), at a preset interval, triggered by significant changes in the process dynamics.

[0064] Adjustments for each key process parameter, calculated in real time by the PID controller, are automatically and precisely applied to the corresponding physical actuators via the control interface. A complete closed-loop control process, encompassing deviation determination, adjustment calculation, and adjustment application, continuously and rapidly controls each monitored micro-area deposition unit, ensuring that the actual deposition state of the microcapsule material, despite the influence of various potential disturbances, continuously and dynamically approaches and ultimately accurately and stably maintains the desired deposition target state specified by the execution command.

[0065] By continuously identifying the dynamic characteristics of the deposition process online and adaptively adjusting the PID core gain parameters accordingly, a key technical advantage is achieved: it significantly improves the absolute accuracy and long-term consistency of microcapsule deposition, effectively suppressing various unmodeled dynamics and external disturbances during the production process, thereby ensuring highly stable and reliable deposition quality under complex real-world conditions. At the same time, this mechanism significantly reduces the need for frequent, experience-based manual PID parameter tuning by operators, significantly improving the system's automation level, production preparation efficiency, and adaptability to diverse printing tasks.

[0066] Intelligent control module: Receives deposited substrates, control parameters, and execution commands, monitors color development characteristics in real time according to the program through the online monitoring system, determines the deviation between the color development characteristics monitored in real time and the target color characteristics defined by the control parameters through the adaptive control algorithm, dynamically optimizes and adjusts the control parameters of the divisible areas, and finally outputs the completed color development substrate and detailed execution data.

[0067] The intelligent control module first receives a substrate with a precisely deposited but not yet fully developed microcapsule pattern from the execution module. Simultaneously, the module retrieves control parameters related to the current print job and initial excitation settings for each separable area from the execution command generated by the input module. These control parameters clearly define the desired target color characteristics for the image area, such as target CIELAB L*a*b* coordinates, acceptable color difference ΔE range, and color uniformity standards. The initial excitation settings provide a starting point for the subsequent color development process. Depending on the color development mechanism of the microcapsules used—for example, photocuring, thermal activation, or laser selective color development—the excitation units can be specifically configured as a high-precision, tunable UV LED light source array, an infrared heating matrix, and a laser emission system controlled by a precision scanning galvanometer. These excitation units, in response to control commands, apply precisely controlled energy, such as light intensity, wavelength distribution, exposure time, heating temperature, and duration, to specific separable areas on the substrate.

[0068] Furthermore, while the color stimulation process is initiated and ongoing, an online monitoring system, specifically a machine vision system, continuously monitors the color development status of each separable area on the substrate in real time, according to the monitoring program and area divisions defined in the execution command. The machine vision system dynamically adjusts its frequency based on the color development rate to capture real-time image data of the gradual color development of the substrate surface under stimulation. This image data is then fed into the image processing unit. The image processing unit first removes noise and performs geometric correction on the captured image, then precisely locates each separable area to be monitored within the current field of view. Next, from these located areas, the average CIELAB L*a*b* value of the current color development status and the standard deviation of the color differences within the area are calculated. These calculated L*a*b* values and the standard deviation of the color differences within the area constitute the real-time monitored color development characteristics, which are continuously transmitted as high-frequency feedback signals to the subsequent adaptive control algorithm.

[0069] By providing precise printing targets and initial stimulus settings, combined with an advanced machine vision system that can provide real-time, quantitative color and uniformity feedback on controllable partitions and dynamically adjust the monitoring frequency according to the color development rate, a technical foundation is laid for subsequent adaptive control algorithms to accurately judge current deviations and dynamically optimize stimulus parameters to achieve ultimate accurate color reproduction and high consistency.

[0070] Furthermore, based on the real-time feedback from the machine vision system regarding the specific deviations between the current actual color rendering characteristics of each separable region (including average CIELAB values and color uniformity indices) and the target color characteristics, the adaptive control algorithm initiates its core dynamic excitation parameter optimization and adjustment process. This process precisely utilizes a predictive dynamic process response model currently deployed in the system. This model, within its internal structure, accurately characterizes the dynamic impact of adjustments to various excitation parameters within a specific separable region on the expected subsequent short-term evolution of the color rendering characteristics, specifically providing a quantitative prediction of the evolution trajectory of the L*a*b* color coordinates. During each control cycle of the intelligent control module, upon receiving new deviation information, the adaptive control algorithm first applies heuristic logic to construct a set of candidate corrections to the excitation unit parameter adjustments based on the specific deviations (including both the nature and magnitude) between the current separable region's color rendering characteristics and the corresponding target color characteristics. First, the logic analyzes each deviation to identify the dominant deviation component that most significantly impacts overall color quality (based on a pre-defined quality optimization objective). For example, is the lightness (L*) deviation the largest, the a* or b* deviation the most prominent, or the color uniformity metric the least satisfactory? The core of this heuristic logic for determining the dominant deviation component relies on referencing and executing a pre-defined, pre-built heuristic rule set for adjusting control parameters. This rule set is not based on machine learning training during the algorithm's runtime, but rather is comprehensively developed and solidified during the system design phase. First, it includes a deep physical and chemical understanding of the specific microcapsule color development mechanism, such as how different excitation energies (light intensity, wavelength, and heat) affect the microcapsule reaction rate, the amount of colorant generated, and the final color state. Second, it incorporates recognized fundamental principles of color science, such as the correspondence between changes in individual components (L*, a*, and b*) and color perception (brightness, red-green, yellow-blue) in color spaces like CIELAB, as well as the fundamental laws of color mixing. In addition, it also includes systematic offline experimental data analysis and empirical summaries of successful historical production cases. From a large amount of experimental and production data, through statistical analysis and expert summary, effective adjustment strategies and parameter sensitivity information for typical deviation patterns are extracted. This control parameter adjustment heuristic rule set specifically and logically encapsulates different types of color rendering characteristic deviations. For example, it clearly maps the relationship between identified dominant deviations such as luminance L* values significantly below the target, a* values that are excessively reddish, or poor color uniformity in a certain image area and the key excitation parameters recommended for adjustment. It also clearly maps the total exposure time of a specific light source, peak power, energy ratio of light sources of different wavelengths, and key points of the temperature curve of a specific heating area. These parameters are preset with recommended adjustment directions and adjustment priorities aimed at neutralizing the current dominant deviation.Based on this rule set, once the algorithm identifies the current dominant deviation, it can automatically query and match the corresponding adjustment rules, thereby identifying the key incentive parameters that need to be adjusted and obtaining its preliminary adjustment direction with clear improvement intentions.

[0071] Furthermore, for each identified key excitation parameter, the algorithm does not conduct a broad, aimless search, but rather systematically generates several specific, small-scale tentative adjustment values around the current setting value of the parameter. These adjustment values include an option to slightly increase the parameter value, an option to slightly decrease the parameter value, and in some cases, an option to keep the parameter value unchanged. These specific tentative adjustments for the selected key excitation parameters are applied separately to the current overall excitation parameter settings, thus forming different candidate correction excitation unit parameter adjustment schemes within a small neighborhood of the current solution. These precisely generated candidate adjustment schemes are then submitted to the dynamic process response model, which then uses each candidate correction scheme as input and calls the dynamic process response model to independently predict the expected time evolution trajectory of the color rendering characteristics of the corresponding area in the next few control steps after applying the specific adjustment.

[0072] Next, the system uses a comprehensive dynamic trajectory utility function to quantitatively evaluate and rank the multiple color evolution trajectories predicted by the model. This utility function operates as follows: First, for each predicted color evolution trajectory, the function accurately calculates and extracts a set of predefined key dynamic performance indicators (KPIs). These KPIs specifically describe key trajectory qualities, including: final predicted color difference, which is the color difference between the color achieved at the end of the predicted trajectory sequence and the target color; expected convergence time, which measures the number of control cycles required for the predicted color trajectory to reach and stabilize within the target color's tolerance band; maximum color component overshoot, which is the maximum deviation of any color component (e.g., L*, a*, b*) from its target value; and trajectory smoothness, which quantifies the smoothness of color changes by assessing the degree of oscillation or irregular fluctuation in the predicted trajectory.

[0073] After calculating these individual dynamic performance indicators, the comprehensive dynamic trajectory utility function combines these different performance indicators through a weighted linear combination into a single, overall score representing the overall utility and desirability of the predicted trajectory. The weight coefficients corresponding to each dynamic performance indicator reflect the performance preference and priority of each dynamic quality (e.g., fastest color rendering speed, highest color accuracy, and optimal process stability) adopted by the system's current preset quality mode. These weight coefficients are applied as parameters of the currently effective control strategy to clarify the relative importance of each dynamic quality in calculating the comprehensive performance score. The algorithm ultimately selects the corrected excitation unit parameters corresponding to the expected color evolution trajectory with the highest overall comprehensive utility score from all predicted and utility-evaluated candidate correction solutions. These parameters are used as the output instructions generated during this control cycle to adjust the excitation unit's operating state in real time.

[0074] By applying a dynamic process response model to predict the short-term color evolution trajectories of various candidate parameter adjustments and selecting the optimal one based on a heuristic trajectory quality evaluation function that considers dynamic qualities such as convergence speed, stability, and smoothness, the adaptive control algorithm achieves forward-looking intelligent optimization of the excitation parameters. This not only effectively corrects current deviations but also guides the color development process along the optimal path to quickly and stably approach the target, significantly improving color control accuracy, dynamic quality, system adaptability, and the efficiency of online decision-making.

[0075] Optimization module: collects the full-process execution data and quality indicators of each module for evaluation, obtains optimization commands, and deploys and updates modules in the system according to the optimization commands.

[0076] The optimization module is equipped with a dedicated data interface and processing unit to continuously and in real time collect and aggregate execution data and result data covering the entire process of each microcapsule image printing task from all other business modules in the system (i.e., input module, execution module, and intelligent control module). These data specifically include:

[0077] The core content includes the key features of the original image file, the preliminary control parameters generated by the GBDT model, the decision results of the conditional optimization gating, the final control parameters output by the APEO algorithm, and the generated execution commands. During the microcapsule deposition process, the actual set values and adjustment history of key process operating parameters, the real-time deposition status feedback data sequence monitored by online sensors (such as vision sensors), the internal state of the parameter self-tuning PID controller (such as the identified process model parameters and adjusted PID gains), and any deviations and correction records. During the color development process, the color evolution trajectory of each separable area monitored in real time by the machine vision system (such as the L*a*b* value sequence and uniformity index changes), the dynamic adjustment history and specific values of the excitation parameters by the adaptive control algorithm, and the compliance of the color characteristics of each area with the target at the end of the color development. A comprehensive evaluation of the final print quality, including indicators automatically obtained by the system's integrated online quality inspection equipment and manually entered after offline inspection, such as the overall verified color difference ΔE based on a standard color chart, visual defects in specific image areas, and customer feedback levels. All of these multi-source heterogeneous data are given a unique task identifier, timestamp, and relevant contextual information (such as the materials used, substrates, and equipment status). After cleaning, conversion, and alignment, they are uniformly stored in a structured central historical production database, providing a high-quality data foundation for subsequent evaluation and learning.

[0078] Triggered by an operator or at a set, fixed-cycle timer, the optimization module conducts in-depth analysis and performance evaluation of data accumulated in the historical production database. It monitors the long-term performance trends and stability of the system as a whole and key modules (such as GBDT parameter prediction, APEO optimization efficiency, PID deposition control accuracy, and intelligent color development control). It identifies whether the applicability of the current system-level predictive control model (GBDT model in the input module and dynamic process response model used by the intelligent control module) has weakened due to changes in process conditions. It analyzes the effectiveness of the existing adaptive control strategy (heuristic rule parameters of the APEO algorithm, trajectory evaluation function weights in the intelligent control module, and PID self-tuning rule meta-parameters in the execution module) to determine whether further optimization is possible. Through correlation analysis, it identifies the key factors contributing to quality issues and efficiency bottlenecks. Based on these evaluation results, the optimization module identifies the specific models and parameter sets in the current system that most need optimization and determines the optimization goals and directions.

[0079] Once the optimization requirements and objectives are determined, the optimization module invokes its core online learning mechanism, leveraging accumulated, preprocessed historical production data to dynamically optimize and retrain the system-level predictive control models and adaptive control strategies in need of optimization. For predictive control models (GBDT, dynamic process response models), the optimization module employs incremental learning algorithms, fine-tuning the existing model's parameters online using newly acquired data. When model performance degrades to a certain level, a full offline retraining based on an expanded dataset is triggered to generate an optimized model.

[0080] For the adaptive control strategy adopted in the system and its core adjustable parameters, such as the heuristic rule weights that may exist in the APEO algorithm, the weight coefficient of the trajectory evaluation function in the intelligent control module, and the tuning rule meta-parameters (such as expected response time and robustness index weight) in the parameter self-tuning PID control algorithm of the execution module, the optimization module uses a genetic algorithm for offline optimization. This genetic algorithm iteratively evaluates and screens many possible combinations of these strategy parameters. In each generation of evolution, the algorithm will use the comprehensive system performance (for example, average printing quality, production efficiency, and material consumption over a period of time) obtained by simulation and evaluation based on historical data as the fitness function, retain and combine parameter sets with better performance, and introduce random mutations to explore new possibilities until a set of strategy parameter settings that can significantly improve the expected overall performance of the system is found.

[0081] After generating an optimization model and strategy, the optimization module first conducts internal validation to ensure that their introduction will not negatively impact system stability and production quality. This validation is achieved through performance evaluation on a historical data backtesting set. Only models and strategies that have been verified to outperform the current version and are stable and reliable will enter the automatic deployment process. This model then calls a pre-trained deployment evaluation model, which processes data characterizing the optimization model and strategy (including their expected performance and resource usage), as well as data characterizing the current system state and potential deployment impact, to output a set of quantitative deployment condition evaluation metrics.

[0082] For optimization results that pass internal validation, the optimization module then invokes a pre-trained, multi-factor weighted scoring model specifically designed to quantitatively assess deployment conditions. The internal structure of this scoring model and the weights of its various evaluation factors are established through offline machine learning and statistical modeling analysis conducted by the optimization module using extensive historical deployment data. This historical deployment data provides detailed information on the characteristic parameters of previously deployed new models and policies, the specific system state at the time of deployment, and feedback on the actual impact of deployment on overall system performance and operational stability. During runtime, the multi-factor weighted scoring model receives detailed characteristic data for the new versions of the models and policies to be deployed. This data clearly covers the expected performance improvement demonstrated during the validation phase and the expected changes in compute and memory resource usage. It also combines key metrics collected in real time from various system units to characterize the overall system operational stability and current load, along with a set of pre-defined quantitative deployment risk assessment inputs. These inputs include the predicted level of system stability after the new version is introduced, the estimated probability and magnitude of regression in key performance indicators, the expected increase in compute resource load, and an assessment of compatibility issues with existing system components. Using its internal, multi-factor weighted scoring logic, the deployment assessment model comprehensively calculates and analyzes these multi-dimensional inputs to output a structured, quantitative set of deployment condition evaluation metrics. This set of metrics clearly defines the expected overall benefit score of deploying the new version's optimizations, the estimated probability of deployment success, and the associated risk ratings.

[0083] Subsequently, the deployment strategy decision unit within the optimization module receives and processes the set of deployment condition evaluation indicators output by the quantitative deployment evaluation model, which include the expected comprehensive benefit score, estimated success probability, and various risk levels for the new version. The core function of this decision unit is to perform logical judgments based on a preconfigured, structured deployment decision table. This decision table internally solidifies the numerical ranges for different deployment condition evaluation indicators, explicitly and directly mapping them to specific, predefined deployment action instructions. These rules are pre-set by the system based on a strategic trade-off between deployment benefits, introduced risks, and current system stability. By consulting this deployment decision table and matching the current evaluation indicators, the decision unit ultimately generates a specific optimization command. This command specifies one of the following: immediate and complete replacement of the old version; selective, small-scale trial deployment of the new version with simultaneous performance monitoring; or temporary suspension of deployment due to determination that current conditions are unsuitable. Finally, the optimization module executes the specific deployment operation specified in the deployment action instruction, securely and efficiently updating the optimization model and strategy to the corresponding functional modules within the system, enabling immediate implementation in subsequent tasks.

[0084] Through continuous deep learning and intelligent optimization of execution data and quality indicators throughout the entire printing process, this optimization module continuously improves the prediction accuracy of the system's core predictive control model and the regulatory efficiency of key adaptive control strategies. This directly overcomes the challenges of reduced and ineffective precision control capabilities caused by model aging, suboptimal parameters, and strategies. Through rigorous verification of optimized models and strategies and intelligent, risk-controlled automatic deployment, the entire microcapsule printing system ensures that it can consistently achieve and maintain highly accurate microcapsule image color rendering despite changes in material properties, evolving equipment states, and complex task demands.

[0085] The present invention provides an intelligent control system for printing microcapsule images. The input module intelligently calculates and refines initial control parameters through a gradient boosting decision tree and optimization algorithm, laying the foundation for high-precision operation. The execution module combines online sensor feedback with parameter self-tuning PID control to achieve dynamic and precise deposition of microcapsules. The intelligent control module uses machine vision for real-time monitoring and dynamically optimizes the color development process through an adaptive control algorithm to ensure the precise achievement of the final color characteristics. The optimization module continuously improves the long-term effectiveness and adaptability of the overall precise control of the system through learning, evaluation, and model updating of full-process data. This fully closed-loop intelligent design, from initial setting, precise execution, real-time color development regulation to long-term optimization, realizes adaptive and precise control of the entire process of microcapsule image construction.

[0086] Example 2: In order to achieve intelligent and precise control of the permeability of microcapsule image developer, Company B introduced a printing microcapsule image intelligent control method provided by the present invention. The method flow chart is as follows: Figure 3 As shown, the specific process is as follows:

[0087] Receive the input digital image file as the basic program setting, integrate the inherent color gamut capability of the selected material and historical production data, intelligently calculate the control parameters, and generate execution commands and control signals;

[0088] First, the system receives a digital design file containing the target image information and preset ideal developer penetration characteristics for each area of the image. These penetration characteristics are defined as target penetration depth, penetration rate curve, and penetration uniformity standards. These indicators are pre-set based on the known correlation between the penetration behavior of the selected microcapsule, developer, and substrate material system and the final color development effect. Subsequently, a gradient boosted decision tree (GBDT) model is used to process this information, integrating a database of penetration-related characteristics of the selected material (including kinetic parameters of the effect of temperature on penetration) with historical production penetration and color development data. This information is then processed to generate a preliminary set of temperature curve settings and corresponding initial parameters for the developer penetration kinetic model designed to achieve the target penetration characteristics. The Adaptive Perturbation Exploration Optimization (APEO) algorithm is then used to refine and optimize these preliminary temperature curve settings and model parameters, outputting the final initial temperature control program and control signal.

[0089] Receive execution commands and image data, combine with real-time status information monitored by online sensors, dynamically adjust key process operating parameters, and output substrates and related execution data with microcapsule deposition regulated according to instructions.

[0090] Furthermore, according to the deposition instructions contained in the initial temperature control program generated in the previous step, the microcapsule material is deposited with high precision on the designated area of the substrate. During this process, the system uses online sensors to monitor the deposition process in real time and dynamically adjusts key process operating parameters through a self-tuning PID control algorithm to ensure the accuracy of the deposition pattern, laying the foundation for subsequent precise penetration control.

[0091] Receive the deposited substrate, control parameters and execution commands, monitor the color development characteristics in real time according to the program through the machine vision system, determine the deviation between the color development characteristics monitored in real time and the target color characteristics defined by the control parameters through the adaptive control algorithm, dynamically optimize and adjust the control parameters of the divisible areas, and finally output the color-developed substrate and detailed execution data;

[0092] Furthermore, after microcapsule deposition is complete, the colorant penetration control and color activation phase begins. At this point, the system drives the precision temperature control components configured in the excitation unit to apply the starting temperature set by the initial temperature control program to the microcapsule area on the substrate. The colorant penetration kinetics model built into the intelligent control module is activated. This model uses the current real-time monitored regional temperature, exposure time, and material properties as inputs to dynamically predict and output the current colorant penetration rate and achieved penetration depth. The system's adaptive control algorithm receives the real-time penetration status data output by the colorant penetration kinetics model and continuously compares it with the set target penetration characteristic indicators to determine the deviation between the current penetration status and the target. Based on this deviation, combined with the machine vision system's monitoring results of the simultaneous color change trends, the adaptive control algorithm uses a dynamic process response model to predict the combined impact of different temperature adjustment strategies on the subsequent penetration rate and final color development. It then calculates and outputs precise adjustment instructions for the temperature control components to dynamically optimize the heating power, heating and cooling rates, and holding time. This adjustment is designed to precisely guide the actual penetration process of the developer to the target trajectory, while synergistically controlling other necessary color development excitation parameters to ensure that the final image achieves the expected color characteristics.

[0093] Gather the full-process execution data and quality indicators of each module for evaluation, obtain optimization commands, and deploy and update the modules in the system according to the optimization commands.

[0094] Furthermore, data from the entire process is collected, specifically including, in this embodiment, the actual temperature curve of the application, the predicted sequence of the permeation kinetics model, color evolution data monitored by machine vision, and a quantitative assessment of the color quality improvement of the final product resulting from permeation optimization. Through in-depth analysis of this data, a genetic algorithm is employed to optimize the strategies of the GBDT model and APEO algorithm used to generate the initial temperature control program in the input module. Parameters of the developer permeation kinetics model, as well as the dynamic process response model and heuristic rule set related to temperature-controlled permeation, are continuously learned and refined in the intelligent control module. Based on the optimization commands, relevant models and strategies in the system are deployed and updated, achieving iterative improvements in the accuracy and effectiveness of the entire intelligent control method.

[0095] To verify the effectiveness of the present method, Company B's original method was compared with the present method in terms of color difference between the final product and the target, mean absolute error in penetration depth, and product rejection rate due to poor penetration. A smaller color difference between the final product and the target indicates a color closer to the target; a smaller mean absolute error in penetration depth indicates more precise penetration control and more reliable functional implementation; and a lower rejection rate due to poor penetration indicates a higher yield rate. The two methods were tested using the same input data. The results are shown in Table 2.

[0096] Table 2 B Comparison results between the original method and the method of the present invention

[0097]

[0098] The method presented in this paper enables precise control of every key step in the entire microcapsule application process. It accurately calculates initial process parameters, precisely executes material deposition, and provides real-time adaptive adjustments to dynamic color development and activation. Through continuous learning and iterative optimization, the system continuously improves the accuracy of its control strategy and its adaptability to changing operating conditions, achieving comprehensive, high-level precision control.

[0099] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A microcapsule image intelligent control system for printing, comprising: Input module: Receives input digital image files as basic program settings, integrates the inherent characteristic parameters of the selected material and historical operation data, intelligently calculates control parameters, and generates execution commands and control signals; Execution module: Receives execution commands and image setting data, combines real-time status information monitored by online sensors, dynamically adjusts key process operating parameters, and outputs substrates and related execution data for controlling microcapsule deposition according to instructions; The intelligent control module receives the substrate after deposition processing, target characteristic parameters, and execution commands, and monitors the output color rendering characteristics in real time according to the program through the online monitoring system. During the color rendering process, the image data of each separable area on the substrate during the color rendering process is captured in real time and processed to locate the target area and calculate the quantitative color parameters and color uniformity therefrom. These are used as the color rendering characteristics output by the real-time monitoring and fed back to the adaptive control algorithm. The adaptive control algorithm determines the deviation between the real-time monitored color rendering characteristics and the target requirements defined by the target characteristic parameters, dynamically optimizes and adjusts the excitation parameters of the separable areas, and ultimately outputs a substrate that meets the set requirements and detailed execution data. The specific processing flow is as follows: For each separable area, the adaptive control algorithm calculates and generates a set of corrected excitation unit parameters based on the quantified deviation between the current color rendering characteristics of the separable area monitored in real time by machine vision and the preset target color rendering characteristics, combined with the dynamic process response model, to minimize the quantified deviation and bring the color rendering characteristics closer to the target. The corrected excitation unit parameters are then applied to the excitation units of the corresponding separable areas to adjust their operating states in real time. Optimization module: collects the full-process execution data and performance indicators of each module for evaluation, obtains optimization commands, and deploys and updates modules in the system according to the optimization commands.

2. The printing microcapsule image intelligent control system according to claim 1, characterized in that: The specific process of obtaining the intelligent calculation control parameters is as follows: The basic program settings, the inherent color gamut capability data of the selected materials, and the historical production data are processed by the gradient boosting decision tree model to generate preliminary control parameters. The preliminary control parameters are used as the initial solution and judged based on the color rendering quality optimization goal and the process feasibility constraints. If no further optimization is required, the preliminary control parameters are used as the final control parameters after verification and correction. If further optimization is required, the adaptive perturbation exploration optimization algorithm is used for iterative refinement to output the final control parameters.

3. The printing microcapsule image intelligent control system according to claim 2, characterized in that: The adaptive perturbation exploration optimization algorithm includes intelligently selecting the parameters to be adjusted and the perturbation direction based on a heuristic rule set; dynamically and adaptively setting the perturbation amplitude of the control parameters, iteratively generating candidate parameter combinations, and updating the optimal parameter set after verification and evaluation until the termination condition is met.

4. The printing microcapsule image intelligent control system according to claim 1, characterized in that: The dynamic adjustment of key process operating parameters includes: continuously acquiring and analyzing feedback data reflecting the current real-time application status of the microcapsule material from an online sensor; instantly comparing the acquired real-time application status feedback data with the desired deposition target state received from the control instruction to determine the deviation between the actual application state and the desired deposition target state; Based on the deviation, the required adjustment amount of the key deposition parameter is calculated in real time, and the adjustment amount is automatically applied to the corresponding key deposition parameter to continuously reduce the deviation so that the actual application state of the microcapsule material dynamically approaches and is maintained at the desired deposition target state.

5. The printing microcapsule image intelligent control system according to claim 4, characterized in that: The adjustment required to calculate the key deposition parameters in real time includes: Analyzing historical adjustment instruction data for the key deposition parameters and corresponding real-time material application state feedback data provided by online sensors, and continuously estimating and updating key dynamic characteristic parameters of the microcapsule deposition process online using a recursive estimation algorithm; Based on key dynamic characteristic parameters and according to preset PID parameter tuning rules, the proportional, integral and differential gain parameters of the PID control algorithm are automatically and periodically calculated and set.

6. The printing microcapsule image intelligent control system according to claim 1, characterized in that: The collection of full-process execution data and quality indicators of each module for evaluation includes: The deployment decision model is used to process execution data and quality indicators, output risk assessment indicators and deployment gains, and the decision model is used to combine historical deployment cases to process risk assessment indicators and deployment gains to obtain optimization commands.

7. A method for intelligent control of microcapsule images for printing, using the intelligent control system for microcapsule images for printing according to claim 1, characterized in that: Receive the input digital image file as the basic program setting, integrate the inherent characteristic parameters of the selected material and historical operation data, intelligently calculate the relevant control parameters, and generate execution commands and control signals; receive the execution command and image setting data, combine the real-time status information monitored by the online sensor, dynamically adjust the key process operation parameters, and output the substrate and related execution data for controlling the microcapsule deposition according to the instructions; Receive the printing material after deposition processing, target characteristic parameters and execution commands, monitor the output color rendering characteristics in real time according to the program through the online monitoring system, judge the deviation between the color rendering characteristics monitored in real time and the target requirements defined by the target characteristic parameters through the adaptive control algorithm, dynamically optimize and adjust the relevant control parameters of the divisible areas, and finally output the printing material and detailed execution data that meet the set requirements; collect the full-process execution data and performance indicators of each module for evaluation, obtain the optimization command, and deploy and update the modules in the system according to the optimization command.

Images