Intelligent ink droplet control method and system of digital printing machine and digital printing machine

Abstract

The invention relates to the technical field of digital printing machines, in particular to an intelligent ink droplet control method and system of a digital printing machine and the digital printing machine. The method comprises the steps of real-time data acquisition, multi-dimensional parameter modeling, real-time ink droplet behavior prediction, self-adaptive ink jet parameter adjustment, closed-loop feedback control, medium characteristic self-adaptive matching, intelligent multi-region optimization and environmental factor compensation. Ink droplet behaviors and environmental data are collected in real time through a high-speed camera and various sensors, a nonlinear model is constructed by using a deep learning technology, and a dynamic parameter optimization curve is generated. According to the method, the printing quality and efficiency are remarkably improved, and the method is suitable for various media and complex scenes.

Description

Technical Field

[0001] The present invention relates to the technical field of digital printing presses, and in particular to an intelligent ink drop control method and system for a digital printing press and a digital printing press. Background Art

[0002] Digital printing technology has developed rapidly in recent years. With its advantages of no plate making, on-demand printing, high efficiency and flexibility, it has been widely used in commercial printing, packaging printing and industrial applications. In the inkjet process of traditional digital printing equipment, the speed, shape and landing position of ink droplets are key factors affecting printing quality. However, due to the dynamic changes in the printing environment, media characteristics and equipment performance, it is difficult for existing technologies to ensure the stability and accuracy of ink droplet behavior, which poses a severe challenge to high-precision and high-consistency printing.

[0003] Traditional solutions for digital printing technology mainly focus on inkjet print head control, fixed parameter settings, and simple feedback adjustment mechanisms. These technologies have laid the foundation for the initial popularization of digital printing equipment, but they still have significant limitations when facing complex environments, diverse media, and high-precision requirements.

[0004] 1. High environmental sensitivity: Environmental factors such as temperature, humidity, static electricity, and equipment vibration can significantly affect the flight trajectory and landing point of ink droplets, resulting in blurred image edges, uneven colors, and other issues. Traditional inkjet equipment usually uses fixed parameter settings and cannot adapt to real-time environmental changes.

[0005] 2. Poor media adaptability: Different printing media (such as paper, plastic, cloth and metal surfaces) have different ink absorption, roughness and conductivity. Traditional systems often require manual adjustment of inkjet parameters, which is time-consuming and difficult to ensure optimal parameters.

[0006] 3. Insufficient dynamic adjustment capability: Inkjet parameters (such as voltage, pulse frequency and jet angle) are usually set before printing, but there is a lack of real-time feedback and dynamic adjustment mechanism in the actual inkjet process, resulting in limited accuracy and efficiency.

[0007] 4. Nonlinear complexity has not been fully addressed: The relationship between ink droplet behavior and the environment, media and inkjet parameters is highly nonlinear and dynamic. The existing technology lacks effective modeling and optimization methods, making it difficult to comprehensively improve printing quality.

[0008] In order to solve the above problems, some advanced digital printing technologies try to introduce sensor networks and simple feedback mechanisms to adjust inkjet parameters by real-time monitoring of the environment and media status. However, these technologies are usually based on static models and cannot capture the complex nonlinear relationship between multi-dimensional parameters, nor can they fully utilize the dynamic information in the time series. Therefore, the improvement of printing accuracy and efficiency is still limited. Summary of the invention

[0009] In order to solve the above technical problems, the purpose of the present invention is to provide an intelligent ink drop control method for a digital printing press, which integrates environmental parameters, medium characteristics and inkjet parameters by constructing a nonlinear multidimensional model, realizes multi-module linkage, dynamically predicts ink drop flight behavior, and updates inkjet parameters in real time through high-frequency control signals. This method combines time series analysis with an innovative nonlinear model of deep learning, and can adapt to environmental changes and media differences in real time. At the same time, a high-speed visual monitoring system and an environmental sensor network are used to dynamically collect inkjet behavior and environmental status data, generate optimization curves and guide inkjet parameter adjustments. Through this method, printing accuracy, efficiency and stability can be significantly improved to meet the needs of high-quality printing in complex environments and multiple media.

[0010] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solutions: An intelligent ink drop control method for a digital printing press, characterized in that the method comprises the following steps: 1) Real-time data collection: The shape, speed, landing point location and color distribution data of ink droplets during the inkjet process, as well as environmental parameters, are collected through high-speed cameras and environmental sensors. The environmental parameters include temperature, humidity, static electricity and medium surface roughness; 2) Multi-dimensional parameter modeling: Use deep learning technology to build a nonlinear model between ink droplet behavior and environmental factors, media characteristics and inkjet parameters, and generate a dynamic parameter optimization curve; 3) Real-time ink droplet behavior prediction: Based on the time series analysis algorithm, the flight trajectory deviation and deformation of the ink droplets and their impact on the target printing quality are predicted; 4) Adaptive inkjet parameter adjustment: According to the prediction results of ink droplet behavior, the voltage, pulse frequency, injection time and nozzle opening and closing state of the inkjet head are dynamically adjusted to optimize the size, speed and injection angle of the ink droplets; 5) Closed-loop feedback control: Generate control signals by real-time monitoring of ink droplet landing point deviation data and update inkjet parameters at a frequency of at least 5,000 times per second.

[0011] Preferably, the multi-dimensional parameter modeling utilizes a joint model of a convolutional neural network (CNN) and a recurrent neural network (RNN) to analyze both the spatial behavior characteristics of ink droplets and the dynamic changes in the time series.

[0012] Preferably, the nonlinear model uses multi-layer nonlinear transformation to integrate environmental parameters, media characteristics and inkjet parameters into a dynamic prediction framework: ; Where: y(t): ink drop behavior including speed, size, and landing point deviation; Φ: dynamic multi-layer nonlinear function, implemented by a neural network; ϵ(t): unmodeled error.

[0013] The model structure combines the following multi-level nonlinear calculations: ; X=[E,M,P]: input vector, including environmental parameters E, medium characteristics M and inkjet parameters P; W1, W2, W3: weight matrix, optimized by training data; b1,b2,b3: bias vector; σ(·): activation function; The input parameter X is processed as follows: Environmental parameters E(t)=[T,H,S,V]: including temperature, humidity, static electricity, and vibration; Medium properties M(t)=[A,R,C]: ink absorption, roughness, conductivity; Inkjet parameters P(t)=[V s ,F p ,θ]: nozzle voltage, pulse frequency, and injection angle; Decomposed into deep feature extraction layers: Environment module: ; Media Module: ; Inkjet module: ; Finally the outputs of these modules are combined: ; The output goes through the final layer: ; Combined with the dynamic behavior of time series, time-related parameters are added: ; in α i is the time decay coefficient, which is used to weight the impact of historical data on current decisions.

[0014] Preferably, the method further comprises analyzing the ink absorption, roughness and conductivity of the medium surface through a medium identification module, and dynamically loading an inkjet parameter optimization scheme for the corresponding medium.

[0015] Preferably, the media identification module automatically identifies the media type and loads the optimal inkjet parameters through high-resolution scanning equipment and material library matching technology.

[0016] Preferably, the method further comprises dividing the target image into a plurality of regions using a region segmentation algorithm, and adjusting the inkjet parameters for each region respectively.

[0017] Preferably, the method further comprises dynamically adjusting inkjet parameters in combination with real-time environmental data to compensate for inkjet deviations caused by changes in temperature, humidity or static electricity.

[0018] Preferably, the environmental factor compensation includes adjusting the electric field distribution of the nozzle according to the data of the electrostatic sensor to reduce the deviation of the ink droplet during the ejection process.

[0019] Furthermore, the present invention also provides an intelligent ink drop control system for a digital printing press, which implements the method described above, including: 1) High-speed visual monitoring unit: used to collect ink drop position, shape and color distribution data in real time; 2) Environmental perception module: including temperature and humidity sensors, electrostatic sensors and medium roughness detection devices; 3) Deep learning module: used to analyze the collected data and generate optimized inkjet parameters; 4) Inkjet control unit: connected to the deep learning module, used to dynamically adjust the voltage, pulse frequency and injection time of the inkjet head; 5) Closed-loop feedback control module: generates control signals based on real-time monitoring data; 6) Medium identification module: used to analyze and match the characteristic parameters of different media.

[0020] Furthermore, the present invention also provides a digital printing machine, comprising: 1) The intelligent ink drop control system; 2) Media transport module: used to transport a variety of media including paper, plastic, cloth and metal surfaces; 3) Ink system: supports UV curing ink and water-based ink, and has automatic cleaning function; 4) Control panel: used to set and monitor printing parameters in real time.

[0021] The present invention adopts the above-mentioned technical solution, and realizes the intelligence and efficiency of the digital printing machine in the dynamic adjustment of multi-dimensional parameters by introducing deep learning modeling, nonlinear dynamic optimization and closed-loop control technology. The specific technical effects include the following points: 1. Improve printing quality: The present invention realizes dynamic optimization of ink droplet behavior by real-time acquisition of ink droplet shape, speed, landing point location and color distribution data, combined with deep learning modeling; at the same time, the ink droplet landing accuracy is improved, effectively reducing image blur and color unevenness caused by offset and deformation. Furthermore, the present invention adopts a regional segmentation algorithm to independently adjust the inkjet parameters of different areas of the target image, ensuring the uniformity of printing quality and detail expression of complex images and multi-level structures.

[0022] 2. Enhance environmental adaptability: The present invention uses an environmental sensing module to collect temperature, humidity, static electricity and medium surface roughness data in real time, and dynamically adjusts inkjet parameters to significantly reduce the impact of environmental fluctuations on printing quality. At the same time, based on the electrostatic sensor data, the nozzle electric field distribution is adjusted to effectively reduce the deviation of ink droplets during the jetting process.

[0023] 3. Improve multi-media compatibility The present invention automatically analyzes the ink absorption, roughness and conductivity of the medium through the medium identification module, and dynamically loads the optimal inkjet parameters, which can adapt to a variety of media such as paper, plastic, cloth, metal, etc. This solves the problem that traditional printing presses need frequent manual adjustments during the medium type switching process. Furthermore, the high-resolution scanning equipment combined with the material library matching technology provides exclusive optimization solutions for different media, improving the wide compatibility and ease of operation of the printing press.

[0024] 4. Improve printing efficiency The present invention uses closed-loop feedback control and a parameter update frequency of at least 5,000 times per second to ensure that the inkjet parameters are always in the best state during high-speed inkjet. This reduces downtime adjustment time and production interruption, and improves equipment utilization. At the same time, combined with time series analysis technology, the offset and deformation of the ink droplet flight trajectory are predicted in real time, thereby optimizing the inkjet parameters in advance and shortening the parameter adjustment response time.

[0025] 5. Save resources The present invention dynamically adjusts the ink drop size and spray angle, reduces ink overflow and repeated spraying, and increases ink utilization by at least 30%. High-precision inkjet control and area-level optimization significantly reduce the scrap rate caused by printing deviation and save media costs.

[0026] 6. Improve system stability and reliability The deep learning module of the present invention continuously optimizes the nonlinear model by analyzing the historical data of the environment, media and inkjet parameters, thereby improving the long-term stability and intelligence level of the system. Whether in complex environments (such as high humidity and high static electricity) or multi-media scenarios, the present invention can maintain stable performance and reduce the risk of downtime or failure caused by environmental changes.

[0027] In summary, the present invention integrates real-time data acquisition, deep learning modeling, dynamic parameter optimization and closed-loop control technology, providing a highly intelligent solution for digital printing machines. It can adapt to a variety of complex environments and media, improve printing quality, efficiency and resource utilization, reduce the need for manual intervention, and significantly improve the overall performance and market competitiveness of digital printing equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a flowchart of the method of the present invention.

[0029] Figure 2 The figure is a dynamic curve diagram of temperature (red dashed line) and humidity (blue dotted line) fluctuations over time.

[0030] Figure 3 Dynamic curves for voltage (solid green line) and frequency (solid orange line) based on the optimization model. DETAILED DESCRIPTION

[0031] The following is a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] like Figure 1 An intelligent ink drop control method for a digital printing press is shown, the method comprising the following steps: 1) Real-time data collection: The shape, speed, landing point location and color distribution data of ink droplets during the inkjet process, as well as environmental parameters, are collected through high-speed cameras and environmental sensors. The environmental parameters include temperature, humidity, static electricity and medium surface roughness; 2) Multi-dimensional parameter modeling: Use deep learning technology to build a nonlinear model between ink droplet behavior and environmental factors, media characteristics and inkjet parameters, and generate a dynamic parameter optimization curve; 3) Real-time ink droplet behavior prediction: Based on the time series analysis algorithm, the flight trajectory deviation and deformation of the ink droplets and their impact on the target printing quality are predicted; 4) Adaptive inkjet parameter adjustment: According to the prediction results of ink droplet behavior, the voltage, pulse frequency, injection time and nozzle opening and closing state of the inkjet head are dynamically adjusted to optimize the size, speed and injection angle of the ink droplets; 5) Closed-loop feedback control: Generate control signals by real-time monitoring of ink droplet landing point deviation data, and update inkjet parameters at a frequency of at least 5,000 times per second; 6) Adaptive matching of media characteristics: The media recognition module analyzes the ink absorption, roughness and conductivity of the media surface, and dynamically loads the inkjet parameter optimization solution for the corresponding media; 7) Intelligent multi-region optimization: The target image is divided into multiple regions using a regional segmentation algorithm, and the inkjet parameters are adjusted for each region; 8) Environmental factor compensation: Dynamically adjust inkjet parameters based on real-time environmental data to compensate for inkjet deviations caused by changes in temperature, humidity or static electricity.

[0033] 1. Real-time data collection In order to accurately capture the ink droplet behavior and environmental changes during the inkjet process, the present invention needs to combine high-speed cameras, environmental sensors and data preprocessing technology to achieve real-time data collection.

[0034] 1. High-speed camera collects ink drop data 1.1 Camera selection: Use an industrial-grade high-speed camera with a high frame rate (≥5000FPS) to ensure continuous imaging of ink droplets during flight. The resolution should meet the requirements for ink droplet detail detection (such as ≥1920×1080 pixels).

[0035] 1.2 Data collection process: 1.2.1 Shape Detection: The contour features of the ink drop are extracted through image segmentation algorithms. The shape of the ink drop is obtained by applying edge detection methods (such as the Canny algorithm).

[0036] 1.2.2 Speed ​​calculation: The flying speed is calculated by the position change of ink droplets in consecutive frames: .

[0037] 1.2.3 Landing point location record: Use the image coordinates to convert to the actual space coordinates and record the ink droplet landing point: (x actual ,y actual ).

[0038] 1.2.4 Color distribution analysis: Extract the color channel values ​​(such as RGB or LAB color space) of the ink drop image, and calculate the color uniformity and saturation.

[0039] 1.2.5 Synchronous processing: Ensure that the camera and inkjet action are synchronized to avoid data offset.

[0040] 2. Environmental sensors collect environmental parameters 2.1 Sensor selection: Temperature and humidity sensor: Measure the temperature T(t) and humidity H(t) of the inkjet environment. Use a high-precision sensor (such as ±0.1°C temperature error, ±1% humidity error).

[0041] Electrostatic sensor: Measures the electrostatic intensity S(t) in the inkjet environment using a non-contact electrostatic sensor.

[0042] Roughness detection sensor: Use laser or optical sensor to measure the microscopic roughness RRR of the media surface.

[0043] 2.2 Data collection process: Temperature and humidity: Collect temperature and humidity data T(t) and H(t) once per second and record the changing trend.

[0044] Electrostatics: Measures the electrostatic field strength S(t) near the inkjet path and media surface.

[0045] Roughness: The laser sensor scans the surface of the medium and calculates the roughness parameter R, using the root mean square height (RMS) metric: .

[0046] 2.3 Data Fusion: The data from each sensor is synchronously integrated to form a unified environmental parameter input.

[0047] 3. Data Preprocessing 3.1 Denoising Apply Gaussian filtering or median filtering to the images collected by the camera to remove noise. Use Kalman filtering on the sensor data to smooth the changes in environmental parameters.

[0048] 3.2 Normalization: Normalize data of different dimensions to a uniform range (such as [0,1]): .

[0049] 3.3 Time Synchronization: Use a unified clock to time-align camera and sensor data to ensure data consistency.

[0050] 2. Multidimensional parameter modeling The multidimensional parameter modeling of the present invention combines convolutional neural networks (CNN) and recurrent neural networks (RNN) to establish a nonlinear relationship between ink droplet behavior and environmental factors, medium characteristics, and inkjet parameters, thereby generating a dynamic parameter optimization curve. Figure 2 The fluctuations of temperature (red dashed line) and humidity (blue dotted line) over time are given, simulating the changes under complex environmental conditions. Figure 3The voltage (green solid line) and frequency (orange solid line) are dynamically adjusted based on the optimization model to adapt to real-time environmental changes and inkjet requirements.

[0051] 1. Nonlinear Model The nonlinear model uses multiple layers of nonlinear transformations to integrate environmental parameters, media characteristics, and inkjet parameters into a dynamic prediction framework: ; Where: y(t): ink drop behavior including speed, size, and landing point deviation; Φ: dynamic multi-layer nonlinear function, implemented by a neural network; ϵ(t): unmodeled error.

[0052] The model structure combines the following multi-level nonlinear calculations: ; X=[E,M,P]: input vector, including environmental parameters E, medium characteristics M and inkjet parameters P; W1,W2,W3: weight matrix, optimized by training data; b1,b2,b3: bias vector; σ(·): activation function.

[0053] The input parameter X is processed as follows: Environmental parameters E(t)=[T,H,S,V]: including temperature, humidity, static electricity, and vibration; Medium properties M(t)=[A,R,C]: ink absorption, roughness, conductivity; Inkjet parameters P(t)=[V s ,F p ,θ]: nozzle voltage, pulse frequency, and injection angle; Decomposed into deep feature extraction layers: Environment module: ; Media Module: ; Inkjet module: ; Finally the outputs of these modules are combined: ; The output goes through the final layer: ; Combined with the dynamic behavior of time series, time-related parameters are added: ; in α i is the time decay coefficient, which is used to weight the impact of historical data on current decisions.

[0054] 3. Real-time ink droplet behavior prediction The real-time ink droplet behavior prediction of the present invention uses a time series analysis algorithm to predict the flight trajectory deviation and deformation of ink droplets and their impact on printing quality. The long short-term memory network (LSTM) is used to process time series data. The following are the specific implementation steps: 1. LSTM model structure Input layer: input sliding window time series data X seq .

[0055] LSTM hidden layer: captures long-term and short-term dependencies in time series: ; h t : hidden state; c t : Unit status.

[0056] Output layer: Output ink drop trajectory deviation Δx, Δy and deformation ΔS: .

[0057] 2. Prediction Step (1) Flight trajectory deviation prediction Predict the trajectory deviation of ink droplets during flight: Model input: ; Model output: .

[0058] (2) Ink droplet deformation prediction Predict the deformation of ink droplets during flight due to changes in environment and speed: Input: X seq； Output: .

[0059] 4. Adaptive inkjet parameter adjustment Adaptive inkjet parameter adjustment dynamically optimizes the parameters of the inkjet head (voltage, pulse frequency, jetting time and nozzle opening and closing status) by analyzing the predicted results of ink droplet behavior to ensure precise control of ink droplet size, speed and jetting angle. The following is the specific implementation method: 1. Input and analysis of prediction results (1) Input data The following prediction results are obtained from the real-time ink droplet behavior prediction module: ; Δx: the flight trajectory deviation of the ink droplet; ΔS(t): the deformation degree of the ink droplet.

[0060] At the same time, the real-time collection of environmental and medium data: ; Environmental parameters E(t)=[T(t),H(t),S(t)]; medium characteristics M(t)=[A,R,C].

[0061] (2) Definition of deviation Drop point deviation: ; Target behavior adjustment goal: reduce Δd and minimize ΔS(t).

[0062] 2. Rules and formulas for dynamically adjusting parameters (1) Nozzle voltage Vs Adjust voltage to optimize drop volume and minimize deformation.

[0063] Adjustment rules:

[0064] K v : Adjustment coefficient (determined according to the characteristics of the medium); if the ink drop is too large (ΔS>0), reduce V s ; If the ink droplet is too small (ΔS<0), increase V s .

[0065] (2) Pulse frequency Fp Adjust the frequency to compensate for trajectory deviation.

[0066] Adjustment rules:

[0067] K f : Frequency adjustment factor; increase frequency to improve droplet stability and reduce offset.

[0068] (3) Injection time t s Optimize momentum to correct trajectory.

[0069] Adjustment rules: t s (t) = t s (t−1)+K t (Δx+Δy) K t : Time adjustment coefficient; dynamically adjust the injection time according to the offset direction.

[0070] (4) Nozzle opening and closing status The opening and closing state of the nozzle determines the initial angle and shape of the ink droplet; the nozzle opening and closing angle is dynamically controlled to correct the flight trajectory.

[0071] Adjustment rules:

[0072] Kθ : Angle adjustment factor; corrects the spray direction to reduce deviation.

[0073] 3. Parameter adjustment algorithm Based on the input prediction data and real-time collected data, the following adaptive parameter adjustment process is performed: Step 1: Calculate the deviation The trajectory deviation Δd and deformation ΔS are calculated based on the prediction results.

[0074] Determine the size of the deviation: If Δd>threshold, perform offset compensation; if ΔS>threshold, optimize deformation.

[0075] Step 2: Determine the adjustment amount Calculate the adjustment parameters based on the deviation size:

[0076] The adjustment amount for each parameter is calculated by the above rules.

[0077] Step 3: Update parameters in real time Adjust the inkjet head parameters in real time: Voltage: V s (t + 1)=V s (t)+ΔV s ; frequency: F p (t + 1)=F p (t)+ΔF p ; time: t s (t + 1)=t s (t)+Δt s ; angle: θ(t + 1)=θ(t)+Δθ ; 5. Closed-loop feedback control Closed-loop feedback control monitors the droplet landing deviation in real time, generates control signals to dynamically adjust the inkjet parameters, and ensures the stability and accuracy of the droplet behavior. The following is a specific implementation method: 1. Data collection and deviation calculation (1) Real-time data collection The following data is collected by high-speed cameras and sensors: Landing point coordinates: actual ink droplet landing point coordinates (x actual ,y actual ); Target coordinates: ideal ink droplet landing point coordinates (xtarget ,y target ).

[0078] (2) Deviation calculation Calculate the deviation between the actual droplet landing point and the target droplet landing point: Δdx=x actual −x target ,Δdy=y actual −y target

[0079] Δdx, Δdy: deviations in the X-axis and Y-axis directions; Δd: overall deviation, used for subsequent control.

[0080] 2. Control signal generation (1) PID controller design A proportional-integral-derivative (PID) controller is used to generate control signals that adjust the inkjet parameters.

[0081] The output of the PID controller is:

[0082] u(t): control signal (adjustment amount); e(t)=Δd(t): current deviation; K p ,K i ,K d : Proportional, integral, and differential gains.

[0083] Independent control of Δdx and Δdy:

[0084]

[0085] 3. Parameter adjustment (1) Adjust the nozzle voltage V s Voltage affects the ink drop size, adjust the formula: ; K v : Voltage adjustment coefficient.

[0086] (2) Adjust the pulse frequency F p The pulse frequency affects the ink droplet velocity, and the adjustment formula is:

[0087] K f : Frequency adjustment coefficient.

[0088] (3) Adjust the injection angle θ Angle controls the direction of the landing point, adjust the formula:

[0089] K θ : Angle adjustment coefficient.

[0090] (4) Dynamic injection time t s The jetting time affects the momentum of the ink droplets, and the adjustment formula is:

[0091] K t : Time adjustment factor.

[0092] 4. High-frequency control updates (1) Control the update frequency The closed-loop controller runs at least 5,000 times per second; each time it collects the latest deviation data, generates control signals in real time and updates the inkjet parameters.

[0093] (2) Filtering In order to avoid the interference of sensor noise on the control signal, filtering technology is used to smooth the input data: Kalman Filter:

[0094] z t : measured value; K t : Filter gain.

[0095] 6. Adaptive matching of dielectric characteristics Adaptive matching of media characteristics analyzes the surface characteristics of the media (such as ink absorption, roughness, conductivity, etc.) through the media identification module, dynamically loads the optimal inkjet parameter solution, and realizes rapid adaptation and efficient printing of various media. The following is the specific implementation method: 1. Data Collection (1) Medium characteristics collection Real-time detection of key characteristics of the medium through a variety of sensors: Ink absorption A: Use a high-precision ink diffusion sensor or image analysis equipment to measure the diffusion rate and diffusion area of ​​ink droplets on the surface of the medium. Measurement formula: A = diffusion area / ink drop volume; Surface roughness R: Use a laser displacement sensor or optical microscope to scan the microscopic morphology of the medium surface and calculate the roughness parameters.

[0096] Typical indicators: ; z i : surface height value; : Average surface height.

[0097] Conductivity C: Use a contact or non-contact conductivity sensor to measure the conductivity of the media and evaluate the effect of static electricity on inkjet behavior. Measurement unit: (S / m).

[0098] (2) Data collection synchronization The medium characteristic data [A, R, C] and the environmental data [T, H, S] are collected synchronously to form a complete input feature.

[0099] 2. Media identification (1) Material classification Classify the media characteristic data through the media identification module: Use labeled data to train a classification model (such as a support vector machine (SVM) or a convolutional neural network (CNN)).

[0100] Based on parameters such as ink absorption A, roughness R, conductivity C, etc., the media is classified into specific types (such as paper, plastic, cloth, metal, etc.).

[0101] (2) Classification model formula The classification model is Φ: medium type = Φ(A, R, C); Φ is a nonlinear mapping function based on deep learning.

[0102] (3) Data Matching According to the identified medium type, find the corresponding optimization parameter solution in the material database: P optimal =DB(Φ(A,R,C)); DB: Material database; optimal : Optimized inkjet parameter scheme.

[0103] 3. Dynamically load inkjet parameters (1) Parameter mapping rules Map the optimization scheme in the material database to the inkjet parameters: Nozzle voltage V s :V s =f1(A); The voltage is adjusted according to the ink absorption to control the ink drop size.

[0104] Pulse frequency F p :F p =f2(R); Adjust frequency based on roughness to optimize droplet stability.

[0105] Injection angle θ: θ=f3(C); Adjust the spray direction according to conductivity to reduce static interference.

[0106] (2) Dynamic parameter adjustment formula Dynamically update inkjet parameters based on real-time data collected: P(t)=P baseline +ΔP(A,R,C); P baseline : Default inkjet parameters; ΔP(A,R,C): Parameter correction calculated based on media characteristics.

[0107] 4. Adaptive matching algorithm (1) Data processing Collect input features: X = [A, R, C, T, H, S] (2) Matching algorithm Dynamically select optimization solutions based on input features: Preset rules select inkjet parameters based on input features; trained deep learning models are used to predict parameter adjustments.

[0108] (3) Output Generate optimized inkjet parameters P optimal , including: nozzle voltage V s ; Pulse frequency F p ; Injection time t s ; Injection angle θ.

[0109] 7. Intelligent multi-region optimization Intelligent multi-region optimization divides the target image into multiple regions through the region segmentation algorithm, and adjusts the inkjet parameters based on the regional characteristics to ensure the details and overall quality of complex image printing. The following is the specific implementation method: 1. Data preprocessing (1) Input data Target image: The resolution of the input image I is (W, H), and the pixel values ​​represent color or grayscale.

[0110] Segmentation goal: Divide the image into multiple regions {R1, R2, …, Rn} according to image characteristics (such as brightness, texture, color, etc.).

[0111] (2) Normalize the pixel values ​​of the input image to ensure that the pixel value range is [0,1][0,1][0,1].

[0112] 2. Region Segmentation Algorithm (1) Basis for division Image segmentation is performed based on the following characteristics: Color: Based on pixel color (such as RGB, LAB color space).

[0113] Brightness: Based on the gray value distribution.

[0114] Texture: Based on local features (such as gradients or wavelet transforms).

[0115] Complexity: The richness of regional details.

[0116] (2) Algorithm Select a suitable segmentation algorithm to divide the image into multiple regions.

[0117] 2.1 Threshold-based Segmentation Compare the pixel values ​​of an image with one or more thresholds to divide the image into regions:

[0118] T i : Threshold, determined by image histogram or Otsu algorithm.

[0119] 2.2 K-means clustering Cluster pixel values ​​and assign each pixel to the nearest cluster center.

[0120] Clustering formula: ; k: the number of regions to be segmented; μ i : The mean value of each region.

[0121] 2.3 Superpixel Segmentation The SLIC (Simple Linear Iterative Clustering) algorithm is used to generate superpixels.

[0122] Superpixel region merging formula: ; c: color distance weight; s: spatial distance weight.

[0123] 3. Regional characteristics analysis (1) Color and brightness characteristics Calculate the mean color and brightness of each region: ; I c (x,y): pixel color value; I l (x,y): pixel brightness value.

[0124] (2) Texture characteristics Extract texture features (such as gradient magnitude or wavelet energy) from each region:

[0125] T i : The average texture characteristics of the region.

[0126] (3) Complexity characteristics Define the detail complexity of the area:

[0127] Var: Variance of pixel values ​​within the region.

[0128] 4. Inkjet parameter optimization (1) Inkjet parameter mapping Dynamically adjust inkjet parameters based on regional characteristics: Nozzle voltage V s : Adjust drop size based on color and brightness average: V s =f1(C i ,L i ) Pulse frequency F p : Adjust ink drop speed according to texture characteristics: F p =f2(T i ) Injection time t s : Adjust the droplet momentum according to complexity: t s =f3(D i ) (2) Dynamic loading parameters Apply the optimization parameters to the corresponding regions: P i ={V s ,F p ,t s ,θ},∀R i .

[0129] 5. Multi-area inkjet execution (1) Regional Priority Sorting Sort by regional complexity Di, giving priority to areas with complex details: P riority (R i )=D i (2) Inkjet printing in steps The inkjet tasks for each area are completed in order of priority, ensuring that details come first.

[0130] 8. Compensation for environmental factors Environmental factor compensation dynamically adjusts the inkjet head's inkjet parameters (voltage, pulse frequency, jetting time and jetting angle) by real-time monitoring of parameters such as temperature, humidity and static electricity to reduce the impact of environmental changes on ink droplet behavior. The following is a specific implementation method: 1. Environmental data collection and processing (1) Environmental data collection The following environmental parameters are obtained in real time through sensors: Temperature T(t): Ambient temperature collected by temperature sensor (unit: °C); Humidity H(t): collects ambient humidity through humidity sensor (unit: %RH); Static Electricity S(t): The electrostatic field strength of the inkjet path and the media surface is measured by an electrostatic sensor (unit: kV / m).

[0131] (2) Data preprocessing De-noising and normalization of the collected data: Denoising: Use a Kalman filter to smooth sensor noise.

[0132] Normalization: Scale the data to the uniform range [0,1].

[0133] (3) Deviation calculation Calculate the deviation required to compensate for changes in environmental parameters: ΔP=f(T,H,S) ΔP: Correction value of inkjet parameters caused by environmental changes.

[0134] 2. Compensation Model (1) Parameter relationship model Construct the relationship between environmental factors and inkjet behavior through experiments or data training: Temperature T(t): Increased temperature will reduce the viscosity of the ink droplets and increase their flying speed.

[0135] Compensation formula:

[0136] K T : Temperature compensation coefficient; T0: reference temperature.

[0137] Humidity H(t): Increased humidity increases ink droplet diffusion.

[0138] Compensation formula:

[0139] K H : Humidity compensation coefficient; H0: reference humidity.

[0140] Static electricity S(t): Increased static electricity will cause ink droplets to deflect.

[0141] Compensation formula:

[0142] KS : Electrostatic compensation coefficient.

[0143] (2) Comprehensive compensation formula The temperature, humidity and static electricity are calculated comprehensively to correct the inkjet parameters: .

[0144] 3. Real-time compensation process (1) Data collection and analysis Real-time acquisition of temperature T(t), humidity H(t) and static electricity S(t).

[0145] Calculate the deviation between the current environmental parameters and the reference values: ΔT=T(t)−T0, ΔH=H(t)−H0, ΔS=S(t)−S0; (2) Generating compensation signal Calculate the compensation signal based on the deviation: ΔP=[ΔV s ,ΔF p ,Δt s ,Δθ] ΔV s : Voltage adjustment; ΔF p : Pulse frequency adjustment; Δt s : Injection time adjustment; Δθ: Injection angle adjustment.

[0146] (3) Real-time parameter adjustment Apply the compensation signal to the inkjet head: Voltage adjustment: V s (t+1)=V s (t)+ΔV s ; Frequency adjustment: F p (t+1)=F p (t)+ΔF p ; Time adjustment: t s (t+1)=t s (t)+Δt s ; Angle adjustment: θ(t+1)=θ(t)+Δθ.

[0147] The following describes in detail a specific embodiment of the present invention, in conjunction with an actual application scenario, a process of implementing high-precision printing of a complex image in a high-humidity environment.

[0148] 1. Example Background 1.1 Environmental conditions: Temperature: 30°C; Humidity: 75%; Electrostatic strength: 2 kV / m 2 .

[0149] 1.2 Medium characteristics: Media type: smooth plastic sheet; ink absorption: A=0.3; surface roughness: R=0.2 μm; conductivity: C=0.1 S / m.

[0150] 1.3 Target image: Resolution: 300dpi.

[0151] Characteristics: The image contains highlight areas (such as white parts), high-texture areas (parts with complex details) and medium-brightness areas (background parts).

[0152] 2. Specific implementation steps Step 1: Collect data in real time Ink droplet behavior data collection: Use a high-speed camera to capture the ink droplet shape, speed and landing position in real time.

[0153] Analyze ink drop shape: Use the Canny algorithm to extract the ink drop outline.

[0154] Calculate the ink droplet velocity: v(t)=Δx / Δtv(t); Assuming the inter-frame displacement is 0.2 mm and the time interval is 0.001 s, then: v(t)=0.2 / 0.001=200 mm / s; Environmental parameter collection: Temperature T(t)=30℃, humidity H(t)=75%, electrostatic intensity S(t)=2 kV / m; laser sensor measures the surface roughness of the medium R=0.2 μm.

[0155] Step 2: Multidimensional parametric modeling Input data construction: X(t)=[T(t),H(t),S(t),A,R,C,Vs,Fp,θ] Deep Learning Models: Convolutional neural network extracts media characteristics and environmental characteristics; LSTM processes inkjet parameters and time series data.

[0156] Predicting ink droplet behavior: Landing point deviation: Δx(t)=0.1 mm, Δy(t)=0.2 mm; Ink drop deformation: ΔS(t)=0.05 mm.

[0157] Step 3: Real-time ink droplet behavior prediction Predict trajectory deviation based on LSTM model:

[0158] Deformation value prediction: ΔS(t)=0.05 mm.

[0159] Step 4: Adaptive inkjet parameter adjustment Nozzle voltage adjustment: ink droplet deformation ΔS = 0.05 mm, adjustment voltage: V s (t+1)=V s (t)+K v *ΔS; Assume K v =10 V / mm, then: ΔV s =10*0.05=0.5 V; Pulse frequency adjustment: offset Δd = 0.223 mm, adjustment frequency: F p (t+1)=F p (t)−K f *Δd; Assume K f =50 kHz / mm, then: ΔF p =50⋅0.223=11.15 kHz Injection angle adjustment: offset direction: Δθ=−K θ *arctan(Δy / Δx); Assume K θ =5 ° / rad, then: Δθ=−5*arctan(0.2 / 0.1)=−5*1.107=−5.54°.

[0160] Step 5: Closed-loop feedback control Real-time monitoring of landing point deviation: Deviation value: Δd=0.223 mm PID control signal generation:

[0161] Proportional gain K p =2, integral gain K i =0.5, differential gain K d =1, error e(t)=0.223e, then:

[0162] Dynamically calculated control signals are used to adjust inkjet parameters.

[0163] Step 6: Adaptive matching of dielectric properties Detection medium characteristics: ink absorption A=0.3, roughness R=0.2 μm, conductivity C=0.1 S / m.

[0164] Material library matching: Query material library: P optimal =DB(A,R,C); Get the optimized parameter scheme V s =15 V,Fp =20 kHz,θ=2 ° .

[0165] Step 7: Smart Multi-Region Optimization Region segmentation: Use the K-means algorithm to divide the image into three regions: Highlight area R1: white background; High texture area R2: image details; Medium brightness area R3: background pattern.

[0166] Dynamic inkjet adjustment: Highlight area R1: reduce voltage and increase frequency; High texture area R2: increase the injection time and voltage; Medium brightness area R3: Keep the default parameters.

[0167] Step 8: Compensation for environmental factors Temperature and humidity compensation: humidity rises H(t)=75%, adjust voltage: V s (t+1)=V s (t)+K H *(H(t)−H0); Assume K H =0.1, then: ΔV s =0.1*(75−50)=2.5 V; Electrostatic compensation: electrostatic strength S(t) = 2 kV / m, adjust the spray angle: θ(t+1) = θ(t) − K S *S(t); Assume K S =1° / kV / m, then: Δθ=-1*2=-2°.

[0168] The above is a description of the embodiments of the present invention. Through the above description of the disclosed embodiments, professionals and technicians in the field can implement or use the present invention. Various modifications to these embodiments will be apparent to professionals and technicians in the field. The general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown in this article, but will conform to the widest range consistent with the principles and novelties disclosed herein.

Claims

1. An intelligent ink drop control method for a digital printing press, characterized in that: The method comprises the following steps: 1) Real-time data collection: The shape, speed, landing point location and color distribution data of ink droplets during the inkjet process, as well as environmental parameters, are collected through high-speed cameras and environmental sensors. The environmental parameters include temperature, humidity, static electricity and medium surface roughness; 2) Multi-dimensional parameter modeling: Use deep learning technology to build a nonlinear model between ink droplet behavior and environmental factors, media characteristics and inkjet parameters, and generate a dynamic parameter optimization curve; 3) Real-time ink droplet behavior prediction: Based on the time series analysis algorithm, the flight trajectory deviation and deformation of the ink droplets and their impact on the target printing quality are predicted; 4) Adaptive inkjet parameter adjustment: According to the prediction results of ink droplet behavior, the voltage, pulse frequency, injection time and nozzle opening and closing state of the inkjet head are dynamically adjusted to optimize the size, speed and injection angle of the ink droplets; 5) Closed-loop feedback control: Generate control signals by real-time monitoring of ink droplet landing point deviation data and update inkjet parameters at a frequency of at least 5,000 times per second.

2. The intelligent ink drop control method of a digital printing press according to claim 1, characterized in that: The multi-dimensional parameter modeling utilizes a joint model of a convolutional neural network (CNN) and a recurrent neural network (RNN) to analyze both the spatial behavior characteristics of ink droplets and the dynamic changes in the time series.

3. The intelligent ink drop control method of a digital printing press according to claim 1, characterized in that: The nonlinear model uses multiple layers of nonlinear transformations to integrate environmental parameters, media characteristics, and inkjet parameters into a dynamic prediction framework: ； Where: y(t): ink drop behavior including speed, size, and drop point deviation; Φ: dynamic multi-layer nonlinear function, implemented by neural network; ϵ(t): unmodeled error; The model structure combines the following multi-level nonlinear calculations: ； X=[E,M,P]: input vector, including environmental parameters E, medium characteristics M and inkjet parameters P; W1, W2, W3: weight matrix, optimized by training data; b1,b2,b3: bias vector; σ(·): activation function; The input parameter X is processed as follows: Environmental parameters E(t)=[T,H,S,V]: including temperature, humidity, static electricity, and vibration; Medium properties M(t)=[A,R,C]: ink absorption, roughness, conductivity; Inkjet parameters P(t)=[V s ,F p ,θ]: nozzle voltage, pulse frequency, and injection angle; Decomposed into deep feature extraction layers: Environment module: ; Media Module: ; Inkjet module: ; Finally the outputs of these modules are combined: ； The output goes through the final layer: ； Combined with the dynamic behavior of time series, time-related parameters are added: ； where α i is the time decay coefficient, which is used to weight the impact of historical data on current decisions.

4. The intelligent ink drop control method of a digital printing press according to claim 1, characterized in that: The method also includes analyzing the ink absorption, roughness and conductivity of the medium surface through a medium identification module, and dynamically loading an inkjet parameter optimization solution for the corresponding medium.

5. The intelligent ink drop control method of a digital printing press according to claim 1, characterized in that: The media identification module automatically identifies the media type and loads the optimal inkjet parameters through high-resolution scanning equipment and material library matching technology.

6. The intelligent ink drop control method of a digital printing press according to claim 1, characterized in that: The method also includes dividing the target image into a plurality of regions by using a region segmentation algorithm, and adjusting the inkjet parameters for each region respectively.

7. The intelligent ink drop control method of a digital printing press according to claim 1, characterized in that: The method also includes dynamically adjusting inkjet parameters in combination with real-time environmental data to compensate for inkjet deviations caused by changes in temperature, humidity or static electricity.

8. The intelligent ink drop control method of a digital printing press according to claim 1, characterized in that: The environmental factor compensation includes adjusting the electric field distribution of the nozzle according to the data of the electrostatic sensor to reduce the deviation of the ink droplet during the ejection process.

9. An intelligent ink drop control system for a digital printing press, characterized in that: The system implements the method described in any one of claims 1 to 8, including: 1) High-speed visual monitoring unit: used to collect ink drop position, shape and color distribution data in real time; 2) Environmental perception module: including temperature and humidity sensors, electrostatic sensors and medium roughness detection devices; 3) Deep learning module: used to analyze the collected data and generate optimized inkjet parameters; 4) Inkjet control unit: connected to the deep learning module, used to dynamically adjust the voltage, pulse frequency and injection time of the inkjet head; 5) Closed-loop feedback control module: generates control signals based on real-time monitoring data; 6) Medium identification module: used to analyze and match the characteristic parameters of different media.

10. A digital printing machine, characterized in that: include: 1) The intelligent ink drop control system according to claim 9; 2) Media transport module: used to transport a variety of media including paper, plastic, cloth and metal surfaces; 3) Ink system: supports UV curing ink and water-based ink, and has automatic cleaning function; 4) Control panel: used to set and monitor printing parameters in real time.

Images