Micro-coating paint and method for coating and sizing heat sublimation transfer paper

Abstract

The invention relates to a micro-coating paint for coating and sizing thermal dye sublimation transfer paper and a method thereof, the micro-coating paint is composed of a water-based resin emulsion, an inorganic filler, an organic modifier, a dispersant and water, has excellent adhesion, wear resistance and ink absorbency, and is suitable for various substrates such as paper, plastic and metal. According to the preparation method, an artificial intelligence algorithm and a sensor technology are introduced, real-time monitoring and dynamic optimization of the production process are achieved, and the production efficiency and the product quality are improved. The coating not only meets the environmental protection requirement, but also reduces the cost and improves the economic benefit through intelligent production, has wide application prospects and remarkable market competitiveness, and promotes the technical progress of the heat sublimation transfer paper industry.

Description

Technical Field

[0001] The invention belongs to the technical field of papermaking and printing, and in particular relates to a micro-coating coating and a method for coating and sizing thermal sublimation transfer paper. Background Art

[0002] In the production of thermal sublimation transfer paper, traditional coating and sizing methods suffer from poor adhesion, insufficient abrasion resistance, and poor chemical resistance, which impact transfer quality and paper performance. Furthermore, existing coating formulations and preparation processes are complex and costly, making them difficult to meet market demand. Therefore, the development of efficient, low-cost, and high-performance micro-coating coatings and their preparation methods is of great significance. Summary of the Invention

[0003] (1) Purpose of the invention

[0004] In order to overcome the above shortcomings, the purpose of the present invention is to provide a micro-coating coating and method and application for coating and sizing of thermal sublimation transfer paper to solve the above technical problems.

[0005] (2) Technical solution

[0006] To achieve the above objectives, the technical solutions provided by this application are as follows:

[0007] A micro-coating coating for coating and sizing of thermal sublimation transfer paper, the micro-coating coating comprising the following components:

[0008] 50-70% water-based resin emulsion; 10-20% inorganic filler; 5-15% organic modifier; 1-5% dispersant; the balance is water;

[0009] The aqueous resin emulsion is selected from acrylic resin emulsion, polyurethane resin emulsion or a mixture thereof;

[0010] The inorganic filler is selected from calcium carbonate, talc, kaolin or a mixture thereof.

[0011] Preferably, the organic modifier is selected from polyvinyl alcohol, polyethylene glycol or a mixture thereof.

[0012] Preferably, the dispersant is selected from polyphosphates, polycarboxylates or mixtures thereof.

[0013] A method for preparing a micro-coating for coating and sizing thermal sublimation transfer paper comprises the following steps:

[0014] S1: mixing water-based resin emulsion, inorganic filler, organic modifier and dispersant in proportion;

[0015] S2. Heat the mixture to 60-80°C under stirring and stir for 30-60 minutes;

[0016] S3 uses sensors to collect real-time data on temperature, viscosity, and pH, and dynamically adjusts stirring speed and heating temperature through artificial intelligence algorithms;

[0017] S4 is cooled to room temperature and the pH value is adjusted to 7-8 to obtain a micro-coating;

[0018] S5 uses machine vision technology to collect images of the paint surface, detects the paint surface quality through deep learning algorithms, and automatically screens out unqualified products.

[0019] Preferably, the stirring speed is 300-500 rpm.

[0020] Preferably, the step S3 specifically includes the following steps:

[0021] S31 data preprocessing normalizes the collected sensor data to eliminate dimensional differences:

[0022]

[0023]

[0024]

[0025] in, represents the normalized temperature value, T(t) represents the original temperature value, T min , T max are the minimum and maximum temperatures, represents the normalized viscosity value, η(t) represents the original viscosity value, η min , η max are the minimum and maximum values ​​of viscosity, represents the normalized pH value, pH(t) represents the original pH value, and pH min , pH max are the minimum and maximum pH values;

[0026] S32 model prediction and dynamic adjustment uses a pre-trained feedforward neural network to process the collected normalized data and predict the optimal stirring speed ω(t) and heating temperature Ttarget(t) under the current state:

[0027] z (l) =W (l) a (l-1) +b (l)

[0028] a (l) =f(z (l) )

[0029] Among them, z(1) is the linear combination of the lth layer, W (1) is the weight matrix, a (1-1) is the activation value of the previous layer, b (1) is the bias term, f is the activation function;

[0030] S33 feedback and control dynamically adjusts stirring speed and heating temperature based on model prediction results:

[0031]

[0032]

[0033] Among them, ω model and T model It is a prediction function based on a neural network model, which is used to output the optimal stirring speed and target temperature.

[0034] Preferably, in S5, the image recognition model is implemented based on a convolutional neural network, and its basic formula is:

[0035] z (l) =W (l) *a (l-1) +b (l)

[0036] a (l) =f(z (l) )

[0037] Among them, * represents the convolution operation, W (1) is the convolution kernel, a (1-1) is the input feature map, b (1) is the bias term, and f is the activation function.

[0038] A micro-coating system for coating and sizing thermal sublimation transfer paper, comprising:

[0039] Raw material storage and delivery mechanism: multiple storage tanks are set up to store raw materials, equipped with liquid level sensors to monitor the inventory, and accurately delivered to the mixing reactor according to the formula ratio through metering pumps. Flow sensors monitor in real time to ensure delivery accuracy;

[0040] Mixing reaction mechanism: The mixing reactor has heating and stirring functions. Temperature, viscosity, and pH sensors collect data in real time. The AI ​​algorithm dynamically adjusts the stirring speed and heating temperature to ensure uniform mixing of the coating.

[0041] Cooling and pH adjustment mechanism: A circulating cooling water or air cooling system is used to cool the paint to room temperature. The automatic acid and alkali adding device accurately adjusts the pH value to 7-8 according to the pH sensor data to ensure stable paint performance.

[0042] Quality inspection agency: High-resolution cameras capture images of the paint surface, and convolutional neural network models analyze and identify defects, automatically screening out unqualified products to ensure that the paint quality meets standards;

[0043] Product storage and output mechanism: Qualified coatings are stored in dedicated tanks, and liquid level and temperature sensors monitor the storage status in real time; unqualified products are transported to the processing area for re-adjustment or disposal, and qualified coatings are transported to the coating line or packaged for output as needed.

[0044] Preferably, the quality inspection mechanism specifically includes:

[0045] (1) Image acquisition unit:

[0046] High-resolution camera: Installed on the paint delivery pipeline or detection platform, it is used to capture the paint surface image in real time to ensure that the image clarity and resolution meet the detection requirements;

[0047] Light source system: Provides uniform and stable light source to avoid image quality degradation caused by insufficient or uneven light, which affects detection accuracy;

[0048] (2) Image processing unit:

[0049] Image preprocessing unit: performs preprocessing operations on the collected images, including denoising and enhancement to improve image quality and provide clearer images for subsequent analysis;

[0050] Feature extraction unit: uses a convolutional neural network model to extract key features from the image, including particle distribution, texture, and defect shape, providing basic data for defect identification;

[0051] (3) Defect detection unit:

[0052] Deep learning algorithm unit: Based on the pre-trained convolutional neural network model, it analyzes the extracted features, automatically identifies defects such as uneven particles, bubbles, and cracks on the coating surface, and determines the location and type of the defects;

[0053] Defect classification unit: Based on the identification results, the defects are classified into different categories, including minor defects and major defects, to provide a basis for subsequent processing;

[0054] (4) Quality judgment and feedback unit:

[0055] Quality judgment unit: judges the test results according to the preset quality standards to determine whether the coating is qualified. For unqualified products, it automatically issues an alarm and marks them;

[0056] Feedback and recording unit: Feedback the test results and judgment information to the control system, and record the test data and images for subsequent analysis and tracing.

[0057] Beneficial effects:

[0058] This micro-coating coating for sublimation transfer paper, its preparation method, and its application achieve the combined advantages of high performance, efficient production, wide applicability, and environmental protection and energy conservation through optimized formulation and the introduction of intelligent preparation processes. The coating exhibits excellent adhesion, abrasion resistance, and ink absorption, making it suitable for a variety of substrates, including paper, plastic, and metal surfaces, while also meeting environmental requirements. Intelligent production improves production efficiency and quality stability, reduces costs, and brings significant economic benefits and market competitiveness to enterprises, driving technological advancement in the industry. DETAILED DESCRIPTION

[0059] In order to make the purpose, technical solutions and advantages of the present invention more clear, the present invention is further described in detail below in conjunction with specific embodiments. It should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessary confusion of the concept of the present invention.

[0060] The present invention provides a micro-coating coating for coating and sizing of thermal sublimation transfer paper, wherein the micro-coating coating comprises the following components:

[0061] 50-70% water-based resin emulsion; 10-20% inorganic filler; 5-15% organic modifier; 1-5% dispersant; the balance is water;

[0062] By rationally combining water-based resin emulsion, inorganic fillers, organic modifiers, and dispersants, this micro-coating exhibits excellent overall performance. The water-based resin emulsion imparts excellent film-forming properties and adhesion; the inorganic fillers enhance the coating's abrasion and chemical resistance; the organic modifiers increase the coating's flexibility and ink absorption; and the dispersants ensure the stability of the coating system.

[0063] The aqueous resin emulsion is selected from acrylic resin emulsion, polyurethane resin emulsion or a mixture thereof, taking both cost and performance into consideration, so that the coating has higher mechanical strength and good weather resistance.

[0064] The inorganic filler is selected from calcium carbonate, talc, kaolin or a mixture thereof. These fillers are widely available, inexpensive, and can effectively improve the physical properties of the coating, such as hardness and glossiness.

[0065] The organic modifier is selected from polyvinyl alcohol, polyethylene glycol or a mixture thereof. These substances have good water solubility and film-forming properties, can further optimize the flexibility and ink absorption of the coating, and make the transferred pattern clearer and fuller.

[0066] The dispersant is selected from polyphosphates, polycarboxylates or mixtures thereof. These dispersants have high dispersing properties and can evenly disperse solid particles in the coating, prevent precipitation and agglomeration, and extend the shelf life of the coating.

[0067] A method for preparing a micro-coating for coating and sizing thermal sublimation transfer paper comprises the following steps:

[0068] S1: mixing water-based resin emulsion, inorganic filler, organic modifier and dispersant in proportion;

[0069] S2: heating the mixture to 60-80° C. under stirring, and stirring for 30-60 minutes at a stirring speed of 300-500 rpm;

[0070] S3 uses sensors to collect real-time data on temperature, viscosity, and pH, and dynamically adjusts stirring speed and heating temperature through artificial intelligence algorithms;

[0071] The S3 specifically includes the following steps:

[0072] S31 data preprocessing normalizes the collected sensor data to eliminate dimensional differences:

[0073]

[0074]

[0075]

[0076] in, represents the normalized temperature value, T(t) represents the original temperature value, T min , T max are the minimum and maximum temperatures, represents the normalized viscosity value, η(t) represents the original viscosity value, η min , η max are the minimum and maximum values ​​of viscosity, represents the normalized pH value, pH(t) represents the original pH value, and pH min , pH max are the minimum and maximum pH values;

[0077] S32 model prediction and dynamic adjustment uses a pre-trained feedforward neural network to process the collected normalized data and predict the optimal stirring speed ω(t) and heating temperature Ttarget(t) under the current state:

[0078] z (l) =W (l) a (l-1) +b(l)

[0079] a (l) =f(z (l) )

[0080] Among them, z (1) is the linear combination of the lth layer, W (1) is the weight matrix, a (1-1) is the activation value of the previous layer, b (1) is the bias term, f is the activation function;

[0081] S33 feedback and control dynamically adjusts stirring speed and heating temperature based on model prediction results:

[0082]

[0083]

[0084] Among them, ω model and T model It is a prediction function based on a neural network model, which is used to output the optimal stirring speed and target temperature.

[0085] S4 is cooled to room temperature and the pH value is adjusted to 7-8 to obtain a micro-coating;

[0086] S5 uses machine vision technology to collect images of the paint surface, detects the paint surface quality through deep learning algorithms, and automatically screens out unqualified products.

[0087] In S5, the image recognition model is implemented based on a convolutional neural network, and its basic formula is:

[0088] z (l) =W (l) *a (l-1) +b (l)

[0089] a (l) =f(z (l) )

[0090] Among them, * represents the convolution operation, W (1) is the convolution kernel, a (1-1) is the input feature map, b (1) is the bias term, and f is the activation function.

[0091] The introduction of artificial intelligence algorithms and sensor technology enables real-time monitoring and dynamic optimization of the coating preparation process. By collecting key parameters such as temperature, viscosity, and pH in real time and using a feedforward neural network model for data analysis and prediction, the system can automatically adjust the stirring speed and heating temperature to ensure the stability and consistency of the coating's performance.

[0092] Dynamic adjustment of stirring speed and heating temperature can be accurately controlled according to the actual state of the coating, avoiding parameter fluctuations caused by human factors in traditional processes and improving production efficiency and product quality.

[0093] Machine vision technology is used to detect the surface quality of paint, and a convolutional neural network model is used to analyze the collected images. This can quickly and accurately identify defects on the paint surface, such as particles, bubbles, cracks, etc., and automatically screen out unqualified products, greatly improving the efficiency and accuracy of quality inspection and reducing the defective rate.

[0094] A micro-coating system for coating and sizing thermal sublimation transfer paper comprises the following mechanisms:

[0095] Raw material storage and delivery mechanism: Multiple independent storage tanks are set up to store water-based resin emulsion, inorganic filler, organic modifier, dispersant and water. Each tank is equipped with a liquid level sensor to monitor the raw material inventory in real time. When the raw material level falls below the set value, an alarm is automatically triggered and a notice to refill is issued. The raw materials are accurately delivered to the mixing reactor according to the formula ratio by a metering pump. The delivery pipeline is made of corrosion-resistant materials to ensure that the raw materials are not contaminated during the delivery process. The delivery pipeline is equipped with a flow sensor to monitor the raw material flow in real time to ensure delivery accuracy.

[0096] Mixing reaction mechanism: The mixing reactor has heating and stirring functions. The heating system adopts electric heating or steam heating, which can accurately control the temperature within the range of 60-80°C. The stirring device adopts a variable-speed stirrer, and the stirring speed can be adjusted within the range of 300-500 rpm. The reactor is equipped with a temperature sensor, a viscosity sensor and a pH sensor to collect temperature, viscosity and pH value data in real time, and transmit the data to the control system. Based on the artificial intelligence algorithm and the feedforward neural network model, the data collected by the sensor is received, and after data preprocessing (normalization), the model is used to predict the optimal stirring speed and heating temperature under the current state, and dynamically adjust the stirrer speed and heating system power to ensure the stability and consistency of the coating preparation process. At the same time, the control system also has data storage and analysis functions, which can analyze historical data and optimize model parameters;

[0097] Cooling and pH adjustment mechanism: The paint is cooled to room temperature using a circulating cooling water or air cooling system. During the cooling process, the paint temperature is continuously monitored to ensure that the cooling rate meets the requirements. An automatic acid and alkali adding device is equipped to automatically calculate and add the appropriate amount of acid or alkali solution based on the pH sensor data, accurately adjusting the pH value to 7-8 to ensure stable paint performance.

[0098] Quality inspection agency: High-resolution cameras capture images of the paint surface, and convolutional neural network models analyze and identify defects, automatically screening out unqualified products to ensure that the paint quality meets standards;

[0099] Product Storage and Delivery: Dedicated paint storage tanks are installed to store qualified micro-coating paint. These tanks are equipped with level and temperature sensors to monitor the paint's storage status in real time, ensuring its stability and quality during storage. Unqualified products are transported via dedicated pipelines to a disposal area for re-provisioning or disposal. This process complies with environmental protection requirements and avoids environmental pollution. Qualified micro-coating paint can be transported via pipelines to the sublimation transfer paper coating line or packaged and delivered via packaging equipment. During the delivery process, flow meters and metering pumps ensure accurate paint delivery.

[0100] Preferably, the quality inspection mechanism specifically includes:

[0101] (1) Image acquisition unit:

[0102] High-resolution camera: Installed on the paint delivery pipeline or detection platform, it is used to capture the paint surface image in real time to ensure that the image clarity and resolution meet the detection requirements;

[0103] Light source system: Provides uniform and stable light source to avoid image quality degradation caused by insufficient or uneven light, which affects detection accuracy;

[0104] (2) Image processing unit:

[0105] Image preprocessing unit: performs preprocessing operations on the collected images, including denoising and enhancement to improve image quality and provide clearer images for subsequent analysis;

[0106] Feature extraction unit: uses a convolutional neural network model to extract key features from the image, including particle distribution, texture, and defect shape, providing basic data for defect identification;

[0107] (3) Defect detection unit:

[0108] Deep learning algorithm unit: Based on the pre-trained convolutional neural network model, it analyzes the extracted features, automatically identifies defects such as uneven particles, bubbles, and cracks on the coating surface, and determines the location and type of the defects;

[0109] Defect classification unit: Based on the identification results, the defects are classified into different categories, including minor defects and major defects, to provide a basis for subsequent processing;

[0110] (4) Quality judgment and feedback unit:

[0111] Quality judgment unit: judges the test results according to the preset quality standards to determine whether the coating is qualified. For unqualified products, it automatically issues an alarm and marks them;

[0112] Feedback and recording unit: Feedback the test results and judgment information to the control system, and record the test data and images for subsequent analysis and tracing.

[0113] The present invention achieves the combined advantages of high performance and efficient production by optimizing the coating formula and introducing an intelligent preparation process. The rationally proportioned aqueous resin emulsion, inorganic filler, organic modifier and dispersant in the coating formula enable it to have excellent film-forming properties, adhesion, wear resistance and ink absorption, while taking into account both cost and performance. The intelligent preparation process, combined with artificial intelligence algorithms and sensor technology, realizes real-time monitoring and dynamic optimization of the production process, ensures the stability and consistency of coating performance, and improves production efficiency and quality control levels. Its water-based system and intelligent production method also meet the requirements of environmental protection and sustainable development, reducing production costs and energy consumption. It not only improves the performance and quality of thermal sublimation transfer paper, but also brings significant economic benefits and market competitiveness to enterprises, and promotes technological progress and industrial upgrading in related industries.

[0114] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A micro-coating coating for coating and sizing of thermal sublimation transfer paper, characterized in that: The micro-coating comprises the following components: 50-70% water-based resin emulsion; 10-20% inorganic filler; 5-15% organic modifier; 1-5% dispersant; the balance is water; The aqueous resin emulsion is selected from acrylic resin emulsion, polyurethane resin emulsion or a mixture thereof; The inorganic filler is selected from calcium carbonate, talc, kaolin or a mixture thereof.

2. The micro-coating coating for coating and sizing of thermal sublimation transfer paper according to claim 1, characterized in that: The organic modifier is selected from polyvinyl alcohol, polyethylene glycol or a mixture thereof.

3. The micro-coating coating for coating and sizing of thermal sublimation transfer paper according to claim 1, characterized in that: The dispersant is selected from polyphosphates, polycarboxylates or mixtures thereof.

4. A method for preparing a micro-coating for coating and sizing of thermal sublimation transfer paper according to any one of claims 1 to 3, characterized in that: The following steps are involved: S1: mixing water-based resin emulsion, inorganic filler, organic modifier and dispersant in proportion; S2. Heat the mixture to 60-80°C under stirring and stir for 30-60 minutes; S3 uses sensors to collect real-time data on temperature, viscosity, and pH, and dynamically adjusts stirring speed and heating temperature through artificial intelligence algorithms; S4 is cooled to room temperature and the pH value is adjusted to 7-8 to obtain a micro-coating; S5 uses machine vision technology to collect images of the paint surface, detects the paint surface quality through deep learning algorithms, and automatically screens out unqualified products.

5. The method for preparing the micro-coating for coating and sizing of thermal sublimation transfer paper according to claim 4, characterized in that: The stirring speed is 300-500 rpm.

6. The method for preparing the micro-coating for coating and sizing of thermal sublimation transfer paper according to claim 4, characterized in that: The S3 specifically includes the following steps: S31 data preprocessing normalizes the collected sensor data to eliminate dimensional differences: in, represents the normalized temperature value, T(t) represents the original temperature value, T min， T max are the minimum and maximum temperatures, represents the normalized viscosity value, η(t) represents the original viscosity value, η min , η max are the minimum and maximum values ​​of viscosity, represents the normalized pH value, pH(t) represents the original pH value, and pH min , pH max are the minimum and maximum pH values; S32 model prediction and dynamic adjustment uses a pre-trained feedforward neural network to process the collected normalized data and predict the optimal stirring speed ω(t) and heating temperature Ttarget(t) under the current state: z (l) =W (l) a (l-1) +b (l) a (l) =f(z (l) ) Among them, z (l) is the linear combination of the lth layer, W (l) is the weight matrix, a (l-1) is the activation value of the previous layer, b (l) is the bias term, f is the activation function; S33 feedback and control dynamically adjusts stirring speed and heating temperature based on model prediction results: Among them, ω model and T model It is a prediction function based on a neural network model, which is used to output the optimal stirring speed and target temperature.

7. The method for preparing the micro-coating for coating and sizing of thermal sublimation transfer paper according to claim 4, characterized in that: In S5, the image recognition model is implemented based on a convolutional neural network, and its basic formula is: z (l) =W (l) *a (l-1) +b (l) a (l) =f(z (l) ) Among them, * represents the convolution operation, W (l) is the convolution kernel, a (l-1) is the input feature map, b (l) is the bias term, and f is the activation function.

8. A micro-coating system for coating and sizing thermal sublimation transfer paper according to any one of claims 1 to 7, characterized in that: include: Raw material storage and delivery mechanism: multiple storage tanks are set up to store raw materials, equipped with liquid level sensors to monitor the inventory, and accurately delivered to the mixing reactor according to the formula ratio through metering pumps. Flow sensors monitor in real time to ensure delivery accuracy; Mixing reaction mechanism: The mixing reactor has heating and stirring functions. Temperature, viscosity, and pH sensors collect data in real time. The AI ​​algorithm dynamically adjusts the stirring speed and heating temperature to ensure uniform mixing of the coating. Cooling and pH adjustment mechanism: A circulating cooling water or air cooling system is used to cool the paint to room temperature. The automatic acid and alkali adding device accurately adjusts the pH value to 7-8 according to the pH sensor data to ensure stable paint performance. Quality inspection agency: High-resolution cameras capture images of the paint surface, and convolutional neural network models analyze and identify defects, automatically screening out unqualified products to ensure that the paint quality meets standards; Product storage and output mechanism: Qualified coatings are stored in dedicated tanks, and liquid level and temperature sensors monitor the storage status in real time; unqualified products are transported to the processing area for re-adjustment or disposal, and qualified coatings are transported to the coating line or packaged for output as needed.

9. A micro-coating system for coating and sizing thermal sublimation transfer paper according to claim 8, characterized in that: The quality inspection agencies specifically include: (1) Image acquisition unit: High-resolution camera: Installed on the paint delivery pipeline or detection platform, it is used to capture the paint surface image in real time to ensure that the image clarity and resolution meet the detection requirements; Light source system: Provides uniform and stable light source to avoid image quality degradation caused by insufficient or uneven light, which affects detection accuracy; (2) Image processing unit: Image preprocessing unit: performs preprocessing operations on the collected images, including denoising and enhancement to improve image quality and provide clearer images for subsequent analysis; Feature extraction unit: uses a convolutional neural network model to extract key features from the image, including particle distribution, texture, and defect shape, providing basic data for defect identification; (3) Defect detection unit: Deep learning algorithm unit: Based on the pre-trained convolutional neural network model, it analyzes the extracted features, automatically identifies defects such as uneven particles, bubbles, and cracks on the coating surface, and determines the location and type of the defects; Defect classification unit: Based on the identification results, the defects are classified into different categories, including minor defects and major defects, to provide a basis for subsequent processing; (4) Quality judgment and feedback unit: Quality judgment unit: judges the test results according to the preset quality standards to determine whether the coating is qualified. For unqualified products, it automatically issues an alarm and marks them; Feedback and recording unit: Feedback the test results and judgment information to the control system, and record the test data and images for subsequent analysis and tracing.

Images