One-component water-based hot-drilling coating

Abstract

The present application relates to the technical field of water-based hot-drilling coatings, and specifically discloses a one-component water-based hot-drilling coating, wherein the one-component water-based hot-drilling coating comprises the following components and their weight percentages: 30-70 parts of a water-based single-liquid o-cresol-formaldehyde epoxy resin dispersion; 5-30 parts of a water-based color paste; 5-45 parts of a filler; 0.5-8 parts of a water-based auxiliary agent; and 5-30 parts of deionized water. When applied, the coating can be cross-linked and cured to form a dense paint film without adding an external curing agent, and has excellent performance. In the process of preparing the water-based single-liquid o-cresol-formaldehyde epoxy resin dispersion, artificial intelligence technology is used to monitor and analyze the epoxy equivalent and reaction temperature of the product in the esterification reaction process in real time, and the adjustment direction of the temperature is intelligently guided based on the time-series correlation response relationship between the two. The coating not only solves the problems of poor adhesion, water resistance, and organic solvent resistance of the existing one-component hot-drilling coating without adding a curing agent, but also realizes real-time control of the reaction process to ensure that the epoxy equivalent meets the requirements.

Description

Technical Field

[0001] The present application relates to the technical field of water-based hot-drilling coatings, and more specifically, to a one-component water-based hot-drilling coating. Background Art

[0002] In the field of home decoration, hot-drilling is often used to enhance the appearance of items, that is, hot-melt adhesive is used to bond the diamond particles to the substrate. First, a pre-treatment coating is formed on the diamond particles with hot-drilling paint to improve adhesion and bonding to ensure the stability and durability of the hot-drilling. Hot-drilling paint is divided into oily and water-based. Oily paint is widely used due to its advantages such as wear resistance and weather resistance, but the volatile organic compounds (VOC) it contains are harmful to the environment and health and require a good ventilation environment. Therefore, the industry is developing water-based hot-drilling paint as an environmentally friendly alternative.

[0003] According to the industry standard T / ZZB 3495-2023, water-based hot-drilling coatings must meet specific performance indicators, such as adhesion requirements ≥10Mpa, cross-cut test (cross-cut spacing 1 mm) ≤0 level, volatile organic compound (VOC) content ≤150 (g / L), and no decrease in adhesion after immersion in organic solvents for more than 4 hours. In order to meet the requirements of the existing water-based hot diamond coating, two-component water-based hot diamond coating must be used. The two-component water-based hot diamond coating refers to a water-based hot diamond coating that contains both water-based resin and external curing agent. The external curing agent can form a cross-linked network structure with the water-based resin to give the coating film-forming properties, form a dense coating, and improve the adhesion between the coating and the substrate. Its characteristics are that it needs to be prepared and used immediately, that is, when used, the curing agent needs to be added and mixed on site to prepare the target coating. Its usable time is only 4-8 hours, and it has the disadvantages of cumbersome construction and a short operating window period. If no external curing agent is added, the existing water-based hot diamond coating cannot form a dense coating with a cross-linked network structure, so that the product is easy to fall off during use. Commonly used curing agents include amino resins and isocyanates, but in actual production, they have problems such as high temperature energy consumption and release of toxic gases that cause harm to the human body and the environment.

[0004] In addition, water-based resins, which are important components in existing water-based coatings, usually rely on artificial experience to control the reaction process during the preparation process, resulting in large fluctuations in resin performance and high instability. For example, o-cresol epoxy resin is a commonly used water-based resin. The phenolic condensation and epoxy group reaction involved in its synthesis process are extremely sensitive to temperature. Any error in temperature control may lead to unnecessary side reactions, affecting the epoxy equivalent of the resin, thereby resulting in poor performance of the resin such as viscosity, curing speed and thermal stability, resulting in uneven coating, difficult to control coating thickness, difficult construction, poor adhesion, poor durability, and increased scrap rate in the coating.

[0005] Therefore, a one-component water-based hot-drilling coating with strong adhesion, good resistance to organic solvents and water resistance, and harmless to the human body and the environment is expected. Summary of the invention

[0006] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a one-component water-based hot-drilling coating, comprising a water-based single-liquid o-cresol epoxy resin dispersion of a specific structure and proportion, synergistically with a water-based color paste, filler, and water-based auxiliary agent in a specific proportion, and can be cross-linked and cured to form a dense paint film without the need for an external curing agent when applied, and has excellent performance. The water-based single-liquid o-cresol epoxy resin dispersion uses artificial intelligence technology to monitor and analyze the epoxy equivalent and reaction temperature of the product in the esterification reaction process in real time during the preparation process, and intelligently guides the adjustment direction of the temperature based on the time-series correlation response relationship between the two, which not only solves the problems of poor adhesion, water resistance, and organic solvent resistance of the existing one-component hot-drilling coating without a curing agent, but also realizes real-time control of the reaction process to ensure that the epoxy equivalent meets the requirements. Therefore, the VOC content of the water-based hot diamond coating prepared in the present application is ≤100g / L, the cross-cut adhesion of the water-based hot diamond coating is 5B or grade 0, the pull-out adhesion is ≥10Mpa, and the pull-out adhesion loss after resistance to organic solvent immersion is ≤5%, which fully meets the performance requirements of the water-based hot diamond coating.

[0007] Accordingly, the present application provides a one-component water-based hot diamond coating, wherein the one-component water-based hot diamond coating comprises the following components and their weight percentages:

[0008] Water-based one-component o-cresol epoxy resin dispersion 30-70

[0009] Water-based color paste 5-30

[0010] Filler 5-45

[0011] Water-based additive 0.5-8

[0012] Deionized water 5-30;

[0013] The water-based single-liquid o-cresol epoxy resin contains 80%-95% of a unidirectional hydrophilic component A and 5%-20% of an internal curing component B. The structural formula of the unidirectional hydrophilic component A is shown in Formula 1.

[0014]

[0015] Formula 1

[0016] Wherein, n is 1-10, and the structural formula of R includes the following two structures:

[0017] , , ,

[0018] Formula 2

[0019] In formula 2, R 1 , R 2 A hydrocarbon structure having 1 to 20 carbon atoms, wherein the hydrocarbon structure is selected from a mixture of one or more saturated hydrocarbons or unsaturated hydrocarbon structures such as straight-chain aliphatic alkanes, branched-chain aliphatic alkanes, cyclic alkanes, olefins, aromatic hydrocarbons, etc.;

[0020] R 3 NHR 4 R 5 R 6 ]+ cationic group, where R 4 , R 5 , R 6 Can be independently selected from H, CH 3 , C 2 H 5 , C 3 H 7 , C 2 H 4 One or more combinations of OH;

[0021] The epoxy equivalent weight (EEW) of the one-way hydrophilic component A is greater than 10,000; the solid acid value of the one-way hydrophilic component A is 48-52 mgKOH / g; the neutralization degree of the one-way hydrophilic component A is 65% to 95%;

[0022] The structural formula of the internal curing component B is shown in Formula 3:

[0023]

[0024] Formula 3

[0025] Where n is 1-10.

[0026] According to another aspect of the present application, in the one-component water-based hot diamond coating, the filler may be an organic filler (such as cellulose, lignin, etc.), an inorganic non-metallic filler (such as calcium carbonate, talc, mica, titanium dioxide), or a metal filler (such as aluminum foil powder, metal copper powder, etc.);

[0027] According to another aspect of the present application, in the one-component water-based hot diamond coating, the water-based color paste can be a water-based resin-free color paste or a water-based carrier resin co-grinding color paste, and the color category is not limited;

[0028] According to another aspect of the present application, in the one-component water-based hot-drilling coating, the water-based additive can be a water-based defoamer, a water-based wetting agent, a water-based leveling agent, a water-based bactericide, a water-based mildewproof agent, a water-based anti-rust agent, a water-based thickener, a water-based anti-sagging agent, a water-based dispersant, a water-based film-forming agent, a water-based drying agent, a water-based drying agent, a water-based anti-skinning agent, a water-based matting agent, a water-based light stabilizer, a water-based antistatic agent, a water-based adhesion promoter, a water-based anti-floating color and floating additive, etc.

[0029] According to another aspect of the present application, the cross-cut adhesion of the one-component water-based hot diamond coating is 5B or level 0, and the pull-off adhesion is ≥10 MPa.

[0030] According to another aspect of the present application, the VOC content of the one-component water-based hot diamond coating is ≤100 g / L.

[0031] According to another aspect of the present application, the preparation method of the aqueous single-liquid o-cresol epoxy resin dispersion comprises: step 1: adding o-cresol epoxy resin and a co-solvent into a glass reaction bottle, and heating the o-cresol epoxy resin so that the o-cresol epoxy resin is completely dissolved to obtain an o-cresol epoxy resin solution; step 2: adding a monobasic acid and a catalyst into the o-cresol epoxy resin solution, and controlling the reaction temperature by a temperature controller until the reaction is completed when the epoxy equivalent EEW is greater than 10000 to obtain a first reaction solution; step 3: adding anhydride into the first reaction solution to adjust the acidity of the first reaction solution. When the value reaches 48mgKOH / g-52mgKOH / g, the reaction is terminated to obtain a second reaction liquid; step 4: adding a volatile amine neutralizer and the o-cresol epoxy resin to the second reaction liquid to obtain the aqueous single-liquid o-cresol epoxy resin; step 5: adding deionized water to the aqueous single-liquid o-cresol epoxy resin at a uniform rate of 6-14g / min, the weight ratio of the aqueous single-liquid o-cresol epoxy resin to deionized water is 1:0.85-1:1.15, and emulsifying is carried out with high-speed stirring to obtain the aqueous single-liquid o-cresol epoxy resin dispersion.

[0032] In the preparation method of the above-mentioned aqueous single-liquid o-cresol epoxy resin dispersion, the cosolvent is selected from any one or more of ethylene glycol butyl ether, diethylene glycol butyl ether, diethylene glycol dimethyl ether, dipropylene glycol dimethyl ether, propylene glycol methyl ether, dipropylene glycol methyl ether, and dipropylene glycol butyl ether.

[0033] In the preparation method of the above-mentioned aqueous single-liquid o-cresol epoxy resin dispersion, the o-cresol epoxy resin is selected from any one of Nan Ya NPCN704, Changchun CNE202, Shengquan SQCN704M, and Aimonte EMTER638S.

[0034] In the preparation method of the above-mentioned water-based single-liquid o-cresol epoxy resin dispersion, the unit acid is selected from any one of formic acid, acetic acid, coconut oleic acid, isooctanoic acid, isononanoic acid, soybean oil fatty acid, stearic acid, lauric acid, linoleic acid, ricinoleic acid, eleostearic acid, benzoic acid, acrylic acid, and methacrylic acid; and the catalyst is selected from any one of tetraethylammonium bromide, tetraethylammonium chloride, tetraethylammonium hydroxide, benzyltriethylammonium chloride, triphenylphosphine, and triethylamine.

[0035] In the preparation method of the above-mentioned aqueous single-liquid o-cresol epoxy resin dispersion, the acid anhydride is selected from any one of acetic anhydride, benzoic anhydride, phthalic anhydride, tetrahydrophthalic anhydride, hexahydrophthalic anhydride, trimellitic anhydride and maleic anhydride.

[0036] In the preparation method of the above-mentioned aqueous single-liquid o-cresol epoxy resin dispersion, the neutralizing agent is selected from any one of triethylamine, ammonia water, N,N-dimethylethanolamine, and 2-amino-2-methyl-1-propanol.

[0037] In the preparation method of the above-mentioned water-based single-liquid o-cresol-formaldehyde epoxy resin dispersion, the step 2 includes: obtaining the epoxy equivalent of the first reaction liquid at multiple sampling points by a sampling method; collecting the reaction temperature values ​​of the multiple sampling points by a temperature sensor; arranging the epoxy equivalent of the first reaction liquid at the multiple sampling points and the reaction temperature values ​​of the multiple sampling points into an epoxy equivalent time series input vector and a reaction temperature time series input vector according to the time dimension; linearly interpolating the epoxy equivalent time series input vector and the reaction temperature time series input vector to obtain an epoxy equivalent time series linear interpolation input vector and a reaction temperature time series linear interpolation input vector; dividing the epoxy equivalent time series linear interpolation input vector and the reaction temperature time series linear interpolation input vector according to a predetermined time scale and inputting them into a time series encoder based on a 1D-CNN model to obtain an epoxy equivalent local time series correlation feature vector and a sequence of local timing association feature vectors of reaction temperature; inputting each group of corresponding epoxy equivalent local timing association feature vectors and reaction temperature local timing association feature vectors of the sequence of epoxy equivalent local timing association feature vectors and the sequence of reaction temperature local timing association feature vectors into a feature fine-grained association distinction significant fusion module to obtain a sequence of reaction temperature-epoxy equivalent local timing response interaction feature vectors; inputting the sequence of reaction temperature-epoxy equivalent local timing response interaction feature vectors into a node feature propagation network guided by energy timing decay to obtain a reaction temperature-epoxy equivalent timing interaction propagation aggregation representation vector; inputting the reaction temperature-epoxy equivalent timing interaction propagation aggregation representation vector into a reaction temperature controller based on a classifier to obtain a control instruction, wherein the control instruction is used to indicate whether the reaction temperature value at the current time point should increase, decrease or remain unchanged.

[0038] In the preparation method of the above-mentioned water-based single-liquid o-cresol-formaldehyde epoxy resin dispersion, the sequence of the epoxy equivalent local time series correlation feature vectors and the sequence of the reaction temperature local time series correlation feature vectors are input into the feature fine-grained correlation distinction significant fusion module to obtain a sequence of reaction temperature-epoxy equivalent local time series response interaction feature vectors, including: calculating the global eigenvalue association matrix between the epoxy equivalent local time series correlation feature vectors and the corresponding reaction temperature local time series correlation feature vectors; the global eigenvalue association matrix is ​​converted into the global eigenvalue association matrix. A matrix input learnable gating function is used to obtain a correlation distinguishable weight matrix; the correlation distinguishable weight matrix is ​​used as a fusion mask matrix, and the matrix products of the epoxy equivalent local timing association feature vector, the reaction temperature local timing association feature vector and the fusion mask matrix are respectively calculated to obtain a distinguished and enhanced epoxy equivalent local timing association feature vector and a distinguished and enhanced reaction temperature local timing association feature vector; the distinguished and enhanced epoxy equivalent local timing association feature vector and the distinguished and enhanced reaction temperature local timing association feature vector are fused to obtain the reaction temperature-epoxy equivalent local timing response interaction feature vector.

[0039] In the preparation method of the above-mentioned water-based single-liquid o-cresol-formaldehyde epoxy resin dispersion, the sequence of the reaction temperature-epoxy equivalent local time series response interactive feature vectors is input into the node feature propagation network guided by energy time series attenuation to obtain the reaction temperature-epoxy equivalent time series interactive propagation polymerization representation vector, including: based on the maximum value, average value and variance of each reaction temperature-epoxy equivalent local time series response interactive feature vector in the sequence of the reaction temperature-epoxy equivalent local time series response interactive feature vector, the node energy statistical range of each reaction temperature-epoxy equivalent local time series response interactive feature vector is calculated. The node energy statistical paradigm value is obtained by using the node energy statistical paradigm value corresponding to the current reaction temperature-epoxy equivalent local timing response interaction characteristic vector in the sequence of the node energy statistical paradigm value as the current node energy statistical paradigm value, and the other node energy statistical paradigm values ​​are used as the historical node energy statistical paradigm values ​​to obtain a sequence of the current node energy statistical paradigm value and the historical node energy statistical paradigm value; and each other reaction temperature-epoxy equivalent local timing response interaction characteristic vector in the sequence of the reaction temperature-epoxy equivalent local timing response interaction characteristic vector and the current node energy statistical paradigm value are statistically compared. The node propagation space span values ​​between the temperature-epoxy equivalent local timing response interaction feature vectors are calculated to obtain a sequence of node propagation space span values; a preset attenuation constant is used as a weight to calculate the weighted sum of each node propagation space span value in the sequence of node propagation space span values ​​and its own exponential function value with the natural constant as the base to obtain a sequence of space span attenuation factors; the corresponding division results of each historical node energy statistical paradigm value in the sequence of historical node energy statistical paradigm values ​​and each space span attenuation factor in the sequence of space span attenuation factors are calculated to obtain a node energy propagation attenuation factor. A sequence of numerical values; using the sequence of node energy propagation attenuation coefficient values ​​as a weight sequence, calculating the weighted sum of all other reaction temperature-epoxy equivalent local timing response interaction feature vectors in the sequence of reaction temperature-epoxy equivalent local timing response interaction feature vectors to obtain a historical node energy decay timing aggregate feature vector; fusing the current node energy statistical paradigm value to calculate the weighted sum of the historical node energy decay timing aggregate feature vector and the current reaction temperature-epoxy equivalent local timing response interaction feature vector to obtain the reaction temperature-epoxy equivalent timing interaction propagation aggregate representation vector.

[0040] Compared with the prior art, the one-component water-based hot-drilling coating provided by the present application has long-term stability, does not shorten the operating window of the coating, is harmless to the human body and the environment, can be cross-linked and cured to form a dense paint film without adding an external curing agent when used, has excellent adhesion, water resistance, and organic solvent resistance, solves the problems of poor adhesion, water resistance, and organic solvent resistance of the existing one-component hot-drilling coating without adding a curing agent, and solves the problems of short operating window, high energy consumption for high-temperature curing, release of toxic gases, and harm to the human body and the environment caused by the existing two-component hot-drilling coating with an external curing agent. Therefore, the VOC content of the water-based hot-drilling coating prepared by the present application is ≤100g / L, the cross-cut adhesion of the water-based hot-drilling coating is 5B or level 0, the pull-out adhesion is ≥10Mpa, and the pull-out adhesion loss after organic solvent immersion is ≤5%, which fully meets the performance requirements of water-based hot-drilling coating.

[0041] In addition, in the one-component water-based hot-drilling coating, the water-based one-liquid o-cresol-formaldehyde epoxy resin dispersion comprises a one-way hydrophilic component A and an internal curing component B, the one-way hydrophilic component A has a reversible ionic hydrophilic chain segment of a carboxylic acid anion and an amine cation, the internal curing component B has long-term storage stability, can be cross-linked and cured to form a dense paint film without adding an external curing agent when used, and has excellent performance. In the preparation process, artificial intelligence technology is used to monitor and analyze the epoxy equivalent and reaction temperature of the product in the esterification reaction process in real time, and the adjustment direction of the temperature is intelligently guided based on the time-series correlation response relationship between the two, which not only solves the problem of poor adhesion, water resistance, and organic solvent resistance of the existing one-component water-based hot-drilling coating without adding a curing agent, but also realizes real-time control of the reaction process, ensures that the epoxy equivalent meets the requirements, ensures accurate control of the reaction degree of the water-based one-liquid o-cresol-formaldehyde epoxy resin dispersion, and ensures that it has excellent and stable performance when used in the one-component water-based hot-drilling coating. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0043] Figure 1 The present invention is a flow chart of a method for preparing a one-component water-based hot-drilling coating using a water-based one-liquid o-cresol-formaldehyde epoxy resin dispersion according to an embodiment of the present application.

[0044] Figure 2 This is a flow chart of step 2 in the method for preparing a one-component water-based hot-drilling coating using a water-based one-liquid o-cresol-formaldehyde epoxy resin according to an embodiment of the present application. DETAILED DESCRIPTION

[0045] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0046] In view of the above technical problems, the present application provides a one-component water-based hot diamond coating, wherein the one-component water-based hot diamond coating comprises the following components and their weight percentages:

[0047] Water-based one-component o-cresol epoxy resin dispersion 30-70

[0048] Water-based color paste 5-30

[0049] Filler 5-45

[0050] Water-based additives 0.5-8

[0051] Deionized water 5-30;

[0052] The water-based single-liquid o-cresol epoxy resin comprises a unidirectional hydrophilic component A and an internal curing component B of a specific structure and ratio, wherein the unidirectional hydrophilic component A has a reversible ionic hydrophilic chain segment of a carboxylic acid anion and an amine cation, and the internal curing component B has long-term storage stability, and is applied to water-based hot-drilling coatings without the need for an external curing agent, and the internal curing component B does not shorten the operating window period of the coating and is harmless to the human body and the environment, and the reversible ionic hydrophilic chain segment in the unidirectional hydrophilic component A is reversibly converted into a carboxyl group and interacts with the internal curing component B, so that cross-linking and curing can be performed to form a dense paint film, which has excellent adhesion, water resistance, and organic solvent resistance, thereby solving the problems of poor adhesion, water resistance, and organic solvent resistance of existing one-component hot-drilling coatings without a curing agent, and solving the problems of short operating window period, high energy consumption for high-temperature curing, release of toxic gases, and harm to the human body and the environment caused by the external curing agent of the existing two-component hot-drilling coating. The single-liquid type means that it is supplied in a single-component form and contains an internal curing component, and the internal curing component refers to a latent curing component (or inert curing component) with long-term storage stability. The latent curing component described in this application refers to o-cresol epoxy resin. The one-way hydrophilicity means that in the process of the reversible ionic hydrophilic chain forming a paint film, the amine cation and the carboxylic acid anion dissociate, and the amine neutralizer evaporates with the water so that component A no longer has secondary water solubility (i.e., hydrophilic irreversibility).

[0053] Specifically, the water-based single-liquid o-cresol epoxy resin contains 80%-95% of a unidirectional hydrophilic component A and 5%-20% of an internal curing component B. The structural formula of the unidirectional hydrophilic component A is shown in Formula 1.

[0054]

[0055] Formula 1

[0056] Wherein, n is 1-10; the structural formula of R includes the following two structures:

[0057] , , ,

[0058] Formula 2:

[0059] In formula 2, R 1 , R 2 is selected from a hydrocarbon structure having 1 to 20 carbon atoms, wherein the hydrocarbon structure is selected from a mixture of one or more saturated hydrocarbons or unsaturated hydrocarbon structures such as straight-chain aliphatic alkanes, branched-chain aliphatic alkanes, cyclic alkanes, olefins, aromatic hydrocarbons, etc.; R 3 NHR 4 R 5 R 6 ] + Cationic group, where R 4 , R 5 , R 6 Can be independently selected from H, CH 3 , C 2 H 5 , C 3 H 7 , C 2 H 4 One or more combinations of OH. The epoxy equivalent EEW of the one-way hydrophilic component A is greater than 10000; the solid acid value of the one-way hydrophilic component A is 48-52 mgKOH / g, indicating that 48-52 mg of potassium hydroxide is required to neutralize 1 g of the acidic substance in the one-way hydrophilic component A; the neutralization degree of the one-way hydrophilic component A is 65% to 95%, and the neutralization degree refers to the proportion of carboxyl groups in the one-way hydrophilic component A that are neutralized into salts by amine neutralizers.

[0060] In one embodiment of the present invention, in the one-component water-based hot diamond coating, the filler may be an organic filler (such as cellulose, lignin, etc.), an inorganic non-metallic filler (such as calcium carbonate, talc, mica, titanium dioxide), or a metal filler (such as aluminum foil powder, metal copper powder, etc.);

[0061] In one embodiment of the present invention, in the one-component water-based hot diamond coating, the water-based color paste can be a water-based resin-free color paste or a water-based carrier resin co-grinding color paste, and the color category is not limited;

[0062] In one embodiment of the present invention, in the one-component water-based hot-drilling paint, the water-based additive can be a water-based defoamer, a water-based wetting agent, a water-based leveling agent, a water-based bactericide, a water-based mildewproof agent, a water-based anti-rust agent, a water-based thickener, a water-based anti-sagging agent, a water-based dispersant, a water-based film-forming agent, a water-based drying agent, a water-based drying agent, a water-based anti-skinning agent, a water-based matting agent, a water-based light stabilizer, a water-based antistatic agent, a water-based adhesion promoter, a water-based anti-floating color and floating additive, etc.

[0063] Figure 1 Flow chart of the preparation method of the aqueous single-liquid o-cresol epoxy resin dispersion according to the embodiment of the present application. Figure 1 As shown, the preparation method of the aqueous single-liquid o-cresol epoxy resin dispersion comprises: step 1: adding o-cresol epoxy resin and a co-solvent into a glass reaction bottle, and heating the o-cresol epoxy resin to completely dissolve the o-cresol epoxy resin to obtain an o-cresol epoxy resin solution; step 2: adding a monobasic acid and a catalyst into the o-cresol epoxy resin solution, and controlling the reaction temperature by a temperature controller until the reaction is completed when the epoxy equivalent EEW is greater than 10000 to obtain a first reaction liquid; step 3: adding anhydride into the first reaction liquid to adjust the acid value of the first reaction liquid to 48m gKOH / g-52mgKOH / g, the reaction is terminated to obtain a second reaction liquid; step 4: adding a volatile amine neutralizer and the o-cresol epoxy resin to the second reaction liquid to obtain the water-based single-liquid o-cresol epoxy resin; step 5: adding deionized water to the water-based single-liquid o-cresol epoxy resin at a uniform rate of 6-14g / min, the weight ratio of the water-based single-liquid o-cresol epoxy resin to deionized water is 1:0.85-1:1.15, and emulsifying is carried out by high-speed stirring to obtain the water-based single-liquid o-cresol epoxy resin dispersion.

[0064] More specifically, during the entire reaction process, high-purity nitrogen is continuously introduced into the portion above the liquid phase, specifically including:

[0065] At room temperature, add 4 to 8 parts of co-solvent and 15 to 20 parts of o-cresol epoxy resin, and raise the temperature to completely dissolve the o-cresol epoxy resin.

[0066] Add mono-acid according to the molar ratio of o-cresol epoxy resin to mono-acid of 1:0.99, 0.05-0.15 parts of catalyst, the reaction temperature is 90-120°C, and the reaction is completed when the epoxy equivalent weight EEW>10000.

[0067] Acid anhydride is added at a molar ratio of o-cresol epoxy resin to acid anhydride of 1:0.65-1:0.85, the reaction temperature is 80-120°C, and the reaction is completed when the acid value decreases to 48-52 mgKOH / g.

[0068] Add 4 to 8 parts of co-solvent, cool to below 40°C, add volatile amine neutralizer at a molar ratio of acid anhydride to neutralizer of 1:0.65 to 1:0.95, react for 5-10 minutes, add 3 to 8 parts of o-cresol epoxy resin and dissolve completely to obtain the water-based single-liquid o-cresol epoxy resin.

[0069] Preferably, in step 1, the temperature is raised to 60-90°C to completely dissolve the o-cresol-formaldehyde epoxy resin; more preferably, the temperature is raised to 80°C.

[0070] Preferably, in steps 1 and 4, the co-solvent refers to an organic solvent having hydrophilicity and a boiling point ≥120°C; more preferably, the co-solvent is selected from any one or more of ethylene glycol butyl ether, diethylene glycol butyl ether, diethylene glycol dimethyl ether, dipropylene glycol dimethyl ether, propylene glycol methyl ether, dipropylene glycol methyl ether, and dipropylene glycol butyl ether.

[0071] Preferably, in step 1, the o-cresol-formaldehyde epoxy resin is selected from any one of Nan Ya NPCN704, Changchun CNE202, Shengquan SQCN704M, and Emter EMTER638S.

[0072] Preferably, in step 1, the number of added co-solvents is 4 to 6.

[0073] Preferably, in step 1, the amount of o-cresol-formaldehyde epoxy resin added is 15 to 17 parts.

[0074] Preferably, in step 2, the unit acid refers to a saturated or unsaturated organic acid having ≤20 carbon atoms; the unit acid is selected from any one of formic acid, acetic acid, coconut oleic acid, isooctanoic acid, isononanoic acid, soybean oil fatty acid, stearic acid, lauric acid, linoleic acid, ricinoleic acid, elaeolic acid, benzoic acid, acrylic acid, and methacrylic acid.

[0075] Preferably, in step 2, the catalyst is selected from any one of tetraethylammonium bromide, tetraethylammonium chloride, tetraethylammonium hydroxide, benzyltriethylammonium chloride, triphenylphosphine and triethylamine.

[0076] Preferably, in step 2, the reaction temperature is 110°C.

[0077] Preferably, in step 2, the reaction time is 8-16 hours; more preferably, the reaction time is 10-12 hours.

[0078] Preferably, in step 3, the acid anhydride is selected from any one of acetic anhydride, benzoic anhydride, phthalic anhydride, tetrahydrophthalic anhydride, hexahydrophthalic anhydride, trimellitic anhydride, and maleic anhydride.

[0079] Preferably, in step 3, the reaction temperature is 100°C.

[0080] Preferably, in step 3, the reaction time is 3-6 hours; more preferably, the reaction time is 4 hours.

[0081] Preferably, in step 4, the neutralizing agent is selected from any one of triethylamine, aqueous ammonia, N,N-dimethylethanolamine and 2-amino-2-methyl-1-propanol; more preferably, the neutralizing agent is triethylamine.

[0082] Preferably, in step 4, the molar ratio of the acid anhydride to the amine neutralizing agent is 1:0.65 to 1:0.75.

[0083] Preferably, in step 5, the dripping rate of deionized water is 10 g / min.

[0084] Preferably, in step 5, the weight ratio of the aqueous one-liquid o-cresol epoxy resin to deionized water is 1:1.

[0085] Preferably, step 5 further includes the step of filtering the mixed solution through a 1-10 μm filter element after emulsification is completed; more preferably, the filter element is 1 μm.

[0086] The detection method of this application is as follows:

[0087] Number average molecular weight test method: GB / T 36214.4-2018 Plastics size exclusion chromatography for the determination of average molecular weight and molecular weight distribution of polymers Part 4: High temperature method;

[0088] Epoxy equivalent test method: GB / T 4612-2008 Determination of epoxy equivalent of plastic epoxy compounds;

[0089] Acid value test method: GB / T 2895-2008 Determination of partial acid value and total acid value of plastic polyester resin;

[0090] Pull-off adhesion: Tested by the pull-off method in GB / T 5210 Determination of coating adhesion;

[0091] Cross-cut adhesion: Tested using the cross-cut test of paint and varnish films in GB / T 9286;

[0092] Resistance to organic solvents: Under normal temperature of 25°C, completely immersed in tetrachloroethylene solvent for dry cleaning for 1 hour.

[0093] Volatile organic compound (VOC) content: tested according to the provisions of 6.2.1.2 of GB 30981-2020 Limits of Hazardous Substances in Industrial Protective Coatings;

[0094] Water resistance: According to the provisions of 9.1 of GB / T 1733-1993, the test plate is immersed in the third-grade water that meets the requirements of GB / T 6682 for the specified time. Take out the sample and observe.

[0095] Salt spray resistance: According to the provisions of GB / T 1771-2007 Determination of neutral salt spray resistance of paints and varnishes.

[0096] The VOC content of the water-based hot diamond coating prepared in the present application is ≤100g / L, the cross-cut adhesion of the water-based hot diamond coating is 5B or grade 0, the pull-out adhesion is ≥10Mpa, and the pull-out adhesion loss after resistance to organic solvent immersion is ≤5%, which fully meets the performance requirements of the water-based hot diamond coating.

[0097] Example 1

[0098] Preparation of water-based one-component o-cresol epoxy resin dispersion for one-component water-based hot-drilling coating:

[0099] In a 1000ml straight four-necked glass reaction bottle equipped with a 0-200℃ digital thermometer, a variable frequency stirrer, a 316 stainless steel stirring paddle, a simple condensation tower, and a high-purity nitrogen injection device, high-purity nitrogen is continuously introduced into the part above the liquid phase during the whole reaction process, and 50g of propylene glycol butyl ether cosolvent and 200g of SQCN704H solid epoxy resin are added in sequence under room temperature and static conditions, and the temperature is raised to 80℃ to melt the material and dissolve it completely;

[0100] Add 115.14g benzoic acid and 1.1g triphenylphosphine catalyst, heat to 100℃ and react for 12 hours, then take a sample to test the epoxy equivalent (EEW>10000 is considered qualified);

[0101] Add 102.77g hexahydrophthalic anhydride and continue to react at 100℃ for 4 hours until the acid value drops to 48-52mgKOH / g, which is considered acceptable.

[0102] Add 50g of propylene glycol methyl ether as a cosolvent and cool to below 40°C, add 57.34g of triethylamine as a neutralizer, react for 10 minutes, then add 50g of SQCN704H solid epoxy resin, and after uniform dissolution, obtain a water-based single-liquid o-cresol epoxy resin;

[0103] In a high-speed dispersion reactor equipped with an efficient cooling system, 625.25 g of water-based single-liquid o-cresol epoxy resin was added, high-speed stirring was started, and 544.53 g of deionized water was uniformly added dropwise into the reactor (the dropping rate was 10 g / min). After emulsification was completed, the mixed liquid was filtered through a 1 μm filter element to obtain a water-based single-liquid o-cresol epoxy resin dispersion.

[0104] The performance test results of the obtained water-based single-liquid o-cresol epoxy resin are as follows:

[0105] Table 1 Performance parameters of water-based single-liquid o-cresol epoxy resin

[0106]

[0107] Example 2

[0108] The aqueous one-liquid o-cresol epoxy resin dispersion prepared in Example 1 was used to prepare a one-component aqueous hot-drilling coating, which contained the following components and their weight percentages: 60 of aqueous one-liquid o-cresol epoxy resin dispersion; 5 of aqueous color paste; 35 of filler; 1 of aqueous auxiliary agent; and 30 of deionized water.

[0109] Table 2 Performance parameters of one-component water-based hot-drilling coating

[0110]

[0111] Example 3

[0112] As mentioned in the above-mentioned background technology, in the esterification process of the unit acid of step 2 and o-cresol epoxy resin, it is necessary to reasonably control the reaction temperature to ensure that the esterification reaction is fully carried out, so as to improve the epoxide equivalent of resin. However, in the existing water-based resin preparation process, it is usually dependent on artificial experience to regulate reaction parameters, which is not only inefficient, but also highly subjective, and it is difficult to ensure the consistency and reproducibility of the reaction. In view of the above-mentioned technical problems, the technical conception of the present application is to use the artificial intelligence technology based on deep learning to carry out real-time monitoring and data analysis on the epoxide equivalent and reaction temperature of the product in the esterification process of step 2, respectively capture the time-series variation characteristics of epoxide equivalent and reaction temperature, and then based on the time-series correlation response relationship between the two, guide the adjustment direction of reaction temperature. In this way, real-time control of the esterification process can be achieved, ensuring that the epoxide equivalent of resin is stabilized within the target range, so as to improve the stability and consistency of resin performance.

[0113] Figure 2 Flow chart of the preparation method of water-based single-liquid o-cresol epoxy resin according to an embodiment of the present application. Figure 2As shown, step 2 includes the following steps: S110, obtaining the epoxy equivalent of the first reaction liquid at multiple sampling points by a sampling method; S120, collecting the reaction temperature values ​​of the multiple sampling points by a temperature sensor; S130, arranging the epoxy equivalent of the first reaction liquid at the multiple sampling points and the reaction temperature values ​​of the multiple sampling points into an epoxy equivalent time series input vector and a reaction temperature time series input vector according to the time dimension; S140, linearly interpolating the epoxy equivalent time series input vector and the reaction temperature time series input vector to obtain an epoxy equivalent time series linear interpolation input vector and a reaction temperature time series linear interpolation input vector; S150, dividing the epoxy equivalent time series linear interpolation input vector and the reaction temperature time series linear interpolation input vector according to a predetermined time scale and inputting them into a time series encoder based on a 1D-CNN model respectively to obtain a sequence and an inverse of the epoxy equivalent local time series correlation feature vector. The sequence of local timing-related feature vectors of the temperature should be obtained; S160, each group of corresponding epoxy equivalent local timing-related feature vectors and reaction temperature local timing-related feature vectors of the sequence of epoxy equivalent local timing-related feature vectors and the sequence of reaction temperature local timing-related feature vectors are input into the feature fine-grained association distinction significant fusion module to obtain a sequence of reaction temperature-epoxy equivalent local timing response interaction feature vectors; S170, the sequence of reaction temperature-epoxy equivalent local timing response interaction feature vectors is input into the node feature propagation network guided by energy timing attenuation to obtain a reaction temperature-epoxy equivalent timing interaction propagation aggregation representation vector; S180, the reaction temperature-epoxy equivalent timing interaction propagation aggregation representation vector is input into a reaction temperature controller based on a classifier to obtain a control instruction, and the control instruction is used to indicate that the reaction temperature value at the current time point should increase, decrease or remain unchanged.

[0114] In the above-mentioned preparation method of water-based single-liquid o-cresol epoxy resin, the step S110 and the step S120 obtain the epoxy equivalent of the first reaction liquid at multiple sampling points by sampling method, and collect the reaction temperature values ​​of the multiple sampling points by temperature sensor. It should be understood that chemical reaction is a dynamic process, and the properties of its products (epoxy equivalent) and reaction conditions (temperature) will change over time. In order to accurately adjust the reaction temperature according to the real-time changes of epoxy equivalent to ensure the high efficiency of the reaction and the high quality of the product, in the technical solution of the present application, the epoxy equivalent value and the corresponding reaction temperature value of the product are collected by setting multiple sampling time points during the reaction process, so as to capture the real-time change trend of epoxy equivalent and reaction temperature, so as to perform corresponding feedback regulation.

[0115] In the above-mentioned preparation method of water-based single-liquid o-cresol epoxy resin, in step S130, the epoxy equivalent of the first reaction liquid of the plurality of sampling points and the reaction temperature values ​​of the plurality of sampling points are arranged as an epoxy equivalent time series input vector and a reaction temperature time series input vector according to the time dimension. It should be understood that since chemical reactions are time-dependent, in order to understand the evolution law of epoxy equivalent and reaction temperature in the time dimension, the epoxy equivalent of the first reaction liquid of the plurality of sampling points and the reaction temperature values ​​of the plurality of sampling points are further arranged according to their corresponding sampling time sequence, and their time sequence relationship is maintained, thereby providing an orderly data basis for subsequent data analysis.

[0116] In the preparation method of the above-mentioned water-based single-liquid o-cresol-formaldehyde epoxy resin, the step S140 performs linear interpolation on the epoxy equivalent timing input vector and the reaction temperature timing input vector to obtain the epoxy equivalent timing linear interpolation input vector and the reaction temperature timing linear interpolation input vector. It should be understood that in the actual sampling process, due to equipment limitations, cost considerations or the selection of sampling frequency, the setting of sampling points is usually discontinuous, which may lead to sparse data points and affect the subsequent analysis accuracy. Therefore, in the technical solution of the present application, a linear interpolation method is used to interpolate the epoxy equivalent timing input vector and the reaction temperature timing input vector to increase the density of data points, so that the data is more continuous and smooth on the time axis, thereby helping to improve the accuracy of data analysis and the predictive performance of the model.

[0117] In the above-mentioned preparation method of water-based single-liquid o-cresol epoxy resin, in step S150, the time-series linear interpolation input vector of the epoxy equivalent and the time-series linear interpolation input vector of the reaction temperature are segmented at a predetermined time scale and then respectively input into a time encoder based on a 1D-CNN model to obtain a sequence of local time-series correlation feature vectors of the epoxy equivalent and a sequence of local time-series correlation feature vectors of the reaction temperature. That is, in order to understand the variation law of the epoxy equivalent and the reaction temperature in the time dimension in a fine-grained manner, in the calculation scheme of the present application, the time-series linear interpolation input vector of the epoxy equivalent and the time-series linear interpolation input vector of the reaction temperature are first segmented at a predetermined time scale, and then a one-dimensional convolutional neural network (1D-CNN) is used as a sequence encoder to process the segmented time segment data, and through convolution operations and pooling operations, the local patterns and time dependencies in the input data are fully understood, and the time-series correlation features of the epoxy equivalent and the reaction temperature in the local time scale are extracted, thereby providing an effective feature representation for subsequent correlation analysis.

[0118] In the preparation method of the above-mentioned water-based single-liquid o-cresol epoxy resin, in the step S160, each group of corresponding epoxy equivalent local time series correlation feature vectors and reaction temperature local time series correlation feature vectors of the sequence of the epoxy equivalent local time series correlation feature vectors and the sequence of the reaction temperature local time series correlation feature vectors are input into the feature fine-grained correlation distinction significant fusion module to obtain a sequence of reaction temperature-epoxy equivalent local time series response interactive feature vectors. That is, in order to deeply explore the complex nonlinear correlation response relationship between epoxy equivalent and reaction temperature, in the technical solution of the present application, a feature fine-grained correlation distinction significant fusion module is introduced to perform feature correlation response analysis on the epoxy equivalent local time series correlation feature vectors and the reaction temperature local time series correlation feature vectors in each local time segment. Specifically, the feature fine-grained correlation distinguishing significant fusion module calculates the global eigenvalue association matrix between the epoxy equivalent local time series correlation feature vector and the reaction temperature local time series correlation feature vector to quantify the interaction and correlation between the two and establish a global relationship model between the two. Subsequently, the global eigenvalue association matrix is ​​processed based on the gating mechanism to learn and output the correlation distinguishable weight matrix of the eigenvalue granularity between the epoxy equivalent and the reaction temperature, and the matrix product operation is performed on the epoxy equivalent local time series correlation feature vector and the reaction temperature local time series correlation feature vector to achieve fine-grained feature selection and enhancement, which not only considers the relative importance between feature vectors, but also considers the contribution of each element within the feature vector, so that the distinguished and enhanced feature vectors emphasize their respective key information. Finally, the distinguished and enhanced epoxy equivalent local time series correlation feature vector and the reaction temperature local time series correlation feature vector are fused through a cascade operation to obtain the reaction temperature-epoxy equivalent local time series response interaction feature vector. Through this sophisticated correlation analysis and adaptive weight allocation, the temporal dynamic response relationship between epoxy equivalent and reaction temperature is effectively revealed, providing strong characteristic support for subsequent temperature control.

[0119] Specifically, the step S160 includes: calculating the global eigenvalue association matrix between the epoxy equivalent local timing association feature vector and the corresponding reaction temperature local timing association feature vector; inputting the global eigenvalue association matrix into a learnable gating function to obtain a correlation distinguishable weight matrix; using the correlation distinguishable weight matrix as a fusion mask matrix, respectively calculating the matrix product between the epoxy equivalent local timing association feature vector, the reaction temperature local timing association feature vector and the fusion mask matrix to obtain a differentiated enhanced epoxy equivalent local timing association feature vector and a differentiated enhanced reaction temperature local timing association feature vector; fusing the differentiated enhanced epoxy equivalent local timing association feature vector and the differentiated enhanced reaction temperature local timing association feature vector to obtain the reaction temperature-epoxy equivalent local timing response interaction feature vector.

[0120] That is, the step S160 includes: processing each group of corresponding epoxy equivalent local timing correlation feature vectors and reaction temperature local timing correlation feature vectors using the following feature interaction response fusion formula to obtain the reaction temperature-epoxy equivalent local timing response interaction feature vector, wherein the feature interaction response fusion formula is:

[0121]

[0122]

[0123]

[0124]

[0125]

[0126]

[0127] in, represents the epoxy equivalent local time series correlation feature vector, represents the local time series correlation feature vector of the reaction temperature, represents the transpose of the eigenvector, represents the global eigenvalue incidence matrix, represents the exponential function operation with e as the base, represents the correlation distinguishable weight matrix, represents the matrix multiplication operation, represents the distinguishing enhanced epoxy equivalent local temporal correlation feature vector, represents the local temporal correlation feature vector for distinguishing the enhanced reaction temperature, Indicates cascade operation, Represents the reaction temperature-epoxy equivalent local timing response interaction feature vector.

[0128] In the above-mentioned preparation method of water-based single-liquid o-cresol epoxy resin, in step S170, the sequence of the reaction temperature-epoxy equivalent local time series response interaction feature vectors is input into the node feature propagation network guided by energy time series decay to obtain the reaction temperature-epoxy equivalent time series interaction propagation polymerization representation vector. It should be understood that the reaction temperature-epoxy equivalent local time series response interaction feature vector reveals the interaction between the reaction temperature and the epoxy equivalent in the local time period, which has important guiding significance for the feedback control of the reaction temperature. However, considering that the response interaction characteristics of the more distant historical time segments will gradually decay on the current reaction state as time goes by, therefore, in the technical solution of the present application, the sequence of the reaction temperature-epoxy equivalent local time series response interaction feature vectors is processed by the node feature propagation network guided by energy time series decay to capture the dynamic propagation mode of the reaction temperature-epoxy equivalent interaction characteristics. Specifically, the node feature propagation network uses the energy intensity of each reaction temperature-epoxy equivalent local timing response interaction feature vector as the basis for feature propagation aggregation, and introduces a node energy attenuation mechanism in the feature propagation aggregation process. By calculating the spatial span between each reaction temperature-epoxy equivalent local timing response interaction feature vector and the current (i.e., the end of the time series) reaction temperature-epoxy equivalent local timing response interaction feature vector, a corresponding energy attenuation coefficient is generated, so that when the features are aggregated, the feature influence of the early time period is gradually weakened, while the features of the recent time period are enhanced, thereby more comprehensively and accurately understanding the dynamic interactive response pattern between reaction temperature and epoxy equivalent, generating a reaction temperature-epoxy equivalent timing interaction propagation aggregation representation vector, and providing an important regulation basis for subsequent temperature optimization control.

[0129] Specifically, the step S170 includes: calculating the node energy statistical paradigm value of each reaction temperature-epoxy equivalent local timing response interactive feature vector based on the maximum value, average value and variance of each reaction temperature-epoxy equivalent local timing response interactive feature vector in the sequence of reaction temperature-epoxy equivalent local timing response interactive feature vectors to obtain a sequence of node energy statistical paradigm values, wherein the node energy statistical paradigm value corresponding to the current reaction temperature-epoxy equivalent local timing response interactive feature vector in the sequence of node energy statistical paradigm values ​​is used as the current node energy statistical paradigm value, and other node energy statistical paradigm values ​​are used as historical node energy statistical paradigm values ​​to obtain a sequence of current node energy statistical paradigm values ​​and historical node energy statistical paradigm values; and counting the node propagation space span value between each other reaction temperature-epoxy equivalent local timing response interactive feature vector in the sequence of reaction temperature-epoxy equivalent local timing response interactive feature vectors and the current reaction temperature-epoxy equivalent local timing response interactive feature vector to obtain a node propagation space span. A sequence of values; using a preset attenuation constant as a weight, calculating the weighted sum of each node propagation space span value in the sequence of node propagation space span values ​​and its own exponential function value with the natural constant as the base to obtain a sequence of space span attenuation factors; calculating the corresponding division results of each historical node energy statistical paradigm value in the sequence of historical node energy statistical paradigm values ​​and each space span attenuation factor in the sequence of space span attenuation factors to obtain a sequence of node energy propagation attenuation coefficient values; using the sequence of node energy propagation attenuation coefficient values ​​as a weight sequence, calculating the weighted sum of all other reaction temperature-epoxy equivalent local timing response interaction feature vectors in the sequence of reaction temperature-epoxy equivalent local timing response interaction feature vectors to obtain a historical node energy decay time series aggregation feature vector; fusing the current node energy statistical paradigm value to calculate the weighted sum of the historical node energy decay time series aggregation feature vector and the current reaction temperature-epoxy equivalent local timing response interaction feature vector to obtain the reaction temperature-epoxy equivalent time series interaction propagation aggregation representation vector.

[0130] That is, the step S170 includes: processing the sequence of the reaction temperature-epoxy equivalent local timing response interaction feature vectors using the following timing propagation fusion formula to obtain the reaction temperature-epoxy equivalent timing interaction propagation aggregation representation vector, wherein the timing propagation fusion formula is:

[0131]

[0132]

[0133]

[0134]

[0135]

[0136] in, represents the sequence of the reaction temperature-epoxy equivalent local time response interaction feature vectors, The value of is the number of feature vectors in the sequence of the reaction temperature-epoxy equivalent local timing response interaction feature vectors, , , , and The first, second, and third in the sequence of the reaction temperature-epoxy equivalent local timing response interaction feature vectors are represented respectively. , and the current reaction temperature-epoxy equivalent local time series response interaction feature vector, Indicates the The first characteristic vector of the interaction between reaction temperature and epoxy equivalent local time series response eigenvalues, The value of The length of the interaction characteristic vector of the reaction temperature-epoxy equivalent local timing response, For the said The mean of each eigenvalue of the reaction temperature-epoxy equivalent local time series response interaction eigenvector, For the said The variance of each eigenvalue of the interaction eigenvector of the reaction temperature-epoxy equivalent local time series response, Indicates the The maximum value of each eigenvalue of the reaction temperature-epoxy equivalent local time series response interaction eigenvector, is the bias term, For the said The node energy statistical norm value of the reaction temperature-epoxy equivalent local timing response interaction feature vector, Indicates the The node propagation space span value between the reaction temperature-epoxy equivalent local timing response interaction feature vector and the current reaction temperature-epoxy equivalent local timing response interaction feature vector, and are different preset attenuation constants, and are different weight hyperparameters, is the energy statistical paradigm value of the current node, The reaction temperature-epoxy equivalent timing interaction propagates the polymerization representation vector.

[0137] In the preparation method of the above-mentioned water-based single-liquid type o-cresol epoxy resin, the step S180 inputs the reaction temperature-epoxy equivalent time series interactive propagation polymerization representation vector into a reaction temperature controller based on a classifier to obtain a control instruction, and the control instruction is used to indicate whether the reaction temperature value at the current time point should increase, decrease, or remain unchanged. That is, the reaction temperature-epoxy equivalent time series interactive propagation polymerization representation vector is feature parsed by a trained classification model to identify the relationship trend between the reaction temperature and the epoxy equivalent at the current time point, map the current reaction state to a predefined control instruction space, and output the reaction temperature adjustment instruction, which is used to guide the temperature control direction in the reaction process in real time to keep the epoxy equivalent of the resin stable within the target range. In this way, intelligent control of the esterification reaction process is achieved, the stability and consistency of the resin performance are improved, the problem of relying on artificial experience to control reaction parameters in the prior art is effectively solved, and production efficiency and product quality are improved.

[0138] Preferably, considering that the sequence of the reaction temperature-epoxy equivalent local timing response interaction feature vectors is used to express the reaction temperature-epoxy equivalent local timing response interaction characteristics in each local time domain, after passing through the node feature propagation network guided by energy timing attenuation, while performing full-time domain timing node propagation aggregation, the obtained reaction temperature-epoxy equivalent timing interaction propagation aggregation representation vector will also have a timing node propagation aggregation offset caused by the source data associated timing distribution expression offset of the time series of the reaction temperature value of the epoxy equivalent and the reaction liquid relative to the first reaction liquid. Therefore, it is expected to further improve the full-time domain aggregation regression comprehensibility of the reaction temperature-epoxy equivalent timing interaction propagation aggregation representation vector, thereby improving the accuracy of the control instructions obtained by its input based on the classifier-based reaction temperature controller.

[0139] Based on this, in the preferred example, inputting the reaction temperature-epoxy equivalent time series interactive propagation polymerization representation vector into a classifier-based reaction temperature controller to obtain a control instruction specifically includes:

[0140] Subtract the zero norm of the reaction temperature-epoxy equivalent timing interactive propagation polymerization representation vector from the length of the reaction temperature-epoxy equivalent timing interactive propagation polymerization representation vector to obtain the reaction temperature-epoxy equivalent timing interactive propagation polymerization isolated zero value;

[0141] Calculate the base-two logarithm of the square of the reaction temperature-epoxy equivalent timing cross-propagation polymerization isolated zero value and the sum of the reaction temperature-epoxy equivalent timing cross-propagation polymerization isolated zero value to obtain the reaction temperature-epoxy equivalent timing cross-propagation polymerization superposition information value;

[0142] Calculate each eigenvalue of the reaction temperature-epoxy equivalent timing interactive propagation polymerization representation vector as the base, the difference between the isolated zero value of the reaction temperature-epoxy equivalent timing interactive propagation polymerization and one as the exponential power function, and perform point multiplication with the reaction temperature-epoxy equivalent timing interactive propagation polymerization superposition information value to obtain a first reaction temperature-epoxy equivalent timing interactive propagation polymerization intermediate vector;

[0143] After performing a dot multiplication on the reaction temperature-epoxy equivalent timing interactive propagation polymerization representation vector and the difference of the reaction temperature-epoxy equivalent timing interactive propagation polymerization isolated zero value minus one, the dot multiplication is then performed on the reciprocal of the reaction temperature-epoxy equivalent timing interactive propagation polymerization isolated zero value to obtain a second reaction temperature-epoxy equivalent timing interactive propagation polymerization intermediate vector;

[0144] Calculate an exponential function with a natural constant as the base, where each eigenvalue of the second reaction temperature-epoxy equivalent timing interactive propagation polymerization intermediate vector is an exponential function to obtain a third reaction temperature-epoxy equivalent timing interactive propagation polymerization intermediate vector;

[0145] performing point addition of the first reaction temperature-epoxy equivalent timing interactive propagation polymerization intermediate vector and the third reaction temperature-epoxy equivalent timing interactive propagation polymerization intermediate vector to obtain an optimized reaction temperature-epoxy equivalent timing interactive propagation polymerization representation vector; and

[0146] The optimized reaction temperature-epoxy equivalent time series interaction propagation polymerization representation vector is input into a classifier-based reaction temperature controller to obtain a control instruction.

[0147] That is, the reaction temperature-epoxy equivalent time series interactive propagation polymerization representation vector, for example, is recorded as The optimization process is expressed as:

[0148]

[0149]

[0150] in, represents the reaction temperature-epoxy equivalent timing interaction propagation polymerization representation vector, represents the zero norm of a vector, represents the length of the reaction temperature-epoxy equivalent timing interaction propagation polymerization representation vector, Indicates the reaction temperature-epoxy equivalent timing interaction propagates the isolated zero value of polymerization, It is the point multiplication by position. is added by position, A power function representing the calculation of the characteristic values ​​of each position in the characteristic vector with the difference of the reaction temperature-epoxy equivalent time series interactive propagation polymerization isolated zero value minus one as the exponent, The optimized reaction temperature-epoxy equivalent timing interaction propagation polymerization representation vector is shown.

[0151] In this way, for the high-dimensional feature manifold of the reaction temperature-epoxy equivalent timing interactive propagation aggregation representation vector, the eigenvalues ​​of the feature set are used as the vector field representation of the aggregation dimension, and the superposition value of the vector field of the reaction temperature-epoxy equivalent timing interactive propagation aggregation representation vector at the isolated zero position is used as the order information to fix the local position of the eigenvalues ​​of its feature set, and a bias for the reversibility of the feature regression distribution field of the reaction temperature-epoxy equivalent timing interactive propagation aggregation representation vector is added as a reward to achieve the mapping target tracking of the regression distribution of the reaction temperature-epoxy equivalent timing interactive propagation aggregation representation vector for the eigenvalue position, so that the feature set of the reaction temperature-epoxy equivalent timing interactive propagation aggregation representation vector can perceive the mapping migration to the aggregation distribution, thereby improving the accuracy of the control instructions obtained by the reaction temperature controller based on the classifier of the reaction temperature-epoxy equivalent timing interactive propagation aggregation representation vector by improving the full-time domain aggregation regression comprehensibility of the reaction temperature-epoxy equivalent timing interactive propagation aggregation representation vector.

[0152] In summary, the preparation method of the water-based single-liquid o-cresol epoxy resin according to the embodiment of the present application is explained, which uses artificial intelligence technology based on deep learning to monitor and analyze the epoxy equivalent and reaction temperature of the product in the esterification reaction process of step 2 in real time, respectively capturing the time series change characteristics of the epoxy equivalent and the reaction temperature, and then guiding the adjustment direction of the reaction temperature based on the time series correlation response relationship between the two. In this way, real-time control of the esterification reaction process can be achieved to ensure that the epoxy equivalent of the resin is stable within the target range, thereby improving the stability and consistency of the resin performance.

[0153] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for preparing a one-component water-based hot-drilling coating, characterized in that: The components and their weight percentages of the one-component water-based hot diamond coating are as follows: The water-based single-liquid o-cresol epoxy resin comprises 80%-95% of a one-way hydrophilic component A and 5%-20% of an internal curing component B. The structural formula of the one-way hydrophilic component A is shown in Formula 1. Wherein, n is 1-10, and the structural formula of R includes the following two structures: In formula 2, R1 and R2 are selected from hydrocarbon structures having 1 to 20 carbon atoms, and R3 is [NHR4R5R6] + Cationic group, wherein R4, R5, and R6 can be independently selected from one or more combinations of H, CH3, C2H5, C3H7, and C2H4OH; The structural formula of the internal curing component B is shown in Formula 3: Wherein, n is 1-10; The preparation method of the aqueous single-liquid o-cresol epoxy resin dispersion comprises: Step 1: adding o-cresol-formaldehyde epoxy resin and a co-solvent into a glass reaction bottle, and heating the reaction bottle so that the o-cresol-formaldehyde epoxy resin is completely dissolved to obtain an o-cresol-formaldehyde epoxy resin solution; Step 2: adding a monobasic acid and a catalyst to the o-cresol-formaldehyde epoxy resin solution, and controlling the reaction temperature by a temperature controller until the reaction is completed when the epoxy equivalent weight (EEW) is greater than 10,000 to obtain a first reaction solution; Step 3: adding anhydride to the first reaction solution to adjust the acid value of the first reaction solution to 48 mgKOH / g-52 mgKOH / g, and then completing the reaction to obtain a second reaction solution; Step 4: adding a volatile amine neutralizer and the o-cresol-formaldehyde epoxy resin to the second reaction liquid to obtain the water-based single-liquid o-cresol-formaldehyde epoxy resin; Step 5: uniformly adding deionized water to the aqueous single-liquid o-cresol-formaldehyde epoxy resin at a dropping rate of 6-14 g / min, wherein the weight ratio of the aqueous single-liquid o-cresol-formaldehyde epoxy resin to deionized water is 1:0.85-1:1.15, and emulsifying with high-speed stirring to obtain the aqueous single-liquid o-cresol-formaldehyde epoxy resin dispersion; Wherein, the step 2 comprises: Obtaining the epoxy equivalent of the first reaction solution at multiple sampling points by a sampling method; Collecting reaction temperature values ​​of the plurality of sampling points by means of a temperature sensor; Arrange the epoxy equivalent of the first reaction liquid at the plurality of sampling points and the reaction temperature values ​​at the plurality of sampling points into an epoxy equivalent time series input vector and a reaction temperature time series input vector according to the time dimension respectively; Performing linear interpolation on the epoxy equivalent timing input vector and the reaction temperature timing input vector to obtain an epoxy equivalent timing linear interpolation input vector and a reaction temperature timing linear interpolation input vector; The epoxy equivalent time series linear interpolation input vector and the reaction temperature time series linear interpolation input vector are segmented according to a predetermined time scale and then respectively input into a time encoder based on a 1D-CNN model to obtain a sequence of epoxy equivalent local time series correlation feature vectors and a sequence of reaction temperature local time series correlation feature vectors; Inputting the sequence of the epoxy equivalent local time series correlation feature vector and the sequence of the reaction temperature local time series correlation feature vector into a feature fine-grained correlation distinction significant fusion module to obtain a sequence of reaction temperature-epoxy equivalent local time series response interaction feature vectors; Inputting the sequence of the reaction temperature-epoxy equivalent local time series response interaction feature vectors into a node feature propagation network guided by energy time series decay to obtain a reaction temperature-epoxy equivalent time series interaction propagation aggregation representation vector; Inputting the reaction temperature-epoxy equivalent time series interactive propagation polymerization representation vector into a classifier-based reaction temperature controller to obtain a control instruction, wherein the control instruction is used to indicate whether the reaction temperature value at the current time point should increase, decrease, or remain unchanged; The sequence of the epoxy equivalent local time series correlation feature vector and the sequence of the reaction temperature local time series correlation feature vector are input into the feature fine-grained correlation distinction significant fusion module to obtain the sequence of reaction temperature-epoxy equivalent local time series response interaction feature vectors, including: Calculating a global eigenvalue association matrix between the epoxy equivalent local time series association eigenvector and the corresponding reaction temperature local time series association eigenvector; Inputting the global eigenvalue association matrix into a learnable gating function to obtain a correlation distinguishable weight matrix; Using the correlation distinguishable weight matrix as a fusion mask matrix, respectively calculating the matrix products of the epoxy equivalent local time series correlation feature vector, the reaction temperature local time series correlation feature vector and the fusion mask matrix to obtain a distinguished enhanced epoxy equivalent local time series correlation feature vector and a distinguished enhanced reaction temperature local time series correlation feature vector; Merging the distinguishing and strengthening epoxy equivalent local time series association feature vector and the distinguishing and strengthening reaction temperature local time series association feature vector to obtain the reaction temperature-epoxy equivalent local time series response interaction feature vector; Inputting the sequence of the reaction temperature-epoxy equivalent local time series response interaction feature vectors into a node feature propagation network guided by energy time series decay to obtain a reaction temperature-epoxy equivalent time series interaction propagation aggregation representation vector, including: Based on the maximum value, average value and variance of each reaction temperature-epoxy equivalent local timing response interaction feature vector in the sequence of reaction temperature-epoxy equivalent local timing response interaction feature vectors, the node energy statistical paradigm value of each reaction temperature-epoxy equivalent local timing response interaction feature vector is calculated to obtain a sequence of node energy statistical paradigm values, wherein the node energy statistical paradigm value corresponding to the current reaction temperature-epoxy equivalent local timing response interaction feature vector in the sequence of node energy statistical paradigm values ​​is used as the current node energy statistical paradigm value, and other node energy statistical paradigm values ​​are used as historical node energy statistical paradigm values ​​to obtain a sequence of current node energy statistical paradigm values ​​and historical node energy statistical paradigm values; Counting the node propagation space span values ​​between each other reaction temperature-epoxy equivalent local timing response interaction feature vector in the sequence of reaction temperature-epoxy equivalent local timing response interaction feature vector and the current reaction temperature-epoxy equivalent local timing response interaction feature vector to obtain a sequence of node propagation space span values; Using a preset attenuation constant as a weight, calculating the weighted sum of each node propagation space span value in the sequence of node propagation space span values ​​and its own exponential function value with a natural constant as the base to obtain a sequence of space span attenuation factors; Calculate the corresponding division results of each historical node energy statistical normal value in the sequence of the historical node energy statistical normal value and each spatial span attenuation factor in the sequence of the spatial span attenuation factor to obtain a sequence of node energy propagation attenuation coefficient values; Taking the sequence of node energy propagation attenuation coefficient values ​​as a weight sequence, calculating the weighted sum of all other reaction temperature-epoxy equivalent local timing response interaction feature vectors in the sequence of reaction temperature-epoxy equivalent local timing response interaction feature vectors to obtain a historical node energy attenuation timing aggregation feature vector; The current node energy statistical paradigm value is integrated to calculate the weighted sum of the historical node energy decay timing aggregation feature vector and the current reaction temperature-epoxy equivalent local timing response interaction feature vector to obtain the reaction temperature-epoxy equivalent timing interaction propagation aggregation representation vector.

2. The method for preparing the one-component water-based hot-drilling coating according to claim 1, characterized in that: The cross-cut adhesion of the one-component water-based hot diamond coating is 5B or level 0, and the pull-off adhesion is ≥10Mpa.

3. The method for preparing the one-component water-based hot-drilling coating according to claim 1, characterized in that: The VOC content of the one-component water-based hot diamond paint is ≤100g / L.

4. The method for preparing the one-component water-based hot-drilling coating according to claim 1, characterized in that: The unit acid is selected from any one of formic acid, acetic acid, coconut oleic acid, isooctanoic acid, isononanoic acid, soybean oil fatty acid, stearic acid, lauric acid, linoleic acid, ricinoleic acid, eleostearic acid, benzoic acid, acrylic acid, and methacrylic acid; the catalyst is selected from any one of tetraethylammonium bromide, tetraethylammonium chloride, tetraethylammonium hydroxide, benzyltriethylammonium chloride, triphenylphosphine, and triethylamine.

5. The method for preparing the one-component water-based hot-drilling coating according to claim 1, characterized in that: The acid anhydride is selected from any one of acetic anhydride, benzoic anhydride, phthalic anhydride, tetrahydrophthalic anhydride, hexahydrophthalic anhydride, trimellitic anhydride and maleic anhydride.

6. The method for preparing the one-component water-based hot-drilling coating according to claim 1, characterized in that: The neutralizing agent is selected from any one of triethylamine, ammonia water, N,N-dimethylethanolamine and 2-amino-2-methyl-1-propanol.

Images