A UV resin coating paint surface defect detection method and system

Abstract

The present invention proposes a UV resin coating paint surface defect detection method and system. The UV resin coating paint surface defect detection method comprises: extracting the coating volume corresponding to the UV resin to be detected, and using the coating volume corresponding to the UV resin to be detected to obtain the amount of photoinitiator and active diluent to be added; adding photoinitiator and active diluent according to the amount to form a mixed UV resin coating; after the photoinitiator and active diluent are fully mixed with the UV resin coating, controlling the coating spray to spray according to the target thickness of the UV resin coating to form a cured paint surface; using an image acquisition device to collect paint surface image information, and using a neural network model to determine whether there are bubbles, shrinkage holes and cracks. The system comprises modules corresponding to the steps of the method.

Description

Technical Field

[0001] The invention provides a UV resin coating paint surface defect detection method and system, belonging to the technical field of paint surface detection. Background Art

[0002] UV resin coating surface defect detection is a method for comprehensively evaluating the performance of UV resin coatings, mainly including the following aspects:

[0003] Physical property testing: Through hardness testing, adhesion testing, impact resistance testing and friction resistance testing, the hardness and wear resistance of the coating, its bonding ability with the substrate, impact resistance and wear resistance, etc. are evaluated.

[0004] Chemical performance testing: The stability, corrosion resistance, safety and fire resistance of the coating under various environmental conditions are evaluated through weather resistance testing, chemical resistance testing, toxicity testing and fire resistance testing.

[0005] In general, UV resin coating surface defect detection is a comprehensive evaluation method, which aims to comprehensively test the various properties of UV resin coatings to ensure their quality and reliability. However, the existing UV resin coating surface defect detection technology has the problem that the paint spraying control strategy cannot adapt to different paint thickness conditions, resulting in larger paint defects and a higher paint defect rate. Summary of the invention

[0006] The present invention provides a UV resin coating paint surface defect detection method and system, which is used to solve the problem that the paint surface defect detection of UV resin coating in the prior art cannot adapt to the paint surface spraying control strategy under different paint surface thicknesses, resulting in larger paint surface defects and higher paint surface defect rate. The technical scheme adopted is as follows:

[0007] A UV resin coating paint surface defect detection method, the UV resin coating paint surface defect detection method comprising:

[0008] Extracting the coating volume corresponding to the UV resin to be detected, and using the coating volume corresponding to the UV resin to be detected to obtain the amount of photoinitiator and reactive diluent to be added;

[0009] Adding a photoinitiator and a reactive diluent according to the added amounts to form a mixed UV resin coating;

[0010] After the photoinitiator and the reactive diluent are fully mixed with the UV resin coating, the coating is controlled to be sprayed according to the target thickness of the UV resin coating to form a cured paint surface;

[0011] The image acquisition device is used to collect paint surface image information, and the neural network model is used to determine whether there are bubbles, shrinkage holes, cracks, etc.

[0012] Further, extracting the coating volume corresponding to the UV resin to be detected, and using the coating volume corresponding to the UV resin to be detected to obtain the amount of photoinitiator and reactive diluent to be added, including:

[0013] Extract the spraying area and spraying thickness corresponding to the UV resin to be tested;

[0014] Obtaining the coating volume corresponding to the UV resin to be tested according to the spraying area and the spraying thickness;

[0015] The amount of photoinitiator and reactive diluent to be added is determined according to the coating volume corresponding to the UV resin to be detected and the preset resource percentages of the photoinitiator and reactive diluent.

[0016] Further, after the photoinitiator and the reactive diluent are fully mixed with the UV resin coating, the coating is controlled to be sprayed according to the target thickness of the UV resin coating to form a cured paint surface, including:

[0017] Extracting a target thickness and a spraying strategy; wherein the spraying strategy includes reaching the target thickness after spraying two layers and reaching the target thickness after spraying three layers;

[0018] Setting the sub-thickness of each layer according to the target thickness and the viscosity of the mixed UV resin coating;

[0019] Spraying the UV resin coating according to the sub-thickness until the target thickness is reached;

[0020] After the UV resin coating is sprayed to reach the target thickness, the sprayed surface is irradiated and cured using an ultraviolet lamp; wherein the irradiation time length and intensity of the ultraviolet light are obtained by the following formula:

[0021]

[0022]

[0023] Among them, T g represents the duration of ultraviolet irradiation; H represents the value corresponding to the target thickness; T0 represents the unit time, which is 1000s; P represents the value corresponding to the power of the ultraviolet lamp; x represents the absorption rate of the current UV resin coating for ultraviolet rays; y represents the adjustment coefficient; m represents the number of spray layers corresponding to the spraying strategy; n represents the historical curing times of UV resin coatings with the same properties as the current UV resin coating; f xi Δf represents the change in the UV absorption rate of the UV resin coating cured for the i-th time;xi It indicates the theoretical change of the absorption rate for each unit thickness change of the UV resin coating spraying thickness, and the unit thickness value range is 0.7um-1.3um;

[0024]

[0025] Among them, U v It represents the irradiation intensity of ultraviolet light; H0 represents the preset thickness threshold; I represents the light intensity of the ultraviolet lamp; S represents the spraying area of ​​the UV resin coating.

[0026] Further, the sub-thickness of each layer is set according to the target thickness and the viscosity of the mixed UV resin coating, including:

[0027] When the target thickness exceeds the preset thickness threshold, the target thickness is reached after three layers of spraying; wherein the sub-thickness corresponding to each layer of spraying is obtained by the following formula:

[0028]

[0029] Among them, H1 represents the sub-thickness corresponding to the first coating layer from bottom to top; H2 represents the sub-thickness corresponding to the second coating layer from bottom to top; H3 represents the sub-thickness corresponding to the first coating layer from bottom to top;

[0030] When the target thickness does not exceed the preset thickness threshold, the target thickness is reached after two layers are sprayed; wherein the sub-thickness corresponding to each spray layer is obtained by the following formula:

[0031]

[0032]

[0033] Among them, H1 represents the sub-thickness corresponding to the first coating layer from bottom to top; H2 represents the sub-thickness corresponding to the second coating layer from bottom to top; ΔH represents the compensation thickness.

[0034] Furthermore, the image acquisition device is used to collect the image information of the paint surface, and the neural network model is used to determine whether there are bubbles, shrinkage holes and cracks, including:

[0035] Using an image acquisition device to acquire image data corresponding to the paint surface, wherein the image acquisition device includes but is not limited to a camera;

[0036] Retrieving a neural network model that has completed training and test optimization from a database, wherein the neural network model includes but is not limited to a convolutional neural network;

[0037] The image data corresponding to the paint surface is input into a neural network model, and the image data is recognized by the neural network model to determine whether there are bubbles, shrinkage holes and cracks in the image data corresponding to the paint surface, and the recognition result is output.

[0038] A UV resin coating paint surface defect detection method, the UV resin coating paint surface defect detection system comprises:

[0039] An information extraction module is used to extract the coating volume corresponding to the UV resin to be detected, and use the coating volume corresponding to the UV resin to be detected to obtain the amount of photoinitiator and active diluent to be added;

[0040] A mixing control module, used for adding a photoinitiator and a reactive diluent according to the added amounts to form a mixed UV resin coating;

[0041] A spraying control module, used for controlling the coating to be sprayed according to a target thickness of the UV resin coating after the photoinitiator and the reactive diluent are fully mixed with the UV resin coating to form a cured paint surface;

[0042] The defect monitoring module is used to collect paint surface image information using an image acquisition device and use a neural network model to determine whether there are bubbles, shrinkage holes and cracks.

[0043] Furthermore, the information extraction module includes:

[0044] A spraying information extraction module is used to extract the spraying area and spraying thickness corresponding to the UV resin to be detected;

[0045] A spraying volume acquisition module, used for acquiring the coating volume corresponding to the UV resin to be detected according to the spraying area and the spraying thickness;

[0046] The material addition control module is used to determine the amount of photoinitiator and active diluent to be added according to the coating volume corresponding to the UV resin to be detected and the preset resource percentage of the photoinitiator and the active diluent.

[0047] Furthermore, the spraying control module includes:

[0048] A strategy and thickness information extraction module, used to extract the target thickness and spraying strategy; wherein the spraying strategy includes reaching the target thickness after spraying two layers and reaching the target thickness after spraying three layers;

[0049] A sub-thickness acquisition module, used to set the sub-thickness of each layer according to the target thickness and the viscosity of the mixed UV resin coating;

[0050] A spraying execution module, used for spraying UV resin coating according to the sub-thickness until the target thickness is reached;

[0051] The curing control module is used to irradiate and cure the sprayed surface with an ultraviolet lamp after the UV resin coating reaches the target thickness; wherein the irradiation time length and intensity of the ultraviolet light are obtained by the following formula:

[0052]

[0053]

[0054] Among them, T g represents the duration of ultraviolet irradiation; H represents the value corresponding to the target thickness; T0 represents the unit time, which is 1000s; P represents the value corresponding to the power of the ultraviolet lamp; x represents the absorption rate of the current UV resin coating for ultraviolet rays; y represents the adjustment coefficient; m represents the number of spray layers corresponding to the spraying strategy; n represents the historical curing times of UV resin coatings with the same properties as the current UV resin coating; f xi Indicates the change in the UV absorption rate of the UV resin coating cured for the i-th time; Δf xi It indicates the theoretical change of the absorption rate for each unit thickness change of the UV resin coating spraying thickness, and the unit thickness value range is 0.7um-1.3um;

[0055]

[0056] Among them, U v It represents the irradiation intensity of ultraviolet light; H0 represents the preset thickness threshold; I represents the light intensity of the ultraviolet lamp; S represents the spraying area of ​​the UV resin coating.

[0057] Furthermore, the sub-thickness acquisition module includes:

[0058] The first sub-thickness acquisition module is used to spray three layers to reach the target thickness when the target thickness exceeds a preset thickness threshold; wherein the sub-thickness corresponding to each spray layer is obtained by the following formula:

[0059]

[0060] Among them, H1 represents the sub-thickness corresponding to the first coating layer from bottom to top; H2 represents the sub-thickness corresponding to the second coating layer from bottom to top; H3 represents the sub-thickness corresponding to the first coating layer from bottom to top;

[0061] The second sub-thickness acquisition module is used to achieve the target thickness after spraying two layers when the target thickness does not exceed the preset thickness threshold; wherein the sub-thickness corresponding to each spray layer is obtained by the following formula:

[0062]

[0063]

[0064] Among them, H1 represents the sub-thickness corresponding to the first coating layer from bottom to top; H2 represents the sub-thickness corresponding to the second coating layer from bottom to top; ΔH represents the compensation thickness.

[0065] Furthermore, the defect monitoring module includes:

[0066] An image acquisition module, used to acquire image data corresponding to the paint surface using an image acquisition device, wherein the image acquisition device includes but is not limited to a camera;

[0067] A model retrieval module, used to retrieve a neural network model that has completed training and test optimization from a database, wherein the neural network model includes but is not limited to a convolutional neural network;

[0068] The recognition control module is used to input the image data corresponding to the paint surface into the neural network model, and recognize the image data through the neural network model, determine whether there are bubbles, shrinkage holes and cracks in the image data corresponding to the paint surface, and output the recognition result.

[0069] Beneficial effects of the present invention:

[0070] The present invention provides a UV resin coating paint surface defect detection method and system, specifically a fast, accurate and automated UV resin coating paint surface defect detection method. By combining image acquisition and neural network model, efficient recognition of paint surface defects is achieved, and the accuracy and reliability of defect detection are improved. At the same time, the method reduces the labor intensity of manual detection, improves production efficiency, and helps to realize the automation and intelligence of industrial production. In addition, the technical solution also has a wide range of application prospects and can be applied to various industrial fields that require UV resin coatings, such as automobile manufacturing, furniture manufacturing, electronic product manufacturing, etc. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 is a flow chart of the method of the present invention;

[0072] Figure 2 The system block diagram of the system of the present invention. DETAILED DESCRIPTION

[0073] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0074] The embodiment of the present invention provides a method for detecting defects on a UV resin coating surface. Figure 1 As shown, the UV resin coating paint surface defect detection method includes:

[0075] S1, extracting the coating volume corresponding to the UV resin to be detected, and using the coating volume corresponding to the UV resin to be detected to obtain the amount of photoinitiator and reactive diluent to be added;

[0076] S2, adding a photoinitiator and a reactive diluent according to the added amounts to form a mixed UV resin coating;

[0077] S3, after the photoinitiator and the reactive diluent are fully mixed with the UV resin coating, the coating is controlled to be sprayed according to the target thickness of the UV resin coating to form a cured paint surface;

[0078] S4. Use an image acquisition device to collect paint surface image information, and use a neural network model to determine whether there are bubbles, shrinkage holes, cracks, etc.

[0079] The working principle of the above technical solution is: extract the coating volume corresponding to the UV resin to be tested: this step obtains the volume of the UV resin coating to be tested by measurement or calculation, providing basic data for the subsequent determination of the amount of photoinitiator and active diluent to be added.

[0080] The amount of photoinitiator and reactive diluent required to be added is obtained by using the coating volume corresponding to the UV resin to be tested: the required amount of photoinitiator and reactive diluent required to be added is calculated based on the volume of the UV resin coating and the known concentration or ratio of the photoinitiator and reactive diluent in the coating.

[0081] The photoinitiator and the reactive diluent are added according to the added amounts to form a mixed UV resin coating: According to the calculated added amounts, the photoinitiator and the reactive diluent are added to the UV resin coating and mixed to form a UV resin coating sample to be tested.

[0082] After the photoinitiator and the active diluent are fully mixed with the UV resin coating, the coating is controlled to be sprayed according to the target thickness of the UV resin coating to form a cured paint surface: after being evenly mixed, the UV resin coating is sprayed on the surface of the substrate according to a preset target thickness using a spraying device, and cured under ultraviolet light to form a paint surface.

[0083] Use image acquisition devices to collect paint surface image information, and use neural network models to determine whether there are bubbles, shrinkage holes and cracks: Use high-resolution image acquisition devices to capture microscopic images of the paint surface, and input these images into a pre-trained neural network model. After training with a large number of samples, the neural network model has learned how to identify and determine whether there are defects such as bubbles, shrinkage holes and cracks on the paint surface. Through the judgment of the neural network, defects on the paint surface can be detected quickly and accurately.

[0084] The effect of the above technical solution is: through the combination of image acquisition device and neural network model, fast and accurate detection of paint surface defects is achieved. Compared with traditional visual inspection or simple image processing methods, this method greatly improves the efficiency and accuracy of detection and reduces the possibility of misjudgment and missed detection. This technical solution automates the detection process and reduces the degree of human participation. Through preset programs and algorithms, the whole process from paint mixing, spraying to defect identification can be automatically completed, reducing the influence of human factors on the detection results.

[0085] Since UV resin coatings are widely used in many industries, this technical solution has broad application prospects. Whether it is surface coating in automobile manufacturing, decorative coating in furniture manufacturing, or protective coating in electronic product manufacturing, this technical solution can be used for quality monitoring and defect detection. The implementation of this technical solution helps to promote the automation and intelligent upgrading of industrial production. By introducing advanced detection technology and equipment, enterprises can improve production processes, improve product quality, and enhance market competitiveness. By improving detection efficiency and accuracy, this technical solution can help enterprises reduce production costs and reduce scrap rates, thereby improving overall economic benefits. At the same time, the automated and intelligent production process can also save a lot of labor costs for enterprises. The implementation of this technical solution helps to strengthen technical exchanges and cooperation between enterprises and between enterprises and scientific research institutions. Through joint research and development, the technical solution can be continuously improved and perfected to promote technological progress in related fields.

[0086] At the same time, since UV resin coatings have the advantages of fast curing and low volatile organic compound emissions, the implementation of this technical solution will also help companies achieve environmental protection and sustainable development goals. By improving production processes and using environmentally friendly materials, the negative impact on the environment can be reduced and the social responsibility of companies can be enhanced. The innovation of this technical solution lies in the combination of image acquisition, neural network technology and UV resin coating detection, which realizes the automation and intelligence of defect detection. This innovation-driven development model helps promote scientific and technological progress and industrial upgrading in related industries and promote the sustainable and healthy development of the economy.

[0087] In summary, the above-mentioned technical solutions have rich technical effects and application value in improving detection efficiency and accuracy, realizing automation and intelligence, promoting industrial production upgrades, reducing costs and improving efficiency, promoting technical exchanges and cooperation, environmental protection and sustainable development, and innovation-driven development.

[0088] In one embodiment of the present invention, the volume of coating corresponding to the UV resin to be detected is extracted, and the amount of photoinitiator and reactive diluent to be added is obtained by using the volume of coating corresponding to the UV resin to be detected, including:

[0089] S101, extracting the spraying area and spraying thickness corresponding to the UV resin to be tested;

[0090] S102, obtaining the coating volume corresponding to the UV resin to be tested according to the spraying area and the spraying thickness;

[0091] S103, determining the amount of photoinitiator and reactive diluent to be added according to the coating volume corresponding to the UV resin to be detected and the preset resource percentages of the photoinitiator and reactive diluent.

[0092] The working principle of the above technical solution is: Extract the spraying area and spraying thickness corresponding to the UV resin to be tested: This step is to obtain the coating requirements of the UV resin coating, that is, the area to be coated and the thickness of the coating. These parameters are the key factors in calculating the volume of the coating.

[0093] The coating volume corresponding to the UV resin to be tested is obtained according to the spraying area and the spraying thickness: Based on the known spraying area and the spraying thickness, combined with the density of the coating (the mass of the coating per unit volume), the required coating volume can be calculated.

[0094] Determine the amount of photoinitiator and reactive diluent to be added based on the volume of the coating corresponding to the UV resin to be tested and the preset resource percentage of the photoinitiator and reactive diluent: This step is based on the volume of the coating and the known concentration or ratio (resource percentage) of the photoinitiator and reactive diluent in the coating to calculate the amount of photoinitiator and reactive diluent to be added.

[0095] The effect of the above technical solution is that the technical solution extracts the spraying area and spraying thickness corresponding to the UV resin to be tested, and calculates the coating volume based on these parameters, thereby more accurately determining the amount of photoinitiator and active diluent to be added. Compared with the traditional method based only on experience or experimental data, this method is more scientific and accurate.

[0096] By accurately determining the volume of the coating, it is possible to ensure that the amount of photoinitiator and reactive diluent added matches the needs of the UV resin coating, avoiding over-addition or under-addition, thereby optimizing the performance and curing effect of the coating.

[0097] In addition, this technical solution also improves the reliability and consistency of detection. Since the volume of the coating is the key factor in determining the amount of photoinitiator and reactive diluent to be added, this method has better consistency and comparability in the detection of different batches or different production conditions.

[0098] In summary, this technical solution achieves accurate calculation of the amount of photoinitiator and active diluent added to UV resin coatings by extracting the spraying area and spraying thickness corresponding to the UV resin to be tested, and combining the preset resource percentages of photoinitiator and active diluent. This method improves the accuracy and reliability of detection, and helps to improve product quality and production efficiency.

[0099] In one embodiment of the present invention, after the photoinitiator and the reactive diluent are fully mixed with the UV resin coating, the coating is controlled to be sprayed according to the target thickness of the UV resin coating to form a cured paint surface, comprising:

[0100] S301, extracting a target thickness and a spraying strategy; wherein the spraying strategy includes reaching the target thickness after spraying two layers and reaching the target thickness after spraying three layers;

[0101] S302, setting the sub-thickness of each layer according to the target thickness and the viscosity of the mixed UV resin coating;

[0102] S303, spraying UV resin coating according to the sub-thickness until the target thickness is reached;

[0103] S304, after the UV resin coating reaches the target thickness, the sprayed surface is irradiated and cured by an ultraviolet lamp; wherein the irradiation time length and intensity of the ultraviolet light are obtained by the following formula:

[0104]

[0105]

[0106] Among them, T g represents the duration of ultraviolet irradiation; H represents the value corresponding to the target thickness; T0 represents the unit time, which is 1000s; P represents the value corresponding to the power of the ultraviolet lamp; x represents the absorption rate of the current UV resin coating for ultraviolet rays; y represents the adjustment coefficient; m represents the number of spray layers corresponding to the spraying strategy; n represents the historical curing times of UV resin coatings with the same properties as the current UV resin coating; f xiΔf represents the change in the UV absorption rate of the UV resin coating cured for the i-th time; xi It indicates the theoretical change of the absorption rate for each unit thickness change of the UV resin coating spraying thickness, and the unit thickness value range is 0.7um-1.3um;

[0107]

[0108] Among them, U v It represents the irradiation intensity of ultraviolet light; H0 represents the preset thickness threshold; I represents the light intensity of the ultraviolet lamp; S represents the spraying area of ​​the UV resin coating.

[0109] The working principle of the above technical solution is as follows: Extract the target thickness and spraying strategy: This step is to clarify the final thickness requirement of the coating and the spraying strategy to achieve this thickness. The spraying strategy may include spraying two or three layers to achieve the target thickness. Set the sub-thickness of each layer according to the target thickness and the viscosity of the mixed UV resin coating: Considering that the viscosity of the coating will affect the spraying effect and thickness, this step is to set the expected thickness of each layer of coating according to the target and the characteristics of the coating.

[0110] The UV resin coating is sprayed according to the sub-thickness until the target thickness is reached: the UV resin coating is sprayed in layers by the spraying equipment according to the set sub-thickness until the target total thickness is reached. After the UV resin coating is sprayed to reach the target thickness, the sprayed surface is irradiated and cured by an ultraviolet lamp: in order to make the UV resin coating cure quickly, the coating surface is irradiated by an ultraviolet lamp.

[0111] The effect of the above technical solution is that the technical solution achieves precise control of the quality of the paint surface by precisely controlling the thickness of each layer and the total thickness, and using ultraviolet light for rapid curing. This control not only improves the flatness and uniformity of the paint surface, but also ensures that the coating has the required physical and chemical properties.

[0112] By setting the sub-thickness of each layer and adjusting it according to the viscosity of the paint, this technical solution can better cope with the spraying requirements of paints with different viscosities. This helps to avoid problems such as uneven spraying or overspray caused by too high or too low viscosity of the paint.

[0113] By using ultraviolet light for rapid curing, this technical solution shortens the curing time and improves production efficiency. At the same time, by controlling the exposure time and intensity of ultraviolet light, it can ensure that the coating is fully cured and obtains the desired properties.

[0114] In addition, the technical solution also takes into account the changes in the UV resin coating's absorption rate of ultraviolet rays and the impact of historical curing times, which helps to more accurately predict and control the curing effect. By adjusting the UV irradiation time and intensity, and controlling the spraying strategy of the UV resin coating, the technical solution not only improves product quality and performance, but also saves costs and time for the company. On the other hand, the above method can adaptively adjust the UV lamp irradiation intensity and time according to the spraying situation, which can effectively improve the adaptive adjustability and adjustment accuracy of the UV lamp irradiation.

[0115] In summary, this technical solution achieves precise control of the paint surface quality by precisely controlling the thickness of each layer, the total thickness, and using ultraviolet light for rapid curing. This control not only improves the quality and performance of the product, but also saves costs and time for the company.

[0116] In one embodiment of the present invention, the sub-thickness of each layer is set according to the target thickness and the viscosity of the mixed UV resin coating, including:

[0117] S3021. When the target thickness exceeds a preset thickness threshold, three layers are sprayed to reach the target thickness; wherein the sub-thickness corresponding to each spray layer is obtained by the following formula:

[0118]

[0119] Among them, H1 represents the sub-thickness corresponding to the first coating layer from bottom to top; H2 represents the sub-thickness corresponding to the second coating layer from bottom to top; H3 represents the sub-thickness corresponding to the first coating layer from bottom to top;

[0120] S3022: When the target thickness does not exceed the preset thickness threshold, two layers are sprayed to reach the target thickness; wherein the sub-thickness corresponding to each spray layer is obtained by the following formula:

[0121]

[0122]

[0123] Among them, H1 represents the sub-thickness corresponding to the first coating layer from bottom to top; H2 represents the sub-thickness corresponding to the second coating layer from bottom to top; ΔH represents the compensation thickness.

[0124] The working principle of the above technical solution is: when the target thickness exceeds the preset thickness threshold, the target thickness is reached after three layers of spraying: when the required coating thickness is large, in order to ensure the quality and uniformity of the coating, three layers of spraying are selected. The thickness of each layer is calculated by a preset formula. When the target thickness does not exceed the preset thickness threshold, the target thickness is reached after two layers of spraying: when the required coating thickness is small, in order to improve production efficiency, two layers of spraying are selected. Similarly, the thickness of each layer is also calculated by a preset formula.

[0125] The effect of the above technical solution is that the technical solution realizes precise control of the paint surface quality by selecting the appropriate number of spray layers according to the target thickness and the viscosity of the UV resin coating and accurately calculating the thickness of each layer. This control not only ensures the uniformity and flatness of the coating, but also helps to avoid defects caused by overspray or underspray.

[0126] Through the preset thickness threshold, the technical solution can select the appropriate spraying strategy according to different coating requirements. When the target thickness is large, spraying three layers can ensure the quality and stability of the coating; when the target thickness is small, spraying two layers can improve production efficiency. At the same time, the above method can effectively improve the matching between the spraying thickness setting and the actual spraying situation, as well as the adaptability of transformation and strategy adjustment according to different spraying situations, thereby effectively improving the mobility of the adaptive adjustment of the spraying strategy.

[0127] Using a preset formula to calculate the thickness of each layer, the technical solution can accurately control the coating thickness of each layer according to the viscosity characteristics of the paint. This helps to avoid problems such as uneven spraying or overspray caused by too high or too low viscosity.

[0128] In summary, this technical solution achieves precise control of the paint surface quality by selecting the appropriate number of spray layers according to the target thickness and the viscosity of the UV resin coating and accurately calculating the thickness of each layer. This control not only improves the quality and performance of the product, but also saves costs and time for the enterprise.

[0129] In one embodiment of the present invention, an image acquisition device is used to collect paint surface image information, and a neural network model is used to determine whether bubbles, shrinkage cavities, cracks, etc. exist, including:

[0130] S401, using an image acquisition device to acquire image data corresponding to the paint surface, wherein the image acquisition device includes but is not limited to a camera;

[0131] S402, retrieving a neural network model that has completed training and test optimization from a database, wherein the neural network model includes but is not limited to a convolutional neural network;

[0132] S403, inputting the image data corresponding to the paint surface into the neural network model, and identifying the image data through the neural network model, determining whether there are bubbles, shrinkage holes and cracks in the image data corresponding to the paint surface, and outputting the identification result.

[0133] The working principle of the above technical solution is: using the image acquisition device to collect image data corresponding to the paint surface: using a high-resolution camera or other image acquisition equipment to capture real-time images of the coating surface. These image data contain key information such as the surface texture, color and structure of the coating.

[0134] Retrieve the trained and tested neural network models from the database: After repeated optimization with a large amount of training data and test data, the neural network models have the ability to identify different defects. These models can extract features from the input image data and make accurate judgments.

[0135] The image data corresponding to the paint surface is input into the neural network model, and the image data is recognized by the neural network model: after receiving the image data, the neural network model will perform a series of complex calculations and analyses to identify defects such as bubbles, shrinkage holes and cracks on the coating surface. This process is automated and does not require human intervention.

[0136] The effect of the above technical solution is that the technical solution realizes rapid and accurate detection of paint surface defects by combining the image acquisition device and the neural network model. Compared with traditional visual inspection or simple image processing methods, this method greatly improves the efficiency and accuracy of detection and reduces the possibility of misjudgment and missed detection.

[0137] Image data collected by high-resolution cameras can provide rich surface information, providing strong data support for the recognition of neural network models. The trained and optimized neural network model has powerful feature extraction and classification capabilities, and can accurately determine various defects on the coating surface.

[0138] This defect detection method based on image acquisition device and neural network model has broad application prospects. Whether it is automobile manufacturing, furniture manufacturing or electronic product manufacturing, this technical solution can be used for quality monitoring and defect detection to improve production efficiency and product quality.

[0139] In summary, this technical solution achieves rapid and accurate detection of paint surface defects by combining image acquisition devices and neural network models. This method improves production efficiency and product quality, saving costs and time for enterprises.

[0140] The embodiment of the present invention provides a method for detecting defects on a UV resin coating surface. Figure 2As shown, the UV resin coating paint surface defect detection system includes:

[0141] An information extraction module is used to extract the coating volume corresponding to the UV resin to be detected, and use the coating volume corresponding to the UV resin to be detected to obtain the amount of photoinitiator and active diluent to be added;

[0142] A mixing control module, used for adding a photoinitiator and a reactive diluent according to the added amounts to form a mixed UV resin coating;

[0143] A spraying control module, used for controlling the coating to be sprayed according to a target thickness of the UV resin coating after the photoinitiator and the reactive diluent are fully mixed with the UV resin coating to form a cured paint surface;

[0144] The defect monitoring module is used to collect paint surface image information using an image acquisition device, and use a neural network model to determine whether there are bubbles, shrinkage holes, cracks, etc.

[0145] The working principle of the above technical solution is: extract the coating volume corresponding to the UV resin to be tested: this step obtains the volume of the UV resin coating to be tested by measurement or calculation, providing basic data for the subsequent determination of the amount of photoinitiator and active diluent to be added.

[0146] The amount of photoinitiator and reactive diluent required to be added is obtained by using the coating volume corresponding to the UV resin to be tested: the required amount of photoinitiator and reactive diluent required to be added is calculated based on the volume of the UV resin coating and the known concentration or ratio of the photoinitiator and reactive diluent in the coating.

[0147] The photoinitiator and the reactive diluent are added according to the added amounts to form a mixed UV resin coating: According to the calculated added amounts, the photoinitiator and the reactive diluent are added to the UV resin coating and mixed to form a UV resin coating sample to be tested.

[0148] After the photoinitiator and the active diluent are fully mixed with the UV resin coating, the coating is controlled to be sprayed according to the target thickness of the UV resin coating to form a cured paint surface: after being evenly mixed, the UV resin coating is sprayed on the surface of the substrate according to a preset target thickness using a spraying device, and cured under ultraviolet light to form a paint surface.

[0149] Use image acquisition devices to collect paint surface image information, and use neural network models to determine whether there are bubbles, shrinkage holes and cracks: Use high-resolution image acquisition devices to capture microscopic images of the paint surface, and input these images into a pre-trained neural network model. After training with a large number of samples, the neural network model has learned how to identify and determine whether there are defects such as bubbles, shrinkage holes and cracks on the paint surface. Through the judgment of the neural network, defects on the paint surface can be detected quickly and accurately.

[0150] The effect of the above technical solution is: through the combination of image acquisition device and neural network model, fast and accurate detection of paint surface defects is achieved. Compared with traditional visual inspection or simple image processing methods, this method greatly improves the efficiency and accuracy of detection and reduces the possibility of misjudgment and missed detection. This technical solution automates the detection process and reduces the degree of human participation. Through preset programs and algorithms, the whole process from paint mixing, spraying to defect identification can be automatically completed, reducing the influence of human factors on the detection results.

[0151] Since UV resin coatings are widely used in many industries, this technical solution has broad application prospects. Whether it is surface coating in automobile manufacturing, decorative coating in furniture manufacturing, or protective coating in electronic product manufacturing, this technical solution can be used for quality monitoring and defect detection. The implementation of this technical solution helps to promote the automation and intelligent upgrading of industrial production. By introducing advanced detection technology and equipment, enterprises can improve production processes, improve product quality, and enhance market competitiveness. By improving detection efficiency and accuracy, this technical solution can help enterprises reduce production costs and reduce scrap rates, thereby improving overall economic benefits. At the same time, the automated and intelligent production process can also save a lot of labor costs for enterprises. The implementation of this technical solution helps to strengthen technical exchanges and cooperation between enterprises and between enterprises and scientific research institutions. Through joint research and development, the technical solution can be continuously improved and perfected to promote technological progress in related fields.

[0152] At the same time, since UV resin coatings have the advantages of fast curing and low volatile organic compound emissions, the implementation of this technical solution will also help companies achieve environmental protection and sustainable development goals. By improving production processes and using environmentally friendly materials, the negative impact on the environment can be reduced and the social responsibility of companies can be enhanced. The innovation of this technical solution lies in the combination of image acquisition, neural network technology and UV resin coating detection, which realizes the automation and intelligence of defect detection. This innovation-driven development model helps promote scientific and technological progress and industrial upgrading in related industries and promote the sustainable and healthy development of the economy.

[0153] In summary, the above-mentioned technical solutions have rich technical effects and application value in improving detection efficiency and accuracy, realizing automation and intelligence, promoting industrial production upgrades, reducing costs and improving efficiency, promoting technical exchanges and cooperation, environmental protection and sustainable development, and innovation-driven development.

[0154] In one embodiment of the present invention, the information extraction module includes:

[0155] A spraying information extraction module is used to extract the spraying area and spraying thickness corresponding to the UV resin to be detected;

[0156] A spraying volume acquisition module, used for acquiring the coating volume corresponding to the UV resin to be detected according to the spraying area and the spraying thickness;

[0157] The material addition control module is used to determine the amount of photoinitiator and active diluent to be added according to the coating volume corresponding to the UV resin to be detected and the preset resource percentage of the photoinitiator and the active diluent.

[0158] The working principle of the above technical solution is: Extract the spraying area and spraying thickness corresponding to the UV resin to be tested: This step is to obtain the coating requirements of the UV resin coating, that is, the area to be coated and the thickness of the coating. These parameters are the key factors in calculating the volume of the coating.

[0159] The coating volume corresponding to the UV resin to be tested is obtained according to the spraying area and the spraying thickness: Based on the known spraying area and the spraying thickness, combined with the density of the coating (the mass of the coating per unit volume), the required coating volume can be calculated.

[0160] Determine the amount of photoinitiator and reactive diluent to be added based on the volume of the coating corresponding to the UV resin to be tested and the preset resource percentage of the photoinitiator and reactive diluent: This step is based on the volume of the coating and the known concentration or ratio (resource percentage) of the photoinitiator and reactive diluent in the coating to calculate the amount of photoinitiator and reactive diluent to be added.

[0161] The effect of the above technical solution is that the technical solution extracts the spraying area and spraying thickness corresponding to the UV resin to be tested, and calculates the coating volume based on these parameters, thereby more accurately determining the amount of photoinitiator and active diluent to be added. Compared with the traditional method based only on experience or experimental data, this method is more scientific and accurate.

[0162] By accurately determining the volume of the coating, it is possible to ensure that the amount of photoinitiator and reactive diluent added matches the needs of the UV resin coating, avoiding over-addition or under-addition, thereby optimizing the performance and curing effect of the coating.

[0163] In addition, this technical solution also improves the reliability and consistency of detection. Since the volume of the coating is the key factor in determining the amount of photoinitiator and reactive diluent to be added, this method has better consistency and comparability in the detection of different batches or different production conditions.

[0164] In summary, this technical solution achieves accurate calculation of the amount of photoinitiator and active diluent added to UV resin coatings by extracting the spraying area and spraying thickness corresponding to the UV resin to be tested, and combining the preset resource percentages of photoinitiator and active diluent. This method improves the accuracy and reliability of detection, and helps to improve product quality and production efficiency.

[0165] In one embodiment of the present invention, the spray control module comprises:

[0166] A strategy and thickness information extraction module, used to extract the target thickness and spraying strategy; wherein the spraying strategy includes reaching the target thickness after spraying two layers and reaching the target thickness after spraying three layers;

[0167] A sub-thickness acquisition module, used to set the sub-thickness of each layer according to the target thickness and the viscosity of the mixed UV resin coating;

[0168] A spraying execution module, used for spraying UV resin coating according to the sub-thickness until the target thickness is reached;

[0169] The curing control module is used to irradiate and cure the sprayed surface with an ultraviolet lamp after the UV resin coating reaches the target thickness; wherein the irradiation time length and intensity of the ultraviolet light are obtained by the following formula:

[0170]

[0171]

[0172] Among them, T g represents the duration of ultraviolet irradiation; H represents the value corresponding to the target thickness; T0 represents the unit time, which is 1000s; P represents the value corresponding to the power of the ultraviolet lamp; x represents the absorption rate of the current UV resin coating for ultraviolet rays; y represents the adjustment coefficient; m represents the number of spray layers corresponding to the spraying strategy; n represents the historical curing times of UV resin coatings with the same properties as the current UV resin coating; f xi Δf represents the change in the UV absorption rate of the UV resin coating cured for the i-th time; xi It indicates the theoretical change of the absorption rate for each unit thickness change of the UV resin coating spraying thickness, and the unit thickness value range is 0.7um-1.3um;

[0173]

[0174] Among them, U v It represents the irradiation intensity of ultraviolet light; H0 represents the preset thickness threshold; I represents the light intensity of the ultraviolet lamp; S represents the spraying area of ​​the UV resin coating.

[0175] The working principle of the above technical solution is as follows: Extract the target thickness and spraying strategy: This step is to clarify the final thickness requirement of the coating and the spraying strategy to achieve this thickness. The spraying strategy may include spraying two or three layers to achieve the target thickness. Set the sub-thickness of each layer according to the target thickness and the viscosity of the mixed UV resin coating: Considering that the viscosity of the coating will affect the spraying effect and thickness, this step is to set the expected thickness of each layer of coating according to the target and the characteristics of the coating.

[0176] The UV resin coating is sprayed according to the sub-thickness until the target thickness is reached: the UV resin coating is sprayed in layers by the spraying equipment according to the set sub-thickness until the target total thickness is reached. After the UV resin coating is sprayed to reach the target thickness, the sprayed surface is irradiated and cured by an ultraviolet lamp: in order to make the UV resin coating cure quickly, the coating surface is irradiated by an ultraviolet lamp.

[0177] The effect of the above technical solution is that the technical solution achieves precise control of the quality of the paint surface by precisely controlling the thickness of each layer and the total thickness, and using ultraviolet light for rapid curing. This control not only improves the flatness and uniformity of the paint surface, but also ensures that the coating has the required physical and chemical properties.

[0178] By setting the sub-thickness of each layer and adjusting it according to the viscosity of the paint, this technical solution can better cope with the spraying requirements of paints with different viscosities. This helps to avoid problems such as uneven spraying or overspray caused by too high or too low viscosity of the paint.

[0179] By using ultraviolet light for rapid curing, this technical solution shortens the curing time and improves production efficiency. At the same time, by controlling the exposure time and intensity of ultraviolet light, it can ensure that the coating is fully cured and obtains the desired properties.

[0180] In addition, the technical solution also takes into account the changes in the UV resin coating's UV absorption rate and the impact of historical curing times, which helps to more accurately predict and control the curing effect. By adjusting the UV exposure time and intensity, and controlling the UV resin coating's spraying strategy, the technical solution improves product quality and performance while also saving costs and time for the company.

[0181] In summary, this technical solution achieves precise control of the paint surface quality by precisely controlling the thickness of each layer, the total thickness, and using ultraviolet light for rapid curing. This control not only improves the quality and performance of the product, but also saves costs and time for the company.

[0182] In one embodiment of the present invention, the sub-thickness acquisition module includes:

[0183] The first sub-thickness acquisition module is used to spray three layers to reach the target thickness when the target thickness exceeds a preset thickness threshold; wherein the sub-thickness corresponding to each spray layer is obtained by the following formula:

[0184]

[0185] Among them, H1 represents the sub-thickness corresponding to the first coating layer from bottom to top; H2 represents the sub-thickness corresponding to the second coating layer from bottom to top; H3 represents the sub-thickness corresponding to the first coating layer from bottom to top;

[0186] The second sub-thickness acquisition module is used to achieve the target thickness after spraying two layers when the target thickness does not exceed the preset thickness threshold; wherein the sub-thickness corresponding to each spray layer is obtained by the following formula:

[0187]

[0188]

[0189] Among them, H1 represents the sub-thickness corresponding to the first coating layer from bottom to top; H2 represents the sub-thickness corresponding to the second coating layer from bottom to top; ΔH represents the compensation thickness.

[0190] The working principle of the above technical solution is: when the target thickness exceeds the preset thickness threshold, the target thickness is reached after three layers of spraying: when the required coating thickness is large, in order to ensure the quality and uniformity of the coating, three layers of spraying are selected. The thickness of each layer is calculated by a preset formula. When the target thickness does not exceed the preset thickness threshold, the target thickness is reached after two layers of spraying: when the required coating thickness is small, in order to improve production efficiency, two layers of spraying are selected. Similarly, the thickness of each layer is also calculated by a preset formula.

[0191] The effect of the above technical solution is that the technical solution realizes precise control of the paint surface quality by selecting the appropriate number of spray layers according to the target thickness and the viscosity of the UV resin coating and accurately calculating the thickness of each layer. This control not only ensures the uniformity and flatness of the coating, but also helps to avoid defects caused by overspray or underspray.

[0192] Through the preset thickness threshold, the technical solution can select the appropriate spraying strategy according to different coating requirements. When the target thickness is large, spraying three layers can ensure the quality and stability of the coating; when the target thickness is small, spraying two layers can improve production efficiency.

[0193] Using a preset formula to calculate the thickness of each layer, the technical solution can accurately control the coating thickness of each layer according to the viscosity characteristics of the paint. This helps to avoid problems such as uneven spraying or overspray caused by too high or too low viscosity.

[0194] In summary, this technical solution achieves precise control of the paint surface quality by selecting the appropriate number of spray layers according to the target thickness and the viscosity of the UV resin coating and accurately calculating the thickness of each layer. This control not only improves the quality and performance of the product, but also saves costs and time for the enterprise.

[0195] In one embodiment of the present invention, the defect monitoring module includes:

[0196] An image acquisition module, used to acquire image data corresponding to the paint surface using an image acquisition device, wherein the image acquisition device includes but is not limited to a camera;

[0197] A model retrieval module, used to retrieve a neural network model that has completed training and test optimization from a database, wherein the neural network model includes but is not limited to a convolutional neural network;

[0198] The recognition control module is used to input the image data corresponding to the paint surface into the neural network model, and recognize the image data through the neural network model, determine whether there are bubbles, shrinkage holes and cracks in the image data corresponding to the paint surface, and output the recognition result.

[0199] The working principle of the above technical solution is: using the image acquisition device to collect image data corresponding to the paint surface: using a high-resolution camera or other image acquisition equipment to capture real-time images of the coating surface. These image data contain key information such as the surface texture, color and structure of the coating.

[0200] Retrieve the trained and tested neural network models from the database: After repeated optimization with a large amount of training data and test data, the neural network models have the ability to identify different defects. These models can extract features from the input image data and make accurate judgments.

[0201] The image data corresponding to the paint surface is input into the neural network model, and the image data is recognized by the neural network model: after receiving the image data, the neural network model will perform a series of complex calculations and analyses to identify defects such as bubbles, shrinkage holes and cracks on the coating surface. This process is automated and does not require human intervention.

[0202] The effect of the above technical solution is that the technical solution realizes rapid and accurate detection of paint surface defects by combining the image acquisition device and the neural network model. Compared with traditional visual inspection or simple image processing methods, this method greatly improves the efficiency and accuracy of detection and reduces the possibility of misjudgment and missed detection.

[0203] Image data collected by high-resolution cameras can provide rich surface information, providing strong data support for the recognition of neural network models. The trained and optimized neural network model has powerful feature extraction and classification capabilities, and can accurately determine various defects on the coating surface.

[0204] This defect detection method based on image acquisition device and neural network model has broad application prospects. Whether it is automobile manufacturing, furniture manufacturing or electronic product manufacturing, this technical solution can be used for quality monitoring and defect detection to improve production efficiency and product quality.

[0205] In summary, this technical solution achieves rapid and accurate detection of paint surface defects by combining image acquisition devices and neural network models. This method improves production efficiency and product quality, saving costs and time for enterprises.

[0206] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A UV resin coating paint surface defect detection method, characterized in that: The UV resin coating paint surface defect detection method comprises: Extracting the coating volume corresponding to the UV resin to be detected, and using the coating volume corresponding to the UV resin to be detected to obtain the amount of photoinitiator and reactive diluent to be added; Adding a photoinitiator and a reactive diluent according to the added amounts to form a mixed UV resin coating; After the photoinitiator and the reactive diluent are fully mixed with the UV resin coating, the coating is controlled to be sprayed according to the target thickness of the UV resin coating to form a cured paint surface; The image acquisition device is used to collect the image information of the paint surface, and the neural network model is used to determine whether there are bubbles, shrinkage holes and cracks; Wherein, after the photoinitiator and the reactive diluent are fully mixed with the UV resin coating, the coating is controlled to be sprayed according to the target thickness of the UV resin coating to form a cured paint surface, including: Extracting a target thickness and a spraying strategy; wherein the spraying strategy includes reaching the target thickness after spraying two layers and reaching the target thickness after spraying three layers; Setting the sub-thickness of each layer according to the target thickness and the viscosity of the mixed UV resin coating; Spraying the UV resin coating according to the sub-thickness until the target thickness is reached; After the UV resin coating is sprayed to reach the target thickness, the sprayed surface is irradiated and cured using an ultraviolet lamp; wherein the irradiation time length and intensity of the ultraviolet light are obtained by the following formula: Among them, T g represents the duration of ultraviolet irradiation; H represents the value corresponding to the target thickness; T0 represents the unit time, which is 1000s; P represents the value corresponding to the power of the ultraviolet lamp; x represents the absorption rate of the current UV resin coating for ultraviolet rays; y represents the adjustment coefficient; m represents the number of spray layers corresponding to the spraying strategy; n represents the historical curing times of UV resin coatings with the same properties as the current UV resin coating; f xi Δf represents the change in the UV absorption rate of the UV resin coating cured for the i-th time; xi It indicates the theoretical change of the absorption rate for each unit thickness change of the UV resin coating spraying thickness, and the unit thickness value range is 0.7um-1.3um; Among them, U v It represents the irradiation intensity of ultraviolet light; H0 represents the preset thickness threshold; I represents the light intensity of the ultraviolet lamp; S represents the spraying area of ​​the UV resin coating.

2. The UV resin coating surface defect detection method according to claim 1, characterized in that: Extracting the coating volume corresponding to the UV resin to be detected, and using the coating volume corresponding to the UV resin to be detected to obtain the amount of photoinitiator and active diluent to be added, including: Extract the spraying area and spraying thickness corresponding to the UV resin to be tested; Obtaining the coating volume corresponding to the UV resin to be tested according to the spraying area and the spraying thickness; The amount of the photoinitiator and the reactive diluent to be added is determined according to the coating volume corresponding to the UV resin to be detected and the preset mass percentages of the photoinitiator and the reactive diluent.

3. The UV resin coating surface defect detection method according to claim 1, characterized in that: The sub-thickness of each layer is set according to the target thickness and the viscosity of the mixed UV resin coating, including: When the target thickness exceeds the preset thickness threshold, the target thickness is reached after three layers of spraying; wherein the sub-thickness corresponding to each layer of spraying is obtained by the following formula: Among them, H1 represents the sub-thickness corresponding to the first coating layer from bottom to top; H2 represents the sub-thickness corresponding to the second coating layer from bottom to top; H3 represents the sub-thickness corresponding to the first coating layer from bottom to top; When the target thickness does not exceed the preset thickness threshold, the target thickness is reached after two layers are sprayed; wherein the sub-thickness corresponding to each spray layer is obtained by the following formula: Among them, H1 represents the sub-thickness corresponding to the first coating layer from bottom to top; H2 represents the sub-thickness corresponding to the second coating layer from bottom to top; ΔH represents the compensation thickness.

4. The UV resin coating surface defect detection method according to claim 1, characterized in that: The image acquisition device is used to collect the paint surface image information, and the neural network model is used to determine whether there are bubbles, shrinkage holes and cracks, including: Using an image acquisition device to collect image data corresponding to the paint surface; Retrieve the neural network model that has completed training and test optimization from the database; The image data corresponding to the paint surface is input into a neural network model, and the image data is recognized by the neural network model to determine whether there are bubbles, shrinkage holes and cracks in the image data corresponding to the paint surface, and the recognition result is output.

5. A UV resin coating paint surface defect detection system, characterized in that: The UV resin coating paint surface defect detection system comprises: An information extraction module is used to extract the coating volume corresponding to the UV resin to be detected, and use the coating volume corresponding to the UV resin to be detected to obtain the amount of photoinitiator and active diluent to be added; A mixing control module, used for adding a photoinitiator and a reactive diluent according to the added amounts to form a mixed UV resin coating; A spraying control module, used for controlling the coating to be sprayed according to a target thickness of the UV resin coating after the photoinitiator and the reactive diluent are fully mixed with the UV resin coating to form a cured paint surface; A defect monitoring module is used to collect paint surface image information using an image acquisition device and determine whether there are bubbles, shrinkage holes and cracks using a neural network model; Wherein, the spraying control module includes: A strategy and thickness information extraction module, used to extract the target thickness and spraying strategy; wherein the spraying strategy includes reaching the target thickness after spraying two layers and reaching the target thickness after spraying three layers; A sub-thickness acquisition module, used to set the sub-thickness of each layer according to the target thickness and the viscosity of the mixed UV resin coating; A spraying execution module, used for spraying UV resin coating according to the sub-thickness until the target thickness is reached; The curing control module is used to irradiate and cure the sprayed surface with an ultraviolet lamp after the UV resin coating reaches the target thickness; wherein the irradiation time length and intensity of the ultraviolet light are obtained by the following formula: Among them, T g represents the duration of ultraviolet irradiation; H represents the value corresponding to the target thickness; T0 represents the unit time, which is 1000s; P represents the value corresponding to the power of the ultraviolet lamp; x represents the absorption rate of the current UV resin coating for ultraviolet rays; y represents the adjustment coefficient; m represents the number of spray layers corresponding to the spraying strategy; n represents the historical curing times of UV resin coatings with the same properties as the current UV resin coating; f xi Indicates the change in the UV absorption rate of the UV resin coating cured for the i-th time; Δf xi It indicates the theoretical change of the absorption rate for each unit thickness change of the UV resin coating spraying thickness, and the unit thickness value range is 0.7um-1.3um; Among them, U v It represents the irradiation intensity of ultraviolet light; H0 represents the preset thickness threshold; I represents the light intensity of the ultraviolet lamp; S represents the spraying area of ​​the UV resin coating.

6. The UV resin coating surface defect detection system according to claim 5, characterized in that: The information extraction module comprises: A spraying information extraction module is used to extract the spraying area and spraying thickness corresponding to the UV resin to be detected; A spraying volume acquisition module, used for acquiring the coating volume corresponding to the UV resin to be detected according to the spraying area and the spraying thickness; The substance addition control module is used to determine the amount of photoinitiator and active diluent to be added according to the coating volume corresponding to the UV resin to be detected and the preset mass percentage of the photoinitiator and the active diluent.

7. The UV resin coating surface defect detection system according to claim 5, characterized in that: The sub-thickness acquisition module includes: The first sub-thickness acquisition module is used to spray three layers to reach the target thickness when the target thickness exceeds a preset thickness threshold; wherein the sub-thickness corresponding to each spray layer is obtained by the following formula: Among them, H1 represents the sub-thickness corresponding to the first coating layer from bottom to top; H2 represents the sub-thickness corresponding to the second coating layer from bottom to top; H3 represents the sub-thickness corresponding to the first coating layer from bottom to top; The second sub-thickness acquisition module is used to achieve the target thickness after spraying two layers when the target thickness does not exceed the preset thickness threshold; wherein the sub-thickness corresponding to each spray layer is obtained by the following formula: Among them, H1 represents the sub-thickness corresponding to the first coating layer from bottom to top; H2 represents the sub-thickness corresponding to the second coating layer from bottom to top; ΔH represents the compensation thickness.

8. The UV resin coating surface defect detection system according to claim 5, characterized in that: The defect monitoring module comprises: An image acquisition module, used to acquire image data corresponding to the paint surface using an image acquisition device; The model retrieval module is used to retrieve the neural network model that has completed training and test optimization from the database; The recognition control module is used to input the image data corresponding to the paint surface into the neural network model, and recognize the image data through the neural network model, determine whether there are bubbles, shrinkage holes and cracks in the image data corresponding to the paint surface, and output the recognition result.

Images