Microelement analysis-based anti-aging prediction method and system for automobile paint protection film

Abstract

The application discloses an anti-aging prediction method and system for automobile paint surface protection film based on microelement analysis, and relates to the technical field of anti-aging evaluation of adhesive materials.The method comprises the following steps: based on the automobile paint surface protection film, a micro-spectral probe array is laid out, and a multi-spectral cooperative detection coordinate system is set; a dynamic material degradation characteristic map is constructed; meanwhile, a dynamic environment simulation cabin is configured, and an accelerated aging data set is obtained; the quantitative relationship between the microelement migration trajectory and the mechanical property degradation law is simulated, and the residual service life of the automobile paint surface protection film is inversely predicted in a cross-scale manner.The application solves the technical problems in the prior art that the microelement valence state distribution of the automobile paint surface protection film is difficult to accurately analyze, the residual service life prediction lacks cross-scale analysis means, and the aging prediction accuracy is insufficient, realizes the microelement valence state distribution analysis of the automobile paint surface protection film and the cross-scale inverse prediction of the residual service life, and improves the technical effect of the aging prediction accuracy of the protection film.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of adhesion material anti-aging evaluation, and particularly relates to an automobile paint protection film anti-aging prediction method and system based on microelement analysis. BACKGROUND

[0002] With the vigorous development of the automobile industry, the application of automobile paint protection film is increasingly widespread, which plays a key role in protecting automobile paint from scratches, oxidation, ultraviolet damage, etc. However, the existing automobile paint protection film anti-aging performance evaluation and life prediction technology has many deficiencies. On the one hand, the traditional detection method is difficult to accurately analyze the valence state distribution of microelements inside the protection film, and the migration rule of microelements in the aging process and the influence on the performance of the protection film are limited; on the other hand, in predicting the remaining service life of the protection film, there is a lack of cross-scale analysis means, and the correlation between microstructure changes and macro mechanical property degradation cannot be considered comprehensively, resulting in low prediction accuracy and difficulty in meeting the needs of scientific maintenance and timely replacement of the protection film in actual application.

[0003] The existing technology has the technical problems of difficulty in accurately analyzing the valence state distribution of microelements in automobile paint protection film, lack of cross-scale analysis means for predicting the remaining service life, and low accuracy of aging prediction. SUMMARY

[0004] The present application provides an automobile paint protection film anti-aging prediction method and system based on microelement analysis, which is used to solve the technical problems of difficulty in accurately analyzing the valence state distribution of microelements in automobile paint protection film, lack of cross-scale analysis means for predicting the remaining service life, and low accuracy of aging prediction in the prior art.

[0005] In view of the above problems, the present application provides an automobile paint protection film anti-aging prediction method and system based on microelement analysis.

[0006] In a first aspect of the present application, an automobile paint protection film anti-aging prediction method based on microelement analysis is provided, which comprises:

[0007] Based on the automobile paint protection film, the micro-spectral probe array is laid out, the micro-element valence state distribution of the automobile paint protection film is analyzed by X-ray photoelectron spectroscopy and Raman spectroscopy, and a multi-spectral collaborative detection coordinate system is set.

[0008] In a second aspect of the present application, an automobile paint protection film anti-aging prediction system based on micro-element analysis is provided, and the system comprises:

[0009] The detection coordinate system setting module is used for laying out a micro-spectral probe array based on the automobile paint protection film, analyzing the micro-element valence state distribution of the automobile paint protection film by X-ray photoelectron spectroscopy and Raman spectroscopy, and setting a multi-spectral collaborative detection coordinate system. The characteristic map construction module is used for mapping the micro-element distribution concentration and the chemical bond state change data in the multi-spectral collaborative detection coordinate system, and constructing a dynamic material degradation characteristic map. The accelerated aging data set acquisition module is used for simultaneously configuring a dynamic environment simulation cabin with ultraviolet radiation parameters, acidic corrosion parameters and temperature and humidity cyclic load to obtain an accelerated aging data set. The residual service life prediction module is used for simulating the quantitative relationship between the micro-element migration trajectory and the mechanical property degradation law in the dynamic material degradation characteristic map, combining the accelerated aging data set, and performing cross-scale reverse prediction of the residual service life of the automobile paint protection film.

[0010] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0011] Based on the automobile paint protection film, the micro-spectral probe array is laid out, the micro-element valence state distribution of the automobile paint protection film is analyzed by X-ray photoelectron spectroscopy and Raman spectroscopy, and a multi-spectral collaborative detection coordinate system is set. The characteristic map construction module is used for mapping the micro-element distribution concentration and the chemical bond state change data in the multi-spectral collaborative detection coordinate system, and constructing a dynamic material degradation characteristic map. The accelerated aging data set acquisition module is used for simultaneously configuring a dynamic environment simulation cabin with ultraviolet radiation parameters, acidic corrosion parameters and temperature and humidity cyclic load to obtain an accelerated aging data set. The residual service life prediction module is used for simulating the quantitative relationship between the micro-element migration trajectory and the mechanical property degradation law in the dynamic material degradation characteristic map, combining the accelerated aging data set, and performing cross-scale reverse prediction of the residual service life of the automobile paint protection film. BRIEF DESCRIPTION OF DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and all other drawings obtained by those of ordinary skill in the art without creative effort based on these drawings also belong to the protection scope of the present application.

[0013] Figure 1 A flowchart of an anti-aging prediction method for a car paint protective film based on micro-element analysis is provided in the embodiments of the present application.

[0014] Figure 2 A structural diagram of an anti-aging prediction system for a car paint protective film based on micro-element analysis is provided in the embodiments of the present application.

[0015] Legend: detection coordinate system setting module 10, feature map construction module 20, accelerated aging data set acquisition module 30, and residual service life prediction module 40. DETAILED DESCRIPTION

[0016] The present application provides an anti-aging prediction method and system for a car paint protective film based on micro-element analysis, which is used to solve the technical problems in the prior art that the micro-element valence distribution of the car paint protective film is difficult to accurately analyze, the residual service life prediction lacks cross-scale analysis means, and the aging prediction accuracy is insufficient.

[0017] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort belong to the protection scope of the present application.

[0018] Embodiment one, as shown in the present application provides an anti-aging prediction method for a car paint protective film based on micro-element analysis, which comprises: Figure 1

[0019] Step S100: based on the car paint protective film, a micro-area spectral probe array is arranged, the micro-element valence distribution of the car paint protective film is analyzed by X-ray photoelectron spectroscopy and Raman spectroscopy, and a multi-spectral collaborative detection coordinate system is set.

[0020] ​Specifically, first, based on the different positions and characteristic areas of the automobile paint protective film, a micro-spectral probe array is arranged, which can accurately collect local microscopic data. Then, X-ray photoelectron spectroscopy and Raman spectroscopy are used in combination. X-ray photoelectron spectroscopy can accurately determine the chemical state and valence state of elements, and Raman spectroscopy can effectively obtain the vibration information of chemical bonds. The two work together to comprehensively analyze the valence state distribution of microelements in the automobile paint protective film, and reveal the existence form of elements and the characteristics of chemical bonds from the microscopic level. On this basis, a multi-spectral collaborative detection coordinate system is set up, which integrates the spatial information of different spectral detection data. The micro-spectral probe array collection point is taken as the coordinate reference, and the valence state distribution data of various microelements are accurately positioned. This provides a unified and accurate spatial reference system for subsequent mapping of microelement distribution concentration and chemical bond state change data, and for constructing a dynamic material degradation characteristic map, ensuring the relevance of the data and the accuracy of the analysis.

[0021] Step S200: In the multi-spectral collaborative detection coordinate system, map the valence state distribution data of various microelements and the chemical bond state change data, and construct a dynamic material degradation characteristic map.

[0022] Specifically, for the microelement distribution concentration and chemical bond state change data in the multi-spectral collaborative detection coordinate system, the Apriori algorithm is used to mine the frequently occurring item sets and association rules. For example, the potential association between different microelement distribution concentrations and specific chemical bond state changes is analyzed, and those microelement combinations that frequently appear at the same time and their corresponding chemical bond state change patterns are found. These association rules are important basis for constructing the map. Then, the LSTM algorithm is used to process time series data, and the microelement distribution concentration and chemical bond state change data collected at different time points are arranged in chronological order into a time-space sequence and input into the LSTM network. The memory unit of LSTM can effectively capture the long-term dependencies in the data, such as the continuous influence of microelement migration on chemical bond state over a long period of time. Through the training and learning of the LSTM network, it will automatically extract features from the data, which reflect the trend and law of material degradation over time. Finally, the association rules mined by the Apriori algorithm are combined with the features extracted by the LSTM algorithm. According to the spatial structure of the multi-spectral collaborative detection coordinate system, these association rules and features are mapped to the corresponding positions to construct a dynamic material degradation characteristic map. If new data is obtained through the micro-crack capture instruction, or the confidence analysis of the map is performed based on the accelerated aging data set of the dynamic environment simulation cabin and it is found that the map needs to be updated, the Apriori algorithm and the LSTM algorithm are used to process the new data, and the map is correspondingly revised and improved, to ensure that the map can accurately reflect the material degradation characteristics of the automobile paint protective film at different stages.

[0023] Step S300: At the same time, configure a dynamic environment simulation cabin with ultraviolet radiation parameters, acid corrosion parameters, and temperature and humidity cycle load to obtain an accelerated aging data set.

[0024] Specifically, by configuring a dynamic environment simulation cabin to simulate real-world usage scenarios, precise ultraviolet radiation parameters are set according to the intensity and duration of ultraviolet radiation that the car paint protection film may encounter in actual use, simulating the aging effect of sunlight on the protection film. Considering the acid corrosion effects of acid rain, industrial pollution, etc., determine the acid corrosion parameters to simulate the erosion process of acidic substances on the protection film. At the same time, according to the temperature and humidity variation law of different regions, set the temperature and humidity cycle load to simulate the aging of the protection film in the alternating temperature and humidity environment. In this simulation cabin, various high-precision sensors are deployed to monitor and record the performance changes of the car paint protection film under the action of different environmental parameters, such as microelement migration, chemical bond rupture, color change, and mechanical property change. As the simulation time progresses, these data accumulate to form an accelerated aging data set. This data set not only contains the aging information of the protection film caused by multiple harsh environments in a short time, but also provides key data support for subsequent simulation of microelement migration trajectory and prediction of mechanical property degradation law based on dynamic material degradation characteristic map, and further realizes accurate prediction of the remaining service life of the car paint protection film. Moreover, by deploying a transfer learning framework, the simulation cabin data and multi-climate environment monitoring data are adapted to the domain, and the performance evolution map of the material under extreme environmental conditions is synthesized using a generative adversarial network, continuously optimizing and enriching the accelerated aging data set and improving its representativeness for actual complex environments.

[0025] Step S400: In the dynamic material degradation characteristic map, combine the accelerated aging data set to simulate the quantitative relationship between the microelement migration trajectory and the mechanical property degradation law, and perform cross-scale reverse prediction of the remaining service life of the car paint protection film.

[0026] Specifically, the microelement distribution concentration, chemical bond state change data in the dynamic material degradation feature map, and the environmental parameters and material performance change data in the accelerated aging data set are preprocessed to meet the algorithm input requirements. Using the finite element analysis method, according to the material properties, microelement distribution and environmental load conditions of the protective film, the migration process of microelements at different time steps is simulated, and a numerical model of microelement migration is established, so as to obtain the microelement migration trajectory. Then, the convolutional neural network (CNN) is used to extract features from the microelement migration trajectory data and the corresponding mechanical property change data. The convolution layer of CNN can automatically learn the local features in the data, and the pooling layer is used to reduce the data dimension and retain the key features. Through multi-layer convolution and pooling operations, deep features between microelement migration and mechanical property degradation are extracted. These features are input into the long short-term memory network (LSTM), which can effectively process time series data and capture the trend and long-term dependence of microelement migration and mechanical property degradation over time, thereby establishing a quantitative relationship model between the two. In terms of cross-scale reverse prediction, based on the established quantitative relationship model, starting from the current macro mechanical property data of the protective film, the history of microelement migration is inversely calculated, and the future migration of microelements and the resulting mechanical property changes are predicted. When the mechanical property reaches the pre-set failure threshold, the corresponding time is the remaining service life of the automotive paint protective film. During the prediction process, the model will be updated and optimized according to the newly acquired micro-crack capture instruction data, interfacial adhesion change and other information to improve the prediction accuracy.

[0027] In one possible implementation, step S100 further includes:

[0028] Step S110: Based on the micro-spectral probe array, a fiber Bragg grating sensor network is established to collect elastic wave signals generated by micro-crack propagation and extract crack propagation rate characteristic frequency band energy values.

[0029] Step S120: When the crack propagation rate characteristic frequency band energy value exceeds the characteristic frequency band energy threshold under the material fracture toughness threshold, the damage area is located.

[0030] Specifically, a pre-arranged micro-spectral probe array is used to build a fiber Bragg grating sensor network. The fiber Bragg grating sensor has extremely high sensitivity and the ability to perceive environmental changes. When micro-crack propagation occurs inside the car paint protective film, this process will trigger the propagation of elastic waves in the protective film material. These elastic waves will cause a small strain in the surrounding fiber Bragg grating sensors during propagation. Based on the optical properties of fiber Bragg grating, the generation of strain will cause the corresponding change in the center wavelength of the reflected light. By continuously monitoring the change in reflected light wavelength through optical demodulation equipment, the elastic wave signal generated by micro-crack propagation can be collected. Subsequently, digital signal processing technology is used to analyze the collected elastic wave signal in depth. First, the noise interference in the signal is removed through filtering algorithm to improve the quality of the signal. Then, frequency spectrum analysis method such as fast Fourier transform (FFT) is used to convert the time-domain elastic wave signal to frequency domain and find out the characteristic frequency band closely related to the crack propagation rate. Within these characteristic frequency bands, the crack propagation rate characteristic frequency band energy value is extracted. This energy value serves as a key indicator for quantifying the degree of micro-crack propagation, providing important data support for subsequent evaluation of the damage condition of the protective film.

[0031] When the crack propagation rate characteristic frequency band energy value exceeds the characteristic frequency band energy threshold set according to the material fracture toughness threshold, the damage area positioning program is started. At this time, the infrared thermal imaging array deployed on the surface of the protective film begins to play a role, continuously monitoring the temperature field distribution on the surface of the protective film at a high frequency. Due to the latent heat characteristics of the phase change material, which absorbs or releases a large amount of heat during the change of physical state, a thermal shock damage accumulation index is set based on this characteristic. This index can quantify the damage degree of the protective film caused by thermal shock due to factors such as micro-crack propagation. In the suspected damage area, the local temperature rise rate is continuously monitored based on the thermal shock damage accumulation index. Once an abnormal local temperature rise rate is detected, it indicates that there is a high possibility of micro-crack propagation intensification or other damage at this location, and the micro-crack capture instruction is activated. This instruction will mobilize relevant image acquisition and analysis equipment to accurately capture the specific location and propagation direction of the micro-crack in the protective film using image processing algorithms, providing key information for subsequent evaluation of damage degree, development of repair strategies, and triggering of on-demand release of microcapsule antioxidants, thereby ensuring the protective performance and service life of the car paint protective film.

[0032] In one possible implementation, step S120 further includes:

[0033] Step S121: deploy an infrared thermal imaging array to continuously monitor the temperature field distribution on the surface of the protective film, and set a thermal shock damage accumulation index based on the latent heat characteristics of the phase change material.

[0034] Step S122: In the damage area, using the thermal shock damage cumulative index, when detecting abnormal local temperature rise rate, activate the micro-crack capture instruction, which is used to capture the micro-crack position and micro-crack propagation direction.

[0035] Specifically, the quantitative monitoring of thermal shock damage is achieved by deploying an infrared thermal imaging array combined with the characteristics of phase change materials. On the surface of the automobile paint protection film, an infrared thermal imaging array is uniformly deployed, which can monitor the temperature of the protection film surface in real time with high sensitivity and high frequency, and convert invisible thermal radiation into intuitive temperature field distribution images. Due to the factors such as micro-crack propagation and friction during the use of the automobile paint protection film, local temperature changes will occur, which are closely related to the damage of the protection film. Phase change materials have unique latent heat characteristics, which can absorb or release a large amount of heat when they undergo a physical state change. By using this characteristic, the thermal shock damage cumulative index is set by combining the data monitored by the infrared thermal imaging array. First, the phase change temperature range and latent heat value of the phase change material under certain conditions are determined, and the corresponding relationship between temperature change and thermal shock energy is established based on this. Real-time temperature data of the protection film surface is obtained by the infrared thermal imaging array, and the temperature change trend and amplitude are analyzed. When the temperature change involves the phase change process of the phase change material, the heat absorbed or released is calculated according to the latent heat of phase change, and is accumulated. This cumulative value is the thermal shock damage cumulative index, which comprehensively reflects the damage degree of the protection film under the action of thermal shock, and provides an important quantitative basis for subsequent judgment of whether the protection film has serious damage and whether further measures need to be taken.

[0036] After determining the damage area of the automobile paint protection film, the thermal shock damage cumulative index set in the early stage is used to further investigate the micro-crack situation. Temperature data is continuously collected in the damage area, and the local temperature rise rate is calculated in real time based on the thermal shock damage cumulative index, which considers the latent heat characteristics of the phase change material and the temperature field distribution, and can accurately reflect the influence of thermal shock on the protection film. When the local temperature rise rate is detected to be abnormal, it is likely that the local heat production is abnormal due to factors such as friction and stress concentration during the propagation of micro-cracks. At this time, the micro-crack capture instruction is activated quickly. This instruction will mobilize professional equipment such as high-resolution microscopes and ultrasonic flaw detectors, and use image processing and pattern recognition algorithms to conduct comprehensive scanning of the damage area. The microscope can clearly present the microstructure of the protection film surface, and the ultrasonic flaw detector can detect the hidden micro-cracks inside. By analyzing the collected images and signals, the specific position of the micro-crack is accurately identified, and the propagation direction of the micro-crack is determined according to the morphological changes of the micro-crack at different times.

[0037] In one possible implementation, step S100 further includes:

[0038] Step S130: The intermediate layer of the automobile paint protection film is a microcapsule antioxidant, and the substrate layer of the automobile paint protection film is a shape memory polymer.

[0039] Step S140: According to the distribution concentration of each microelement, the three-dimensional molecular chain network of the protection film is reconstructed.

[0040] Step S150: Using the reconstructed three-dimensional molecular chain network of the protection film, the correlation between the quantum chemistry prediction cross-linking bond breaking energy threshold and the free radical generation rate is analyzed, and when abnormal aggregation of zinc element is detected, the antioxidant consumption reminder is triggered and the supplementary coating is determined.

[0041] Specifically, the automobile paint protection film is composed of specific materials, among which the intermediate layer contains microcapsule antioxidants, and the substrate layer adopts shape memory polymer, laying the foundation for the performance of the protection film. The microcapsule antioxidant in the intermediate layer can release antioxidant substances when needed to inhibit the oxidation of the paint surface; the shape memory polymer in the substrate layer gives the protection film certain self-repairing ability, which can restore to its original state after being slightly damaged.

[0042] By using high-resolution spectral imaging technology combined with micro-spectral probe array, the microelement distribution concentration data at different positions in the automobile paint protection film can be accurately obtained, and these data are accurate to nanometer scale. Then, using atom probe tomography technology (APT), the mutual position relationship between microelements and molecular chains at atomic scale is directly observed, which further assists in determining the connection information of molecular chains. In terms of computational simulation, molecular dynamics simulation software is used to model based on the obtained microelement distribution data. In the software, microelements are regarded as special atomic types, which are placed in the simulation space according to the actual measured concentration distribution, and the interaction potential function between microelements and atoms constituting the protection film molecules is used to describe their interaction force. For example, for the interaction between metal microelements and organic molecular chains, metal-organic interaction potential is used for simulation. In the simulation process, appropriate environmental conditions such as temperature and pressure are set to simulate the thermal motion and interaction process of molecular chains in the actual use environment. Through long-time simulation evolution, the molecular chains naturally grow and cross-link under the influence of microelements, gradually forming a three-dimensional molecular chain network structure.

[0043] After the reconstruction of the three-dimensional molecular chain network of the automobile paint protection film is completed, the relationship between the cross-linking bond breaking energy threshold and the free radical generation rate is analyzed on the reconstructed three-dimensional molecular chain network model by means of quantum chemical calculation method. By accurately calculating the quantum chemical parameters such as molecular orbital energy level and electron cloud distribution, the stability of cross-linking bond and the generation process of free radical under different conditions are simulated. The cross-linking bond is the key connection to maintain the stability of the molecular structure of the protection film, and its breaking energy threshold reflects the ability to resist damage; while the free radical as a highly active chemical species, its generation rate affects the aging and degradation speed of the molecular chain. By analyzing the correlation between the two, the aging process of the protection film under the action of various environmental factors can be understood from the microscopic level. In real-time monitoring, once abnormal aggregation of zinc element is detected, a series of response measures will be started. The abnormal aggregation of zinc element often indicates that the chemical reaction inside the protection film is out of balance, which may accelerate the generation of free radicals, and then cause the cross-linking bond to break, resulting in the degradation of the performance of the protection film. At this time, the antioxidant consumption reminder is triggered, informing the relevant personnel that the consumption speed of the antioxidant in the protection film is accelerated and needs to be paid attention to in time. At the same time, based on the analysis of the reconstructed three-dimensional molecular chain network, combined with the microstructure changes of the zinc element aggregation area and the damage of the surrounding molecular chain, the type and position of the coating that needs to be supplemented are determined. For example, if it is found that the cross-linking bond of the molecular chain near the zinc element aggregation area is severely broken, and a large number of free radicals are generated, it can be determined that a coating containing specific antioxidant components and repair materials is supplemented in this area to repair the damaged molecular chain structure, enhance the antioxidant ability of the protection film, restore its protective performance, and prolong the service life of the automobile paint protection film.

[0044] In one possible implementation manner, the step S130 further includes:

[0045] Step S131: Collect the captured micro-crack positions and micro-crack propagation directions by the micro-crack capturing instruction to determine the interfacial bonding force.

[0046] Step S132: Trigger the on-demand release of the microcapsule antioxidant when the interfacial bonding force decreases to a bonding force critical value.

[0047] Specifically, first, the Canny edge detection algorithm is used to process the images collected by the high-resolution microscope. The Gaussian filter is used to remove noise, calculate the gradient amplitude and direction, apply non-maximum suppression to refine the edges, and determine the true and potential edges using the double-threshold algorithm. The edge profile of the micro-crack is accurately extracted, and the position and shape parameters of the micro-crack are determined. For the signal data obtained by ultrasonic flaw detection, the short-time Fourier transform (STFT) algorithm is used to convert the time-domain signal into a time-frequency two-dimensional graph. The characteristics of the echo signal at different times and frequencies are analyzed, and the wavelet denoising algorithm is used to remove the interference in the signal, so as to accurately determine the position and expansion direction of the micro-crack inside the protective film. Subsequently, the finite element analysis algorithm is used to divide the protective film into a finite number of units based on the theory of elasticity. According to the position and expansion direction of the micro-crack, the boundary conditions and loads are set, and the stress intensity factor at the tip of the micro-crack is calculated by solving the linear equation system. At the same time, the support vector machine regression (SVR) algorithm is introduced. A large number of historical data containing micro-crack characteristics (such as length, width, expansion angle, stress intensity factor, etc.) and corresponding interfacial adhesion are used as the training set to construct a nonlinear mapping model of micro-crack characteristics and interfacial adhesion. The micro-crack characteristic data obtained at present is input into the trained SVR model, and the interfacial adhesion value of the protective film is calculated to realize the accurate calculation from the micro-crack information to the interfacial adhesion.

[0048] The interfacial adhesion value is continuously monitored and compared with the pre-set adhesion critical value in real time. The critical value is determined through a large number of material mechanics experiments, aging tests, and actual use scenario simulations. It is an important dividing line for whether the performance of the protective film is within a safe range. Once the interfacial adhesion decreases to the adhesion critical value, it means that the interaction between molecular chains is weakened due to the expansion of micro-cracks, environmental erosion, and other factors in the protective film, and the interfacial structure is damaged, and the oxidation risk increases sharply. At this time, the on-demand release mechanism of the microcapsule antioxidant is triggered immediately. The microcapsules in the middle layer of the automobile paint protective film are made of special high molecular materials and can stably wrap the antioxidant under normal conditions. When the release instruction is triggered, the microcapsules will rupture due to changes in the surrounding environmental stress, temperature rise, or pH change, and release the internal antioxidant to the damaged area of the protective film. The antioxidant rapidly diffuses and reacts with free radicals, effectively inhibiting the further development of the oxidation reaction, repairing the damaged molecular chain structure, and enhancing the interfacial adhesion, thereby timely blocking the deterioration trend of the protective film performance and prolonging its service life, providing continuous and reliable protection for the automobile paint.

[0049] In one possible implementation, step S300 further includes:

[0050] Step S310: Deploy a transfer learning framework to domain adapt the dynamic environment simulation chamber data to the multi-climate environment monitoring data, and synthesize the material performance evolution map under extreme environmental conditions through a generative adversarial network.

[0051] Step S320: According to the material performance evolution map, perform confidence analysis on the dynamic material degradation feature map, and if the confidence is lower than the confidence threshold, update the dynamic material degradation feature map with the micro-crack capture instruction.

[0052] Specifically, a transfer learning framework based on deep convolutional neural network (DCNN) is deployed. The data generated by the dynamic environment simulation chamber and the multi-climate environment monitoring data are preprocessed respectively, including normalization, filtering and feature extraction. The DCNN is used to extract the deep feature representation of the two kinds of data. To solve the problem of domain difference, the maximum mean discrepancy (MMD) algorithm is introduced to minimize the difference between the feature distributions of the two data sets to achieve domain adaptation. During the training process of DCNN, the network parameters are constantly adjusted to reduce the MMD loss, so that the simulation chamber data and the actual monitoring data are as close as possible in the feature space. Then, a generative adversarial network (GAN) is constructed to synthesize the material performance evolution map under extreme environmental conditions. GAN consists of a generator (G) and a discriminator (D). The generator uses long short-term memory network (LSTM) because it is good at processing sequence data and is suitable for simulating the evolution of material performance over time. The discriminator uses convolutional neural network (CNN) to distinguish between generated maps and real extreme environment material performance data. During the training process, the generator tries to generate realistic extreme environment material performance evolution maps, while the discriminator tries to distinguish between true and false data. Through continuous adversarial training, the performance of both is improved. The goal is to minimize the loss function of the generator and the discriminator. The parameters of the generator and the discriminator are updated alternately until the generator can generate high-quality extreme environment material performance evolution maps consistent with the distribution of real data, providing a reliable basis for subsequent material performance analysis and prediction.

[0053] The random forest algorithm is used to analyze and update the dynamic material degradation feature map. First, the material performance evolution map and the key performance index data (such as the change value of tensile strength and light transmittance with time) in the dynamic material degradation feature map are taken as characteristic variables, and a small amount of actual accuracy labels annotated by humans are introduced as target variables to construct a training data set. The random forest algorithm is used to train the model on the training set. This algorithm constructs multiple decision trees, randomly selects some features for optimal partitioning at each tree node split, and finally determines the prediction result through majority voting (classification) or averaging (regression). After training, the dynamic material degradation feature map data to be evaluated is input into the trained random forest model, and the model outputs the matching degree prediction value of the map with the material performance evolution map, which is used as the confidence level. If the confidence level is lower than the pre-set threshold, the micro-crack capture instruction is triggered, and the protective film image is collected through a high-resolution microscope. The target detection algorithm based on convolutional neural network (CNN), such as YOLO series algorithm, is used to identify and locate the micro-cracks in the image, and obtain the position, length, and expansion direction of the micro-cracks. Finally, these new data are added to the database of the dynamic material degradation feature map as new characteristic variables, and the random forest model is retrained to update the dynamic material degradation feature map, ensuring that it can accurately reflect the actual degradation state of the protective film.

[0054] In one possible implementation manner, the step S122 further includes:

[0055] Step S1221: Based on historical failure cases, analyze the relationship between sulfur element penetration depth and yellowing index, and mine the spatial correlation features of the anisotropic degradation mode of the automobile paint protective film.

[0056] Step S1222: Formulate an anisotropic degradation prediction path based on the spatial correlation features of the anisotropic degradation mode of the automobile paint protective film, and the anisotropic degradation prediction path is used for capturing and clipping optimization of the micro-crack capture instruction.

[0057] Specifically, the relationship between the sulfur element penetration depth and the yellowing index is analyzed by a multiple linear regression algorithm, and the spatial correlation characteristics of the anisotropic degradation mode are mined using a geographic weighted regression (GWR) algorithm. First, the sulfur element penetration depth, environmental temperature, humidity, and other factors that may affect the yellowing index in historical failure cases are input into the multiple linear regression model as independent variables, and the yellowing index is input as the dependent variable. The least squares method is used to optimize the model parameters, and the influence coefficients of each factor on the yellowing index are solved to establish a quantitative relationship model between the sulfur element penetration depth and the yellowing index. For mining the spatial correlation characteristics of the anisotropic degradation mode, the protective film is divided into multiple grid cells according to the spatial position, and the sulfur element penetration depth, micro-crack density, and other degradation indicators in each grid cell are used as attribute data. Combined with geographic coordinate information, the geographic weighted regression algorithm is used. This algorithm assigns different weights to each observation point, estimates the regression coefficients by local weighted least squares method, captures the non-stationarity of the degradation indicators in space, analyzes the spatial correlation rules between different positions of the anisotropic degradation mode, and identifies the aggregation and directionality of the spatial distribution of sulfur element penetration and other degradation characteristics, providing key data support for subsequent degradation analysis.

[0058] The anisotropic degradation prediction path is formulated by using a long short-term memory network (LSTM) algorithm, and the path is used to optimize the micro-crack capture instruction. First, the spatial correlation characteristics of the anisotropic degradation mode of the automotive paint protective film are sorted into time series data, which contain information such as the sulfur element penetration depth, yellowing index, and micro-crack development in different positions and directions. These time series data are input into the LSTM model. The LSTM model can handle long-term dependencies in sequence data, and its internal memory cells and gating mechanisms can effectively capture complex dynamic changes in the degradation process of the protective film. In the training stage, the historical degradation data is used to train the model, and the weight parameters of the model are continuously adjusted by the back propagation algorithm to minimize the error between the predicted value and the actual value. The trained LSTM model can predict the anisotropic degradation at different time points in the future and generate an anisotropic degradation prediction path. The path describes the degradation trend of the protective film in various positions and directions in detail. Next, according to the generated anisotropic degradation prediction path, the greedy algorithm is used to capture and optimize the micro-crack capture instruction. The greedy algorithm makes the best choice at each step, judges which areas and directions are more likely to have micro-cracks in the future according to the prediction path, and preferentially increases the frequency and accuracy of micro-crack capture in these high-risk areas, while appropriately reducing the capture operation in low-risk areas. Thus, under the premise of ensuring timely detection of micro-cracks, unnecessary detection costs are reduced, and the efficiency and targeting of micro-crack capture are improved.

[0059] In one possible implementation manner, step S132 further includes:

[0060] Step S1321: deploying a terahertz spectrum scanning device to non-contact measure the spatial distribution of the dielectric constant of the automobile paint protective film, and analyze the polarization response characteristics of the filler agglomerates.

[0061] Step S1322: dynamically optimizing the release path of the microcapsule antioxidant based on the polarization response characteristics of the filler agglomerates.

[0062] Specifically, the automobile paint protective film is detected non-invasively by using a terahertz spectrum scanning device. Terahertz waves can penetrate the surface layer of the protective film and interact with the internal material, producing different reflection and transmission signals according to the difference in the dielectric constant of the material. The device emits terahertz waves and receives the reflected signals, converts the time-domain signals into frequency-domain signals through signal processing algorithms such as Fourier transform, and then accurately analyzes the dielectric constant of each region of the protective film to construct a spatial distribution map of the dielectric constant. The change in the dielectric constant is closely related to the internal structure and composition distribution of the protective film. By analyzing the spatial distribution of the dielectric constant, the position and size of the filler agglomerates can be identified. At the same time, the polarization response of the filler agglomerates under the action of the terahertz electric field is measured by using the terahertz time-domain spectroscopy technology. The polarization response characteristics reflect the interaction between the filler agglomerates and the surrounding medium. By analyzing the polarization relaxation process of the filler agglomerates under different frequencies and different electric field strengths, the key parameters of the polarization response, such as the polarizability and the relaxation time, are obtained.

[0063] Based on the obtained polarization response characteristics of the filler agglomerates, the release path of the microcapsule antioxidant is dynamically optimized. The polarization response characteristics of the filler agglomerates can reflect the changes in the microenvironment and material properties in the local area inside the protective film, such as stress concentration and limited molecular chain movement, which are more prone to oxidation. According to the polarization response parameters, the release path of the microcapsule antioxidant is optimized by using a genetic algorithm. The genetic algorithm simulates the biological evolution process to optimize the starting point, ending point and transmission trajectory of the release path, aiming to optimize the release efficiency and antioxidant effect of the microcapsule. In the optimization process, the dielectric constant distribution inside the protective film and the position of the filler agglomerates are considered to determine the release timing and release amount of the microcapsule in different areas. For areas with strong polarization response and high oxidation risk, the release path is planned in priority to enable the microcapsule antioxidant to quickly reach and release, thereby timely inhibiting the oxidation reaction and effectively improving the antioxidant performance and service life of the protective film.

[0064] In one possible implementation manner, step S400 further includes:

[0065] Step S410: In the dynamic material degradation feature map, simulate the failure risk thermodynamic map of the automobile paint surface protection film under different maintenance cycles.

[0066] Step S420: Based on the failure risk thermodynamic map of the automobile paint surface protection film, make periodic automobile paint maintenance judgments in combination with the remaining service life and failure safety threshold, and synchronize the judgment results to the user terminal.

[0067] Specifically, convolutional neural network (CNN) is used in combination with Monte Carlo simulation algorithm to simulate the failure risk thermodynamic map of the automobile paint surface protection film under different maintenance cycles. First, multi-dimensional data such as micro-crack size, distribution, micro-element content change, mechanical performance index at different time points are extracted from the dynamic material degradation feature map, which are arranged into three-dimensional tensor data format suitable for CNN processing. The processed data is input into the pre-trained CNN model, which has been trained on a large number of similar protection film degradation data and can automatically learn the complex features and patterns in the data. CNN extracts local features through convolutional layers, reduces feature dimension through pooling layers, and outputs the probability of failure type that may occur in each region under different maintenance cycles through full connection layer. Then, Monte Carlo simulation algorithm is used to further analyze these failure probabilities. Monte Carlo simulation considers the uncertainty of environmental factors (such as temperature, humidity, ultraviolet radiation, etc.) and use conditions (such as scratching frequency, cleaning method, etc.) through random sampling. For each influencing factor, a reasonable probability distribution is set, and then a large number of random sampling simulations are performed. Each sampling calculates the failure risk value of each region of the protection film according to the failure type probability output by CNN, combined with the structure and material properties of the protection film. After multiple simulations, statistical analysis is performed on all simulation results to obtain the average failure risk value of each region under different maintenance cycles. Finally, these risk values are mapped to color space, and a visual failure risk thermodynamic map is generated using thermodynamic mapping algorithm, with different colors representing different failure risk levels, thereby providing a scientific basis for the maintenance of automobile paint surface protection film.

[0068] The risk value of the area in the failure risk thermal map is quantitatively graded, for example, the high-risk area (marked in red) is assigned a risk score of 90-100, the medium-risk area (marked in yellow) is assigned a risk score of 60-89, and the low-risk area (marked in green) is assigned a risk score of 0-59. At the same time, the current remaining service life data of the protective film is extracted from the dynamic material degradation characteristic map, and a preset failure safety threshold (such as remaining service life less than 3 months or risk score exceeding 80, which triggers maintenance warning) is called. Adopting decision tree algorithm for maintenance determination: if the risk score of a certain area reaches or exceeds the failure safety threshold, regardless of the remaining service life, it is determined to maintain immediately; if the risk score does not reach the threshold, but the remaining service life is less than the preset safety period (such as 1 month), it is also determined to maintain; if the risk score and the remaining service life are both in the safe range, it is determined not to maintain. After the determination is completed, the results are transmitted to the user terminal through the RESTful API interface. If it is determined to maintain, the terminal will push the maintenance suggestion in the form of pop-up window, voice reminder, etc., including recommended maintenance time, applicable maintenance products and nearby professional maintenance stores; if it is determined to be in a safe state, the current health report of the protective film and the next detection reminder are pushed to ensure that the user can grasp the state of the protective film in time and take appropriate measures.

[0069] In the second embodiment, based on the same inventive concept as the anti-aging prediction method of the automotive paint protective film based on microelement analysis in the foregoing embodiments, as shown in Figure 2 The present application provides an anti-aging prediction system for automotive paint protective film based on microelement analysis, and the system and method embodiments in the present application are based on the same inventive concept. The system comprises:

[0070] The detection coordinate system setting module 10 is used to set up a micro-area spectral probe array based on the automotive paint protective film, analyze the valence state distribution of microelements of the automotive paint protective film by X-ray photoelectron spectroscopy and Raman spectroscopy, and set up a multi-spectral collaborative detection coordinate system.

[0071] The characteristic map construction module 20 is used to map the distribution concentration of each microelement and the chemical bond state change data in the multi-spectral collaborative detection coordinate system, and construct a dynamic material degradation characteristic map.

[0072] The accelerated aging data set acquisition module 30 is used to simultaneously configure a dynamic environment simulation cabin with ultraviolet radiation parameters, acid corrosion parameters and temperature and humidity cycle load to acquire an accelerated aging data set.

[0073] The remaining service life prediction module 40 is used to simulate the quantitative relationship between the microelement migration trajectory and the mechanical property degradation law in the dynamic material degradation characteristic map in combination with the accelerated aging data set, and perform cross-scale reverse prediction of the remaining service life of the automotive paint protective film.

[0074] Further, the system is also used to realize the following functions:

[0075] Based on the micro-spectral probe array, a fiber Bragg grating sensor network is established to collect elastic wave signals generated by micro-crack propagation and extract crack propagation rate characteristic frequency band energy values; when the crack propagation rate characteristic frequency band energy values exceed the characteristic frequency band energy threshold under the material fracture toughness threshold, the damage area is located.

[0076] Further, the system is also used to realize the following functions:

[0077] Deploy an infrared thermal imaging array to continuously monitor the surface temperature field distribution of the protective film, set a thermal shock damage accumulation index combined with the latent heat characteristics of the phase change material; in the damage area, use the thermal shock damage accumulation index, when detecting abnormal local temperature rise rate, activate the micro-crack capture instruction, which is used to capture the micro-crack position and micro-crack propagation direction.

[0078] Further, the system is also used to realize the following functions:

[0079] The middle layer of the automobile paint protective film is a microcapsule antioxidant, and the substrate layer of the automobile paint protective film is a shape memory polymer; according to the distribution concentration of each microelement, the three-dimensional molecular chain network of the protective film is reconstructed; using the reconstructed three-dimensional molecular chain network of the protective film, the correlation between the quantum chemical prediction cross-linking bond breaking energy threshold and the free radical generation rate is analyzed, and when zinc element abnormal aggregation is detected, the antioxidant consumption reminder is triggered and the supplementary coating is determined.

[0080] Further, the system is also used to realize the following functions:

[0081] The captured micro-crack position and micro-crack propagation direction obtained by the micro-crack capture instruction are used to determine the interfacial bonding force; when the interfacial bonding force decreases to the bonding force critical value, the on-demand release of the microcapsule antioxidant is triggered.

[0082] Further, the system is also used to realize the following functions:

[0083] Deploy a transfer learning framework to domain adapt the dynamic environment simulation cabin and multi-climate environment monitoring data, and synthesize the material performance evolution map under extreme environmental conditions through the generative adversarial network; according to the material performance evolution map, the confidence of the dynamic material degradation feature map is analyzed, and if the confidence is lower than the confidence threshold, the dynamic material degradation feature map is updated with the micro-crack capture instruction.

[0084] Further, the system is also used to realize the following functions:

[0085] Based on historical failure cases, the relationship between the penetration depth of sulfur element and the yellowing index is analyzed, and the spatial correlation characteristics of the anisotropic degradation mode of the automobile paint protective film are mined; through the spatial correlation characteristics of the anisotropic degradation mode of the automobile paint protective film, an anisotropic degradation prediction path is formulated, and the anisotropic degradation prediction path is used for capturing and cutting optimization of the micro-crack capturing instruction.

[0086] Further, the system is also used to realize the following functions:

[0087] The terahertz spectrum scanning device is deployed, the dielectric constant spatial distribution of the automobile paint protective film is non-contact measured, and the polarization response characteristics of the filler aggregate are analyzed; based on the polarization response characteristics of the filler aggregate, the release path of the microcapsule antioxidant is dynamically optimized.

[0088] Further, the system is also used to realize the following functions:

[0089] In the dynamic material degradation feature map, the failure risk thermodynamic map of the automobile paint protective film under different maintenance periods is simulated; based on the failure risk thermodynamic map of the automobile paint protective film, the periodic automobile paint maintenance is determined in combination with the remaining service life and the failure safety threshold, and the determination result is synchronized to the user terminal.

[0090] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the above describes a specific embodiment of the present application. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0091] The above only describes the preferred embodiments of the present application, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0092] The present application is only an exemplary description of the present application, and should be considered to cover any and all modifications, changes, combinations or equivalents within the scope of the present application. Obviously, those skilled in the art can make various modifications and changes to the present application without departing from the scope of the present application. Thus, if these modifications and changes of the present application belong to the scope of the present application and its equivalent technology, the present application intends to include these modifications and changes.

Claims

1. A method for predicting the anti-aging properties of automotive paint protective films based on micro-element analysis, characterized in that, The method includes: Based on the automotive paint protection film, a micro-area spectral probe array is deployed, including establishing a fiber Bragg grating sensor network based on the micro-area spectral probe array, collecting elastic wave signals generated by microcrack propagation, and extracting the energy value of the characteristic frequency band of crack propagation rate. When the energy value of the characteristic frequency band of the crack propagation rate exceeds the characteristic frequency band energy threshold under the material fracture toughness threshold, the damage area is located. The valence state distribution of micro-elements in automotive paint protection film was analyzed by combining X-ray photoelectron spectroscopy with Raman spectroscopy, and a multispectral collaborative detection coordinate system was established. In the multispectral collaborative detection coordinate system, the distribution concentration and chemical bond state change data of each micro-element are mapped to construct a dynamic material degradation characteristic map. Meanwhile, a dynamic environment simulation chamber was configured with ultraviolet radiation parameters, acid corrosion parameters, and temperature and humidity cyclic loads to obtain accelerated aging datasets. In the dynamic material degradation feature map, combined with the accelerated aging dataset, the quantitative relationship between the migration trajectory of micro-elements and the degradation law of mechanical properties is simulated to perform cross-scale inverse prediction of the remaining service life of automotive paint protection film.

2. The method for predicting the anti-aging properties of automotive paint protective film based on micro-element analysis as described in claim 1, characterized in that, The method for locating the damaged area further includes: Deploy an infrared thermal imaging array to continuously monitor the temperature field distribution on the surface of the protective film, and set a thermal shock damage accumulation index based on the latent heat characteristics of the phase change material. In the damaged area, using the thermal shock damage accumulation index, when an abnormal local temperature rise rate is detected, a microcrack capture command is activated. The microcrack capture command is used to capture the location and direction of microcrack propagation.

3. The method for predicting the anti-aging properties of automotive paint protective film based on micro-element analysis as described in claim 2, characterized in that, The middle layer of the automotive paint protection film is a microcapsule antioxidant, and the substrate layer of the automotive paint protection film is a shape memory polymer. Based on the distribution and concentration of each micro-element, the three-dimensional molecular chain network of the protective film was reconstructed. Using the reconstructed three-dimensional molecular chain network of the protective film, the correlation between the quantum chemical prediction of the cross-linking bond breaking energy threshold and the free radical generation rate was analyzed. When abnormal zinc aggregation was detected, an antioxidant consumption alert was triggered and a replenishment coating was determined.

4. The method for predicting the anti-aging properties of automotive paint protective film based on micro-element analysis as described in claim 3, characterized in that, The middle layer of the automotive paint protection film is a microcapsule antioxidant, and the method further includes: The location and propagation direction of the captured microcracks are collected by the microcrack capture command to determine the interfacial bonding force. When the interfacial binding force decreases to a critical value, the on-demand release of the microcapsule antioxidant is triggered.

5. The method for predicting the anti-aging properties of automotive paint protective film based on micro-element analysis as described in claim 4, characterized in that, The method further includes configuring a dynamic environment simulation chamber using ultraviolet radiation parameters, acid corrosion parameters, and temperature and humidity cyclic loads. A transfer learning framework was deployed to adapt the dynamic environment simulation chamber to multi-climate environment monitoring data, and an adversarial generative network was used to synthesize material performance evolution maps under extreme environmental conditions. Based on the material property evolution spectrum, a confidence analysis is performed on the dynamic material degradation feature spectrum. If the confidence level is lower than the confidence threshold, the dynamic material degradation feature spectrum is updated using the microcrack capture command.

6. The method for predicting the anti-aging properties of automotive paint protective film based on micro-element analysis as described in claim 5, characterized in that, The microcrack capture command is used to capture the location and propagation direction of microcracks, and the method further includes: Based on historical failure cases, the relationship between sulfur penetration depth and yellowing index was analyzed to explore the spatial correlation characteristics of anisotropic degradation modes of automotive paint protection film. Based on the spatial correlation characteristics of the anisotropic degradation mode of the automotive paint protection film, an anisotropic degradation prediction path is formulated. The anisotropic degradation prediction path is used to capture, trim, and optimize the microcrack capture command.

7. The method for predicting the anti-aging properties of automotive paint protective film based on micro-element analysis as described in claim 4, characterized in that, The method further includes triggering the on-demand release of microcapsule antioxidants: Deploy terahertz spectroscopy scanning equipment to non-contactly measure the spatial distribution of dielectric constant of automotive paint protection film and analyze the polarization response characteristics of filler agglomerates; Based on the polarization response characteristics of the filler agglomerates, the release pathway of the microcapsule antioxidants is dynamically optimized.

8. The method for predicting the anti-aging properties of automotive paint protective film based on micro-element analysis as described in claim 1, characterized in that, The method further includes: In the dynamic material degradation characteristic spectrum, a heat map simulating the failure risk of automotive paint protection film under different maintenance cycles is generated. Based on the failure risk heat map of the automotive paint protection film, and combined with the remaining service life and failure safety threshold, periodic automotive paint maintenance is determined, and the determination results are synchronized to the user terminal.

9. A system for predicting the anti-aging properties of automotive paint protective films based on micro-element analysis, characterized in that, The system is used to implement the method for predicting the anti-aging properties of automotive paint protective films based on micro-element analysis as described in any one of claims 1-8, and the system comprises: The detection coordinate system setting module is used to deploy a micro-area spectral probe array based on the automotive paint protection film, analyze the micro-element valence state distribution of the automotive paint protection film by combining X-ray photoelectron spectroscopy and Raman spectroscopy, and set up a multi-spectral collaborative detection coordinate system. The feature map construction module is used to map the distribution concentration and chemical bond state change data of each micro-element in the multispectral collaborative detection coordinate system to construct a dynamic material degradation feature map. The accelerated aging dataset acquisition module is used to simultaneously acquire accelerated aging datasets by configuring a dynamic environment simulation chamber with ultraviolet radiation parameters, acid corrosion parameters, and temperature and humidity cyclic loads. The remaining service life prediction module is used to perform cross-scale inverse prediction of the remaining service life of automotive paint protection film by combining the accelerated aging dataset with the dynamic material degradation feature map to simulate the quantitative relationship between the migration trajectory of micro elements and the law of mechanical property degradation.

Images