Preparation method of rear mold insert composite coating

Abstract

The invention relates to a preparation method of a rear mold insert composite coating in the field of mold accessory manufacturing, which comprises the following steps: extracting grain orientation and interface bonding state information from the surface of an initial transition layer, analyzing grain distribution uniformity and interface stress by adopting an ion beam scanning technology, and determining basic parameters of a coating bonding force; according to the micro-defect distribution data, analyzing the influence degree of defects on thermal fatigue resistance in combination with a preset threshold range to obtain a real-time evaluation result of coating performance; an improved gradient composite coating is generated through an optimized deposition process, the microdefect change trend is scanned again through an online detection system, and the durability of the coating and the improvement range of the production efficiency are determined; key performance indexes are extracted from a simulation result, a data log of an online detection system is combined, technological parameters are iteratively optimized through a gradient descent algorithm, and a final stable coating preparation scheme is obtained.

Description

Technical Field

[0001] The present invention relates to the field of mold accessory manufacturing, and particularly to a method for preparing a composite coating for a rear mold insert. Background Art

[0002] In the field of mold production, as a core component, the rear mold insert directly determines the service life of the mold and the quality of the product. The quality of its surface coating technology has a crucial impact on production efficiency and economic benefits. With the development of die-casting technology towards high temperature, high pressure, and high speed, the coating needs to withstand thermal shock, mechanical wear, and metal liquid erosion under extreme working conditions. Traditional surface treatment methods have been difficult to meet the increasingly demanding performance requirements. Therefore, developing high-performance coatings and their preparation and detection technologies has become an important direction for improving the reliability and intelligence of die-casting molds.

[0003] Currently, although common surface treatment technologies such as nitriding and chrome plating can improve the surface hardness of the insert to a certain extent, problems such as easy peeling of the coating and insufficient thermal fatigue resistance are widespread. In addition, the detection of defects such as microcracks and pores inside the coating relies on offline metallographic analysis, which not only takes a long time and has low efficiency but also cannot timely feedback process defects, resulting in increased difficulty in quality control during the production process. These limitations restrict the stability and durability of the rear mold insert under complex working conditions. The core challenges in the research field focus on how to achieve high bonding strength, high density of the coating, and real-time monitoring of defects. Traditional processes are difficult to form a strong and tough interfacial bond between the substrate and the coating, resulting in easy peeling of the coating during thermal cycling. At the same time, the cumulative disorder of grain orientation and interfacial defects during the coating preparation process further reduces its thermal fatigue resistance. In addition, the offline detection method of microdefects cannot form a closed-loop optimization with the preparation process, resulting in lagging adjustment of process parameters and affecting the yield. These technical problems together constitute the bottleneck for improving the performance of the rear mold insert coating.

[0004] Therefore, how to construct a gradient composite coating with high bonding strength and high density through a multi-energy field collaborative deposition process and integrate an online detection system to real-time identify microdefects and feedback to optimize the process has become a key issue for improving the durability and production efficiency of the rear mold insert. The solution to this problem not only requires breakthroughs in interface strengthening and structure regulation technologies during coating preparation but also needs to achieve dynamic coupling between detection and process, providing a reliable solution for the die-casting industry. Summary of the Invention

[0005] The present invention provides a method for preparing a composite coating for a rear mold insert, including the following steps:

[0006] Obtain the surface data of the rear mold insert substrate, and apply the synergistic action of a plasma field and a thermal field through a multi-energy field deposition device to deposit an initial transition layer on the substrate surface to obtain a prototype of the composite coating with a gradient structure;

[0007] Extract the grain orientation and interface bonding state information from the surface of the initial transition layer, analyze the grain distribution uniformity and interface stress using ion beam scanning technology, and determine the basic parameters of the coating bonding strength;

[0008] For the basic parameters of the coating bonding strength, use a multi-energy field deposition device to adjust the deposition rate and energy input, and continue to deposit a high-density functional layer on the transition layer to obtain an enhanced gradient composite coating;

[0009] Deploy an in-line detection system on the surface of the enhanced gradient composite coating, obtain the distribution data of internal micro-defects in the coating through laser interferometry and ultrasonic scanning, and determine the specific location and scale of micro-cracks and pores;

[0010] According to the distribution data of micro-defects, analyze the degree of influence of the defects on the thermal fatigue resistance in combination with the preset threshold range, and obtain the real-time evaluation result of the coating performance;

[0011] If the evaluation result is lower than the preset performance standard, extract the defect distribution characteristics from the in-line detection system, and feedback to the multi-energy field deposition device to adjust the deposition temperature and ion energy, and optimize the density and bonding strength of the next batch of coatings;

[0012] Generate an improved gradient composite coating through the optimized deposition process, use the in-line detection system to scan the change trend of micro-defects again, and determine the improvement range of the coating durability and production efficiency;

[0013] Obtain the thermal cycle test data of the improved gradient composite coating, use the finite element analysis algorithm to simulate the stress distribution of the coating under high temperature and high pressure conditions, and judge the actual improvement level of the thermal fatigue resistance and interface strengthening;

[0014] Extract the key performance indicators from the simulation results, combine with the data log of the in-line detection system, and iteratively optimize the process parameters through the gradient descent algorithm to obtain the final stable coating preparation scheme.

[0015] The technical solution provided by the embodiments of the present invention may include the following beneficial effects:

[0016] The present invention discloses a preparation method for a composite coating of a rear mold insert. This method forms a composite coating with a gradient structure on the surface of a substrate through a multi-energy field deposition device, and uses an on-line detection system to monitor the coating quality in real time. The present invention first deposits an initial transition layer on the surface of the substrate, and then analyzes the grain distribution and interface stress to determine the coating bonding force parameters. Based on these parameters, the deposition process is adjusted to form a high-density functional layer. The present invention innovatively uses laser interference and ultrasonic scanning technologies to detect micro-defects of the coating, and dynamically optimizes the deposition parameters according to the detection results. Through an iterative optimization process, the present invention can continuously improve the coating performance, enhance its thermal fatigue resistance and durability. Finally, the present invention verifies the coating performance through thermal cycle tests and finite element analysis, and uses machine learning algorithms to optimize the process parameters to achieve the preparation of a high-quality and high-efficiency gradient composite coating. Detailed implementation manners

[0017] The following will clearly and detailedly describe the technical solutions in the embodiments of the present invention in conjunction with the embodiments of the present invention. The described embodiments are only a part of the embodiments of the present invention.

[0018] A preparation method for a composite coating of a rear mold insert in this embodiment may specifically include:

[0019] Step S1, obtaining the surface data of the rear mold insert substrate, and applying the synergistic action of a plasma field and a thermal field through a multi-energy field deposition device to deposit an initial transition layer on the substrate surface to obtain a prototype of a composite coating with a gradient structure.

[0020] Obtaining the characteristic data of the substrate surface to obtain the surface state distribution; for the surface state distribution, applying a plasma field treatment by using a multi-energy field deposition device to obtain a plasma-activated surface; performing thermal field modulation on the plasma-activated surface to obtain a thermally modulated surface; if the uniformity of the thermally modulated surface reaches a preset threshold, depositing a transition layer through a deposition device to obtain an initial coating structure; obtaining the gradient distribution data of the initial coating structure; according to the gradient distribution data, adjusting the field synergy parameters to obtain an optimized composite coating prototype; performing surface detection on the optimized composite coating prototype to obtain the final coating data.

[0021] Exemplarily, characteristic data is extracted from the substrate surface through a sensor to obtain the surface state distribution.

[0022] It can be understood that the core of this step lies in accurately perceiving the physical properties of the substrate surface.

[0023] Exemplarily, assume that the substrate is a metal part. A laser scanner can be used as the sensor to scan the surface roughness. The data shows that the roughness of a certain area is Ra 2.5 microns, while that of another area is Ra 1.8 microns. This distribution reflects the non-uniformity of the surface state and provides a basis for subsequent processing. The beneficial effect of doing so is that it can lay a data foundation for customized surface treatment and avoid blind operations. A multi-energy field deposition device is used to apply a plasma field treatment to the surface state distribution to obtain a plasma-activated surface.

[0024] Specifically, the multi-energy field device may integrate a radio frequency discharge device to generate plasma to bombard the surface.

[0025] In a possible implementation, nitrogen is used as the working gas, the air pressure is controlled at 0.5 Pa, the power is set at 200 W. After the plasma acts for 10 minutes, the surface active sites increase and the chemical bond energy is excited. The advantage of this step is to enhance the surface reactivity and create conditions for subsequent energy injection. Energy injection is performed on the plasma-activated surface through the action of a thermal field to obtain a thermally field-modulated surface.

[0026] It should be noted that the thermal field can be realized by resistance heating.

[0027] For example, the substrate is placed in a thermal environment of 300 degrees Celsius and kept warm for 15 minutes. The surface molecules are rearranged due to thermal energy and the uniformity is improved.

[0028] Preferably, if there are small cracks on the initial surface, the thermal field action can also partially repair the defects and improve the structural stability. The benefit of this treatment is that it provides a more uniform substrate for subsequent coating deposition. If the uniformity of the thermally field-modulated surface reaches a preset threshold, a transition layer is deposited through a deposition device to obtain an initial coating structure.

[0029] In one embodiment, the uniformity threshold is set to a roughness change of less than 0.3 microns. At this time, a 50-nanometer titanium transition layer can be deposited using a magnetron sputtering device. Due to its good adhesion and corrosion resistance, the titanium layer can effectively connect the substrate and the outer coating. The advantage of this design is to enhance the bonding force between the coating and the substrate and extend the service life. Gradient analysis is performed on the initial coating structure to obtain gradient distribution data.

[0030] For example, a scanning electron microscope can be used to observe the cross-section and it is found that the element concentration at the interface between the titanium layer and the substrate shows a smooth transition, while there is a sudden change in the concentration in the outer layer region. This data reflects the hierarchical nature of the coating structure and provides a basis for optimization. Its beneficial effect is to clarify the adjustment direction and avoid coating performance imbalance. The field synergy parameters are adjusted according to the gradient distribution data to obtain a prototype of an optimized composite coating.

[0031] Specifically, if it is found that the outer layer has insufficient hardness, the bias voltage during deposition can be increased to -100V, and at the same time, the working gas pressure can be increased to 1Pa to form a titanium nitride layer with higher hardness. The advantage of this adjustment is to achieve a balance between hardness and toughness and improve the wear resistance of the coating. The surface of the optimized composite coating prototype is detected by image processing technology to obtain the final coating data.

[0032] In a possible implementation, an industrial camera is used to capture the surface image. Combining with the edge detection algorithm, the coating defects are analyzed, and it is found that there are micropores with a diameter of 10 microns in a certain area. After further optimizing the process, the defects are reduced to negligible. The benefit of this detection is to ensure the coating quality and meet the requirements of high-precision applications.

[0033] It can be understood that from feature extraction to final detection, each step is closely linked, jointly supporting the realization of high-quality coatings.

[0034] For example, the initial surface state distribution directly affects the depth of plasma treatment, and the uniformity of thermal field modulation determines the adhesion of the transition layer. This logic of multi-faceted cooperation ensures the rigor of the process and the reliability of the effect.

[0035] Step S2, extract the grain orientation and interface bonding state information from the surface of the initial transition layer, analyze the uniformity of grain distribution and interface stress by using ion beam scanning technology, and determine the basic parameters of the coating bonding force.

[0036] Obtain the grain orientation information and interface bonding information of the transition layer surface, and use ion beam scanning technology to obtain the distribution data of the grains and the stress distribution data of the interface; judge the uniformity of the grain distribution according to a preset threshold to obtain the grain uniformity distribution characteristics; according to the uniformity distribution characteristics, determine the change trend of the interface stress to obtain the interface stress distribution law; for the stress distribution law, extract the coating bonding force parameters to obtain the bonding strength quantization value; if the bonding strength quantization value is lower than the preset threshold, use a machine learning algorithm to adjust the grain orientation characteristics to obtain optimized grain distribution data; according to the optimized distribution data, re-analyze the interface stress distribution to obtain the adjusted bonding force parameters; according to the adjusted bonding force parameters, judge the coating bonding state to determine the final bonding force characteristics of the coating.

[0037] Exemplarily, when extracting the grain orientation and interface bonding information from the transition layer surface, specific data can be obtained through electron backscatter diffraction technology.

[0038] Exemplarily.

[0039] In a possible implementation, a high-resolution microscope is used to scan the surface of the transition layer to obtain a two-dimensional distribution map of grain orientations. Combining the atomic arrangement characteristics at the interface, the tightness of the grain-matrix bonding is preliminarily judged. This method can intuitively reflect the anisotropy of grain orientations. For example, when the grain angle deviation is between 5 degrees and 15 degrees, it indicates that the orientations are relatively consistent. When obtaining grain distribution data and interface stress distribution through ion beam scanning technology.

[0040] Preferably, a focused ion beam device can be used to perform layer-by-layer peeling analysis on the surface.

[0041] Specifically, under the condition that the ion beam energy is set to 30 keV, a 100 μm × 100 μm area is scanned to obtain a grain size distribution range between 0.5 μm and 2 μm, and at the same time, the change of the interface stress value between 50 MPa and 200 MPa is recorded. This way helps to reveal the stress concentration areas and provides data support for subsequent analysis. When using a preset threshold to judge the grain distribution uniformity.

[0042] For example, the uniformity threshold can be set to 80%.

[0043] In one embodiment, if the standard deviation of the grain size in the scanned area is less than 0.3 μm, it is considered to be uniformly distributed.

[0044] It should be noted that this judgment method can quickly screen out areas with abnormal grain distribution, which is convenient for targeted optimization. When analyzing the interface stress change trend through the uniformity distribution characteristics.

[0045] It can be understood that the corresponding relationship between high stress points and grain boundaries can be observed by combining the stress distribution map.

[0046] For example, in areas with high uniformity, the stress value fluctuates less, usually around 10 MPa, while at the boundary, the stress may increase to 150 MPa due to grain mismatch. This regular analysis helps to clarify the driving factors of stress distribution. When extracting the coating bonding strength parameters according to the stress distribution law.

[0047] In a possible implementation, the bonding strength can be measured by nanoindentation technology.

[0048] Specifically, under the condition that the loading force is 10 mN, the indentation depth and the rebound characteristics are recorded, and the quantified bonding strength value is about 2 GPa. This quantified value reflects the adhesion level between the coating and the substrate. If the quantified bonding strength value is lower than the preset threshold, for example, lower than 1.5 GPa, the grain orientation characteristics are adjusted through a machine learning algorithm.

[0049] Exemplarily, a convolutional neural network is used to analyze the grain distribution image, optimize the orientation angle deviation to within 10 degrees, and generate new distribution data. This adjustment can enhance the stability of the interface bonding. When re-analyzing the interface stress based on the optimized distribution data.

[0050] Preferably, ion beam scanning can be repeated to observe whether the stress value drops below 100 MPa.

[0051] In one embodiment, the number of stress concentration points after adjustment is reduced by 30%, indicating a significant optimization effect. This method provides a reliable basis for subsequent parameter adjustment. When judging the coating bonding state through the adjusted bonding force parameters.

[0052] For example, if the bonding strength is increased to 1.8 GPa, it is considered that the coating bonding state is good.

[0053] Specifically, this judgment method can effectively verify the feasibility of the optimization measures and ensure the durability of the coating during use.

[0054] Step S3: For the basic parameters of the coating bonding force, use a multi-energy field deposition device to adjust the deposition rate and energy input, and continue to deposit a high-density functional layer on the transition layer to obtain an enhanced gradient composite coating.

[0055] Obtain the initial data of the deposition rate and energy input generated by the multi-energy field deposition device, and determine the basic parameters of the coating bonding force. Adjust the deposition rate and energy input according to the initial data to obtain the deposition conditions of the transition layer. Deposit a high-density functional layer on the transition layer using the adjusted deposition conditions, and judge the density distribution of the functional layer. Determine the deposition parameters of the gradient composite structure according to the density distribution of the functional layer to obtain a preliminary composite coating. For the preliminary composite coating, use the random forest algorithm to analyze the enhancement effect of the coating bonding force and judge the enhanced characteristics. Obtain the final parameters of the composite coating from the enhanced characteristics to determine the structure of the enhanced gradient composite coating. If the bonding force distribution of the composite coating is uniform, use image processing technology to analyze the surface morphology of the composite coating to obtain the final coating data.

[0056] Exemplarily, obtaining the initial data of the deposition rate and energy input through a multi-energy field deposition device is an important basis for determining the coating bonding force parameters. For example.

[0057] In one possible implementation, a plasma-enhanced chemical vapor deposition device can be used to measure the initial data of a deposition rate of 5 nm / min and an energy input of 200 W by adjusting the radio frequency power and gas flow rate. These data reflect the preliminary conditions for the formation of the transition layer and provide a basis for subsequent parameter adjustment.

[0058] It should be noted that the balance between the deposition rate and the energy input directly affects the microstructure of the transition layer. Excessive energy may lead to coarse grains, while too low a rate may result in insufficient interlayer bonding. When adjusting the deposition rate and energy input according to the initial data.

[0059] It can be understood that this process aims to optimize the deposition conditions of the transition layer.

[0060] Specifically, the deposition rate can be increased to 8 nm / min while adjusting the energy input to 250 W to enhance the atomic migration ability and form a denser transition layer structure.

[0061] In one embodiment, by observing the adjusted transition layer with a scanning electron microscope, it is found that its porosity decreases from 5% to 2%, indicating that the optimization of the deposition conditions significantly improves the interlayer quality. After depositing a high-density functional layer using the adjusted deposition conditions, it is crucial to judge the density distribution of the functional layer.

[0062] Exemplarily, the crystal structure of the functional layer can be analyzed by X-ray diffraction technology, and the uniformity of the density distribution is measured to be over 90%. This high density helps to improve the wear resistance and corrosion resistance of the coating, laying a foundation for the subsequent composite structure. When determining the deposition parameters of the gradient composite structure based on the density distribution of the functional layer.

[0063] Preferably, a multi-layer deposition scheme can be designed according to the density gradient.

[0064] For example, deposit 3 layers of functional layers in sequence on the transition layer, with each layer thickness being 50 nm, 70 nm, and 100 nm respectively to form a gradient composite coating. This structure can effectively disperse the interface stress and improve the overall bonding force. Analyzing the bonding force enhancement effect using the random forest algorithm for the preliminary composite coating is an efficient means.

[0065] In one embodiment, characteristic parameters such as the coating thickness, density, and deposition rate can be input, and the algorithm outputs a bonding force enhancement factor of 1.5 times. This indicates that through a data-driven approach, the key variables affecting the bonding force can be accurately identified. When obtaining the final parameters of the composite coating from the enhanced features.

[0066] For example, the combination of a functional layer thickness of 100 nm and a deposition rate of 10 nm / min can be determined as the final scheme. This parameter combination ensures that the uniformity of the bonding force distribution of the enhanced gradient composite coating reaches over 95%. If the bonding force distribution is uniform, then analyze the surface morphology through image processing technology to obtain the final coating data.

[0067] Specifically, the atomic force microscope can be used to scan the surface of the coating, and the surface roughness Ra is measured to be 0.8 nm. This smooth topography not only reflects the high quality of the coating but also enhances its service life in harsh environments.

[0068] It can be understood that the optimization of the surface topography further verifies the rationality of the deposition parameters and provides guarantee for the long-term stability of the coating performance.

[0069] Step S4, deploy an online detection system on the surface of the enhanced gradient composite coating, and obtain the distribution data of internal micro-defects in the coating through laser interference and ultrasonic scanning to judge the specific positions and scales of micro-cracks and pores.

[0070] Obtain the interference fringe data on the surface of the coating through laser interference to determine the initial contour of the micro-defect distribution; use ultrasonic scanning to conduct depth detection on the inside of the coating to obtain a complete data set of the micro-defect distribution. Apply a convolutional neural network to the micro-defect distribution data to judge the coordinate information of the micro-crack position; calculate the boundary characteristics of the pores according to the micro-defect distribution data to determine the distribution range of the pore scale. If the overlapping area of the micro-crack position and the pore scale exceeds a preset threshold, separate the overlapping defects through an image segmentation algorithm to obtain independent defect features; compare the independent defect features with the layering characteristics of the gradient composite material to judge the depth distribution of the defects inside the coating. Obtain the difference data between the depth distribution and the initial contour, and classify the defect types through a support vector machine to determine the final micro-defect distribution characteristics.

[0071] Exemplarily, obtaining the interference fringe data on the surface of the coating through laser interference can be understood as using the reflection and interference phenomena of the laser beam on the surface of the coating to generate a fringe pattern. For example.

[0072] In a possible implementation, a helium-neon laser with a wavelength of 632.8 nm is used to irradiate the surface of the coating, and the fringe spacing is recorded by an interferometer. The initial contour can display the distribution of micro-defects such as scratches or pits. This method has high sensitivity, can quickly reflect the changes in the surface topography, and helps to improve the accuracy of subsequent analysis. Using ultrasonic scanning to conduct depth detection on the inside of the coating is a non-destructive detection method.

[0073] Specifically, an ultrasonic probe with a frequency of 5 MHz can be used to move on the surface of the coating at a scanning speed of 2 mm / s to obtain the echo signal of internal defects.

[0074] For example, the sudden change in signal intensity may correspond to cracks or pores, and the complete data set can provide three-dimensional information for defect location. The advantage of this method is that it has a wide coverage depth and can reveal problems hidden under the surface layer. Apply a convolutional neural network to the micro-defect distribution data.

[0075] Preferably, the network can be trained to identify defect features.

[0076] For example, ultrasonic and interference data are input into the network. The convolution kernel size is set to 3×3 to extract the edge features of microcracks, and their coordinates are output as (x: 50μm, y: 75μm, z: 20μm). This method can efficiently process complex data, improve the positioning accuracy, and provide a reliable basis for subsequent judgment. The boundary features of pores are calculated from the microdefect distribution data.

[0077] It should be noted that the pore edges can be determined based on the change in image gray level.

[0078] For example, the gray value of the pore boundary is usually 20% lower than that of the surrounding area. Combining algorithms, the pore diameter range can be calculated to be between 10 - 50μm. This analysis helps to evaluate the degree of influence of defects on the coating performance. If the overlapping area between the position of the microcrack and the pore scale exceeds a preset threshold, for example, the overlapping area ratio exceeds 30%, the overlapping defects are separated by an image segmentation algorithm.

[0079] In one embodiment, the watershed algorithm can be used to divide the overlapping area into independent cracks and pores, and features such as crack length 15μm and pore area 25μm are extracted respectively 2 . This separation can more clearly analyze the defect characteristics and avoid confusion. By comparing the independent defect features with the delamination characteristics of the gradient composite material, the defect depth can be judged.

[0080] For example, the thickness of the transition layer is 100μm. If the crack depth reaches 80μm, the bonding strength may be affected.

[0081] Exemplarily, by comparing the delamination density distribution, it can be inferred that the defects are concentrated in the high-density functional layer, improving the analysis pertinence. After obtaining the difference data between the depth distribution and the initial contour, the support vector machine can be used to classify the defect types.

[0082] Specifically, depth differences such as 10μm and 20μm are used as input features to classify defect types such as cracks, pores, or delamination. This method has clear logic and can quickly classify defects, providing a direction for optimizing the coating process.

[0083] In one possible implementation, the final microdefect distribution characteristics can be visually presented through 3D modeling.

[0084] For example, the defect distribution map shows that cracks are concentrated within 50μm of the surface, and pores are mostly distributed in the depth range of 80 - 120μm. Such detailed characteristics help to improve the deposition parameters and enhance the coating durability.

[0085] Step S5: According to the microdefect distribution data, analyze the degree of influence of defects on the thermal fatigue resistance in combination with the preset threshold range, and obtain the real-time evaluation result of the coating performance.

[0086] Obtain micro-defect distribution data, extract the micro-defect distribution data to obtain a set of defect features; combine the set of defect features with a preset threshold to judge the area where the defect exceeds the preset threshold range, and obtain the defect influence range; for the defect influence range, analyze the change trend of the thermal fatigue resistance to obtain the resistance degree distribution; obtain the key indicators of the coating performance from the resistance degree distribution, and determine the performance change characteristics; if the performance change characteristics exceed the preset threshold, use the support vector machine algorithm to classify the coating performance to obtain the performance level division; combine the performance level division with the real-time evaluation requirements to judge the real-time state of the coating performance and obtain the final evaluation result; update the analysis model of the defect influence according to the final evaluation result to obtain the optimized thermal fatigue resistance prediction result.

[0087] Exemplarily, by extracting distribution data from the micro-defect distribution, usually the micro-crack and pore information inside the coating is converted into a quantifiable set of features.

[0088] For example, a three-dimensional distribution map can be generated by scanning data, where each defect point is marked with its spatial coordinates and size. Assume that the length of the micro-crack in a certain area is 0.5 mm and the pore diameter is 0.2 mm, and these data form the basis of the set of defect features.

[0089] In a possible implementation, a preset threshold such as a crack length greater than 0.3 mm or a pore diameter greater than 0.15 mm is combined to screen the key defect areas.

[0090] Exemplarily, if 60% of the defects in a certain area exceed the threshold, it can be judged that this area is the core area of the defect influence range.

[0091] Specifically, when analyzing the defect influence range, it can start from the perspective of thermal fatigue resistance.

[0092] Preferably, by simulating thermal cycle loading, observe the change trend of the temperature distribution in the defect area. For example, if the temperature in a certain defect area rises by more than 20%, it indicates that the thermal fatigue resistance ability decreases.

[0093] In one embodiment, the resistance degree distribution can be divided into three levels: high, medium, and low. Assume that the resistance in a certain area drops to the low level, then record its key indicators such as the thermal conductivity decreasing by 15%.

[0094] It should be noted that the extraction of the performance change characteristics can be based on these indicators to judge whether the coating still meets the usage requirements.

[0095] In a possible implementation, if the performance change characteristics exceed the preset threshold, for example, the thermal conductivity drops by more than 10%, the support vector machine algorithm can be used to classify the performance level.

[0096] For example, the coating performance is divided into three levels: A, B, and C. Level A indicates normal, and Level C indicates that replacement is required. A 12% decrease in the thermal conductivity of a certain area is classified as Level B.

[0097] It can be understood that this classification helps to quickly identify the coating status and improve the evaluation efficiency.

[0098] For example, in combination with the real-time evaluation requirements, temperature and stress data can be collected through sensors to judge the real-time status of the coating performance. Suppose the temperature of a certain area rises abnormally and stress is concentrated, it indicates that the defect has affected the performance, and the real-time status is marked as "attention required".

[0099] In one embodiment, the final evaluation result can be used to update the analysis model.

[0100] Preferably, the model is trained with historical data to increase the accuracy of predicting thermal fatigue resistance by 10%.

[0101] Specifically, when making predictions, the updated model can analyze the influence of defects from multiple aspects.

[0102] For example, in combination with the defect density, distribution uniformity, and material fatigue characteristics, suppose the defect density in a certain area is 5 per cm 2 , it is predicted that its resistance is reduced by 25%, while the density in another area is 2 per cm 2 , and the resistance is only reduced by 8%.

[0103] Exemplarily, this multi-dimensional analysis ensures that the prediction results are more reliable. At the same time, the optimized model can early warn potential failure areas and provide a basis for coating maintenance.

[0104] It should be noted that the advantage of this method lies in forming a closed-loop analysis chain from defect distribution to performance evaluation and then to model optimization.

[0105] Preferably, through the combination of real-time status monitoring and prediction, the service life of the coating can be effectively extended and the maintenance cost can be reduced.

[0106] In one embodiment, if a certain coating is adjusted in time after evaluation, 30% of the potential failure risks can be avoided.

[0107] Step S6, if the evaluation result is lower than the preset performance standard, extract the defect distribution characteristics from the online detection system, and feedback to the multi-energy field deposition equipment to adjust the deposition temperature and ion energy, and optimize the density and bonding strength of the next batch of coatings.

[0108] Obtain the defect distribution characteristics of the online detection system, extract the boundaries of the defect distribution characteristics using image processing technology to obtain defect distribution data; analyze the abnormal areas during the deposition process based on the defect distribution data, use the support vector machine algorithm to judge the relationship between the abnormal areas and the deposition temperature, and determine the temperature adjustment direction; update the control parameters of the deposition equipment according to the temperature adjustment direction, obtain the adjusted deposition temperature value, and get a new temperature configuration; analyze the influence of ion energy on the bonding force through the defect distribution data, use the linear regression algorithm to judge the energy adjustment range, and determine the optimized ion energy value; obtain the current ion energy parameters of the deposition equipment, and adjust the equipment settings in combination with the optimized ion energy value to get a new energy configuration; operate the multi-energy field deposition equipment with the adjusted temperature configuration and energy configuration to obtain the coating data of the next batch; judge the change trend of the coating density and bonding force according to the coating data of the next batch; compare the coating data of the next batch with the preset standard to judge the optimization effect and obtain the batch optimization result.

[0109] In a possible implementation manner, when the detection result is lower than the preset standard, obtaining the defect distribution characteristics from the online detection system is a key link.

[0110] Exemplarily, the microscopic image of the coating surface can be captured by a high-resolution camera, and the feature boundaries can be extracted by combining image processing technology. For example, the edge detection algorithm is used to identify the contour of the defect, and data such as the shape, size, and distribution position of the defect are obtained. Suppose multiple micropores with diameters between 0.1 and 0.5 millimeters are detected on the surface of a certain batch of coatings. These data can intuitively reflect the density and regional characteristics of the defect distribution, providing a basis for subsequent analysis.

[0111] Specifically, when analyzing the abnormal areas during the deposition process through the defect distribution data, the focus can be on the parts where the defects appear concentrated.

[0112] For example, if it is detected that the number of micropores in a certain area accounts for 70% of the total, it may indicate that the deposition conditions in this area are abnormal. When using the support vector machine algorithm to judge the relationship between the abnormal area and the deposition temperature.

[0113] It can be understood that the model is trained through historical data. The defect distribution characteristics and the corresponding temperature values are input, and the judgment of whether the temperature is too high or too low is output. Suppose it is analyzed that the deposition temperature in the defect concentration area reaches 650 degrees Celsius, exceeding the normal range by 50 degrees Celsius, then the temperature adjustment direction is to lower the temperature. This method helps to quickly locate the root cause of the problem.

[0114] Preferably, when updating the control parameters of the deposition equipment according to the temperature adjustment direction, the temperature can be adjusted from 650 degrees Celsius to 600 degrees Celsius.

[0115] In one embodiment, the device achieves this change by adjusting the heating power, and the new temperature configuration takes effect immediately. This can effectively reduce the generation of defects caused by high temperature and improve the coating quality.

[0116] It should be noted that when analyzing the influence of ion energy on the bonding force through defect distribution data analysis, the linear regression algorithm can be used.

[0117] For example, assuming that the defect distribution shows that the ion energy in the region with weak bonding force is 200 electron volts, while the normal region is 250 electron volts, after analysis, it is obtained that the energy needs to be increased by 20% to 240 electron volts as the optimized value. After obtaining the current parameters from the deposition equipment and adjusting them to the new value, the adhesion between the coating and the substrate can be significantly enhanced.

[0118] In one embodiment, after operating the multi-energy field deposition equipment with the adjusted temperature configuration and energy configuration, the coating data of the next batch may show that the density increases from 92% to 95%, and the bonding force increases from 50 Newtons to 60 Newtons. This changing trend indicates that the optimization measures are effective. It can be judged whether the batch optimization result meets the standard by comparing with the preset standard, such as the density needs to reach more than 94%.

[0119] For example, when examining the adjustment effects of temperature and ion energy from multiple aspects, it can be found that the decrease in temperature reduces the microcracks caused by thermal stress, while the increase in energy improves the uniformity of atomic deposition, and the two work together to make the coating performance more stable.

[0120] It can be understood that this optimization not only improves the reliability of the current batch of coatings, but also provides parameter references for subsequent production and reduces the trial-and-error cost.

[0121] In one embodiment, when judging the changing trends of coating density and bonding force, the microscopic structure changes can be observed through a scanning electron microscope, and the specific values can be measured by a bonding force tester. This multi-dimensional verification method ensures the comprehensiveness of the analysis and provides a reliable basis for process improvement.

[0122] Preferably, the optimized batch results can also feed back to the further fine-tuning of the equipment parameters, forming a closed loop of continuous improvement.

[0123] Step S7, generate an improved gradient composite coating through the optimized deposition process, and use the on-line detection system to scan the changing trend of micro-defects again to determine the improvement range of the coating durability and production efficiency.

[0124] Obtain a gradient composite coating sample, which is prepared using preset deposition process parameters; for the gradient composite coating sample, scan its surface using an on-line detection system to obtain distribution characteristic information of surface micro-defects; according to the distribution characteristic information, determine preliminary data of micro-defect changes; use a time series algorithm to process the continuous scanning results of the on-line detection system to obtain trend characteristic values of the micro-defect changes; according to the trend characteristic values, judge the durability index of the gradient composite coating sample; if the durability index is lower than a preset threshold, adjust the deposition process parameters to generate an improved gradient composite coating sample; use the on-line detection system to scan the improved gradient composite coating sample to obtain updated micro-defect change data and determine the improvement range of durability; use a production efficiency evaluation tool to analyze the generation process of the improved gradient composite coating sample to obtain production efficiency improvement range data; extract key features from the production efficiency improvement range data, and combine with the durability improvement range to judge whether the optimization of the deposition process parameters meets the expected standard.

[0125] Exemplarily, when generating gradient composite coating data through optimized deposition processes.

[0126] It can be understood that this process aims to form a coating with a gradient structure by adjusting process parameters.

[0127] For example, in the initial stage, the process may set the deposition temperature at 800 degrees and the ion energy at 50 eV, and an initial coating sample is obtained after running through a multi-energy field deposition device.

[0128] Exemplarily, such a sample may exhibit the characteristic that the hardness gradually increases from the bottom layer to the surface layer, but there may also be micro-cracks due to incomplete parameter optimization. When obtaining the distribution characteristics of micro-defects from the initial coating sample.

[0129] Preferably, a high-resolution optical scanner of the on-line detection system can be used to scan the sample surface.

[0130] In a possible implementation, the scanning resolution is set to 10 microns, the number of micro-defects detected on the sample surface is 15 per square centimeter, and the average defect size is 20 microns.

[0131] Specifically, these data reflect the non-uniformity of the internal stress distribution of the coating, which may be related to the relatively high deposition temperature. The characteristics extracted in this way provide a basis for subsequent analysis. When performing trend analysis on the preliminary data of micro-defect changes.

[0132] For example, a time series algorithm can be used to process the results of 5 consecutive scans.

[0133] In one embodiment, algorithm analysis shows that the number of defects increases from 15 per square centimeter to 18 after 3 scans, indicating insufficient stability of the coating under continuous stress. The eigenvalue of the change trend may show that the defect growth rate reaches 20%, which suggests that the process parameters need to be further adjusted. This analysis helps to judge the coating performance from a dynamic perspective. When judging the coating durability index according to the eigenvalue of the change trend.

[0134] It should be noted that the durability can be evaluated by simulating wear tests.

[0135] In one embodiment, if the preset durability threshold is 500 friction cycles and the current coating shows obvious wear after only 400 cycles, the parameters need to be adjusted.

[0136] For example, the deposition temperature is reduced to 750 degrees and the ion energy is increased to 60 eV to generate an improved coating sample. This adjustment can effectively reduce the internal stress and improve the durability. When running the on-line detection system again with the improved coating sample.

[0137] It can be understood that the updated micro-defect data may show that the number of defects is reduced to 10 per square centimeter and the durability improvement reaches 25%.

[0138] Specifically, this improvement indicates that progress has been made in process optimization in reducing micro-defects. At the same time, the coating adhesion may also be enhanced due to the adjustment of ion energy, which helps to extend the service life. When analyzing the generation process of the improved coating sample using a production efficiency evaluation tool.

[0139] For example, it can be evaluated by counting the output of samples per unit time.

[0140] In one possible implementation, 50 samples were produced per hour before optimization, and it was increased to 60 samples after optimization, with an efficiency improvement of 20%. When extracting key features from the efficiency improvement data.

[0141] Preferably, the stability of equipment operation and the change of energy consumption can be concerned.

[0142] For example, the energy consumption is reduced from 10 kWh per sample to 9 kWh, indicating that the optimization not only improves the efficiency but also reduces the cost. When judging whether the process optimization meets the expected standard by combining the durability improvement and the efficiency improvement.

[0143] Exemplarily, if the expected goal is a 20% improvement in durability and a 15% improvement in efficiency, and the actual result exceeds the expectation, the optimization effect is significant.

[0144] In one embodiment, such comprehensive evaluation can also provide data support for the next round of process iteration to ensure continuous improvement of coating performance and production efficiency. Through multi-dimensional analysis, this method forms a complete logical chain of parameter adjustment and performance improvement.

[0145] Step S8: Obtain the thermal cycle test data of the improved gradient composite coating, use the finite element analysis algorithm to simulate the stress distribution of the coating under high temperature and high pressure conditions, and judge the actual improvement level of thermal fatigue resistance and interface strengthening.

[0146] Obtain the relationship data between the temperature change and the number of cycles of multiple thermal cycle experiments to determine the performance of the coating in multiple cycles; according to the thermal cycle experiment data, use the finite element analysis algorithm to construct a three-dimensional model of the coating under high temperature and high pressure conditions to obtain the stress distribution characteristics in the model; simulate the change of the stress distribution through the finite element analysis algorithm to judge the thermal fatigue resistance level of the coating under high temperature and high pressure conditions; according to the stress distribution and the simulation results of the thermal fatigue resistance, obtain the quantitative index of the coating interface strengthening to determine the improvement degree of the interface strengthening on the thermal fatigue; use the machine learning regression algorithm to process the thermal cycle test data and the simulation results to obtain the correlation law between the thermal fatigue resistance and the interface strengthening; analyze the change trend of the coating performance under different working conditions according to the correlation law to judge the overall improvement level of the improved gradient composite coating; adjust the parameters of the simulation analysis according to the change trend to obtain the optimized coating performance data.

[0147] Exemplarily, for the acquisition of the thermal cycle test data of the improved gradient composite coating.

[0148] Exemplarily, experiments can be carried out through a thermal cycle furnace, with the set temperature range between 200°C and 1000°C and the number of cycles being 500 times. Record the temperature change on the surface of the coating during each cycle and use a thermocouple for real-time monitoring to ensure the continuity of the data.

[0149] For example, in the initial 100 cycles, the temperature rises from 200°C to 800°C, holds for 30 minutes and then drops to 200°C. It is found that no obvious cracks are seen on the surface of the coating, indicating its preliminary thermal shock resistance.

[0150] In one possible implementation, when extracting key parameters from the thermal cycle test data, the change rate of the coating thickness and the initiation time of surface microcracks can be concerned.

[0151] Specifically, assume that the initial thickness is 50 microns, the thickness decreases by 2 microns after 300 cycles, and microcracks appear at the 250th cycle. These parameters provide basic data for subsequent analysis.

[0152] It should be noted that when constructing a three-dimensional model using the finite element analysis algorithm, commercial software such as ANSYS can be selected, and the coating can be divided into two parts, the substrate and the gradient layer, and input.

[0153] Exemplarily, the high-temperature and high-pressure working conditions are set to 900 °C and 10 MPa. The simulation results show that the stress concentration area is located at the interface between the coating and the substrate, and the maximum stress value is 150 MPa. This stress distribution characteristic indicates that the interface bonding strength is the key factor affecting the performance.

[0154] Specifically, when simulating the change of stress distribution, the thermal fatigue resistance can be observed by adjusting the number of cycles and the temperature gradient.

[0155] For example, when the number of cycles is increased to 600, the stress peak rises to 180 MPa, but the coating does not spall, indicating that its thermal fatigue resistance is strong. This helps to judge the stability of the coating under extreme conditions.

[0156] In one embodiment, when obtaining the quantitative index of coating interface strengthening, the shear strength of the improved coating can be measured by interface shear strength test, and it is increased from 50 MPa to 70 MPa.

[0157] Preferably, this improvement indicates that the interface strengthening significantly improves the thermal fatigue resistance and extends the service life of the coating.

[0158] It can be understood that when the machine learning regression algorithm processes data, the random forest model can be selected, and the number of thermal cycles, temperature and stress data are input, and the predicted value of thermal fatigue resistance is output.

[0159] For example, the prediction results show that when the number of cycles exceeds 400, the resistance decreases by 10%, which reveals the law of performance change with working conditions.

[0160] For example, when analyzing the coating performance trend through correlation law, it is found that the resistance is stable below 700 °C and decreases significantly above this temperature. This provides a direction for process optimization, such as adjusting the composition ratio of the gradient layer.

[0161] In one embodiment, the optimized simulation shows that the resistance is increased by 15%, verifying the effectiveness of the adjustment. This method not only improves the coating performance but also provides data support for production.

[0162] Step S9, extract the key performance indicators from the simulation results, combine the data log of the online detection system, and iteratively optimize the process parameters through the gradient descent algorithm to obtain the final stable coating preparation scheme.

[0163] Obtain the simulation results, determine the main performance parameters using the key extraction method, and obtain the performance index data; obtain the data log in the online detection system, and judge the initial values of the process parameters in combination with the performance index data; for the records in the data log, iteratively optimize the process parameters using the gradient descent algorithm to obtain the adjusted parameter set; according to the adjusted parameter set, obtain the change trend during the coating preparation process and determine the direction of parameter adjustment; if the change trend exceeds the preset threshold, re-extract the online detection data through the system combination method to obtain the updated log set; use the updated log set, combine the performance index data, and optimize the process parameters again through the gradient descent algorithm to obtain a stable parameter scheme; according to the stable parameter scheme, obtain the final result of the coating preparation and judge whether it meets the requirements of the stable scheme.

[0164] Exemplarily, when obtaining the performance index data from the simulation results, the key extraction method can be used to determine the main performance parameters.

[0165] For example, after simulating the stress distribution of the coating under high temperature and high pressure, indicators such as the maximum stress value and the number of heat resistance cycles can be extracted.

[0166] In a possible implementation, assume that the simulation shows that the stress peak of the coating is 300 MPa after 500 cycles at 1000 °C. Such data can be used as the basis for performance evaluation. The core of the key extraction method lies in screening the parameters that have the most significant impact on the coating performance and avoiding redundant data from interfering with subsequent analysis. When obtaining the data log from the online detection system, the initial values of the process parameters can be judged in combination with the performance index data.

[0167] Specifically, the detection system may record information such as the temperature of 800 °C and the deposition rate of 5 μm / min during coating deposition.

[0168] Exemplarily, if the performance index shows that the number of heat resistance cycles is related to the deposition rate, the initial process parameters can be set to the historical optimal record close to this value, such as 4.8 μm / min.

[0169] It should be noted that this initial value setting depends on the integrity and accuracy of the log data, which helps to reduce the number of iterations in subsequent optimization. When iteratively optimizing the process parameters through the gradient descent algorithm for the records in the data log, its implementation can be considered from multiple aspects.

[0170] For example, the initial deposition rate is set to 5 μm / min, but the log shows that microcracks appear in the coating at high temperature. The algorithm can be used to gradually adjust it to 4.5 μm / min and observe the trend of crack reduction.

[0171] In one embodiment, if the reduction is 0.1 μm / min per iteration and the number of cracks decreases from 10 to 2 after 5 adjustments, the parameter set tends to be stable. In this way, the optimal solution is gradually approximated through data-driven means, enhancing process controllability. When obtaining the variation trend during the coating preparation process based on the adjusted parameter set, the direction of parameter adjustment can be determined.

[0172] Preferably, if the coating thickness uniformity increases by 15% after the deposition rate decreases from 5 μm / min to 4.5 μm / min, the exploration of the adjustment direction can continue towards a lower rate.

[0173] It can be understood that trend analysis not only reflects the impact of parameter changes on the results but also provides a basis for subsequent optimization, avoiding blind adjustment. If the variation trend exceeds the preset threshold, for example, the thickness uniformity requirement is 90% but the actual measurement only reaches 85%, the online detection data is re-extracted through a systematic combination method.

[0174] In one possible implementation, the update log may show that the temperature fluctuation is too large, such as from 800 °C to 820 °C, affecting the uniformity. At this time, the data is re-collected to ensure that the temperature is controlled within ±5 °C. This update ensures that the data reflects the latest working conditions and improves the analysis accuracy. When using the updated log set in combination with the performance index data to optimize the process parameters again through the gradient descent algorithm, a stable parameter solution can be obtained.

[0175] For example, after adjusting the temperature to 810 °C and the rate to 4.6 μm / min, the uniformity reaches 92%, meeting the requirements.

[0176] Specifically, this iterative optimization ensures parameter stability through repeated verification, avoiding local optimal traps. When obtaining the final result of coating preparation through a stable parameter solution, it can be determined whether the requirements are met.

[0177] For example, the final coating shows no obvious failure after 600 cycles at 1000 °C, indicating that the solution is feasible.

[0178] It should be noted that this judgment relies on the matching of performance indicators and actual requirements, which can effectively guide production practice and improve the reliability of the coating under harsh working conditions.

[0179] The preferred embodiments of the present invention disclosed above are only used to help illustrate the present invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to only the specific implementation manners. Obviously, many modifications and variations can be made according to the content of this specification. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the present invention, so that those skilled in the art can well understand and utilize the present invention. The present invention is only limited by the claims and their full scope and equivalents.

Claims

1. A preparation method of a composite coating for a rear mold insert, characterized in that The method includes the following steps: Step S1: Obtain the surface data of the rear mold insert substrate, and apply the synergistic effect of the plasma field and the thermal field through a multi-energy field deposition device to deposit an initial transition layer on the substrate surface, obtaining a composite coating prototype with a gradient structure; Step S2: Extract the grain orientation and interface bonding state information from the surface of the initial transition layer, analyze the grain distribution uniformity and interface stress using ion beam scanning technology, and determine the basic parameters of the coating bonding force; Step S3: For the basic parameters of the coating bonding force, use a multi-energy field deposition device to adjust the deposition rate and energy input, and continue to deposit a high-density functional layer on the transition layer to obtain an enhanced gradient composite coating; Step S4: Deploy an online detection system on the surface of the enhanced gradient composite coating, obtain the distribution data of internal micro-defects in the coating through laser interference and ultrasonic scanning, and judge the specific positions and scales of micro-cracks and pores; Step S5: According to the distribution data of micro-defects, analyze the influence degree of defects on the thermal fatigue resistance in combination with a preset threshold range, and obtain the real-time evaluation result of the coating performance; Step S6: If the evaluation result is lower than the preset performance standard, extract the defect distribution characteristics from the online detection system, and feedback to the multi-energy field deposition device to adjust the deposition temperature and ion energy, and optimize the density and bonding force of the next batch of coatings; Step S7: Generate an improved gradient composite coating through the optimized deposition process, use the online detection system to scan the change trend of micro-defects again, and determine the improvement range of the coating durability and production efficiency; Step S8: Obtain the thermal cycle test data of the improved gradient composite coating, use the finite element analysis algorithm to simulate the stress distribution of the coating under high-temperature and high-pressure conditions, and judge the actual improvement level of the thermal fatigue resistance and interface strengthening; Step S9: Extract the key performance indicators from the simulation results, combine with the data log of the online detection system, and iteratively optimize the process parameters through the gradient descent algorithm to obtain the final stable coating preparation scheme.

2. The preparation method of a composite coating for a rear mold insert according to claim 1, characterized in that, The said Step S1 includes: Obtain the characteristic data of the substrate surface to obtain the surface state distribution; For the said surface state distribution, apply plasma field treatment using a multi-energy field deposition device to obtain a plasma-activated surface; Perform thermal field modulation on the said plasma-activated surface to obtain a thermally modulated surface; If the uniformity of the said thermally modulated surface reaches the preset threshold, deposit a transition layer through a deposition device to obtain an initial coating structure; Obtain the gradient distribution data of the said initial coating structure; According to the said gradient distribution data, adjust the field synergy parameters to obtain an optimized composite coating prototype; Perform surface detection on the said optimized composite coating prototype to obtain the final coating data.

3. The preparation method of a composite coating for a rear mold insert according to claim 1, characterized in that, The said Step S2 includes: Obtain the grain orientation information and interface bonding information of the transition layer surface, and use ion beam scanning technology to obtain the distribution data of the said grains and the stress distribution data of the said interface; Judge the uniformity of the said grain distribution according to a preset threshold to obtain the grain uniformity distribution characteristics; According to the said uniformity distribution characteristics, determine the change trend of the said interface stress to obtain the interface stress distribution law; For the said stress distribution law, extract the coating bonding force parameters to obtain the bonding strength quantification value; If the combined strength quantization value is lower than a preset threshold, a machine learning algorithm is used to adjust the grain orientation characteristics to obtain optimized grain distribution data; Based on the optimized distribution data, the interfacial stress distribution is re-analyzed to obtain adjusted bonding force parameters; Based on the adjusted bonding force parameters, the coating bonding state is judged to determine the final bonding force characteristics of the coating.

4. The preparation method of a composite coating for a rear mold insert according to claim 1, characterized in that The step S13 includes: Obtain the initial data of the deposition rate and energy input generated by the multi-energy field deposition equipment, and determine the basic parameters of the coating bonding force; Adjust the deposition rate and energy input according to the initial data to obtain the deposition conditions of the transition layer; Deposit a high-density functional layer on the transition layer using the adjusted deposition conditions, and judge the density distribution of the functional layer; Determine the deposition parameters of the gradient composite structure according to the density distribution of the functional layer to obtain a preliminary composite coating; For the preliminary composite coating, use the random forest algorithm to analyze the enhancement effect of the coating bonding force and judge the enhanced features; Obtain the final parameters of the composite coating from the enhanced features to determine the structure of the enhanced gradient composite coating; If the bonding force distribution of the composite coating is uniform, use image processing technology to analyze the surface morphology of the composite coating to obtain the final coating data.

5. The preparation method of a composite coating for a rear mold insert according to any one of claims 1-4, characterized in that, The step S4 includes: Obtain the interference fringe data on the coating surface through laser interference to determine the initial contour of the microdefect distribution; Use ultrasonic scanning to perform depth detection on the inside of the coating to obtain a complete data set of the microdefect distribution; Apply a convolutional neural network to the microdefect distribution data to judge the coordinate information of the microcrack position; Calculate the boundary characteristics of the pores according to the microdefect distribution data to determine the distribution range of the pore size; If the overlapping area between the microcrack position and the pore size exceeds a preset threshold, separate the overlapping defects through an image segmentation algorithm to obtain independent defect features; Compare the independent defect features with the delamination characteristics of the gradient composite material to judge the depth distribution of the defects inside the coating; Obtain the difference data between the depth distribution and the initial contour, and classify the defect types through a support vector machine to determine the final microdefect distribution characteristics.

6. The preparation method of a composite coating for a rear mold insert according to any one of claims 1-4, characterized in that, The step S5 includes: Obtain the microdefect distribution data, and extract the microdefect distribution data to obtain a defect feature set; According to the defect feature set and a preset threshold, judge the area where the defect exceeds the preset threshold range to obtain the defect influence range; For the defect influence range, analyze the change trend of the thermal fatigue resistance to obtain the resistance degree distribution; Obtain the key indicators of the coating performance from the resistance degree distribution to determine the performance change characteristics; If the performance change characteristics exceed a preset threshold, use the support vector machine algorithm to classify the coating performance to obtain the performance grade division; Combine the performance grade division with the real-time evaluation requirements to judge the real-time state of the coating performance and obtain the final evaluation result; Update the analysis model of the defect influence according to the final evaluation result to obtain an optimized prediction result of the thermal fatigue resistance.

7. A method for preparing a composite coating for a rear mold insert according to any one of claims 1-4, characterized in that, The step S6 includes: Obtain the defect distribution characteristics of the on-line detection system, extract the boundaries of the defect distribution characteristics by using image processing technology, and obtain defect distribution data; Analyze the abnormal areas during the deposition process according to the defect distribution data, use the support vector machine algorithm to judge the relationship between the abnormal areas and the deposition temperature, and determine the temperature adjustment direction; Update the control parameters of the deposition equipment according to the temperature adjustment direction, obtain the adjusted deposition temperature value, and obtain a new temperature configuration; Analyze the influence of ion energy on the bonding force through the defect distribution data, use the linear regression algorithm to judge the energy adjustment amplitude, and determine the optimized ion energy value; Obtain the current ion energy parameters of the deposition equipment, and adjust the equipment settings in combination with the optimized ion energy value to obtain a new energy configuration; Operate the multi-energy field deposition equipment with the adjusted temperature configuration and energy configuration to obtain the coating data of the next batch; Judge the change trend of the coating density and bonding force according to the coating data of the next batch; Compare the coating data of the next batch with the preset standard, judge the optimization effect, and obtain the batch optimization result.

8. The preparation method of a composite coating for a rear mold insert according to any one of claims 1-4, characterized in that, The step S7 includes: Obtain a gradient composite coating sample, and the gradient composite coating sample is prepared by using preset deposition process parameters; Scan the surface of the gradient composite coating sample by using an on-line detection system to obtain the distribution characteristic information of surface micro-defects; Determine the preliminary data of the change of micro-defects according to the distribution characteristic information; Process the continuous scanning results of the on-line detection system by using a time series algorithm to obtain the trend characteristic value of the change of micro-defects; Judge the durability index of the gradient composite coating sample according to the trend characteristic value; If the durability index is lower than the preset threshold, adjust the deposition process parameters to generate an improved gradient composite coating sample; Scan the improved gradient composite coating sample by using the on-line detection system, obtain the updated micro-defect change data, and determine the improvement amplitude of durability; Analyze the generation process of the improved gradient composite coating sample by using a production efficiency evaluation tool to obtain the data of the improvement amplitude of production efficiency; Extract the key features from the data of the improvement amplitude of production efficiency, and combine the improvement amplitude of durability to judge whether the optimization of the deposition process parameters meets the expected standard.

9. A method for preparing a composite coating for a rear mold insert according to any one of claims 1-4, characterized in that, The step S8 includes: Obtain the relationship data between the temperature change and the number of cycles in multiple thermal cycle experiments, and determine the performance of the coating in multiple cycles; According to the thermal cycle experiment data, use the finite element analysis algorithm to construct a three-dimensional model of the coating under high temperature and high pressure working conditions, and obtain the stress distribution characteristics in the model; Simulate the change of the stress distribution through the finite element analysis algorithm, and judge the thermal fatigue resistance level of the coating under high temperature and high pressure working conditions; According to the simulation results of the stress distribution and the thermal fatigue resistance, obtain the quantitative index of the interface strengthening of the coating, and determine the improvement degree of the interface strengthening on the thermal fatigue; Process the thermal cycle test data and the simulation results by using a machine learning regression algorithm to obtain the correlation law between the thermal fatigue resistance and the interface strengthening; Analyze the changing trend of the coating performance under different working conditions according to the above correlation law, and judge the overall improvement level of the improved gradient composite coating; Adjust the parameters of the simulation analysis according to the changing trend to obtain the optimized coating performance data.