Performance characterization and optimization method and device for influence of casting surface quality on bonding performance

Abstract

The invention discloses a performance characterization and optimization method and device for the influence of the surface quality of a casting on the bonding performance, and relates to the technical field of data processing.The method comprises the steps that the surface of the casting is divided into a plurality of detection areas, and feature data of the surface of the casting are obtained; inputting the feature data into a preset surface quality analysis model to obtain a quantitative result of the surface quality of the casting; based on the quantification result, a bonding experiment is conducted on the casting, and bonding performance data are obtained; a correlation model of the casting surface quality and the bonding performance is established in combination with the quantification result and the bonding performance data; and the correlation model is used for optimizing the surface quality of the casting, and the bonding performance is improved.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method and device for characterizing and optimizing the effect of casting surface quality on bonding performance. Background Art

[0002] In the field of casting manufacturing, surface quality has an important influence on the bonding performance of castings. With the development of industrial technology, the requirements for the bonding performance of castings are getting higher and higher, especially in the automotive, aerospace, machinery manufacturing and other industries. The bonding performance of castings is directly related to the safety and reliability of the product. Therefore, studying the relationship between the surface quality and bonding performance of castings, optimizing the surface treatment process, and improving the bonding performance have become important topics in the current field of casting manufacturing.

[0003] In the prior art, the quantitative evaluation of casting surface quality mainly includes the detection of surface roughness, chemical composition, defects, etc. However, the correlation between these quantitative results and bonding performance is not clear, and there is a lack of effective prediction models. In actual production, surface treatment solutions are usually selected based on experience or trial and error, which is not only inefficient, but also difficult to ensure the consistency and stability of bonding performance. Summary of the invention

[0004] The purpose of this application is to provide a method and device for characterizing and optimizing the effect of casting surface quality on bonding performance.

[0005] To achieve the above objectives, this application provides the following solutions:

[0006] In a first aspect, the present application provides a method for characterizing and optimizing the effect of casting surface quality on bonding performance, including:

[0007] Dividing the casting surface into a plurality of detection areas to obtain characteristic data of the casting surface;

[0008] Inputting the characteristic data into a preset surface quality analysis model to obtain a quantitative result of the casting surface quality;

[0009] Based on the quantitative results, a bonding experiment is performed on the casting to obtain bonding performance data;

[0010] Combining the quantitative results with the bonding performance data, establishing a correlation model between casting surface quality and bonding performance;

[0011] The correlation model is used to optimize the surface quality of the casting and improve the bonding performance.

[0012] Optionally, the step of dividing the casting surface into a plurality of detection areas comprises:

[0013] According to the geometric shape and material properties of the casting, the casting surface is divided into roughness detection area, chemical composition detection area and defect detection area.

[0014] Optionally, the step of acquiring characteristic data of the casting surface comprises:

[0015] Using a laser confocal microscope and a 3D profilometer to measure the roughness detection area to obtain surface roughness data;

[0016] The chemical composition detection area is analyzed by using X-ray photoelectron spectroscopy and energy spectrum analysis to obtain surface chemical composition data;

[0017] The defect detection area is detected by infrared thermal imaging and ultrasonic detection to obtain surface defect data.

[0018] Optionally, the step of inputting the characteristic data into a preset surface quality analysis model comprises:

[0019] The surface roughness data, surface chemical composition data and surface defect data are input into the surface quality analysis model, and trained through a deep learning algorithm to obtain quantitative results of the casting surface quality.

[0020] Optionally, the step of performing a bonding experiment on the casting based on the quantified result includes:

[0021] Selecting representative casting samples according to the quantitative results;

[0022] Performing surface treatment on the casting sample to simulate different surface treatment schemes;

[0023] The treated casting samples were bonded using different structural adhesives, and mechanical property tests and fatigue life tests were performed to obtain bonding performance data.

[0024] Optionally, the step of establishing a correlation model between casting surface quality and bonding performance by combining the quantification result and the bonding performance data comprises:

[0025] Inputting the quantified results and the bonding performance data into a correlation model building module;

[0026] The quantified results and the bonding performance data are fitted using a machine learning algorithm to establish a correlation model between casting surface quality and bonding performance.

[0027] Optionally, the step of optimizing the casting surface quality and improving the bonding performance by using the correlation model comprises:

[0028] According to the correlation model, predict the bonding performance under different surface treatment schemes;

[0029] Select the surface treatment that predicts the best bonding performance;

[0030] Carry out actual surface treatment on castings and verify whether the bonding performance meets the preset standard requirements.

[0031] In a second aspect, the present application provides a performance characterization and optimization device for the effect of casting surface quality on bonding performance, comprising:

[0032] An acquisition module, used for dividing the casting surface into a plurality of detection areas, and acquiring characteristic data of the casting surface;

[0033] A prediction module, used for inputting the characteristic data into a preset surface quality analysis model to obtain a quantitative result of the casting surface quality;

[0034] A characterization module, for performing bonding experiments on the castings based on the quantified results to obtain bonding performance data;

[0035] Combining the quantitative results with the bonding performance data, establishing a correlation model between casting surface quality and bonding performance;

[0036] The optimization module is used to optimize the surface quality of the casting using the association model to improve the bonding performance.

[0037] Optionally, the acquisition module is further used to:

[0038] According to the geometric shape and material properties of the casting, the casting surface is divided into roughness detection area, chemical composition detection area and defect detection area.

[0039] Optionally, the acquisition module is further used to:

[0040] Using a laser confocal microscope and a 3D profilometer to measure the roughness detection area to obtain surface roughness data;

[0041] The chemical composition detection area is analyzed by using X-ray photoelectron spectroscopy and energy spectrum analysis to obtain surface chemical composition data;

[0042] The defect detection area is detected by infrared thermal imaging and ultrasonic detection to obtain surface defect data.

[0043] Optionally, the prediction module is further used to:

[0044] The surface roughness data, surface chemical composition data and surface defect data are input into the surface quality analysis model, and trained through a deep learning algorithm to obtain quantitative results of the casting surface quality.

[0045] Optionally, the characterization module is further used to:

[0046] Selecting representative casting samples according to the quantitative results;

[0047] Performing surface treatment on the casting sample to simulate different surface treatment schemes;

[0048] The treated casting samples were bonded using different structural adhesives, and mechanical property tests and fatigue life tests were performed to obtain bonding performance data.

[0049] Optionally, the step of establishing a correlation model between casting surface quality and bonding performance by combining the quantification result and the bonding performance data comprises:

[0050] Inputting the quantified results and the bonding performance data into a correlation model building module;

[0051] The quantified results and the bonding performance data are fitted using a machine learning algorithm to establish a correlation model between casting surface quality and bonding performance.

[0052] Optionally, the optimization module is further used to:

[0053] According to the correlation model, predict the bonding performance under different surface treatment schemes;

[0054] Select the surface treatment that predicts the best bonding performance;

[0055] Carry out actual surface treatment on castings and verify whether the bonding performance meets the preset standard requirements.

[0056] In a third aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the performance characterization and optimization method of the influence of casting surface quality on bonding performance as described in any one of the above.

[0057] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the performance characterization and optimization method of the influence of casting surface quality on bonding performance as described in any one of the above.

[0058] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the performance characterization and optimization method of the influence of casting surface quality on bonding performance described in any one of the above.

[0059] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0060] The present application provides a method and device for characterizing and optimizing the effect of casting surface quality on bonding performance. By first being able to comprehensively and accurately obtain key characteristic data of the casting surface, including roughness, chemical composition, and defect distribution, this lays a solid foundation for accurately characterizing the casting surface quality. Subsequently, using advanced surface quality analysis models, we convert these characteristic data into quantitative surface quality indicators, and then establish a direct correlation between casting surface quality and bonding performance through bonding experiments. The establishment of this correlation model enables us to gain in-depth insight into the mechanism of the influence of surface quality on bonding strength, and guide the optimization of surface treatment processes accordingly, thereby significantly improving bonding performance and ensuring the reliability and durability of bonded joints. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0062] Figure 1 A schematic flow chart of a method for characterizing and optimizing the effect of casting surface quality on bonding performance provided in one embodiment of the present application;

[0063] Figure 2 A schematic diagram of functional modules of a device for characterizing and optimizing the effect of casting surface quality on bonding performance provided in one embodiment of the present application;

[0064] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0066] like Figure 1 As shown, some embodiments of the present application provide a performance characterization and optimization method for the influence of casting surface quality on bonding performance. In the embodiments of the present application, the following steps 101 to 105 are included.

[0067] in:

[0068] Step 101: Divide the casting surface into a plurality of detection areas, and obtain characteristic data of the casting surface.

[0069] In the present application embodiment, the surface roughness of the region is measured with high precision using equipment such as a laser confocal microscope and a 3D profiler. These devices can generate a three-dimensional image of the surface topography and calculate key parameters such as average roughness (Ra) and maximum peak-to-valley height (Rz), which are important indicators for describing the microscopic geometry of the casting surface. The surface chemical composition of the region is quantitatively analyzed using technologies such as X-ray photoelectron spectroscopy (XPS) and energy spectrum analysis (EDS). These technologies can identify oxides, pollutants, and other chemical elements on the surface of the casting that may affect the bonding performance, and determine their content and distribution. Non-destructive testing of surface defects in the region is performed using means such as infrared thermal imaging and ultrasonic testing. Infrared thermal imaging can detect local temperature changes caused by defects, while ultrasonic testing can identify different types of defects such as cracks, bubbles, and corrosion points, and record their position, density, and size.

[0070] Step 102: input the characteristic data into a preset surface quality analysis model to obtain a quantitative result of the casting surface quality.

[0071] In the embodiment of the present application, the input feature data is cleaned, standardized and feature extracted to ensure the quality and consistency of the data, and the features that have a significant impact on the bonding performance are extracted. The model is trained using known surface quality and bonding performance data so that the model can learn the complex relationship between surface quality and bonding performance. The pre-treated feature data is input into the trained model, and the model will output the quantitative results of the casting surface quality. These results are usually expressed in the form of numerical values ​​or classification labels, which can intuitively reflect the quality status of the casting surface.

[0072] Step 103: Based on the quantified result, a bonding experiment is performed on the casting to obtain bonding performance data.

[0073] In the present application embodiment, according to the quantification result, the casting samples with large surface quality differences are selected as experimental objects. The selected casting samples are subjected to different surface treatments to simulate the influence of different surface treatment schemes on bonding performance. These treatments may include grinding, sandblasting, chemical cleaning, etc. The treated casting samples are bonded using different structural adhesives, and mechanical property tests (such as shear strength tests, peel tests) and fatigue life tests are performed. Through these tests, the bonding performance data of castings under different surface qualities can be obtained.

[0074] Step 104: Establish a correlation model between casting surface quality and bonding performance by combining the quantification result and the bonding performance data.

[0075] In the present application embodiment, the surface quality quantification result and the bonding performance data are integrated to form a data set containing multidimensional features. According to the characteristics of the data and the complexity of the problem, a suitable machine learning model (such as random forest, neural network, etc.) is selected for modeling. The model is trained using the data set, and the performance of the model is evaluated by methods such as cross-validation. During the training process, the parameters of the model are continuously adjusted to optimize its prediction ability. When the model performance meets the requirements, it is determined as a correlation model of casting surface quality and bonding performance. This model can predict the corresponding bonding performance based on the input surface quality data.

[0076] Step 105: Optimize the surface quality of the casting using the correlation model to improve the bonding performance.

[0077] In the embodiment of the present application, different surface treatment schemes are input into the correlation model to predict the bonding performance under each scheme. According to the prediction results, the surface treatment scheme with the best bonding performance is selected as the scheme for practical application. The casting is actually surface treated according to the selected scheme, and a bonding experiment is performed to verify the optimization effect. If the experimental results show that the bonding performance still has room for improvement, the surface quality can be further optimized by adjusting the surface treatment parameters or trying new treatment schemes.

[0078] The embodiments of the present application firstly comprehensively and accurately obtain the key characteristic data of the casting surface, including roughness, chemical composition and defect distribution, which lays a solid foundation for accurately characterizing the surface quality of the casting. Subsequently, using advanced surface quality analysis models, we convert these characteristic data into quantitative surface quality indicators, and then establish a direct correlation between the surface quality of the casting and the bonding performance through bonding experiments. The establishment of this correlation model enables us to gain a deep insight into the mechanism of the influence of surface quality on bonding strength, and guide the optimization of the surface treatment process accordingly, thereby significantly improving the bonding performance and ensuring the reliability and durability of the bonded joint.

[0079] Optionally, the step 101 includes: dividing the surface of the casting into a roughness detection area, a chemical composition detection area and a defect detection area according to the geometric shape and material properties of the casting.

[0080] In the examples of this application, the overall geometric shape of the casting is carefully observed and analyzed to understand its contours, curved surfaces, corners and other features. Based on the characteristics of the geometric shape, it is determined which areas may have surface quality differences due to shape changes, such as curved surfaces that may be more prone to ripples, and corners that may be more prone to wear or dirt accumulation. Based on these analyses, the geometric shape areas that need special attention are preliminarily divided to prepare for subsequent inspections.

[0081] Gain a deep understanding of the material composition of castings, including main components, alloying elements, microstructure, etc. Analyze the impact of different materials on surface quality, such as certain alloying elements may make the surface more susceptible to oxidation or corrosion, and the unevenness of the microstructure may affect the surface roughness or produce internal defects. Based on the material characteristics, identify possible areas of surface quality problems and consider how to pay special attention to these areas during inspection.

[0082] Combining geometric shape analysis and material characteristics, the casting surface is divided into three specific inspection areas:

[0083] Roughness inspection area: Focus on the micro-geometry of the casting surface and select representative areas for measurement to evaluate the surface smoothness and roughness.

[0084] Chemical composition detection area: For key elements or alloys that may exist in the casting material, select typical areas for chemical composition analysis to understand the surface chemical composition and its distribution.

[0085] Defect detection area: Based on the possible defect risks in the geometry and material properties, select key areas for defect detection, such as cracks, pores, inclusions, etc.

[0086] When dividing the inspection area, it should be ensured that each area can fully reflect the overall condition of the casting surface, while avoiding repeated inspection or missing key areas.

[0087] Optionally, the step 101 includes:

[0088] Step 1011: Use a laser confocal microscope and a 3D profilometer to measure the roughness detection area to obtain surface roughness data.

[0089] In the embodiment of the present application, first, the laser confocal microscope is adjusted to the parameter settings suitable for measuring roughness, including laser wavelength, scanning speed, depth of focus, etc. Then, the microscope is aligned with the roughness detection area, and the microscopic topography image of the surface is obtained by laser scanning. This microscope can capture the tiny ups and downs of the surface with high precision, providing basic data for roughness analysis. Then, a 3D profiler is used to scan the same area to obtain the three-dimensional profile data of the surface. The 3D profiler can construct a three-dimensional model of the surface by measuring the height information of each point on the surface, further enriching the data dimension of the roughness. The data obtained by the laser confocal microscope and the 3D profiler are fused and processed, and the key roughness parameters such as the average roughness (Ra) and the maximum peak-to-valley height (Rz) of the surface are calculated by professional analysis software to form a surface roughness data report.

[0090] Step 1012: Analyze the chemical composition detection area using X-ray photoelectron spectroscopy and energy spectrum analysis to obtain surface chemical composition data.

[0091] In an embodiment of the present application, X-ray photoelectron spectroscopy (XPS) is used: first, an X-ray photoelectron spectrometer is used to irradiate the chemical composition detection area, and after the X-rays interact with the surface atoms, photoelectrons are excited. By measuring the energy distribution of these photoelectrons, the types and valence states of the surface atoms can be inferred, and then the chemical composition information of the surface can be obtained. In order to have a more comprehensive understanding of the chemical composition of the surface, the same area is detected at the same time using energy spectrum analysis technology. Energy spectrum analysis can directly measure the characteristic X-ray radiation of the surface elements, thereby determining the type and relative content of the elements. The data obtained by XPS and EDS are comprehensively analyzed to obtain a detailed report on the surface chemical composition, including the types of elements, content ratios, and possible compound forms.

[0092] Step 1013: Use infrared thermal imaging and ultrasonic testing to detect the defect detection area to obtain surface defect data.

[0093] In an embodiment of the present application, first, an infrared thermal imager is used to scan the defect detection area. Since defects (such as cracks, pores, etc.) will cause changes in the surface thermal conductivity, different temperature distributions will be presented in infrared thermal imaging. By observing and analyzing these temperature differences, the location and morphology of the defects can be preliminarily identified. In order to more accurately detect internal defects, ultrasonic detection technology is used to scan the same area. When ultrasonic waves encounter defects during propagation, they will be reflected, scattered or attenuated. By receiving and processing these ultrasonic signals, the location, size and type of the defects can be accurately determined. The data obtained by infrared thermal imaging and ultrasonic testing are sorted and analyzed to form a detailed defect data report, including the number, distribution, type and possible causes of defects.

[0094] Optionally, the step 102 includes: inputting the surface roughness data, surface chemical composition data and surface defect data into the surface quality analysis model, training it through a deep learning algorithm, and obtaining a quantitative result of the casting surface quality.

[0095] Optionally, the step 103 includes:

[0096] Step 1031: Select representative casting samples according to the quantification results.

[0097] In the present application embodiment, first, based on the casting surface roughness data, chemical composition data and defect data obtained in the previous steps, a comprehensive quality assessment is performed on the casting. According to the evaluation results, representative castings that can cover different quality levels are selected as experimental samples. These samples should be able to reflect the diversity and differences of castings in actual production. Ensure that the number of selected samples is sufficient to meet the statistical requirements of subsequent experimental designs, while considering the availability and cost-effectiveness of the samples.

[0098] Step 1032, performing surface treatment on the casting sample to simulate different surface treatment schemes.

[0099] In the embodiments of the present application, different surface treatment schemes are designed and implemented for the selected casting samples. These schemes may include various processes such as sandblasting, polishing, pickling, electroplating, spraying, etc., which are intended to change the roughness, chemical composition and defect state of the casting surface. Ensure that each surface treatment scheme can effectively change its surface characteristics without destroying the overall structure of the casting. Detailed records are made for each treated casting sample, including the treatment process, treatment parameters and the surface state after treatment, etc., for subsequent analysis and comparison.

[0100] Step 1033, using different structural adhesives to bond the treated casting samples, and performing mechanical property tests and fatigue life tests to obtain bonding performance data.

[0101] In the examples of the present application, various types of structural adhesives are selected as bonding materials according to the experimental design. These structural adhesives should have different chemical compositions, bonding strengths and weather resistance to simulate the diversity in practical applications. According to the standard bonding procedure, the treated casting samples are bonded with the corresponding structural adhesives. Ensure that the operating specifications and bonding areas are consistent during the bonding process, and control the temperature and humidity of the bonding environment to reduce experimental errors.

[0102] The bonded casting samples are subjected to mechanical property tests, including tests of tensile strength, shear strength, peel strength and other indicators. These tests can directly reflect the mechanical properties and load-bearing capacity of the bonded joint. At the same time, fatigue life tests are carried out to simulate the long-term stress conditions of the castings in actual use and evaluate the durability and reliability of the bonded joints. Fatigue life tests can be carried out through cyclic loading or vibration experiments to record the fatigue life of the bonded joints under specific conditions. The test data are recorded and analyzed in detail, including mechanical property test results, fatigue life and possible failure modes, to form a bonding performance data report.

[0103] Optionally, the step 104 includes:

[0104] Step 1041 , inputting the quantification result and the bonding performance data into a correlation model building module.

[0105] Step 1042: Fit the quantified results and the bonding performance data using a machine learning algorithm to establish a correlation model between casting surface quality and bonding performance.

[0106] In the application embodiment, the casting surface quantification results and bonding performance data obtained through experiments and tests in the early stage are sorted, cleaned and standardized to ensure the accuracy and consistency of the data. The processed data is input into the association model establishment module, which is usually a software platform or programming environment that integrates data processing, feature selection, model training and other functions. In the association model establishment module, feature selection technology is used to screen out feature variables that have a significant impact on bonding performance from the casting surface quantification results and bonding performance data. These features may include the average roughness of the surface, the content of specific elements, the type and number of defects, etc. The selected features are further extracted and converted to form feature vectors suitable for processing by machine learning algorithms.

[0107] According to the characteristics of the data and the complexity of the problem, select the appropriate machine learning algorithm for model training. Common algorithms include linear regression, decision tree, random forest, support vector machine, neural network, etc. Consider factors such as the accuracy, stability, interpretability, and computational efficiency of the algorithm to select the most suitable algorithm for this study.

[0108] The selected machine learning algorithm is used to train the input feature vector and bonding performance data. Through continuous iteration and optimization, the model can accurately predict the relationship between casting surface quality and bonding performance. During the training process, cross-validation, grid search and other techniques are used to evaluate the performance of the model, prevent overfitting and underfitting, and ensure the generalization ability of the model.

[0109] Use an independent validation data set to validate the trained model and evaluate its prediction accuracy and reliability. If the model performance is poor, you need to return to the previous step to adjust the feature selection, algorithm parameters, or data processing method. Optimize the model based on the validation results until a satisfactory prediction effect is achieved.

[0110] After training, verification and optimization, a correlation model between casting surface quality and bonding performance was finally established. The model can predict the bonding performance of castings based on the surface quantification results, providing a scientific basis for the design, production and application of castings. The established correlation model is applied to actual casting production and quality control, and the selection and optimization of surface treatment processes are guided by predicting bonding performance. The application effect of the model is regularly evaluated, and the model is updated and iterated according to actual conditions to maintain its accuracy and effectiveness.

[0111] Optionally, the step 105 includes:

[0112] Step 1051: predict the bonding performance under different surface treatment schemes according to the correlation model.

[0113] In the embodiment of the present application, first, the established correlation model is used to input the surface quantitative results (such as roughness, chemical composition, defects, etc.) of the casting under different surface treatment schemes. The model will predict the bonding performance under the corresponding surface treatment scheme based on the input feature data, including key indicators such as mechanical property test results and fatigue life. All possible surface treatment schemes are predicted to obtain a series of prediction results to form a prediction data set.

[0114] Step 1052, selecting a surface treatment solution with the best predicted bonding performance.

[0115] In the examples of this application, the predicted results of bonding performance under different surface treatment schemes are compared based on the predicted data set. According to actual needs, such as pursuing the highest bonding strength, the longest fatigue life or a specific performance combination, the surface treatment scheme with the best predicted bonding performance is selected. Considering the feasibility and cost-effectiveness of actual production, ensure that the selected scheme can be implemented under existing process conditions.

[0116] Step 1053, performing actual surface treatment on the casting and verifying whether the bonding performance meets the preset standard requirements.

[0117] In the embodiment of the present application, a detailed surface treatment process and operating specifications are formulated based on the selected optimal surface treatment solution. The casting to be treated is pretreated, such as cleaning, degreasing, descaling, etc., to ensure that the surface is clean and free of impurities. According to the process flow, the casting is actually surface treated, such as sandblasting, polishing, electroplating, spraying, etc., to ensure that the treatment effect is consistent with the input features in the prediction model.

[0118] After the treatment is completed, the casting is tested for bonding performance, including mechanical performance tests (such as tensile strength, shear strength, etc.) and fatigue life tests. The test results are compared with the preset standard regulations to evaluate whether the bonding performance meets the requirements. If the test results meet the standard regulations, the verification is passed and the surface treatment plan can be considered effective and feasible. If the test results do not meet the standard regulations, the reasons need to be analyzed, which may be problems with the surface treatment process, inaccurate model predictions, or errors in the test method, etc., and corresponding adjustments and optimizations are made based on the analysis results.

[0119] Based on the same inventive concept, the embodiment of the present application also provides a performance characterization and optimization device for realizing the performance characterization and optimization method of the casting surface quality on the bonding performance involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of the performance characterization and optimization device for the effect of the casting surface quality on the bonding performance provided below can refer to the limitations of the performance characterization and optimization method for the effect of the casting surface quality on the bonding performance above, and will not be repeated here.

[0120] In an exemplary embodiment, Figure 2 As shown, a performance characterization and optimization device 20 for the influence of casting surface quality on bonding performance is provided, comprising:

[0121] An acquisition module 201 is used to divide the casting surface into a plurality of detection areas and acquire characteristic data of the casting surface;

[0122] Prediction module 202, used for inputting the characteristic data into a preset surface quality analysis model to obtain a quantitative result of the casting surface quality;

[0123] A characterization module 203 is used to perform a bonding experiment on the casting based on the quantification result to obtain bonding performance data;

[0124] Combining the quantitative results with the bonding performance data, establishing a correlation model between casting surface quality and bonding performance;

[0125] The optimization module 204 is used to optimize the surface quality of the casting using the correlation model to improve the bonding performance.

[0126] Optionally, the acquisition module 201 is further used to:

[0127] According to the geometric shape and material properties of the casting, the casting surface is divided into roughness detection area, chemical composition detection area and defect detection area.

[0128] Optionally, the acquisition module 201 is further used to:

[0129] Using a laser confocal microscope and a 3D profilometer to measure the roughness detection area to obtain surface roughness data;

[0130] The chemical composition detection area is analyzed by using X-ray photoelectron spectroscopy and energy spectrum analysis to obtain surface chemical composition data;

[0131] The defect detection area is detected by infrared thermal imaging and ultrasonic detection to obtain surface defect data.

[0132] Optionally, the prediction module 202 is further configured to:

[0133] The surface roughness data, surface chemical composition data and surface defect data are input into the surface quality analysis model, and trained through a deep learning algorithm to obtain quantitative results of the casting surface quality.

[0134] Optionally, the characterization module 203 is further used for:

[0135] Selecting representative casting samples according to the quantitative results;

[0136] Performing surface treatment on the casting sample to simulate different surface treatment schemes;

[0137] The treated casting samples were bonded using different structural adhesives, and mechanical property tests and fatigue life tests were performed to obtain bonding performance data.

[0138] Optionally, the step of establishing a correlation model between casting surface quality and bonding performance by combining the quantification result and the bonding performance data comprises:

[0139] Inputting the quantified results and the bonding performance data into a correlation model building module;

[0140] The quantified results and the bonding performance data are fitted using a machine learning algorithm to establish a correlation model between casting surface quality and bonding performance.

[0141] Optionally, the optimization module 204 is further configured to:

[0142] According to the correlation model, predict the bonding performance under different surface treatment schemes;

[0143] Select the surface treatment that predicts the best bonding performance;

[0144] Carry out actual surface treatment on castings and verify whether the bonding performance meets the preset standard requirements.

[0145] The embodiments of the present application firstly comprehensively and accurately obtain the key characteristic data of the casting surface, including roughness, chemical composition and defect distribution, which lays a solid foundation for accurately characterizing the surface quality of the casting. Subsequently, using advanced surface quality analysis models, we convert these characteristic data into quantitative surface quality indicators, and then establish a direct correlation between the surface quality of the casting and the bonding performance through bonding experiments. The establishment of this correlation model enables us to gain a deep insight into the mechanism of the influence of surface quality on bonding strength, and guide the optimization of the surface treatment process accordingly, thereby significantly improving the bonding performance and ensuring the reliability and durability of the bonded joint.

[0146] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store performance characterization and optimization data of the influence of the surface quality of the casting on the bonding performance. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a performance characterization and optimization method of the influence of the surface quality of the casting on the bonding performance is realized.

[0147] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0148] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0149] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0150] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0151] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0152] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0153] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.

[0154] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0155] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for characterizing and optimizing the effect of casting surface quality on bonding performance, characterized in that: The performance characterization and optimization method of the influence of the casting surface quality on the bonding performance includes: Dividing the casting surface into a plurality of detection areas to obtain characteristic data of the casting surface; Inputting the characteristic data into a preset surface quality analysis model to obtain a quantitative result of the casting surface quality; Based on the quantitative results, a bonding experiment is performed on the casting to obtain bonding performance data; Combining the quantitative results with the bonding performance data, establishing a correlation model between casting surface quality and bonding performance; The correlation model is used to optimize the surface quality of the casting and improve the bonding performance.

2. The method for characterizing and optimizing the effect of casting surface quality on bonding performance according to claim 1, characterized in that: The step of dividing the casting surface into a plurality of detection areas comprises: According to the geometric shape and material properties of the casting, the casting surface is divided into roughness detection area, chemical composition detection area and defect detection area.

3. The method for characterizing and optimizing the effect of casting surface quality on bonding performance according to claim 2, characterized in that: The step of obtaining characteristic data of the casting surface comprises: Using a laser confocal microscope and a 3D profilometer to measure the roughness detection area to obtain surface roughness data; The chemical composition detection area is analyzed by using X-ray photoelectron spectroscopy and energy spectrum analysis to obtain surface chemical composition data; The defect detection area is detected by infrared thermal imaging and ultrasonic detection to obtain surface defect data.

4. The method for characterizing and optimizing the effect of casting surface quality on bonding performance according to claim 1, characterized in that: The step of inputting the characteristic data into a preset surface quality analysis model comprises: The surface roughness data, surface chemical composition data and surface defect data are input into the surface quality analysis model, and trained through a deep learning algorithm to obtain quantitative results of the casting surface quality.

5. The method for characterizing and optimizing the effect of casting surface quality on bonding performance according to claim 1, characterized in that: The step of performing a bonding experiment on the casting based on the quantitative results comprises: Selecting representative casting samples according to the quantitative results; Performing surface treatment on the casting sample to simulate different surface treatment schemes; The treated casting samples were bonded using different structural adhesives, and mechanical property tests and fatigue life tests were performed to obtain bonding performance data.

6. The method for characterizing and optimizing the effect of casting surface quality on bonding performance according to claim 1, characterized in that: The step of establishing a correlation model between casting surface quality and bonding performance by combining the quantification result and the bonding performance data comprises: Inputting the quantified results and the bonding performance data into a correlation model building module; The quantified results and the bonding performance data are fitted using a machine learning algorithm to establish a correlation model between casting surface quality and bonding performance.

7. The method for characterizing and optimizing the effect of casting surface quality on bonding performance according to claim 1, characterized in that: The step of optimizing the surface quality of the casting by using the correlation model to improve the bonding performance comprises: According to the correlation model, predict the bonding performance under different surface treatment schemes; Select the surface treatment that predicts the best bonding performance; Carry out actual surface treatment on castings and verify whether the bonding performance meets the preset standard requirements.

8. A performance characterization and optimization device for the effect of casting surface quality on bonding performance, characterized in that: The performance characterization and optimization device for the influence of the casting surface quality on the bonding performance comprises: An acquisition module, used for dividing the casting surface into a plurality of detection areas, and acquiring characteristic data of the casting surface; A prediction module, used for inputting the characteristic data into a preset surface quality analysis model to obtain a quantitative result of the casting surface quality; A characterization module, for performing bonding experiments on the castings based on the quantified results to obtain bonding performance data; Combining the quantitative results with the bonding performance data, establishing a correlation model between casting surface quality and bonding performance; The optimization module is used to optimize the surface quality of the casting using the association model to improve the bonding performance.

9. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for characterizing and optimizing the effect of casting surface quality on bonding performance as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the performance characterization and optimization method of the influence of casting surface quality on bonding performance described in any one of claims 1 to 7 are implemented.

Images