Workpiece thermal defect detection method based on big data processing

Abstract

The invention discloses a workpiece thermal defect detection method based on big data processing, and relates to the technical field of mechanical workpiece detection. The method comprises the following steps: acquiring a workpiece surface condition feature data set, and comparing to obtain a workpiece thermal defect detection first deviation value; acquiring a workpiece material feature data set, and comparing to obtain a second deviation value of workpiece thermal defect detection; acquiring a workpiece outer surface thermal defect detection data set, and comprehensively analyzing to obtain a workpiece outer surface thermal defect detection characteristic value; according to the method, the problems that errors and inconsistency exist in detection results, data processing and interpretation are complex and time-consuming, and comparability and consistency of the detection results are poor are solved, comprehensive quality evaluation can be carried out, and the detection accuracy is improved. Accurate judgment of workpiece quality is ensured, measures are taken in time to prevent problems, detection strategies and standards are flexibly adjusted, resource waste is reduced, and the production process is optimized.

Description

[0001] This application is a divisional application of the application filed on November 5, 2024, with application number 202411566883.2 and invention name “Workpiece thermal defect detection method and system based on big data processing”. Technical Field

[0002] The present invention relates to the technical field of mechanical workpiece detection, and in particular to a workpiece thermal defect detection method based on big data processing. Background Art

[0003] Thermal defects refer to a type of defect or problem caused by the action or influence of heat during the processing, use or service of mechanical parts or workpieces. These defects usually involve changes in the structure, performance or shape of the material, and usually include cracks, fatigue, deformation and other problems. These thermal defects may have a serious impact on the performance, life and safety of mechanical parts. Therefore, during the manufacturing and use process, it is necessary to promptly detect and repair these thermal defects through appropriate detection technologies and methods to ensure the quality and reliability of the product. Thermal defect detection of mechanical workpieces refers to the process of detecting and evaluating thermal defects that may occur in mechanical parts during the processing or use process through different methods and technologies. It is an important step to ensure product quality, safety and reliability, reduce manufacturing and maintenance costs, and extend the service life of parts.

[0004] At present, there are still some deficiencies in the research on thermal defect detection of mechanical workpieces. Specifically, traditional thermal defect detection methods for mechanical workpieces can usually only detect surface defects of workpieces, and have weak recognition capabilities for internal defects. The accuracy and stability of detection equipment are affected by many factors, such as environmental changes, temperature and workpiece materials, which may lead to errors and inconsistencies in the detection results. Reliance on manual analysis makes data processing and interpretation complex and time-consuming, increasing the difficulty of operation and the risk of errors. Summary of the Invention

[0005] In response to the shortcomings of the existing technology, the present invention provides a workpiece thermal defect detection method based on big data processing, which solves the problems of traditional mechanical workpiece thermal defect detection methods having weak internal defect recognition ability, possible errors and inconsistencies in detection results, complex and time-consuming data processing and interpretation, increased operational difficulty and error risks, and poor comparability and consistency of detection results.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a workpiece thermal defect detection method based on big data processing, comprising the following steps: obtaining a workpiece surface condition feature data set, and obtaining a first deviation value for workpiece thermal defect detection based on the obtained workpiece surface condition feature data set by comparison; obtaining a workpiece material feature data set, and obtaining a second deviation value for workpiece thermal defect detection based on the obtained workpiece material feature data set by comparison; performing outer surface thermal defect detection on the workpiece, obtaining an outer surface thermal defect detection data set of the workpiece, and performing a comprehensive analysis on the outer surface thermal defect detection data set of the workpiece to obtain a feature value for outer surface thermal defect detection of the workpiece; performing internal thermal defect detection on the workpiece, obtaining an internal thermal defect detection data set of the workpiece, and performing a comprehensive analysis on the internal thermal defect detection data set of the workpiece to obtain a feature value for internal thermal defect detection of the workpiece; performing a comprehensive analysis on the outer surface thermal defect detection feature value of the workpiece, the internal thermal defect detection feature value of the workpiece, the first deviation value for workpiece thermal defect detection, and the second deviation value for workpiece thermal defect detection to obtain a data evaluation value for workpiece thermal defect detection; judging whether the thermal defect of the workpiece is qualified based on the workpiece thermal defect detection data evaluation value, and marking the qualified workpiece.

[0007] Furthermore, the workpiece surface condition feature data set specifically includes workpiece surface roughness, workpiece surface reflectivity, workpiece surface coating thickness, and workpiece surface contamination area.

[0008] Furthermore, the first deviation value for workpiece thermal defect detection is obtained by comparison based on the acquired workpiece surface condition characteristic data set. The specific analysis process is: based on the acquired workpiece surface condition characteristic data set, a comprehensive analysis is performed to obtain a workpiece surface condition characteristic value, and the workpiece surface condition characteristic value is used as an analysis basis for obtaining the first deviation value for workpiece thermal defect detection by comparison; the workpiece surface condition characteristic value is compared with the first deviation value for workpiece thermal defect detection corresponding to each workpiece surface condition characteristic value stored in the database to obtain the first deviation value for workpiece thermal defect detection corresponding to the workpiece surface condition characteristic value.

[0009] Furthermore, the workpiece material characteristic data set specifically includes workpiece density, workpiece melting point, workpiece thermal conductivity, and workpiece thermal expansion coefficient.

[0010] Furthermore, the second deviation value for workpiece thermal defect detection is obtained by comparison based on the acquired workpiece material characteristic data set. The specific analysis process is: based on the acquired workpiece material characteristic data set, a comprehensive analysis is performed to obtain a workpiece material characteristic value, and the workpiece material characteristic value is used as an analysis basis for obtaining the second deviation value for workpiece thermal defect detection by comparison; the workpiece material characteristic value is compared with the second deviation value for workpiece thermal defect detection corresponding to each workpiece material characteristic value stored in the database to obtain the second deviation value for workpiece thermal defect detection corresponding to the workpiece material characteristic value.

[0011] Furthermore, the workpiece outer surface thermal defect detection data set specifically includes the workpiece surface average temperature, the number of workpiece surface cracks, and the workpiece surface oxide layer thickness; the workpiece outer surface thermal defect detection characteristic value is calculated as follows: ; Where: is the average surface temperature of the workpiece, is the reference value of the average surface temperature of the workpiece stored in the database, is the number of cracks on the workpiece surface, is the thickness of the oxide layer on the workpiece surface, is the weight factor of the average surface temperature of the workpiece set in the database, is the weight factor of the number of surface cracks on the workpiece set in the database, is the weight factor of the workpiece surface oxide layer thickness set in the database, It is the characteristic value of thermal defect detection on the outer surface of the workpiece.

[0012] Furthermore, the workpiece internal thermal defect detection data set specifically includes the workpiece internal pore density, the number of workpiece internal defects, and the workpiece internal residual stress.

[0013] Furthermore, the workpiece thermal defect detection data evaluation value is calculated as follows: ; Where: is the characteristic value of thermal defect detection on the outer surface of the workpiece, is the characteristic value for detecting internal thermal defects in the workpiece, is the weight factor of the workpiece surface characteristic value set in the database, is the weight factor of the workpiece material characteristic value set in the database, is the workpiece thermal defect detection data evaluation value, is the first deviation value for workpiece thermal defect detection, The second deviation value for workpiece thermal defect detection, is a natural constant.

[0014] Furthermore, the method of judging whether the thermal defects of the workpiece are qualified based on the evaluation value of the workpiece thermal defect detection data and marking the qualified workpiece is as follows: comparing the evaluation value of the workpiece thermal defect detection data with the workpiece thermal defect detection qualified limit value stored in the database; if the evaluation value of the workpiece thermal defect detection data is higher than the workpiece thermal defect detection qualified limit value, the thermal defect detection of the workpiece is unqualified; if the evaluation value of the workpiece thermal defect detection data is lower than or equal to the workpiece thermal defect detection qualified limit value, the thermal defect detection of the workpiece is qualified, and the workpiece that passes the thermal defect detection is marked as thermal defect qualified.

[0015] The workpiece thermal defect detection system based on big data processing includes a workpiece surface condition feature data acquisition module, a workpiece material feature data acquisition module, a workpiece outer surface thermal defect data acquisition module, a workpiece internal thermal defect data acquisition module, a workpiece thermal defect detection data evaluation value acquisition module and a workpiece thermal defect judgment module, wherein: the workpiece surface condition feature data acquisition module is used to acquire a workpiece surface condition feature data set, and obtain a first deviation value for workpiece thermal defect detection based on the acquired workpiece surface condition feature data set by comparison; the workpiece material feature data acquisition module is used to acquire a workpiece material feature data set, and obtain a second deviation value for workpiece thermal defect detection based on the acquired workpiece material feature data set by comparison; the workpiece outer surface thermal defect data acquisition module is used to perform outer surface thermal defect detection on the workpiece and obtain the outer surface thermal defect data of the workpiece. Thermal defect detection data set, which comprehensively analyzes the workpiece outer surface thermal defect detection data set to obtain the workpiece outer surface thermal defect detection characteristic value; workpiece internal thermal defect data acquisition module, which is used to perform internal thermal defect detection on the workpiece, obtain the workpiece internal thermal defect detection data set, and comprehensively analyze the workpiece internal thermal defect detection data set to obtain the workpiece internal thermal defect detection characteristic value; workpiece thermal defect detection data evaluation value acquisition module, which is used to comprehensively analyze the workpiece outer surface thermal defect detection characteristic value, the workpiece internal thermal defect detection characteristic value, the workpiece thermal defect detection first deviation value and the workpiece thermal defect detection second deviation value to obtain the workpiece thermal defect detection data evaluation value; workpiece thermal defect judgment module, which is used to judge whether the workpiece thermal defect is qualified based on the workpiece thermal defect detection data evaluation value, and mark the qualified workpiece.

[0016] The present invention has the following beneficial effects: (1) This workpiece thermal defect detection method based on big data processing integrates the data of the external surface and internal thermal defect detection characteristic values, the first and second deviation values, and conducts a comprehensive quality assessment, ensuring accurate judgment of the workpiece quality. It can identify potential quality risks at an early stage, especially before the product enters the downstream process or market, and take timely measures to prevent problems from occurring. It can flexibly adjust the detection strategy and standards according to the specific needs of different types of workpieces or different customers, reduce the waste of resources caused by the production of defective products, optimize the production process, promote environmental protection and sustainable development, improve product safety, and avoid safety accidents caused by product defects.

[0017] (2) This workpiece thermal defect detection method based on big data processing integrates multiple key factors affecting workpiece thermal defects (temperature, cracks, oxide layer) into one characteristic value, providing a comprehensive evaluation index. This can avoid the deviation that may be caused by a single parameter, making the evaluation of workpiece thermal defects more comprehensive and accurate. The characteristic value can effectively reflect the status of thermal defects on the workpiece surface, including the influence of cracks, oxide layer, and potential problems caused by temperature changes, which helps to timely discover and diagnose thermal defects and prevent defects from expanding or causing more serious problems.

[0018] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 A flow chart of the workpiece thermal defect detection method based on big data processing of the present invention; Figure 2 This is a schematic diagram of the connection modules of the workpiece thermal defect detection system based on big data processing of the present invention. DETAILED DESCRIPTION

[0020] The embodiment of the present application provides a workpiece thermal defect detection method based on big data processing, which solves the problems of traditional mechanical workpiece thermal defect detection methods having weak internal defect recognition capabilities, possible errors and inconsistencies in detection results, complex and time-consuming data processing and interpretation, increased operational difficulty and error risks, and poor comparability and consistency of detection results.

[0021] See also Figure 1 An embodiment of the present invention provides a technical solution: a workpiece thermal defect detection method based on big data processing, comprising: obtaining a workpiece surface condition feature data set, and obtaining a first deviation value for workpiece thermal defect detection based on the obtained workpiece surface condition feature data set by comparison.

[0022] Specifically, the workpiece surface condition feature data set includes workpiece surface roughness, workpiece surface reflectivity, workpiece surface coating thickness, and workpiece surface contamination area.

[0023] In this embodiment, the surface roughness of the workpiece is the microscopic unevenness of the workpiece surface, which is usually obtained by non-contact measurement of the subtle undulations on the workpiece surface using an optical interference microscope and the principle of light interference. It is a key factor affecting friction, wear, lubrication and contact performance. By controlling the roughness of the workpiece surface, the service life of the workpiece can be extended and maintenance costs can be reduced. The surface reflectivity of the workpiece represents the ability of the workpiece surface to reflect light. It is an important indicator for evaluating the surface finish and cleanliness of the workpiece, affecting the performance of optical components. The reflectivity of light of different wavelengths is usually measured by a spectral reflectometer. It is often used to evaluate the optical properties of materials. By controlling and optimizing the optical properties of optical devices, high-quality imaging or optical performance is ensured. The thickness of the workpiece surface coating determines The protective properties of a given coating, such as corrosion resistance, wear resistance, and insulation, affect the mechanical properties and durability of the coating. This is usually detected using an X-ray fluorescence thickness gauge. By detecting X-ray fluorescence, the coating thickness can be accurately measured. This is applicable to a variety of coating materials, ensuring that the coating has sufficient thickness to provide protection while avoiding material waste. By controlling the coating thickness, the performance and service life of the product can be improved. The contaminated area on the workpiece surface affects the cleanliness of the workpiece and the effect of the surface treatment. Contaminants may affect the quality of subsequent processing such as painting and electroplating. Microscopic inspection is usually performed, using an optical microscope or an electron microscope to observe and measure the contaminated area to ensure that the surface cleanliness meets the processing or use requirements and to avoid contaminants affecting the effects of coating, bonding, and other processes.

[0024] In this embodiment, during the thermal defect detection process of the workpiece, the high roughness surface will cause the scattering of infrared radiation, making the signal received by the thermal imager or infrared thermal imager uneven, increasing the background noise, and may also cause the signal of the detection equipment to be unstable. High roughness will affect the coupling and propagation of ultrasonic waves, resulting in inaccurate data. The uneven surface may cause poor contact of the temperature sensor and produce errors. In high-precision temperature measurement, it may lead to misjudgment of local overheating or uneven cooling. Understanding the surface roughness of the workpiece helps to correct the scattering of infrared thermal imaging or ultrasonic signals caused by the rough surface and reduce measurement errors. Based on the surface roughness data, the parameters of the detection equipment (such as probe contact pressure, scanning speed, etc.) can be adjusted to improve signal stability and Detection accuracy, clarify roughness characteristics, avoid mistaking temperature changes caused by rough surfaces for internal defects. High reflectivity surfaces may reflect a large amount of infrared radiation, resulting in the inability of infrared thermal imagers to accurately measure surface temperature, which may mask potential thermal defects. Especially when it is necessary to detect subtle temperature changes, areas with different surface reflectivity may lead to inconsistent temperature measurements, thereby affecting the location and identification of thermal defects. In laser detection, high reflectivity may cause optical interference, making it difficult for the data acquisition system to capture clear signals. Understanding reflectivity helps to correct the measurement results of the thermal imager, ensure accurate temperature readings, and reduce the impact of reflected light on temperature measurement. Reflectivity data helps select appropriate optical detection equipment and wavelength range to reduce optical interference. , improve the quality of signal acquisition, the thickness of the workpiece surface coating affects heat conduction, and thick coatings may act as heat insulation, so that the surface temperature measurement of the workpiece does not reflect the true internal temperature distribution, which may cover up internal thermal defects or cause misjudgment. In the case of multi-layer coatings, the difference in thermal conductivity of different layers may lead to complex temperature gradients, making thermal imaging analysis more complicated, and different coating materials have different infrared emissivity, which affects the accuracy of infrared thermal imaging. Understanding the coating thickness is helpful for data correction during thermal defect detection to ensure the consistency of detection results. By controlling the coating thickness, it is ensured that the coating has sufficient anti-corrosion, anti-wear and other protective properties. Understanding the coating thickness helps to select a suitable detection method to avoid the coating shielding the signal of internal defects and the surface contamination of the workpiece. The contaminated area directly reflects the cleanliness of the workpiece surface and has an important impact on the quality of subsequent processing such as painting and electroplating. Pollutants such as grease, dust, etc. may absorb or scatter infrared radiation, causing the thermal imaging signal to be distorted and unable to accurately reflect the actual location and size of thermal defects. The presence of pollutants may cause local temperature anomalies, resulting in poor contact of the temperature sensor or temperature measurement errors. Especially in high-temperature or low-temperature applications, the thermal characteristics of pollutants may significantly affect the measurement results. Large-area contamination may reduce the sensitivity of the detection equipment, making small thermal defects difficult to detect. By removing surface pollutants, the absorption and scattering of infrared thermal imaging or ultrasonic signals by pollutants can be reduced, the clarity and accuracy of the detection signal can be enhanced, and the contaminated area data can be clarified.It helps to distinguish between true material defects and artifacts caused by contaminants, reducing false alarms. Contamination area data helps to assess surface cleanliness, improve the quality and uniformity of surface treatments (such as coating and electroplating), and ensure consistency of surface properties.

[0025] Specifically, based on the acquired workpiece surface condition characteristic data set, a first deviation value for workpiece thermal defect detection is obtained by comparison. The specific analysis process is: based on the acquired workpiece surface condition characteristic data set, a comprehensive analysis is performed to obtain a workpiece surface condition characteristic value, and the workpiece surface condition characteristic value is used as an analysis basis for obtaining the first deviation value for workpiece thermal defect detection by comparison; the workpiece surface condition characteristic value is compared with the first deviation value for workpiece thermal defect detection corresponding to each workpiece surface condition characteristic value stored in the database to obtain the first deviation value for workpiece thermal defect detection corresponding to the workpiece surface condition characteristic value.

[0026] In this embodiment, by obtaining parameters such as the workpiece surface roughness, surface reflectivity, surface coating thickness and surface contamination area, these data are comprehensively analyzed to calculate a workpiece surface condition characteristic value, and the calculated workpiece surface condition characteristic value is compared with the historical data stored in the database to obtain the current workpiece surface condition characteristic value minus the absolute value of the historical workpiece surface condition characteristic value stored in the database. The first deviation value of the workpiece thermal defect detection corresponding to the historical workpiece surface condition characteristic value stored in the database corresponding to the value with the smallest absolute value is the first deviation value of the workpiece thermal defect detection corresponding to the current workpiece surface condition characteristic value. The first deviation value reflects the impact of the workpiece surface characteristics on the detection process. By introducing this deviation value, the measurement error caused by these surface characteristics can be corrected to ensure the accuracy of the detection results. In the weighted and accumulated process, the first deviation value helps to compensate for the errors caused by changes in surface characteristics and avoid the accumulation of errors, thereby improving the accuracy of the subsequent overall evaluation value.

[0027] What needs to be explained is that the characteristic value of the workpiece surface condition is calculated as follows: ; Where: is the surface roughness of the workpiece, is the reflectivity of the workpiece surface, is the coating thickness on the workpiece surface, is the contaminated area of ​​the workpiece surface, is the weight factor of the workpiece surface roughness set in the database, is the weight factor of the workpiece surface reflectivity set in the database, is the weight factor of the workpiece surface coating thickness set in the database, is the weight factor of the workpiece surface contamination area set in the database, is the characteristic value of the workpiece surface condition.

[0028] What needs to be explained is that the formula integrates multiple surface feature parameters into one eigenvalue, providing a comprehensive evaluation index, avoiding the bias that may be caused by a single parameter, and more comprehensively reflecting the surface quality of the workpiece. The eigenvalue can provide a unified evaluation standard for different workpiece surface characteristics, which is convenient for quality control and comparison. Different workpieces or application scenarios may have higher requirements for certain surface features. By adjusting the weight factor, the focus can be placed on the features that have the greatest impact on the quality of the workpiece, and quality control measures can be optimized. Mathematical operations such as logarithms and square roots are used in the formula. These processing can effectively deal with the nonlinear relationship between different surface feature parameters and more accurately capture the complex interactions between the surface features of the workpiece. The use of logarithms and square roots can compress the data range and reduce the impact of extreme values ​​on the eigenvalues, thereby improving the stability and reliability of the evaluation. Monitoring and recording these surface parameters will help to control quality during the production process and ensure the surface condition of each workpiece. state is within an acceptable range, thereby stabilizing the thermal defect detection results. Understanding these parameters can help identify factors that may affect the surface quality in the production process, such as coating application, surface cleanliness, etc., thereby improving the process flow and reducing the occurrence of surface defects. The set weight factors of workpiece surface roughness, workpiece surface reflectivity, workpiece surface coating thickness, and workpiece surface contamination area are obtained from the database. Through the historical measurement of workpiece surface roughness, workpiece surface reflectivity, workpiece surface coating thickness, workpiece surface contamination area and workpiece surface condition characteristic values, a mapping set of workpiece surface roughness, workpiece surface reflectivity, workpiece surface coating thickness, workpiece surface contamination area and their corresponding weight factors is established. The current workpiece surface roughness, workpiece surface reflectivity, workpiece surface coating thickness, and workpiece surface contamination area are input into the mapping set to obtain the current workpiece surface roughness, workpiece surface reflectivity, workpiece surface coating thickness, and workpiece surface contamination area corresponding weight factors.

[0029] It needs to be explained that: usually, there is a certain correlation between these parameters, between the surface roughness of the workpiece and the surface reflectivity of the workpiece, and between the surface roughness of the workpiece and the thickness of the workpiece surface coating. The rougher the workpiece surface, the more serious the scattering of reflected light and the lower the reflectivity. Increased roughness will lead to a decrease in reflectivity, and the surface will become more "matte". The rough surface will scatter light, making the reflected light no longer concentrated. This scattering effect not only reduces the reflectivity, but also may cause difficulties in optical detection. Excessive roughness may cause uneven coating and uneven thickness. Surface roughness will affect the flow and spreading performance of the coating, resulting in local changes in coating thickness. The rough surface may cause the coating to accumulate in low-lying areas and form a thinner coating on protrusions, affecting subsequent detection. As a result, between the reflectivity of the workpiece surface and the thickness of the coating on the workpiece surface, the thickness change of the coating will affect the stability and consistency of the surface reflectivity. The coating with uneven thickness may cause local changes in the surface reflectivity, which is particularly significant in optical devices. Between the surface roughness of the workpiece and the contaminated area on the workpiece surface, the rough surface may increase the adhesion of contaminants. Higher surface roughness will provide more surface area and tiny pits. These areas are prone to accumulate contaminants such as grease, dust, etc., which are difficult to remove. Between the thickness of the coating on the workpiece surface and the contaminated area on the workpiece surface, surface contaminants before the coating is applied may affect the uniformity and adhesion of the coating, resulting in uneven coating thickness or coating defects such as bubbles, peeling, etc. The coating can provide a protective barrier to reduce the impact of contaminants on the substrate.

[0030] A workpiece material feature data set is acquired, and a second deviation value for workpiece thermal defect detection is obtained by comparison based on the acquired workpiece material feature data set.

[0031] Specifically, the workpiece material characteristic data set includes workpiece density, workpiece melting point, workpiece thermal conductivity, and workpiece thermal expansion coefficient.

[0032] In this embodiment, the density of the workpiece is the mass of the material per unit volume of the workpiece, which reflects the mass distribution characteristics of the material and affects the mechanical properties, mass and energy absorption capacity of the material. It is usually obtained through an X-ray densitometer, which uses the attenuation of X-rays when passing through the material to calculate the density of the material. The density can ensure that the material meets the quality standards required by the design and help estimate the material cost and transportation cost. The melting point of the workpiece is the temperature at which the workpiece material changes from solid to liquid, which affects the high-temperature performance of the workpiece material and the selection of processing technology. It is usually measured by a thermocouple. The thermocouple is inserted into the material and gradually heated to the temperature at which the material melts. By understanding the melting point of the workpiece material, it can help to select the appropriate welding, forging or casting process to ensure the material The stability and durability of the material in a high temperature environment. The thermal conductivity of the workpiece is the ability of the workpiece material to conduct heat, which affects the heat dissipation performance and temperature distribution of the workpiece material. It is usually obtained through laser flash analysis method. The workpiece material is heated by laser and the temperature response is measured to calculate the thermal conductivity. High thermal conductivity materials are suitable for radiators and high-power electronic components, which help to predict and control the temperature change of the material during the heating process. The thermal expansion coefficient of the workpiece is the ratio of the dimensional change of the workpiece material when the temperature changes, which affects the dimensional stability of the material in a temperature change environment. It is usually obtained by isomorphic thermomechanical analysis method. It is calculated by heating the workpiece material and measuring its length change. Choosing the right material can avoid dimensional deformation caused by temperature change.

[0033] It needs to be explained: in the process of thermal defect detection of workpiece, the density of workpiece affects the heat conduction and heat absorption performance of the material, the higher density material may affect the penetration depth of ultrasonic and X-ray detection, and the material with higher density usually has higher heat capacity, which can absorb and conduct more heat, resulting in reduced temperature gradient, leading to reduced sensitivity of thermal defect detection, density affects the propagation speed and attenuation coefficient of ultrasonic and X-ray, higher density will increase the signal attenuation of these detection methods, making it more difficult to detect internal defects, understanding the density can help distinguish the material type, locate the defects of specific material area in multi-material structure, accurate density data can optimize the frequency and power settings of ultrasonic detection, improve the sensitivity of defect detection, and help predict the thermal response characteristics of workpiece, correct the temperature error caused by density in thermal imaging detection, the melting point of workpiece determines the stability and shape retention ability of material in high temperature environment, in thermal defect detection, high melting point material may need higher detection temperature, increasing the difficulty of detection, high melting point material is not easy to appear melting defect in heat treatment process, but may form thermal cracks or other thermal defects under extremely high temperature, understanding the melting point of material helps to select appropriate thermal detection temperature, avoid material melting or deformation caused by excessive temperature, so as to accurately identify the real thermal defects, melting point data can help analyze the defect types that may be generated in the process of heat treatment and welding, such as melting or thermal stress crack caused by overheating, high thermal conductivity material can distribute heat more evenly and quickly, reducing local overheating, helping detection equipment to more accurately identify thermal defects, thermal conductivity affects the cooling and heating speed of workpiece in processing or use, which is particularly important for thermal imaging detection, high thermal conductivity helps to distribute heat evenly and quickly, so that the internal thermal defects can be more clearly displayed in thermal imaging detection, understanding the thermal conductivity of material can help control the cooling and heating rate of workpiece, avoid thermal stress and crack caused by too fast or too slow heat change, accurate thermal conductivity data helps to correct the thermal conduction effect in thermal imaging detection, improves the detection ability of small or deep thermal defects, thermal expansion coefficient determines the size change of material when temperature changes, material with high thermal expansion coefficient may deform greatly in environment with large temperature fluctuation, leading to thermal stress concentration and potential thermal cracks, in composite material or multi-material system, the difference of thermal expansion coefficient of different materials may cause stress concentration at the interface and increase the risk of thermal defect formation, understanding the thermal expansion coefficient of material helps to predict and analyze the thermal stress concentration area caused by temperature change, which is the potential occurrence point of crack or other defects, in multi-material workpiece, the difference of thermal expansion coefficient may cause stress concentration and delamination at the interface, obtaining thermal expansion coefficient data can help identify and analyze these interface defects.

[0034] Specifically, based on the acquired workpiece material characteristic data set, a second deviation value for workpiece thermal defect detection is obtained by comparison. The specific analysis process is: based on the acquired workpiece material characteristic data set, a comprehensive analysis is performed to obtain a workpiece material characteristic value, and the workpiece material characteristic value is used as an analysis basis for obtaining the second deviation value for workpiece thermal defect detection by comparison; the workpiece material characteristic value is compared with the second deviation value for workpiece thermal defect detection corresponding to each workpiece material characteristic value stored in the database to obtain the second deviation value for workpiece thermal defect detection corresponding to the workpiece material characteristic value.

[0035] In this embodiment, by obtaining the material characteristic data of the workpiece (such as density, melting point, thermal conductivity, thermal expansion coefficient) and calculating the comprehensive material characteristic value, and comparing it with the historical data stored in the database, the second deviation value of the workpiece thermal defect detection is obtained. The second deviation value provides key information about the material characteristics of the workpiece, which helps to identify potential problems in the production process (such as uneven heat treatment, improper material ratio, etc.), guide process improvement, and improve product consistency and quality. By recording and analyzing the second deviation value data, historical data analysis and trend prediction can be carried out to provide data support for long-term quality monitoring and improvement. The density, melting point, thermal conductivity and The four parameters of thermal expansion coefficient are closely related. Density is often related to the structure and composition of the material, affecting its thermal conductivity and thermal expansion coefficient. High-density materials usually have higher thermal conductivity and can conduct heat more effectively. High-melting-point materials usually exhibit lower thermal expansion coefficients in high-temperature environments, reducing the concentration of thermal stress. Thermal conductivity and thermal expansion coefficient jointly affect the behavior of materials under temperature changes. Materials with high thermal conductivity can quickly and evenly distribute heat, reduce local thermal expansion unevenness, and thus reduce thermal stress. These parameters jointly determine the thermal response characteristics of the material, which is crucial for understanding and controlling the formation of thermal defects in workpieces.

[0036] What needs to be explained is that the characteristic value of the workpiece material is calculated as follows: ; Where: is the workpiece density, is the melting point of the workpiece, is the thermal conductivity of the workpiece, is the thermal expansion coefficient of the workpiece, is the weight factor of the workpiece density set in the database, is the weight factor of the workpiece melting point set in the database, is the weight factor of the thermal conductivity of the workpiece set in the database, is the weight factor of the workpiece thermal expansion coefficient set in the database, is the characteristic value of the workpiece material.

[0037] It needs to be explained: by integrating the density, melting point, thermal conductivity and thermal expansion coefficient of the workpiece, and by weighting with the weight factor, the workpiece material characteristic value is obtained, which can comprehensively reflect the overall thermal physical properties of the workpiece material, and provide an intuitive and unified standard for quality assessment and comparison. Through the composition analysis of the material characteristic value, the material properties that mainly affect the workpiece thermal defect detection can be identified, which is of great significance for the key control and optimization in the production and detection process. The characteristic value can also help optimize the parameter setting of thermal defect detection, ensure the accuracy and reliability of detection, and use historical data for comparison to realize trend analysis and prediction, promote data-driven quality control and continuous improvement, and thus improve the consistency and performance of the workpiece. The weight factors of the workpiece density, workpiece melting point, workpiece thermal conductivity and workpiece thermal expansion coefficient are obtained from the database. Through the historical measurement of the workpiece density, workpiece melting point, workpiece thermal conductivity and workpiece thermal expansion coefficient, and the workpiece material characteristic value, a mapping set of the workpiece density, workpiece melting point, workpiece thermal conductivity, workpiece thermal expansion coefficient and their corresponding weight factors is established. The current workpiece density, workpiece melting point, workpiece thermal conductivity and workpiece thermal expansion coefficient are input into the mapping set to obtain the weight factors corresponding to the current workpiece density, workpiece melting point, workpiece thermal conductivity and workpiece thermal expansion coefficient.

[0038] The workpiece is subjected to external surface thermal defect detection to obtain a workpiece external surface thermal defect detection data set. The workpiece external surface thermal defect detection data set is comprehensively analyzed to obtain a workpiece external surface thermal defect detection characteristic value.

[0039] Specifically, the workpiece external surface thermal defect detection data set specifically includes the workpiece surface average temperature, the workpiece surface crack number and the workpiece surface oxide layer thickness. The calculation formula of the workpiece external surface thermal defect detection characteristic value is as follows: In the formula: is the workpiece surface average temperature, is the reference value of the workpiece surface average temperature stored in the database, is the workpiece surface crack number, is the workpiece surface oxide layer thickness, is the weight factor of the workpiece surface average temperature set in the database, is the weight factor of the workpiece surface crack number set in the database, is the weight factor of the workpiece surface oxide layer thickness set in the database, is the workpiece external surface thermal defect detection characteristic value.

[0040] ​In this embodiment, the average surface temperature of the workpiece reflects the thermal state of the workpiece during heat treatment or use, and is an important indicator for evaluating thermal stress, thermal fatigue and potential thermal defects. The temperature distribution on the workpiece surface is usually measured by an infrared thermal imager, and the average temperature is calculated. The number of cracks on the workpiece surface is an important parameter for evaluating the structural integrity of the workpiece, which directly affects the mechanical properties and durability of the workpiece. A large number of cracks will lead to fatigue crack expansion, material failure or increased corrosion. It is usually detected by ultrasonic testing, eddy current testing or X-ray testing to accurately locate and count cracks. The thickness of the oxide layer on the workpiece surface reflects the degree of surface oxidation of the workpiece during heat treatment or use, and is a key factor affecting the corrosion resistance and mechanical properties of the material. An excessively thick or uneven oxide layer may affect the electrical conductivity, thermal conductivity and optical properties of the workpiece. The coating thickness gauge measures the thickness of the oxide layer on the metal surface. There is a positive correlation between the average surface temperature of the workpiece and the number of cracks on the workpiece surface, the average surface temperature of the workpiece and the thickness of the oxide layer on the workpiece surface, and the number of cracks on the workpiece surface and the thickness of the oxide layer on the workpiece surface. Changes in the average surface temperature will cause thermal expansion and contraction of the material, especially when the average surface temperature is uneven, thermal stress will be generated. This thermal stress will trigger or aggravate the formation and expansion of surface cracks. An increase in the average surface temperature will usually accelerate the oxidation reaction, resulting in an increase in the thickness of the oxide layer. Workpieces with higher average surface temperatures are more likely to form thicker oxide layers, especially when exposed to air or other oxidizing environments. Surface cracks can become channels for oxidation reactions, making it easier for oxidizing gases or liquids to penetrate into the material, accelerating the oxidation process around the cracks, and increasing the thickness of the local oxide layer.

[0041] It needs to be explained that: during the thermal defect detection process of the workpiece, uneven surface temperature distribution may lead to thermal gradients inside the workpiece, generate thermal stress, and induce cracks or other thermal defects. Excessively high or low surface temperature may mask actual defects or cause misjudgment, affecting the accuracy of the detection results. By monitoring the average surface temperature, the heat treatment process can be optimized, overheating or overcooling can be avoided, and thermal defects can be reduced. Accurate temperature measurement helps to correct measurement errors caused by temperature and enhance the accuracy and reliability of thermal imaging detection. Cracks may affect the propagation of ultrasonic, X-ray or thermal imaging signals, resulting in misjudgment or missed detection results, as well as affect thermal radiation and reflection characteristics, interfering with the temperature distribution analysis of thermal imaging detection. Detecting cracks helps to repair them in time, prevent crack expansion, and ensure the safety and reliability of the workpiece. Crack counting can help evaluate the fatigue life of the workpiece and guide preventive maintenance and service life prediction. The oxide layer will affect the thermal conductivity, resulting in signal attenuation or distortion of thermal imaging detection. In electromagnetic detection, it will also affect the electrical conductivity of the material, resulting in measurement errors. Monitoring the thickness of the oxide layer can prevent corrosion, extend the service life of the workpiece, and ensure that the oxide layer is within a reasonable range, which helps to maintain the mechanical properties and surface characteristics of the material.

[0042] It should be explained that: integrating multiple key factors affecting workpiece thermal defects (temperature, cracks, oxide layer) into one eigenvalue provides a comprehensive evaluation index, which can avoid the deviation that may be caused by a single parameter and make the evaluation of workpiece thermal defects more comprehensive and accurate. The eigenvalue can effectively reflect the status of thermal defects on the workpiece surface, including the influence of cracks, oxide layer, and potential problems caused by temperature changes, which helps to timely discover and diagnose thermal defects, prevent defects from expanding or causing more serious problems. The set weight factors of the average surface temperature of the workpiece, the number of cracks on the workpiece surface, and the thickness of the oxide layer on the workpiece surface are obtained from the database. Through the historical measurement of the average surface temperature of the workpiece, the number of cracks on the workpiece surface, the thickness of the oxide layer on the workpiece surface and the thermal defect detection eigenvalues ​​of the workpiece outer surface, a mapping set of the average surface temperature of the workpiece, the number of cracks on the workpiece surface, the thickness of the oxide layer on the workpiece surface and their corresponding weight factors is established. The current average surface temperature of the workpiece, the number of cracks on the workpiece surface, and the thickness of the oxide layer on the workpiece surface are input into the mapping set to obtain the weight factors corresponding to the current average surface temperature of the workpiece, the number of cracks on the workpiece surface, and the thickness of the oxide layer on the workpiece surface.

[0043] Perform internal thermal defect detection on the workpiece, obtain a workpiece internal thermal defect detection data set, perform comprehensive analysis on the workpiece internal thermal defect detection data set, and obtain a workpiece internal thermal defect detection characteristic value.

[0044] Specifically, the workpiece internal thermal defect detection data set includes the workpiece internal pore density, the number of workpiece internal defects, and the workpiece internal residual stress.

[0045] In this embodiment, the internal pore density of the workpiece reflects the void ratio inside the material and is an important indicator for evaluating the internal structural integrity of the material. High pore density usually means reduced strength and toughness of the material, which may affect the mechanical properties and durability of the workpiece. It is usually detected by ultrasound, using the reflection and transmission characteristics of ultrasound to detect the existence and density of internal pores. The number of internal defects in the workpiece includes cracks, inclusions, shrinkage holes, etc., which are key factors directly affecting the structural integrity and reliability of the workpiece. The presence of defects will weaken the bearing capacity and fatigue life of the material. It is usually detected by ultrasonic testing, magnetic particle testing, X-ray testing and other technologies to accurately locate and count internal defects. The residual stress inside the workpiece is the stress that is not fully released during the manufacturing or processing of the material. It is an important factor affecting the dimensional stability and structural integrity of the workpiece, which will cause the workpiece to deform or crack during service. X-ray diffraction technology is usually used to measure the lattice strain of the material and calculate the residual stress.

[0046] It should be noted that: during the thermal defect detection process of the workpiece, the presence of pores will change the thermal conductivity characteristics of the material, resulting in local thermal stress concentration, increasing the risk of thermal defects, and also affecting the signal strength and resolution of thermal imaging or ultrasonic detection, affecting the sensitivity and accuracy of detection. Accurately measuring the internal pore density of the workpiece can help evaluate the strength and toughness of the material, prevent material failure due to internal defects, and help optimize casting, welding and other processes to reduce the occurrence of pore defects. Internal defects of the workpiece will affect the propagation of ultrasonic, X-ray or thermal imaging signals, resulting in misjudgment or missed detection of the detection results. The defective area may become a thermal stress concentration point, increasing crack expansion. The risk of crack growth or other thermal defects. Early detection of internal defects helps to repair them in time, prevent defects from expanding, and ensure the safety and reliability of the workpiece. The defect count data can be used to predict the fatigue life of the workpiece and guide preventive maintenance. The superposition of residual stress inside the workpiece and external thermal stress will lead to stress concentration and thermal defects such as crack growth. Residual stress may cause dimensional changes in the workpiece, affecting the assembly and function of precision components. Understanding the distribution of residual stress will help to take stress relief measures, such as heat treatment, to avoid adverse deformation or cracking of the workpiece during service, and can help optimize the processing technology, reduce stress introduction during processing, and improve product quality and precision.

[0047] It should be noted that: Under normal circumstances, there is a positive correlation between the internal pore density of the workpiece and the number of internal defects of the workpiece, between the internal pore density of the workpiece and the internal residual stress of the workpiece, and between the number of internal defects of the workpiece and the internal residual stress of the workpiece. The internal pores and internal defects of the workpiece may be formed simultaneously during the manufacturing or processing of the material. High pore density usually means that there are more unstable factors in the manufacturing process, such as uneven cooling rate or poor material fluidity. The material strength in the pore area is usually low, which can easily become the starting point for crack initiation. Therefore, areas with high pore density are often accompanied by more cracks and other defects. The material discontinuity in areas with high pore density increases. These areas are prone to stress concentration and residual stress during cooling or other processing. Internal defects (such as cracks and inclusions) are stress concentration points. Under the action of external loads or thermal stress, these stress concentration areas are prone to further generate residual stress or aggravate the existing stress state.

[0048] It should be noted that the calculation formula for the characteristic value of internal thermal defect detection of the workpiece is: ; Where: is the pore density inside the workpiece, is the number of internal defects in the workpiece, is the residual stress inside the workpiece, is the weight factor of the internal pore density of the workpiece set in the database, is the weight factor of the number of internal defects of the workpiece set in the database, is the weight factor of the internal residual stress of the workpiece set in the database, is the characteristic value for detecting internal thermal defects in the workpiece, is a natural constant.

[0049] It should be explained that: by comprehensively analyzing the internal pore density, number of defects and residual stress, the characteristic value can predict potential thermal defects at an early stage, help implement preventive maintenance, reduce downtime or rework caused by defects, and reduce product scrap and rework caused by defects by improving the accuracy and timeliness of detection, thereby reducing production costs. At the same time, preventive maintenance and early repair can extend the service life of equipment and workpieces, improve overall economic benefits, and accurate thermal defect detection can significantly improve product quality and safety, especially in key application areas such as aerospace, automobiles and medical equipment. The set weight factors of the workpiece internal pore density, workpiece internal defect number, and workpiece internal residual stress are obtained from the database. Through the historically measured workpiece internal pore density, workpiece internal defect number, workpiece internal residual stress and workpiece internal thermal defect detection characteristic values, a mapping set of the workpiece internal pore density, workpiece internal defect number, workpiece internal residual stress and their corresponding weight factors is established. The current workpiece internal pore density, workpiece internal defect number, and workpiece internal residual stress are input into the mapping set to obtain the current workpiece internal pore density, workpiece internal defect number, and workpiece internal residual stress corresponding weight factors.

[0050] The workpiece thermal defect detection data evaluation value is obtained by comprehensively analyzing the workpiece outer surface thermal defect detection characteristic value, the workpiece internal thermal defect detection characteristic value, the workpiece thermal defect detection first deviation value and the workpiece thermal defect detection second deviation value.

[0051] Specifically, the workpiece thermal defect detection data evaluation value is calculated as follows: ; Where: is the characteristic value for detecting thermal defects on the outer surface of the workpiece, is the characteristic value for detecting internal thermal defects in the workpiece, is the weight factor of the workpiece surface characteristic value set in the database, is the weight factor of the workpiece material characteristic value set in the database, is the workpiece thermal defect detection data evaluation value, is the first deviation value for workpiece thermal defect detection, The second deviation value for workpiece thermal defect detection, is a natural constant.

[0052] In this implementation scheme, the workpiece thermal defect detection data evaluation value integrates the thermal defect detection data of the workpiece outer surface and interior into a comprehensive index, covering the surface and internal characteristics, providing a comprehensive evaluation of the workpiece thermal defects, and helping to more accurately reflect the overall quality status of the workpiece. Incorporating the first deviation value of the workpiece thermal defect detection and the second deviation value of the workpiece thermal defect detection into the calculation of the evaluation value can effectively calibrate and correct the systematic errors in the detection data, ensuring the accuracy and reliability of the final evaluation results. By integrating the characteristic values ​​of the outer surface and the interior and combining the deviation correction, the workpiece thermal defect detection data evaluation value reduces the deviation and misjudgment that may be caused by a single detection data, improves the overall accuracy of thermal defect detection, can identify the parameters that have the greatest impact on the final quality, and helps to focus on controlling key process parameters. The production process is optimized to facilitate the training of new operators, making it easier for them to understand and master the key parameters and evaluation methods of thermal defect detection and improve the overall operation level. The weight factors of the set workpiece outer surface thermal defect detection characteristic values ​​and workpiece internal thermal defect detection characteristic values ​​are obtained from the database. Through the historically measured workpiece outer surface thermal defect detection characteristic values, workpiece internal thermal defect detection characteristic values ​​and workpiece thermal defect detection data evaluation values, a mapping set of the workpiece outer surface thermal defect detection characteristic values, workpiece internal thermal defect detection characteristic values ​​and their corresponding weight factors is established. The current workpiece outer surface thermal defect detection characteristic values ​​and workpiece internal thermal defect detection characteristic values ​​are input into the mapping set to obtain the weight factors corresponding to the current workpiece outer surface thermal defect detection characteristic values ​​and workpiece internal thermal defect detection characteristic values.

[0053] Based on the evaluation value of the workpiece thermal defect detection data, it is judged whether the thermal defect of the workpiece is qualified, and the qualified workpiece is marked.

[0054] Specifically, whether the thermal defects of the workpiece are qualified is judged based on the evaluation value of the workpiece thermal defect detection data, and the qualified workpiece is marked. The specific analysis process is: compare the evaluation value of the workpiece thermal defect detection data with the workpiece thermal defect detection qualified limit value stored in the database; if the evaluation value of the workpiece thermal defect detection data is higher than the workpiece thermal defect detection qualified limit value, the thermal defect detection of the workpiece is unqualified; if the evaluation value of the workpiece thermal defect detection data is lower than or equal to the workpiece thermal defect detection qualified limit value, the thermal defect detection of the workpiece is qualified, and the workpiece that passes the thermal defect detection is marked as thermal defect qualified.

[0055] In this embodiment, by setting a clear workpiece thermal defect detection qualified limit value, a standardized evaluation standard is provided, making the quality judgment process objective and consistent, avoiding subjective judgment bias, ensuring that the quality detection of all workpieces is based on the same standard. By comparing the evaluation value with the qualified limit value, the workpieces can be quickly classified as qualified or unqualified, improving the efficiency of the detection process. The automatic judgment and marking system can handle a large number of workpieces, reducing the time and human resources consumed by manual detection. This process can accurately identify thermal defects in workpieces, ensuring that unqualified workpieces are excluded from the production line at an early stage, preventing them from entering the market or affecting subsequent production processes. Strict quality control helps improve the overall reliability and quality of products. By quickly identifying and processing unqualified workpieces, more resources can be focused on the subsequent processing of qualified workpieces and the preferential processing of qualified workpieces, optimizing the allocation of production resources and improving production efficiency.

[0056] The workpiece thermal defect detection system based on big data processing, as shown in Figure 2 The workpiece thermal defect detection system based on big data processing, as shown in

[0057] In summary, the present application has at least the following effects: the workpiece thermal defect detection method based on big data processing conducts a comprehensive quality assessment by integrating the data of the external surface and internal thermal defect detection characteristic values, the first and second deviation values, thereby ensuring accurate judgment of the workpiece quality, and can identify potential quality risks at an early stage, especially before the product enters the downstream process or market, and take timely measures to prevent problems from occurring. It can flexibly adjust the detection strategies and standards according to the specific needs of different types of workpieces or different customers, reduce the waste of resources caused by the production of defective products, optimize the production process, promote environmental protection and sustainable development, improve product safety, and avoid safety accidents caused by product defects.

[0058] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0059] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0060] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0061] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0062] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0063] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A workpiece thermal defect detection method based on big data processing, characterized in that: The following steps are involved: Acquire a workpiece surface condition feature data set, and compare and obtain a first deviation value for workpiece thermal defect detection based on the acquired workpiece surface condition feature data set, wherein the workpiece surface condition feature data set specifically includes workpiece surface roughness, workpiece surface reflectivity, workpiece surface coating thickness, and workpiece surface contamination area; The data is comprehensively analyzed to calculate the workpiece surface condition characteristic value, and the calculated workpiece surface condition characteristic value is compared with the historical data stored in the database to obtain the current workpiece surface condition characteristic value minus the absolute value of the historical workpiece surface condition characteristic value stored in the database. The first deviation value of the workpiece thermal defect detection corresponding to the historical workpiece surface condition characteristic value stored in the database corresponding to the value with the smallest absolute value is the first deviation value of the workpiece thermal defect detection corresponding to the current workpiece surface condition characteristic value; Acquire a workpiece material feature data set, and compare and obtain a second deviation value for workpiece thermal defect detection based on the acquired workpiece material feature data set, wherein the workpiece material feature data set specifically includes workpiece density, workpiece melting point, workpiece thermal conductivity, and workpiece thermal expansion coefficient; The workpiece is inspected for outer surface thermal defects to obtain a data set of workpiece outer surface thermal defect detection, including the average surface temperature of the workpiece, the number of surface cracks, and the thickness of the oxide layer on the workpiece surface. A comprehensive analysis is performed on the data set of workpiece outer surface thermal defect detection to obtain the workpiece outer surface thermal defect detection feature value, which is calculated as follows: ; Where: is the average surface temperature of the workpiece, is the reference value of the average surface temperature of the workpiece stored in the database, is the number of cracks on the workpiece surface, is the thickness of the oxide layer on the workpiece surface, is the weight factor of the average surface temperature of the workpiece set in the database, is the weight factor of the number of surface cracks on the workpiece set in the database, is the weight factor of the workpiece surface oxide layer thickness set in the database, Characteristic value for detecting thermal defects on the outer surface of the workpiece; Perform internal thermal defect detection on the workpiece to obtain a workpiece internal thermal defect detection data set, specifically including the workpiece internal pore density, the number of internal defects in the workpiece, and the workpiece internal residual stress. Perform a comprehensive analysis on the workpiece internal thermal defect detection data set to obtain the workpiece internal thermal defect detection feature value; The workpiece thermal defect detection data evaluation value is obtained by comprehensively analyzing the workpiece outer surface thermal defect detection characteristic value, the workpiece internal thermal defect detection characteristic value, the workpiece thermal defect detection first deviation value, and the workpiece thermal defect detection second deviation value. The calculation formula is: ; Where: is the characteristic value of thermal defect detection on the outer surface of the workpiece, is the characteristic value for detecting internal thermal defects in the workpiece, is the weight factor of the workpiece surface characteristic value set in the database, is the weight factor of the workpiece material characteristic value set in the database, is the workpiece thermal defect detection data evaluation value, is the first deviation value for workpiece thermal defect detection, The second deviation value for workpiece thermal defect detection, is a natural constant; Based on the evaluation value of the workpiece thermal defect detection data, it is judged whether the thermal defect of the workpiece is qualified, and the qualified workpiece is marked.

2. The workpiece thermal defect detection method based on big data processing according to claim 1, characterized in that: The first deviation value of workpiece thermal defect detection is obtained by comparing the acquired workpiece surface condition feature data set. The specific analysis process is as follows: Based on the acquired workpiece surface condition feature data set, a comprehensive analysis is performed to obtain a workpiece surface condition feature value, which is used as an analysis basis for obtaining a first deviation value for workpiece thermal defect detection by comparison; The workpiece surface condition characteristic value is compared with the first deviation value for workpiece thermal defect detection corresponding to each workpiece surface condition characteristic value stored in the database to obtain the first deviation value for workpiece thermal defect detection corresponding to the workpiece surface condition characteristic value.

3. The workpiece thermal defect detection method based on big data processing according to claim 1, characterized in that: The second deviation value for workpiece thermal defect detection is obtained by comparison based on the acquired workpiece material feature data set. The specific analysis process is as follows: Based on the acquired workpiece material characteristic data set, a comprehensive analysis is performed to obtain a workpiece material characteristic value, which is used as an analysis basis for obtaining a second deviation value for workpiece thermal defect detection by comparison; The workpiece material characteristic value is compared with the second deviation value for workpiece thermal defect detection corresponding to each workpiece material characteristic value stored in the database to obtain the second deviation value for workpiece thermal defect detection corresponding to the workpiece material characteristic value.

4. The workpiece thermal defect detection method based on big data processing according to claim 1, characterized in that: The evaluation value of the workpiece thermal defect detection data is used to determine whether the workpiece thermal defect is qualified, and the qualified workpiece is marked. The specific analysis process is as follows: Comparing the workpiece thermal defect detection data evaluation value with the workpiece thermal defect detection acceptance limit value stored in the database; If the workpiece thermal defect detection data evaluation value is higher than the workpiece thermal defect detection qualified threshold value, the workpiece thermal defect detection fails; If the evaluation value of the workpiece thermal defect detection data is lower than or equal to the workpiece thermal defect detection qualified limit value, the workpiece thermal defect detection is qualified, and the workpiece that passes the thermal defect detection is marked as thermal defect qualified.

Images