Aluminum Alloy Casting Defect Prediction Method and Equipment

Abstract

This application is applicable to the field of aluminum alloy detection technology, and particularly relates to a method and equipment for predicting aluminum alloy casting defects. The method includes: obtaining a set of casting process parameters for a target production line and selecting process parameter combinations with defect risks; determining a second defect feature set from a first defect feature set according to a pre-determined prediction parameter threshold, and further refined screening of the process parameter combinations in the first defect feature set that exceed the prediction parameter threshold; performing melt state analysis on the second defect feature set to obtain a defect marking parameter group for the target production line, dynamically determining the formation of defects in the second defect feature set, and revealing the defect formation and dominant mechanism; determining a defect prediction result based on the defect marking parameter group and the second defect feature set, reflecting whether the process parameter combination will cause casting defects, and dynamically achieving accurate selection before production and defect prediction during the production process, improving the defect prediction accuracy and production line adaptability.

Description

Technical Field

[0001] This application belongs to the technical field of aluminum alloy detection, and particularly relates to a method and equipment for predicting aluminum alloy casting defects. Background Art

[0002] Aluminum alloy casting is a manufacturing process in which molten aluminum alloy is poured into a mold and cooled and solidified. It is widely used in fields such as automobiles, aerospace, and electronics. Its core advantages are that aluminum alloy is lightweight, corrosion-resistant, has good thermal conductivity, and is easy to process.

[0003] In the prior art, the prediction of aluminum alloy casting defects mainly relies on traditional manual detection methods and empirical models. Re-calibration is required for adapting to the process characteristics of different production lines, and prediction deviations and missed judgments are likely to occur under conditions of multi-physical field coupling or process parameter fluctuations. There is a lack of multi-dimensional dynamic analysis tools, resulting in limited defect prediction accuracy and poor production line adaptability. Summary of the Invention

[0004] The embodiments of this application provide a method and equipment for predicting aluminum alloy casting defects, which can solve the problems of limited defect prediction accuracy and poor production line adaptability due to the lack of multi-dimensional dynamic analysis tools in the process of predicting aluminum alloy casting defects.

[0005] In a first aspect, the embodiments of this application provide a method for predicting aluminum alloy casting defects, including:

[0006] Obtain the casting process parameter set of the target production line, and perform defect feature extraction on the casting process parameter set to determine the first defect feature set; wherein, the first defect feature set includes the process parameter combinations with defect risks during the casting process;

[0007] Determine the second defect feature set from the first defect feature set according to the pre-determined prediction parameter threshold; wherein, the second defect feature set includes the process parameter combinations in the first defect feature set that exceed the prediction parameter threshold;

[0008] Perform melt state analysis on the second defect feature set to obtain the defect marking parameter group of the target production line; wherein the defect marking parameter group is used to indicate the formation of defects in the second defect feature set;

[0009] Determine the defect prediction result according to the defect marking parameter group and the second defect feature set; wherein, the defect prediction result is used to reflect whether the process parameter combination will cause casting defects.

[0010] The above technical solutions in the embodiments of this application have at least the following technical effects:

[0011] The aluminum alloy casting defect prediction method provided by the embodiments of the present application selects process parameter combinations with defect risks by obtaining the casting process parameter set of the target production line. According to the pre-determined prediction parameter threshold, the second defect feature set is determined from the first defect feature set, and the process parameter combinations in the first defect feature set that exceed the prediction parameter threshold are further refined and screened. The melt state of the second defect feature set is analyzed to obtain the defect marking parameter group of the target production line, and the formation of defects in the second defect feature set is dynamically determined to reveal the defect formation and the dominant mechanism. According to the defect marking parameter group and the second defect feature set, the defect prediction result is determined to reflect whether the process parameter combination will cause casting defects, and accurate selection before production and defect prediction during the production process are dynamically realized, improving the defect prediction accuracy and the adaptability of the production line.

[0012] In a second aspect, the embodiments of the present application provide an aluminum alloy casting defect prediction system, including:

[0013] An acquisition unit, configured to acquire the casting process parameter set of the target production line, and perform defect feature extraction on the casting process parameter set to determine a first defect feature set; wherein, the first defect feature set includes process parameter combinations with defect risks during the casting process;

[0014] A determination unit, configured to determine a second defect feature set from the first defect feature set according to the pre-determined prediction parameter threshold; wherein, the second defect feature set includes the process parameter combinations in the first defect feature set that exceed the prediction parameter threshold;

[0015] An analysis unit, configured to perform melt state analysis on the second defect feature set to obtain the defect marking parameter group of the target production line; wherein the defect marking parameter group is used to indicate the formation of defects in the second defect feature set;

[0016] A result unit, configured to determine a defect prediction result according to the defect marking parameter group and the second defect feature set; wherein, the defect prediction result is used to reflect whether the process parameter combination will cause casting defects.

[0017] In a third aspect, the embodiments of the present application provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method described in any one of the above aspects is implemented.

[0018] In a fourth aspect, the embodiments of the present application provide a computer program product, which, when running on an electronic device, causes the electronic device to execute the method described in any one of the above aspects.

[0019] It can be understood that the beneficial effects of the second to fourth aspects above can be referred to the relevant descriptions in the above aspects, and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0021] Figure 1 is a schematic flowchart of a method for predicting aluminum alloy casting defects provided by an embodiment of the present application;

[0022] Figure 2 is a schematic operation diagram of a method for predicting aluminum alloy casting defects provided by an embodiment of the present application;

[0023] Figure 3 is a schematic structural diagram of an aluminum alloy casting defect prediction system provided by an embodiment of the present application;

[0024] Figure 4 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0025] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0026] It should be understood that when used in the specification and the appended claims of the present application, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0027] It should also be understood that the term " / and" as used in the specification and the appended claims of the present application refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0028] As used in the specification of this application and the appended claims, the term "if" may be construed, depending on the context, as "when", "once", "in response to determining", or "in response to detecting". Similarly, the phrase "if it is determined" or "if the described condition or event is detected" may be construed, depending on the context, to mean "once it is determined", "in response to determining", "once the described condition or event is detected", or "in response to detecting the described condition or event".

[0029] In addition, in the description of the specification of this application and the appended claims, the terms "first", "second", "third", etc. are used only for distinguishing descriptions and cannot be construed as indicating or implying relative importance.

[0030] The reference to "one embodiment" or "some embodiments" or the like described in the specification of this application means that a specific feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized.

[0031] In the prior art, the prediction of aluminum alloy casting defects mainly relies on traditional manual detection means and empirical models. Re-calibration is required for adaptation to the process characteristics of different production lines, and prediction deviations and missed judgments are likely to occur under conditions of multi-physical field coupling or process parameter fluctuations. There is a lack of multi-dimensional dynamic analysis tools, resulting in limited defect prediction accuracy and poor production line adaptability.

[0032] To solve the above problems, the embodiments of this application provide a method and device for predicting aluminum alloy casting defects. In this method, by obtaining the set of casting process parameters of the target production line, the process parameter combinations with defect risks are selected. According to the pre-determined prediction parameter thresholds, the second defect feature set is determined from the first defect feature set, and further refined screening is performed on the process parameter combinations in the first defect feature set that exceed the prediction parameter thresholds. The melt state of the second defect feature set is analyzed to obtain the defect marking parameter group of the target production line, and the formation of defects in the second defect feature set is dynamically determined to reveal the defect formation and the dominant mechanism. According to the defect marking parameter group and the second defect feature set, the defect prediction result is determined, reflecting whether the process parameter combination will cause casting defects, and accurately selecting the type before production and predicting defects during the production process are dynamically realized, improving the defect prediction accuracy and production line adaptability.

[0033] The aluminum alloy casting defect prediction method provided by the embodiments of the present application can be applied to an electronic device. In this case, the electronic device is the execution subject of the aluminum alloy casting defect prediction method provided by the embodiments of the present application. The embodiments of the present application do not impose any restrictions on the specific type of the electronic device.

[0034] For example, the electronic device can be an ultra-mobile personal computer (UMPC), a netbook, a desktop computer, a computer, a laptop computer, a communication device, a computing device, a satellite wireless device, etc.

[0035] To better understand the aluminum alloy casting defect prediction method provided by the embodiments of the present application, the following provides an exemplary introduction to the specific implementation process of the aluminum alloy casting defect prediction method provided by the embodiments of the present application.

[0036] Figure 1 The schematic flowchart of the aluminum alloy casting defect prediction method provided by the embodiments of the present application is shown. Figure 2 The operation schematic diagram of the aluminum alloy casting defect prediction method provided by the embodiments of the present application is shown. The aluminum alloy casting defect prediction method includes:

[0037] S100, obtain the casting process parameter set of the target production line, and perform defect feature extraction on the casting process parameter set to determine the first defect feature set; wherein, the first defect feature set includes the process parameter combinations with defect risks during the casting process.

[0038] It can be understood that the target production line refers to a specific casting production line that needs to perform defect prediction analysis. The casting process parameter set refers to a set of a series of process parameter combinations involved in the casting process. These process parameter combinations will affect the casting result, such as the melt temperature, mold pressure, solidification rate, etc. Defect feature extraction refers to finding out those characteristic information that may cause defects in the casting from the casting process parameter set. Through certain algorithms and analysis means, the process parameter combinations with defect risks are screened out to form the first defect feature set. It can be implemented by combining the principal component analysis (PCA) algorithm and the logistic regression algorithm.

[0039] Exemplarily, data preprocessing can be performed on the obtained set of casting process parameters to standardize parameters with different dimensions, making them comparable. The PCA algorithm is used to perform dimensionality reduction on the set of casting process parameters to find the principal components that can explain the data variance to the greatest extent. The principal components are actually linear combinations of the original process parameters, and they contain the main information of the original parameters. Through the PCA algorithm, redundant information between parameters can be reduced, highlighting the influence of key parameters on the casting results. After obtaining the principal component parameters processed by PCA, they are used as input variables, and whether the casting has defects (which can be marked as defective or non-defective through actual inspection) is used as the output variable. A logistic regression algorithm is used to build a model, and through training on existing data, the relationship between process parameters and casting defects is learned. The logistic regression model outputs a probability value, indicating the likelihood of the casting having defects under a given combination of process parameters. A suitable probability threshold is set, and when the probability value output by the model exceeds this threshold, the corresponding combination of process parameters is determined to be a combination with a defect risk and included in the first defect feature set. By comprehensively analyzing various parameters in the casting process, those parameter combinations that are closely related to the occurrence of defects are found for further research later.

[0040] S200. Determine a second defect feature set from the first defect feature set according to a pre-determined prediction parameter threshold; wherein, the second defect feature set includes the process parameter combinations in the first defect feature set that exceed the prediction parameter threshold.

[0041] It can be understood that after determining the first set of defect characteristics, it contains numerous combinations of process parameters with defect risks, but the risk levels of these combinations may vary. To further screen out the combinations of process parameters that are more likely to cause actual defects in the casting, a pre-determined prediction parameter threshold is introduced. The prediction parameter threshold is a standard value or range determined through methods such as previous research, experience summary, or experimental verification. It is set separately for different key parameters in the casting process (such as melt temperature, die pressure, solidification rate, etc.). For example, for the melt temperature parameter, based on a large amount of past production data and defect analysis, it is found that when the melt temperature exceeds a certain specific value range, the probability of defects such as shrinkage cavities and cracks in the casting significantly increases. Then this specific value range can be set as the prediction parameter threshold for the melt temperature. The process of determining the second set of defect characteristics from the first set of defect characteristics is to compare the parameter values included in each combination of process parameters in the first set of defect characteristics with the corresponding prediction parameter thresholds. For each combination of process parameters, if at least one of the parameter values falls within its corresponding prediction parameter threshold, then this combination of process parameters is considered to be a combination with a higher defect risk, and it is selected to form the second set of defect characteristics. Based on the first set of defect characteristics, it further focuses on those process parameter combinations with higher risks, making the subsequent analysis and processing more targeted and efficient.

[0042] In a possible implementation manner, S200, determining the second set of defect characteristics from the first set of defect characteristics according to the pre-determined prediction parameter threshold includes:

[0043] S210, performing process condition filtering on the first set of defect characteristics to determine a third set of defect characteristics that meet the preset process window.

[0044] It can be understood that process condition filtering refers to screening the first set of defect characteristics according to certain process condition criteria and removing those combinations of process parameters that do not meet the conditions. A range judgment algorithm can be used to implement process condition filtering. The preset process window is a pre-set range allowed for process parameters. Only when the parameter values in the combination of process parameters are all within this range is the combination considered to meet the preset process window. For each combination of process parameters in the first set of defect characteristics, check in turn whether each parameter value is within the range specified by the preset process window. If all the parameter values of a certain combination of process parameters are within the range, it is retained; otherwise, it is excluded. The process parameter combinations that meet the preset process window are extracted to form the third set of defect characteristics. The fundamental reason for excluding the abnormal set of process parameters is to optimize the data quality and focus on the effective analysis range, which can exclude some abnormal situations caused by unreasonable process conditions and make the subsequent analysis more accurate.

[0045] Optionally, in S210, perform process condition filtering on the first defect feature set to determine a third defect feature set that meets the preset process window, including:

[0046] S211, obtain the standard parameter range of the standard casting process and the actual parameter range of the first defect feature set.

[0047] It can be understood that the standard parameter range of the standard casting process refers to the reasonable range within which each process parameter should be in an ideal and compliant casting process. For example, the melt temperature should be within a certain specific interval, and there is also a corresponding standard range for the die pressure. The actual parameter range of the first defect feature set refers to the range of parameter values measured for the process parameter combinations in the first defect feature set during the actual production process. The standard parameter range of the standard casting process and the actual parameter range of the first defect feature set can be obtained through data query and statistical algorithms.

[0048] Exemplarily, for the standard parameter range of the standard casting process, it can be obtained by querying from a pre-established standard process parameter database. For the actual parameter range of the first defect feature set, by statistically analyzing the actual parameter data of all process parameter combinations in the first defect feature set, the maximum and minimum values of each parameter can be calculated, thereby determining the actual parameter range.

[0049] S212, determine the set of abnormal process parameters in the first defect feature set according to the standard parameter range and the actual parameter range; wherein, the set of abnormal process parameters includes process parameter combinations whose actual parameter range does not conform to the preset deviation rule compared with the standard parameter range.

[0050] It can be understood that the preset process window (standard parameter range) is a reasonable operation interval determined based on historical qualified production experience or material science theory. The process conditions corresponding to the abnormal parameter set are process conditions that exceed the equipment control ability (such as the maximum load limit of the pressure system), belonging to the uncontrollable range. Interval comparison algorithms, deviation calculation, lower limit comparison algorithms, hypothesis testing algorithms, etc. can be used to determine the set of abnormal process parameters. By comparing the standard parameter range and the actual parameter range, it is judged whether there are abnormalities in the process parameter combinations in the first defect feature set.

[0051] Exemplarily, for each process parameter, a t-test is performed on the measured parameter value and the standard parameter range using a hypothesis testing algorithm. The t-test is a statistical method used to compare whether there is a significant difference in the means of two sets of data. In this case, one set of data is the measured parameter value, and the other set of data is the mean and standard deviation corresponding to the standard parameter range. If the result of the t-test shows that the difference between the measured parameter value and the standard parameter range is statistically significant (i.e., the p-value is less than a pre-set significance level, such as 0.05), it is considered that there is a significant deviation in this process parameter, and the process parameter combination containing this process parameter is determined as an abnormal process parameter set. A significant deviation means that the degree of deviation is relatively large and can no longer be considered as normal fluctuations, but may have an adverse impact on the casting result. By determining the abnormal process parameter set, those high-risk process parameter combinations that may cause defects can be further screened out.

[0052] Exemplarily, in S212, according to the standard parameter range and the actual parameter range, determine the abnormal process parameter set in the first defect feature set, including at least one of the following:

[0053] S2121, when the standard parameter range includes the standard interval of the melt temperature and the actual parameter range includes the actual melt temperature, determine the process parameter combination in which the actual melt temperature exceeds the preset deviation range of the melt temperature standard interval as the abnormal process parameter set.

[0054] It can be understood that the standard interval of the melt temperature is the reasonable range that the melt temperature should maintain in the standard casting process. The actual melt temperature is the value of the melt temperature measured during the actual casting process. The preset deviation range is a pre-set allowable temperature fluctuation range. For each process parameter combination, an interval comparison algorithm can be used to compare the actual melt temperature value therein with the new range formed by adding or subtracting the preset deviation range from the melt temperature standard interval. If the actual melt temperature exceeds this new range, it is considered that there is an abnormality in the melt temperature in this process parameter combination, and this process parameter combination is determined as the abnormal process parameter set.

[0055] S2122, when the standard parameter range includes the standard interval of the die pressure and the actual parameter range includes the actual die pressure, determine the process parameter combination in which the actual die pressure is lower than the lower limit of the die pressure standard interval as the abnormal process parameter set.

[0056] It can be understood that the standard range of die pressure is the reasonable range that the die pressure should maintain in the standard casting process, including the upper limit and the lower limit. The actual die pressure is the value of the die pressure measured during the actual casting process. For each combination of process parameters, a lower limit comparison algorithm can be used to compare the actual die pressure value therein with the lower limit value of the standard range of die pressure. When the actual die pressure is lower than the lower limit value of the standard range of die pressure, it is considered that there is an abnormality in the die pressure in this combination of process parameters, and this combination of process parameters is determined as the abnormal process parameter set.

[0057] S2123. When the standard parameter range includes the standard value of solidification rate and the actual parameter range includes the actual solidification rate, the combination of process parameters in which the actual solidification rate deviates from the standard value of solidification rate by a preset deviation range is determined as the abnormal process parameter set.

[0058] It can be understood that the standard value of solidification rate is the reasonable solidification rate specified in the standard casting process. The actual solidification rate is the value of the solidification rate measured during the actual casting process. The preset deviation range is a preset allowable fluctuation range of the solidification rate. For each combination of process parameters, the deviation degree between the actual solidification rate and the standard value of solidification rate therein can be calculated (for example, the absolute value obtained by subtracting the standard value of solidification rate from the actual solidification rate and then dividing by the standard value of solidification rate). Then, the calculated deviation degree is compared with the preset deviation range. When the deviation degree exceeds the preset deviation range, it is considered that there is an abnormality in the solidification rate in this combination of process parameters, and this combination of process parameters is determined as the abnormal process parameter set.

[0059] S213. Remove the abnormal process parameter set from the first defect feature set to determine the third defect feature set that meets the preset process window.

[0060] It can be understood that after determining the abnormal process parameter set in the first defect feature set, the first defect feature set is regarded as a set, and the abnormal process parameter set is also regarded as a set. A set operation algorithm (set difference operation) can be used. Through the set difference operation, the abnormal process parameter set is removed from the first defect feature set. The remaining combinations of process parameters are those combinations of process parameters that not only have a defect risk (belong to the first defect feature set) but also meet the preset process window (there is no significant abnormality in process conditions). Determining these combinations of process parameters as the third defect feature set can make the third defect feature set more accurately reflect the combinations of process parameters that may cause defects under normal process conditions. The third defect feature set reflects all possible combinations of process parameters that can trigger defects under controllable process conditions.

[0061] S220. Determine the critical process parameter interval according to the prediction parameter threshold; wherein, the critical process parameter interval is used to reflect the distribution range of the prediction parameter threshold.

[0062] It can be understood that the prediction parameter threshold is a standard value or range used to measure whether there is a greater risk of defects in the process parameter combination. For each process parameter, the critical process parameter interval is determined according to the prediction parameter threshold. If the prediction parameter threshold is a single value, for example, the prediction parameter threshold of the solidification rate is a certain fixed value , an interval around can be determined in advance according to experience or relevant research, such as as the critical process parameter interval, which is a fluctuation range value set according to the actual situation. If the prediction parameter threshold is an interval, for example, the prediction parameter threshold of the melt temperature is , then this interval can be directly used as the critical process parameter interval, or it can be appropriately adjusted as needed, such as expanding or shrinking by a certain proportion. By determining the critical process parameter interval, it can be more clearly understood which process parameter values need to be focused on.

[0063] S230, screen the third defect feature set according to the critical process parameter interval to determine the second defect feature set of the target production line; wherein, the second defect feature set represents the process parameter combinations whose process parameter values fall within the critical process parameter interval.

[0064] It can be understood that the critical process parameter interval reflects the range of process parameter values related to a higher defect risk. For each process parameter combination in the third defect feature set, check in turn whether each process parameter value therein falls within the corresponding critical process parameter interval. For each process parameter, compare its value with the critical process parameter interval. If the parameter value is within the interval, mark that the parameter meets the condition; if all parameters meet the condition, select this process parameter combination to form the second defect feature set of the target production line. The purpose of doing this is to further screen out those process parameter combinations that are most likely to cause defects, because these process parameter combinations not only meet the preset process window (belonging to the third defect feature set), but also their process parameter values are within the high-risk critical process parameter interval.

[0065] Optionally, S230, screen the third defect feature set according to the critical process parameter interval to determine the second defect feature set of the target production line, including:

[0066] S231, determine the process control dimension corresponding to the critical process parameter interval and the parameter threshold range corresponding to each process control dimension.

[0067] It can be understood that the process control dimension refers to different aspects of controlling and managing process parameters in the casting process, such as temperature, pressure, time, etc. For the critical process parameter range, by analyzing the corresponding process parameters, determine the process control dimensions to which these parameters belong. For each combination of process parameters, through data reading and parsing operations, obtain the specific values of each process parameter among them. The process parameter values are the basis for subsequent screening and analysis. By determining the process control dimension and the process parameter values, it is possible to more accurately judge whether the combination of process parameters in the third defect feature set meets the requirements of the critical process parameter range.

[0068] S232, map the process control dimension and the parameter threshold range corresponding to each process control dimension to the process parameter space, and determine the first boundary condition and the second boundary condition of the process parameter space; wherein, the first boundary condition and the second boundary condition represent the parameter limit values on the process control dimension.

[0069] It can be understood that the process parameter space is an abstract concept used to represent the relationships and variation ranges among process parameters. Mapping the process control dimension and the parameter threshold range corresponding to the process control dimension to the process parameter space is to represent this actual process parameter information in an abstract space for more intuitive analysis of their relationships. Through a spatial mapping and boundary determination algorithm, for each process control dimension, according to the value range of the critical process parameter range, determine the parameter limit values on this dimension, that is, the first boundary condition and the second boundary condition. For example, on the process control dimension of temperature, according to the temperature range of the critical process parameter range, determine the highest temperature as the first boundary condition and the lowest temperature as the second boundary condition. By determining the boundary conditions, the variation range of the process parameters can be clarified, providing a basis for subsequent screening of process parameter combinations.

[0070] S233, traverse each combination of process parameters in the third defect feature set, screen out all combinations of process parameters that simultaneously meet the first boundary condition and the second boundary condition, and determine the second defect feature set of the target production line.

[0071] It can be understood that the third set of defect features is obtained by filtering the first set of defect features according to process conditions, and it contains combinations of process parameters that still have a risk of defects under normal process conditions. The first boundary condition and the second boundary condition are parameter limit values determined according to the process control dimensions corresponding to the critical process parameter intervals, and they limit the reasonable value range of the process parameters in this dimension. For each combination of process parameters in the third set of defect features, the process parameter values it contains can be checked. Only when these process parameter values are neither lower than the lower limit value specified by the second boundary condition nor higher than the upper limit value specified by the first boundary condition in their respective corresponding process control dimensions, that is, when both of these boundary conditions are satisfied simultaneously, does it indicate that this combination of process parameters is within the high-risk and reasonable range defined by the critical process parameter interval. Select the third set of defect features that meet such conditions and form the second set of defect features for the target production line. Because these combinations of process parameters are more likely to cause defects in the casting, classifying them separately as the second set of defect features helps to conduct more targeted in-depth analysis in the follow-up, such as performing melt state analysis on them, etc., so as to more accurately predict the possible defect conditions of the casting and provide strong support for optimizing the casting process and improving product quality.

[0072] Exemplarily, in S233, traverse each combination of process parameters in the third set of defect features, filter out the combinations of process parameters that simultaneously meet the first boundary condition and the second boundary condition, and determine them as the second set of defect features for the target production line, including:

[0073] S2331, when the critical process parameter interval contains multiple sub-intervals, sequentially verify whether each combination of process parameters meets the first boundary condition and the second boundary condition corresponding to each sub-interval.

[0074] It can be understood that the critical process parameter interval is sometimes not a single continuous range, but consists of multiple sub-intervals. For each combination of process parameters, it can be checked one by one whether it meets the first boundary condition and the second boundary condition corresponding to each sub-interval. Each sub-interval has its own specific boundary conditions, and these boundary conditions combined constitute the constraint conditions for this sub-interval. For example, the critical process parameter interval may contain two sub-intervals of temperature, one is a lower temperature range and the other is a higher temperature range, and each sub-interval has corresponding temperature upper and lower limits and other boundary conditions. For each combination of process parameters in the third set of defect features, it is necessary to sequentially determine whether its process parameter values meet the boundary conditions of these two sub-intervals. Through the sequential verification method, the matching situation between the third set of defect features and the critical process parameter interval can be comprehensively determined.

[0075] S2332. When the process parameter combination meets the first boundary condition and the second boundary condition corresponding to any sub-interval, screen the process parameter combination into the second defect feature set.

[0076] It can be understood that in the process of sequentially verifying whether each process parameter combination meets the boundary condition combination corresponding to each sub-interval, if it is found that a certain process parameter combination can meet the boundary condition combination corresponding to any sub-interval, the process parameter combination is screened into the second defect feature set. Because this process parameter combination is within the range defined by each sub-interval of the key process parameter interval, it conforms to the characteristics of a high-risk process parameter combination and may cause defects in the casting. It is selected into the second defect feature set for further in-depth analysis and processing later, as well as more accurate prediction of casting defects.

[0077] S300. Perform a melt state analysis on the second defect feature set to obtain a defect marking parameter group for the target production line; where the defect marking parameter group is used to indicate the formation of defects in the second defect feature set.

[0078] It can be understood that the formation of defects in the second defect feature set of the target production line can be determined by combining the finite element analysis (FEA) algorithm and the association analysis algorithm. Finite element modeling can be performed on the casting process corresponding to the process parameter combinations in the second defect feature set. The melt in the casting process is regarded as being composed of many small units, and the boundary conditions and initial conditions of the model are set according to the process parameters, such as melt temperature, die pressure, etc. Solve the model through finite element analysis software to simulate physical phenomena such as the flow and heat transfer of the melt during solidification, and obtain detailed information on the melt state, such as temperature distribution, stress distribution, etc. After obtaining the results of the finite element analysis, use the association analysis algorithm (such as the Apriori algorithm) to analyze the relationship between the melt state information and the formation of defects. The Apriori algorithm is an algorithm used to mine association rules in data. By setting appropriate support and confidence thresholds, find those melt state parameter combinations that are closely related to the formation of defects, and determine these parameter combinations as the defect marking parameter group. The defect marking parameter group can indicate which process parameter combinations in the second defect feature set have reached the formation of defects, that is, when these parameters are within a specific value or range, the casting is likely to have defects.

[0079] In a possible implementation, S300. Perform a melt state analysis on the second defect feature set to obtain a defect marking parameter group for the target production line, including:

[0080] S310. Perform a multi-dimensional process sensitivity simulation on the second defect feature set to generate a dynamic defect evolution behavior map.

[0081] It can be understood that the Monte Carlo simulation algorithm and the data visualization algorithm can be combined to perform multi-dimensional process sensitivity simulation on the second defect feature set. Through Monte Carlo simulation, for each process parameter combination in the second defect feature set, random sampling can be performed in multiple process control dimensions (such as temperature, pressure, time, etc.). According to the value range and probability distribution of each process parameter, a large number of random process parameter combinations are generated. For each group of randomly generated process parameter combinations, the finite element analysis method is used to simulate the solidification process to obtain the corresponding defect formation results. Through repeated sampling and simulation, a large amount of data on the defect formation under different process parameter combinations is obtained. The data obtained from the Monte Carlo simulation is sorted and analyzed, and the data visualization algorithm (such as drawing contour maps, three-dimensional surface maps, etc.) is used to display the relationship between the defect formation and the process parameters in an intuitive graphical manner, generating a dynamic defect evolution behavior map. The dynamic defect evolution behavior map can reflect how the defects develop with the change of process parameters, providing a basis for subsequent defect analysis.

[0082] Optionally, in S310, performing multi-dimensional process sensitivity simulation on the second defect feature set to generate a dynamic defect evolution behavior map, including:

[0083] S311, applying a preset perturbation gradient to the process parameter combinations in the second defect feature set to generate multiple groups of perturbed process parameter combinations.

[0084] It can be understood that the preset perturbation gradient is an amplitude or rate of parameter change set in advance. The parameter perturbation algorithm can be used to change the process parameters in each process parameter combination in the second defect feature set according to the preset perturbation gradient. For example, if a certain process parameter combination includes melt temperature , die pressure and solidification rate , and the preset perturbation gradient stipulates that the melt temperature increases by each time, the die pressure decreases by each time, and the solidification rate increases by each time. Then for this process parameter combination , new perturbed process parameter combinations , etc. can be generated. By changing the parameters according to the preset perturbation gradient multiple times, multiple groups of perturbed process parameter combinations are generated. Through the parameter perturbation algorithm, different process parameter change situations can be simulated to more comprehensively study the influence of process parameters on defect formation.

[0085] S312, performing solidification process simulation based on multiple groups of perturbed process parameter combinations and outputting the defect formation tendency data under each perturbed process parameter combination.

[0086] It can be understood that the solidification process simulation is based on the finite element method to simulate the casting solidification process corresponding to multiple sets of perturbed process parameter combinations. Corresponding finite element models can be established according to each different set of perturbed process parameter combinations. In the model, the thermophysical properties of the melt (such as specific heat capacity, thermal conductivity, etc.), latent heat of solidification, boundary conditions (such as heat transfer conditions of the mold, etc.), and process parameters (such as melt temperature, mold pressure, solidification rate, etc.) are considered. The finite element solver is used to solve the model to calculate the changes in physical quantities such as the temperature field, stress field, and flow velocity field of the melt during the solidification process. By analyzing the changes in these physical quantities, the possibility and tendency of defect formation are judged. For example, when the temperature field distribution is uneven, defects such as shrinkage cavities and shrinkage porosity may be caused; when the stress field exceeds the strength limit of the material, defects such as cracks may be generated. According to these analysis results, the defect formation tendency data under each perturbed process parameter combination are output. These data can be information such as the type, location, size, and occurrence probability of the defects, providing basic data for establishing the parameter-defect evolution correlation surface subsequently.

[0087] S313. Establish a parameter-defect evolution correlation surface based on the defect formation tendency data, and determine the parameter-defect evolution correlation surface as the dynamic defect evolution behavior mapping.

[0088] It can be understood that the defect formation tendency data can be analyzed. The process parameters (such as melt temperature, mold pressure, solidification rate, etc.) are used as independent variables, and the defect formation tendency (such as the occurrence probability of defects, the size of defects, etc.) is used as the dependent variable. The multiple regression analysis algorithm can be used to establish a mathematical relationship model between the process parameters and the defect formation tendency. Through data fitting, a regression equation is obtained, which describes how the changes in the process parameters affect the defect formation tendency. After obtaining the multiple regression equation, the surface fitting algorithm (such as least squares surface fitting) can be used to visualize the relationship represented by the regression equation in a three-dimensional or higher-dimensional space to generate the parameter-defect evolution correlation surface. For example, when considering the influence of two process parameters, melt temperature and mold pressure, on the defect occurrence probability, a surface can be plotted on a two-dimensional plane with melt temperature as the horizontal axis, mold pressure as the vertical axis, and defect occurrence probability as the vertical axis. This surface intuitively shows the relationship between the process parameters and the defect formation tendency, that is, how the defect formation tendency evolves with the change of the process parameters. Determining this parameter-defect evolution correlation surface as the dynamic defect evolution behavior mapping provides an important tool for subsequent analysis of the defect formation mechanism and prediction of defects.

[0089] S320. Perform defect feature correlation analysis on the second defect feature set based on the dynamic defect evolution behavior mapping to obtain a set of composite defect indicators with defect feature correlation degrees exceeding the threshold.

[0090] It can be understood that for each process parameter combination in the second defect feature set, the process parameter value and defect formation tendency data corresponding to the combination can be obtained according to the dynamic defect evolution behavior mapping. The Pearson correlation coefficient algorithm can be used to calculate the correlation coefficient between each process parameter and the defect formation tendency. The Pearson correlation coefficient is a statistic that measures the degree of linear correlation between two variables. Its value range is between -1 and 1. The closer the absolute value is to 1, the higher the degree of linear correlation between the two variables. By calculating the correlation coefficient, it can be determined which process parameters have a strong correlation with defect formation. By setting a defect feature correlation threshold, the process parameters with an absolute value of the correlation coefficient greater than the threshold can be screened out according to the calculated Pearson correlation coefficient. The screened process parameters are combined to form a composite defect indicator set. The composite defect indicator set is a set of parameters closely related to defect generation. By obtaining this set, it is possible to more accurately understand which factors play a key role in the generation of defects, and provide more targeted information for subsequent defect analysis and prediction.

[0091] S330, prioritizing the composite defect indicator set according to a preset defect coupling effect rule, screening out a characteristic parameter group of a dominant defect formation mechanism, and determining the characteristic parameter group as a defect marking parameter group.

[0092] It can be understood that the preset defect coupling effect rules describe the interaction and influence relationship between different defect indicators. The hierarchical analysis method can be used to analyze the various indicators in the composite defect indicator set according to their hierarchical structure and mutual relationship. A hierarchical model can be constructed to list the target (the iconic parameter group that determines the dominant defect formation mechanism), the criterion (defect coupling effect rule) and the indicator (the various parameters in the composite defect indicator set) as different levels. The weight of each indicator relative to the criterion is determined by pairwise comparison. For example, the importance of the two indicators of melt temperature and mold pressure in defect formation is compared, and the corresponding proportional relationship is given according to expert experience or actual data, and then their weights are calculated. According to the weights of each indicator calculated by the hierarchical analysis method, the indicators in the composite defect indicator set can be prioritized. The indicators with larger weights are placed in front, and the indicators with smaller weights are placed in the back. Then, according to the sorting results, a group of indicators with larger weights are screened out, which constitute the iconic parameter group of the dominant defect formation mechanism. This iconic parameter group is identified as the defect marking parameter group because it can indicate which process parameter combinations have led to defect formation in the second defect feature set, providing an important basis for subsequent defect prediction and helping to control and optimize key process parameters more specifically in actual production.

[0093] Exemplarily, a hierarchical model can be constructed, and the preset defect coupling effect rules are set as the criterion layer, and the various parameters in the composite defect index set constitute the index layer. For example, in aluminum alloy casting, the index layer may include parameters such as melt temperature, mold pressure, solidification rate, cooling rate, etc. These parameters affect each other to varying degrees and have an effect on defect formation. The weight of each index relative to the criterion is determined by pairwise comparison. Take the two indicators of melt temperature and mold pressure as an example. Assuming that under a certain casting process, the influence of melt temperature on defect formation is twice that of mold pressure, then when constructing the judgment matrix, for the comparison between melt temperature and mold pressure, the corresponding element will be assigned a value of 2; conversely, when mold pressure is compared with melt temperature, the element is assigned a value of 1 / 2. By performing similar pairwise comparisons on all indicators, a complete judgment matrix is constructed. The maximum eigenvalue of the judgment matrix and its corresponding eigenvector are calculated using mathematical methods such as the eigenvector method. The values of each element in the obtained eigenvector are the weights of each indicator relative to the criterion. For example, after calculation, the weight of melt temperature is 0.4, the weight of mold pressure is 0.3, the weight of solidification rate is 0.2, the weight of cooling rate is 0.1, and so on. According to the weights of each indicator calculated by the analytic hierarchy process, the indicators in the composite defect indicator set are prioritized. Indicators with larger weights are placed in front, and indicators with smaller weights are placed in the back. Assuming that a weight threshold of 0.3 is set, indicators with weights equal to or greater than the threshold are screened out. In the above example, melt temperature and mold pressure are screened out, and melt temperature and mold pressure together constitute the iconic parameter group of the dominant defect formation mechanism. This iconic parameter group can be identified as a defect marking parameter group because they can accurately indicate which process parameter combinations have achieved defect formation in the second defect feature set.

[0094] S400, determining a defect prediction result according to the defect marking parameter group and the second defect feature set; wherein the defect prediction result is used to reflect whether the process parameter combination will lead to casting defects.

[0095] It can be understood that the defect marking parameter group is obtained after a series of operations such as melt state analysis on the second defect feature set, and it contains a key process parameter combination that can indicate the critical conditions for defect formation. The defect prediction result can be finally determined by comparing and analyzing the defect marking parameter group with the relevant standards. The defect prediction result can intuitively reflect the possibility of defects in castings caused by the process parameter combination of the current target production line in actual production, thereby providing an important basis for decision-making such as process adjustment and quality control in the production process, so as to achieve the purpose of preventing and reducing casting defects.

[0096] In a possible implementation, S400, determining a defect prediction result according to a defect marking parameter group and a second defect feature set, includes:

[0097] S410, obtaining a preset ratio threshold set in advance; wherein, the preset ratio threshold is used to determine whether a process parameter combination in the second defect feature set reaches a defect formation condition.

[0098] It can be understood that the preset ratio threshold set in advance is a standard value set in previous research or experience and stored in a specific data storage location (such as a database, a configuration file, etc.). The defect feature threshold can be obtained from the corresponding data storage location through a data reading algorithm. The defect feature threshold is determined based on the understanding of the defect formation mechanism and experience in actual production, and is used to compare the subsequent process parameter combination with the defect marking parameter group to judge whether the process parameter combination in the second defect feature set reaches the defect formation condition.

[0099] S420, determining the average parameter deviation degree between each process parameter combination in the second defect feature set and the defect marking parameter group.

[0100] It can be understood that for each process parameter combination in the second defect feature set, it includes multiple specific process parameters, such as melt temperature, die pressure, casting speed, etc. These parameters jointly determine the state of the casting process. The defect marking parameter group is obtained through a series of analyses and includes key parameters indicating the critical conditions for defect formation. Each parameter in each process parameter combination can be compared with the corresponding parameter in the defect marking parameter group respectively. For numerical parameters, calculate the absolute value of the difference between them; for some parameters with an interval range, calculate the degree of deviation of the parameter value in the current process parameter combination from the interval range. The deviation degrees of all these parameters can be comprehensively calculated, such as taking the average value, etc., so as to obtain the average parameter deviation degree between the process parameter combination and the defect marking parameter group. The average parameter deviation degree can intuitively reflect the gap size between the current process parameter combination and the critical parameter combination that may cause defects. The larger the deviation degree, the more likely it is to produce defects.

[0101] S430, when the average parameter deviation degree is not less than the preset ratio threshold, obtaining a first defect prediction result of the process parameter combination in the second defect feature set; wherein, the first defect prediction result is used to indicate that the process parameter combination will cause casting defects.

[0102] It can be understood that when the average parameter deviation degree is not less than the preset ratio threshold, it means that the difference between the current process parameter combination and the defect formation critical condition represented by the defect marking parameter group has reached a certain level. The parameter values in the process parameter combination have deviated from the normal range and entered the dangerous area where casting defects may be caused. In actual production, the process parameter setting in this case cannot guarantee the quality of the casting, and will lead to the appearance of defects such as pores, shrinkage porosity, cracks, etc., and a first defect prediction result is obtained, that is, this process parameter combination will cause casting defects.

[0103] S440, in the case where the average parameter deviation degree is less than the preset ratio threshold, obtain the second defect prediction result of the process parameter combination in the second defect feature set; wherein, the second defect prediction result is used to indicate that the process parameter combination will not cause casting defects.

[0104] It can be understood that when the average parameter deviation degree is less than the preset ratio threshold, it indicates that the current process parameter combination is relatively close to the defect formation critical condition indicated by the defect marking parameter group and is in a relatively safe range. At this time, the parameter values in the process parameter combination are within a reasonable fluctuation range, and casting defects will not be caused due to the setting of these parameters. In the actual production scenario, based on such process parameters for casting, the casting can be formed under normal process conditions, and the quality is greatly guaranteed. A second defect prediction result is obtained, that is, this process parameter combination will not cause casting defects, dynamically realizing accurate model selection before production and defect prediction during the production process, and improving the defect prediction accuracy and production line adaptability.

[0105] Corresponding to the aluminum alloy casting defect prediction method in the above embodiments, the embodiments of the present application further provide an aluminum alloy casting defect prediction system, and each unit of the system can implement each step of the aluminum alloy casting defect prediction method. Figure 3 The structural block diagram of the aluminum alloy casting defect prediction system provided by the embodiments of the present application is shown. For the sake of convenience of description, only the parts related to the embodiments of the present application are shown.

[0106] Refer to Figure 3 , the aluminum alloy casting defect prediction system includes:

[0107] An acquisition unit, configured to acquire a casting process parameter set of a target production line, and perform defect feature extraction on the casting process parameter set to determine a first defect feature set; wherein, the first defect feature set includes process parameter combinations with defect risks during the casting process;

[0108] A determination unit, configured to determine a second defect feature set from the first defect feature set according to a pre-determined prediction parameter threshold; wherein, the second defect feature set includes process parameter combinations in the first defect feature set that exceed the prediction parameter threshold;

[0109] An analysis unit for performing a melt state analysis on the second defect feature set to obtain a defect marking parameter group of the target production line; wherein the defect marking parameter group is used to indicate the formation of defects in the second defect feature set.

[0110] A result unit for determining a defect prediction result according to the defect marking parameter group and the second defect feature set; wherein the defect prediction result is used to reflect whether a process parameter combination will cause casting defects.

[0111] It should be noted that the information interaction, execution process, etc. between the above systems / units, due to being based on the same concept as the method embodiments of the present application, for their specific functions and the technical effects brought, please refer to the method embodiment part for details, and will not be elaborated here.

[0112] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit module can exist physically alone, or two or more unit modules can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiments and will not be elaborated here.

[0113] The embodiment of the present application also provides an electronic device. Figure 4 It is a schematic structural diagram of an electronic device provided in an embodiment of the present application. As Figure 4 shown, the electronic device 6 of this embodiment includes: at least one processor 60 ( Figure 4 only one is shown here), at least one memory 61 ( Figure 4 only one is shown here), and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, the electronic device 6 realizes the steps in any of the above method embodiments of the aluminum alloy casting defect prediction method, or the functions of each unit in the above system embodiments.

[0114] Exemplarily, the computer program 62 may be divided into one or more units, which are stored in the memory 61 and executed by the processor 60 to complete this application. The one or more units may be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program 62 in the electronic device 6.

[0115] The electronic device 6 may be a computing device or a terminal device such as a desktop computer, a notebook, a palm computer, and a cloud server. The electronic device may include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art can understand that Figure 4 merely examples of the electronic device 6, which do not constitute a limitation on the electronic device 6, may include more or fewer components than shown in the figure, or combine some components, or different components. For example, it may also include input / output devices, network access devices, buses, etc.

[0116] The processor 60 may be a central processing unit (CPU), and the processor 60 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0117] In some embodiments, the memory 61 may be an internal storage unit of the electronic device 6, such as the hard disk or memory of the electronic device 6. In other embodiments, the memory 61 may also be an external storage device of the electronic device 6, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 6. Further, the memory 61 may also include both the internal storage unit and the external storage device of the electronic device 6. The memory 61 is used to store an operating system, application programs, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 61 may also be used to temporarily store data that has been output or will be output.

[0118] An embodiment of the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0119] An embodiment of the present application provides a computer program product, and when the computer program product runs on an electronic device, the electronic device implements the steps in any of the above method embodiments.

[0120] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above method embodiments of the present application, a computer program can be used to instruct relevant hardware to complete. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps in each of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to an electronic device, a recording medium, a computer memory, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0121] In the above embodiments, the descriptions of the respective embodiments have their own focuses. For parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0122] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A professional technician can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present application.

[0123] In the embodiments provided in the present application, it should be understood that the disclosed aluminum alloy casting defect prediction system / electronic device and method can be implemented in other ways. For example, the aluminum alloy casting defect prediction system / electronic device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections between each other can be through some interfaces, and the indirect couplings or communication connections of devices or units can be in electrical, mechanical or other forms.

[0124] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0125] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for predicting aluminum alloy casting defects, characterized in that, Including: Obtain the casting process parameter set of the target production line, extract defect features from the casting process parameter set, and determine the first defect feature set; wherein, the first defect feature set includes process parameter combinations with defect risks during the casting process; Determine a second defect feature set from the first defect feature set according to a pre-determined prediction parameter threshold; wherein, the second defect feature set includes process parameter combinations in the first defect feature set that exceed the prediction parameter threshold; Perform melt state analysis on the second defect feature set to obtain the defect marking parameter group of the target production line; wherein the defect marking parameter group is used to indicate the formation of defects in the second defect feature set; Determine a defect prediction result according to the defect marking parameter group and the second defect feature set; wherein, the defect prediction result is used to reflect whether the process parameter combination will cause casting defects; Wherein, the determining the second defect feature set from the first defect feature set according to a pre-determined prediction parameter threshold includes: Perform process condition filtering on the first defect feature set to determine a third defect feature set that meets the preset process window; Determine the key process parameter interval according to the prediction parameter threshold; wherein, the key process parameter interval is used to reflect the distribution range of the prediction parameter threshold; Screen the third defect feature set according to the key process parameter interval to determine the second defect feature set of the target production line; wherein, the second defect feature set represents a process parameter combination whose process parameter value falls within the key process parameter interval.

2. The aluminum alloy casting defect prediction method according to claim 1, characterized in that The performing process condition filtering on the first defect feature set to determine a third defect feature set that meets the preset process window includes: Obtain the standard parameter range of the standard casting process and the actual parameter range of the first defect feature set; Determine the abnormal process parameter set in the first defect feature set according to the standard parameter range and the actual parameter range; wherein, the abnormal process parameter set includes process parameter combinations whose actual parameter range does not conform to the preset deviation rule with the standard parameter range; Exclude the abnormal process parameter set from the first defect feature set to determine a third defect feature set that meets the preset process window.

3. The aluminum alloy casting defect prediction method according to claim 2, characterized in that, The determining the abnormal process parameter set in the first defect feature set according to the standard parameter range and the actual parameter range includes at least one of the following: When the standard parameter range includes the melt temperature standard interval and the actual parameter range includes the actual melt temperature, determine the process parameter combination in which the actual melt temperature exceeds the preset deviation range of the melt temperature standard interval as the abnormal process parameter set; When the standard parameter range includes the mold pressure standard interval and the actual parameter range includes the actual mold pressure, determine the process parameter combination in which the actual mold pressure is lower than the lower limit of the mold pressure standard interval as the abnormal process parameter set; When the standard parameter range includes a standard value of solidification rate and the actual parameter range includes an actual solidification rate, a process parameter combination in which the actual solidification rate deviates from a preset deviation range of the standard value of solidification rate is determined as an abnormal process parameter set.

4. The aluminum alloy casting defect prediction method according to claim 1, characterized in that The screening of the third defect feature set according to the key process parameter interval to determine the second defect feature set of the target production line includes: Determine the process control dimension corresponding to the key process parameter interval and the parameter threshold range corresponding to each of the process control dimensions; Mapping the process control dimension and the parameter threshold range corresponding to each process control dimension to a process parameter space, and determining a first boundary condition and a second boundary condition of the process parameter space; wherein the first boundary condition and the second boundary condition represent parameter limit values on the process control dimension; Each process parameter combination in the third defect feature set is traversed, all process parameter combinations that simultaneously satisfy the first boundary condition and the second boundary condition are screened out, and a second defect feature set of the target production line is determined.

5. The aluminum alloy casting defect prediction method according to claim 4, characterized in that, The traversing each process parameter combination in the third defect feature set, screening out all process parameter combinations that simultaneously satisfy the first boundary condition and the second boundary condition, and determining the second defect feature set of the target production line includes: In the case where the key process parameter interval includes multiple sub-intervals, verifying in turn whether each process parameter combination satisfies the first boundary condition and the second boundary condition corresponding to each sub-interval; When a process parameter combination satisfies the first boundary condition and the second boundary condition corresponding to any sub-interval, the process parameter combination is screened into a second defect feature set.

6. The aluminum alloy casting defect prediction method according to claim 1, characterized in that The performing melt state analysis on the second defect feature set to obtain a defect marking parameter group for a target production line includes: Performing a multi-dimensional process sensitivity simulation on the second defect feature set to generate a dynamic defect evolution behavior map; Based on the dynamic defect evolution behavior mapping, defect feature correlation analysis is performed on the second defect feature set to obtain a composite defect indicator set whose defect feature correlation exceeds a threshold; The composite defect indicator set is prioritized according to a preset defect coupling effect rule, a characteristic parameter group of a dominant defect formation mechanism is screened out, and the characteristic parameter group is determined as the defect marking parameter group.

7. The aluminum alloy casting defect prediction method according to claim 6, characterized in that, The performing a multi-dimensional process sensitivity simulation on the second defect feature set to generate a dynamic defect evolution behavior map includes: Applying a preset disturbance gradient to the process parameter combinations in the second defect feature set to generate multiple groups of disturbance process parameter combinations; Performing solidification process simulation based on the plurality of perturbation process parameter combinations, and outputting defect formation tendency data under each perturbation process parameter combination; A parameter defect evolution association surface is established according to the defect formation tendency data, and the parameter defect evolution association surface is determined as a dynamic defect evolution behavior mapping.

8. The aluminum alloy casting defect prediction method according to claim 1, characterized in that The step of determining a defect prediction result according to the defect marking parameter group and the second defect feature set includes: Obtain a preset proportional threshold; wherein, the preset proportional threshold is used to determine whether the process parameter combinations in the second defect feature set reach the defect formation condition; Determine the average parameter deviation degree of each process parameter combination in the second defect feature set from the defect marking parameter group; When the average parameter deviation degree is not less than the preset proportional threshold, obtain a first defect prediction result for the process parameter combinations in the second defect feature set; wherein, the first defect prediction result is used to indicate that the process parameter combinations will cause casting defects; When the average parameter deviation degree is less than the preset proportional threshold, obtain a second defect prediction result for the process parameter combinations in the second defect feature set; wherein, the second defect prediction result is used to indicate that the process parameter combinations will not cause casting defects.

9. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, the method described in any one of claims 1 to 8 is implemented.

Images