Casting blank quality defect analysis method and device, electronic equipment and storage medium

Abstract

The invention discloses a casting blank quality defect analysis method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining various target data, wherein the various target data are parameter data corresponding to a plurality of influence parameters in the continuous casting production process of a casting blank; determining a plurality of target Pearson's correlation coefficients, and determining at least one first target influence parameter causing the target defect of the casting blank according to the target Pearson's correlation coefficients; a P value is determined, and the significance level of the correlation between any first target influence parameter and the target defect is represented; according to the P value, a second target influence parameter is determined, and the second target influence parameter is a first target influence parameter corresponding to the P value smaller than a first preset threshold value; the density condition of the casting blank with the target defect in the first target data range of the second target influence parameter is determined, a second target data range is determined according to the density condition, and the second target data range is used for representing that the density of the casting blank with the target defect in the second target data range is larger than a second preset threshold value.

Description

Technical Field

[0001] The present invention belongs to the technical field of continuous casting production, and in particular relates to a method, device, electronic equipment and storage medium for analyzing quality defects of a casting. Background Art

[0002] Continuous casting is the most common process for solidifying a steel melt with a specific chemical composition into semi-finished castings (such as billets, blooms, and slabs). Molten steel is poured from a ladle into a water-cooled mold. After exiting the mold, the product is supported by rollers and cooled by water spray in a secondary cooling zone. The solidified semi-finished casting (such as the billet) is cut and cooled to room temperature, or slightly heated directly before hot deformation (i.e., rolling). During this process, quality defects can occur in products such as ingots produced through long production processes due to process errors, inappropriate process parameters, or equipment failures. However, because long production processes involve multiple production stages, such as smelting, heating, hot rolling, and solutionizing, identifying the cause of defects has always been a key challenge in resolving these problems. Furthermore, once the corresponding defect cause is determined, more accurately exploring the relationship between the defect cause and ingot quality is also a key difficulty in current actual production processes. Summary of the Invention

[0003] In order to solve the above problems, embodiments of the present invention provide a method, device, electronic device and storage medium for analyzing quality defects of a casting.

[0004] In a first aspect, an embodiment of the present invention provides a method for analyzing quality defects of a casting, comprising:

[0005] Acquiring a plurality of target data, wherein the plurality of target data are parameter data corresponding to a plurality of influencing parameters in a continuous casting production process of the slab, wherein the influencing parameters are parameters causing target defects in the slab;

[0006] Determine a plurality of target Pearson correlation coefficients, wherein the plurality of target Pearson correlation coefficients are Pearson correlation coefficients between a target data corresponding to each influencing parameter and a target defect occurrence frequency;

[0007] determining, based on the multiple target Pearson correlation coefficients, at least one first target influencing parameter that causes a target defect in the cast slab;

[0008] Determining a P value, where the P value is used to represent a significance level of a correlation between any one of the at least one first target influencing parameter and the target defect;

[0009] Determining a second target influencing parameter according to the P value, where the second target influencing parameter is the first target influencing parameter corresponding to the P value that is less than the first preset threshold;

[0010] determining a density of a cast slab in which a target defect occurs within a first target data range of the second target influencing parameter;

[0011] According to the density situation, a second target data range is determined, where the second target data range is used to indicate that the density of the ingot with the target defect occurring within the second target data range is greater than a second preset threshold.

[0012] In a possible implementation, after acquiring the multiple target data, the method further includes:

[0013] Normalization processing is performed on the multiple target data respectively to obtain multiple normalized data.

[0014] In a possible implementation, determining multiple target Pearson correlation coefficients includes:

[0015] The Pearson correlation coefficient for multiple targets is determined by the following formula:

[0016]

[0017] Among them, Cov(X,Y)=E{[XE(X)][YE(Y)]}, represents the average value of X, X represents the normalized data of the parameter data corresponding to any one of the multiple influencing parameters, represents the average value of Y, Y represents the frequency of occurrence of the target defect, n is the number of parameter data corresponding to an influencing parameter, and k is the sequence number.

[0018] In a possible implementation, determining at least one first target influencing parameter causing a target defect in the cast billet based on the multiple target Pearson correlation coefficients includes:

[0019] If the absolute value of any one of the multiple target Pearson correlation coefficients is not 0, it means that the influencing parameter corresponding to the target Pearson correlation coefficient is at least one first target influencing parameter that causes the target defect in the cast billet.

[0020] In a possible implementation, after determining the second target impact parameter according to the P value, the method further includes:

[0021] The production stage at which the target defect occurs in the cast billet is determined according to the second target influencing parameter.

[0022] In a possible implementation, the target defect is a peeling defect.

[0023] In a possible implementation, determining the density of the cast slab in which the target defect occurs within the first target data range of the second target influencing parameter includes:

[0024] The target parameter data of the second target influencing parameter corresponding to each billet is input into the origin software, and the density of the billet with target defects within the first target data range is output, and the target parameter data is within the first target data range.

[0025] In a second aspect, an embodiment of the present invention provides a device for analyzing quality defects of a casting, comprising:

[0026] A data acquisition module is used to acquire a variety of target data, wherein the multiple target data are parameter data corresponding to a plurality of influencing parameters in the continuous casting production process of the slab, wherein the influencing parameters are parameters that cause target defects in the slab;

[0027] A coefficient determination module is used to determine a plurality of target Pearson correlation coefficients, wherein the plurality of target Pearson correlation coefficients are Pearson correlation coefficients between a target data and a target defect occurrence frequency corresponding to each influencing parameter;

[0028] A first parameter determination module is configured to determine at least one first target influencing parameter causing a target defect in the cast billet based on the multiple target Pearson correlation coefficients;

[0029] A P-value determination module, configured to determine a P-value, wherein the P-value is used to represent a significance level of a correlation between any one of the at least one first target influencing parameter and the target defect;

[0030] a second parameter determination module, configured to determine a second target influencing parameter according to the P value, where the second target influencing parameter is the first target influencing parameter corresponding to the P value being less than the first preset threshold;

[0031] a density determination module, configured to determine the density of the ingot with the target defect occurring within the first target data range of the second target influencing parameter;

[0032] The target data range determination module is used to determine a second target data range according to the density situation, where the second target data range is used to indicate that the density of the ingot with the target defect within the second target data range is greater than a second preset threshold.

[0033] In a third aspect, an embodiment of the present invention provides an electronic device, including:

[0034] A memory and a processor, wherein the processor and the memory communicate with each other via a bus; the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the method described in the first aspect and each step in various possible implementations.

[0035] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect and each step in various possible implementations.

[0036] In a fifth aspect, an embodiment of the present invention provides a computer program product comprising instructions, which, when run on a computer, enables the computer to execute the various steps in the method and various possible implementations described in the first aspect.

[0037] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention are: by determining the Pearson correlation coefficient between the parameter data corresponding to multiple influencing parameters in the continuous casting production process of the ingot and the frequency of occurrence of the target defect, at least one first target influencing parameter that causes the target defect can be identified more accurately; according to the P value, the second target influencing parameter is determined, and the second target influencing parameter is the first target influencing parameter corresponding to the P value less than the first preset threshold; by inputting the target parameter data of the second target influencing parameter corresponding to each ingot into the origin software, the density of the ingot in which the target defect occurs within the first target data range of the second target influencing parameter can be determined more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 A diagram of a system architecture applicable to an embodiment of the present invention;

[0039] Figure 2 A schematic flow chart of a method for analyzing quality defects of a casting blank provided by an embodiment of the present invention;

[0040] Figure 3 A schematic diagram of the absolute value and P value of the target Pearson correlation coefficient of target data and target defect occurrence frequency corresponding to each influencing parameter provided in an embodiment of the present invention;

[0041] Figure 4 A schematic diagram showing the relationship between the change in the temperature difference between the inlet and outlet water of the crystallizer during the continuous casting production process of the slab provided by an embodiment of the present invention and the density of the slab having target defects during the continuous casting production process;

[0042] Figure 5 A schematic block diagram of a device for analyzing quality defects of a casting blank provided by an embodiment of the present invention;

[0043] Figure 6 A schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0045] The terms used in the embodiments of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The singular forms "a", "an", "the" and "the" used in the embodiments of the present invention and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise.

[0046] It should be understood that the term "and / or" as used herein is merely a description of the relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the associated objects are in an "or" relationship.

[0047] The word "if," as used herein, may be interpreted as "at the time of" or "when" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if monitoring (stated condition or event)" may be interpreted as "when it is determined" or "in response to determining" or "when detecting (stated condition or event)" or "in response to detecting (stated condition or event)," depending on the context.

[0048] During the continuous casting process, quality defects can occur in products such as ingots, due to operational errors, inappropriate process parameters, or equipment malfunctions. However, because this long production process involves multiple stages, such as smelting, heating, hot rolling, and solutionizing, pinpointing the cause of defects remains a crucial challenge. Furthermore, once the cause of a defect has been determined, more precisely exploring the relationship between the defect cause and ingot quality remains a significant challenge in current production.

[0049] In view of this, the embodiment of the present invention provides a new idea. In order to facilitate the understanding of the present application, the system architecture applicable to the embodiment of the present invention is first described. Figure 1 An exemplary system architecture to which embodiments of the present invention may be applied is shown. Figure 1 As shown in , the system architecture may include a terminal device and a casting quality defect analysis device located on the server side.

[0050] The ingot quality defect analysis device can use the ingot quality defect analysis method provided in the embodiment of the present invention to perform ingot quality defect analysis.

[0051] As one possible implementation, a slab quality defect analysis device can be installed on a server. Users upload various target data to the server via a terminal device. These target data are parameter data corresponding to various influencing parameters during the continuous casting process. These influencing parameters are parameters that cause the target defects in the slab. Then, the ingot quality defect analysis device adopts the ingot quality defect analysis method provided by the embodiment of the present invention to obtain a variety of target data; determine multiple target Pearson correlation coefficients, which are Pearson correlation coefficients of a target data corresponding to each influencing parameter and the frequency of occurrence of the target defect; determine at least one first target influencing parameter that causes the target defect in the ingot based on the multiple target Pearson correlation coefficients; determine the P value, which is used to characterize the significance level of the correlation between any one of the at least one first target influencing parameter and the target defect; determine the second target influencing parameter based on the P value, which is the first target influencing parameter corresponding to the P value that is less than the first preset threshold; determine the density of the ingot with the target defect within the first target data range of the second target influencing parameter; determine the second target data range based on the density, which is used to characterize that the density of the ingot with the target defect within the second target data range is greater than the second preset threshold. Wherein, the ingot quality defect analysis device and the terminal device can interact through the network, Figure 1 The illustrated system illustrates this implementation.

[0052] The above-mentioned casting quality defect analysis device can be set up in a single server, or in a server group consisting of multiple servers, or in a cloud server. A cloud server, also known as a cloud computing server or cloud host, is a host product in the cloud computing service system to solve the defects of difficult management and weak service scalability in traditional physical hosts and virtual private servers (VPS). Figure 1 In addition to the shown architecture, the ingot quality defect analysis device can also be set on a computer terminal with strong computing power.

[0053] Terminal devices may include, but are not limited to, smart mobile terminals, smart home devices, wearable devices, and personal computers (PCs). Smart mobile terminals may include mobile phones, tablets, laptops, PDAs (Personal Digital Assistants), and internet-connected cars. Smart home devices may include smart TVs and smart refrigerators. Wearable devices may include smart watches, smart glasses, virtual reality devices, augmented reality devices, and mixed reality devices (i.e., devices that support both virtual reality and augmented reality).

[0054] Figure 2 A schematic flow chart of a method for analyzing quality defects of a casting provided in an embodiment of the present invention.

[0055] like Figure 2 As shown in , the method may include the following steps:

[0056] Step 201: Acquire a variety of target data, where the multiple target data are parameter data corresponding to a plurality of influencing parameters in the continuous casting production process of the slab, and the influencing parameters are parameters that cause target defects in the slab.

[0057] Step 202: determining a plurality of target Pearson correlation coefficients, where the plurality of target Pearson correlation coefficients are Pearson correlation coefficients between a target data and a target defect occurrence frequency corresponding to each influencing parameter.

[0058] Step 203: Determine at least one first target influencing parameter that causes a target defect in the cast billet based on the multiple target Pearson correlation coefficients.

[0059] Step 204: Determine a P value, where the P value is used to represent the significance level of the correlation between any one of the at least one first target influencing parameter and the target defect.

[0060] Step 205: Determine a second target impact parameter according to the P value, where the second target impact parameter is the first target impact parameter corresponding to the P value that is smaller than the first preset threshold.

[0061] Step 206: Determine the density of the slab in which the target defect occurs under the first target data range of the second target influencing parameter.

[0062] Step 207: Determine a second target data range based on the density condition, where the second target data range is used to indicate that the density of the ingot with the target defect occurring within the second target data range is greater than a second preset threshold.

[0063] First, the above step 201, i.e., "obtaining a variety of target data, where the multiple target data are parameter data corresponding to a plurality of influencing parameters in the continuous casting production process of the ingot, and the influencing parameters are parameters that cause target defects in the ingot" is described in detail in combination with an embodiment of the present invention.

[0064] First, it should be noted that before executing step 201, multiple target data are collected. This multiple target data is parameter data corresponding to multiple influencing parameters during the continuous casting process. The influencing parameters are parameters that cause the target defects in the cast slab. For example, the multiple influencing parameters may include steel grade composition, smelting process, continuous casting parameters, etc. In the embodiments of this application, the multiple influencing parameters are not specifically limited.

[0065] Secondly, it should be noted that after collecting the various target data, the various target data are uploaded to the server side via the terminal device. The ingot quality defect analysis device obtains the various target data from the server side.

[0066] The above step 202, i.e., "determining a plurality of target Pearson correlation coefficients, where the plurality of target Pearson correlation coefficients are Pearson correlation coefficients between a target data corresponding to each influencing parameter and the occurrence frequency of a target defect" is described in detail below in conjunction with an embodiment of the present invention.

[0067] First, it's important to note that the Pearson correlation coefficient, also known as the Pearson product matrix correlation coefficient, is a commonly used statistical metric to quantitatively measure the degree of correlation between two different random variables. The Pearson correlation coefficient is calculated by taking the quotient of the covariance and standard deviation between the two variables. The covariance indicates whether the two variables have consistent trends, while the standard deviation measures the degree of dispersion of the variables. The Pearson correlation coefficient ranges from -1 to 1, with larger absolute values ​​indicating a higher degree of correlation between the two random variables.

[0068] In an embodiment of the present invention, data cleaning is performed on multiple target data to eliminate incomplete or abnormal data. At the same time, in order to avoid the influence of different dimensions between each target data in any target data, each target data is normalized separately. The Max-Min normalization method is selected and the multiple target data after screening are normalized separately to the range [0, 1]. The standard formula is as follows:

[0069]

[0070] Where: X i and are the values ​​of each target data in any target data before and after normalization; X max and X min are the maximum and minimum values ​​of any target data respectively.

[0071] In the embodiment of the present invention, assume that two independent random variables are X and Y, X represents the normalized data of parameter data corresponding to any one of a plurality of influencing parameters, and Y represents the frequency of occurrence of the target defect, then the covariance Cov(X,Y)=E{[XE(X)][YE(Y)]}, represents the average of X, Represents the average value of Y, n is the number of parameter data corresponding to an influencing parameter, and k is the sequence number. The Pearson correlation coefficient γ of multiple targets is determined by the following formula XY :

[0072]

[0073] If the value of the target Pearson correlation coefficient is greater than 0, it reflects a positive correlation between variables X and Y; if the value of the target Pearson correlation coefficient is equal to 0, it indicates that there is no correlation between variables X and Y; if the value of the target Pearson correlation coefficient is less than 0, it reflects a negative correlation between variables X and Y. The larger the absolute value of the numerical value, the stronger the correlation. Therefore, the embodiment of the present invention uses the Pearson correlation coefficient to measure the correlation between the target defect occurrence frequency (i.e., Y) and the normalized data corresponding to any one of the multiple influencing parameters (i.e., ) between them.

[0074] Illustratively, the target defect may be a peeling defect.

[0075] The above step 203, i.e., "determining at least one first target influencing parameter causing target defects in the cast billet based on multiple target Pearson correlation coefficients," is described in detail below in conjunction with an embodiment of the present invention.

[0076] In an embodiment of the present invention, at least one first target influencing parameter that causes a target defect in the billet is determined based on a plurality of target Pearson correlation coefficients. Specifically, if the absolute value of any one of the plurality of target Pearson correlation coefficients is not 0, it indicates that the influencing parameter corresponding to the target Pearson correlation coefficient is the first target influencing parameter that causes a target defect in the billet. If the value of the target Pearson correlation coefficient is greater than 0, a positive correlation is determined between the influencing parameter corresponding to the target Pearson correlation coefficient and the target defect; if the value of the target Pearson correlation coefficient is equal to 0, it indicates that there is no correlation between the influencing parameter corresponding to the target Pearson correlation coefficient and the target defect; if the value of the target Pearson correlation coefficient is less than 0, it reflects a negative correlation between the influencing parameter corresponding to the target Pearson correlation coefficient and the target defect. The larger the absolute value of the target Pearson correlation coefficient, the stronger the correlation. For example, if Figure 3 As shown, the first target impact parameter can be Figure 3The horizontal axis shows the impact parameters of each target.

[0077] The above step 204, i.e., "determining a P value, where the P value is used to characterize the significance level of the correlation between any one of the at least one first target influencing parameter and the target defect," is described in detail below in conjunction with an embodiment of the present invention.

[0078] In the embodiment of the present invention, the significance level must be discussed when discussing whether two variables X and Y are correlated. The correlation between the two may be caused by accidental factors, so the significance level of the correlation between variables X and Y needs to be judged, that is, the significance level of the correlation between variables X and Y needs to be judged based on the P value.

[0079] In an embodiment of the present invention, a P value is determined, where the P value is used to characterize the significance level of the correlation between any one of the at least one first target influencing parameter and the target defect.

[0080] For example, Figure 3 The absolute value and P value of the target Pearson correlation coefficient between the target data and the target defect occurrence frequency corresponding to each influencing parameter are shown.

[0081] The above step 205, i.e., "determining a second target influence parameter according to the P value, where the second target influence parameter is the first target influence parameter corresponding to the P value that is smaller than the first preset threshold," is described in detail below in conjunction with an embodiment of the present invention.

[0082] In the embodiment of the present invention, the second target impact parameter is determined according to the P value.

[0083] In an embodiment of the present invention, a first preset threshold is set and the P value is compared with the first preset threshold to determine a second target impact parameter. The second target impact parameter is the first target impact parameter corresponding to a P value less than the first preset threshold.

[0084] For example, Figure 3 As shown, the first preset threshold is 0.01. Figure 3 It can be seen that the temperature difference between the inlet and outlet water of the crystallizer (including the temperature difference between the inner and outer arcs and the temperature difference between the left and right arcs) has the highest correlation with the target defect. That is, the temperature difference between the inlet and outlet water of the crystallizer during continuous casting production has a high production correlation with the target defect, and its corresponding significance P value is less than 0.01, indicating that it is significantly significant.

[0085] It should be noted that after determining the second target influencing parameter, the production stage at which the target defect appears in the billet is determined based on the second target influencing parameter. Figure 3It can be determined that the temperature difference between the inlet and outlet water of the crystallizer has the highest correlation with the target defect, and its corresponding significance P value is less than 0.01, indicating that it is significantly significant. Therefore, it can be determined that the production stage where the target defect occurs in the casting is the crystallizer stage.

[0086] The above step 206, i.e., "determining the density of the cast billet with the target defect within the first target data range of the second target influencing parameter" is described in detail below in conjunction with an embodiment of the present invention.

[0087] In an embodiment of the present invention, the density of the slab in which the target defect occurs is determined within the first target data range of the second target influencing parameter.

[0088] It should be noted that a dot density map is a graph used to display data distribution. Compared with a histogram, a dot density map can show the distribution of data more smoothly, especially when the amount of data is large or the distribution is relatively continuous.

[0089] In the embodiment of the present invention, Figure 4 As shown, the first target data range is 5.2°C-8.0°C on the vertical axis. Figure 4 The figure shows the change of the temperature difference between the inlet and outlet water of the crystallizer during the continuous casting process. 3 / h, inner and outer arc water inflow 180m 3 / h), by taking advantage of the point density diagram, the change of the temperature difference between the inlet and outlet water of the crystallizer with production is more intuitively displayed. Figure 4 The vertical axis is the temperature difference between the inlet and outlet water of the crystallizer, and the horizontal axis is the casting sequence of the continuous casting production process. Figure 4 Each point in the figure represents a corresponding billet in the billet continuous casting process. Figure 4 The closer the color of the midpoint is to red, the higher the density of the casting billet at this point is. Figure 4 A red star in the image represents a slab with a target defect during continuous casting. However, sometimes the red stars overlap and stack up.

[0090] The above step 207, i.e., "determining a second target data range based on the density, wherein the second target data range is used to characterize that the density of the ingot having the target defect within the second target data range is greater than a second preset threshold," is described in detail below in conjunction with an embodiment of the present invention.

[0091] In an embodiment of the present invention, a second target data range is determined based on the density condition, and the second target data range is used to indicate that the density of the ingot with the target defect occurring within the second target data range is greater than a second preset threshold.

[0092] For example, taking the target defect as a peeling defect, as Figure 4 As shown in the figure, the second target data range determined according to the density is 5.2℃-6.25℃. When the temperature difference between the inlet and outlet water of the crystallizer is small (<6.25℃), Figure 4 A large number of red stars means that the density of the billet with target defects within the second target data range is greater than the second preset threshold. From the perspective of heat transfer in the crystallizer, it can be concluded that under the conditions of constant water volume (water flow rate) and inlet water temperature, the smaller the temperature difference between the inlet and outlet water of the crystallizer, the smaller the amount of heat removed from the crystallizer by the cooling water of the crystallizer. The crystallizer is a key stage in the formation of the primary shell of the billet. The reduction in heat removed means that the solidification of the primary shell is weakened, the thickness of the primary shell is reduced, and it is more fragile. In the subsequent process, the ability of the billet to offset gravity is weakened, which can easily cause cracks in the billet, and then evolve into surface defects of the billet.

[0093] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention are: by determining the Pearson correlation coefficient between the parameter data corresponding to multiple influencing parameters in the continuous casting production process of the ingot and the frequency of occurrence of the target defect, at least one first target influencing parameter that causes the target defect can be identified more accurately; according to the P value, the second target influencing parameter is determined, and the second target influencing parameter is the first target influencing parameter corresponding to the P value less than the first preset threshold; by inputting the target parameter data of the second target influencing parameter corresponding to each ingot into the origin software, the density of the ingot in which the target defect occurs within the first target data range of the second target influencing parameter can be determined more accurately.

[0094] According to an embodiment of another aspect, a device for analyzing quality defects of a casting is provided. Figure 5 FIG. 1 is a schematic block diagram of a device for analyzing quality defects of a casting according to an embodiment of the present invention. Figure 5 As shown, the apparatus 500 may include: a data acquisition module 501, a coefficient determination module 502, a first parameter determination module 503, a P value determination module 504, a second parameter determination module 505, a density determination module 506, and a target data range determination module 507. The main functions of each component module are as follows:

[0095] The data acquisition module 501 is used to acquire a variety of target data, wherein the multiple target data are parameter data corresponding to a plurality of influencing parameters in the continuous casting production process of the slab, wherein the influencing parameters are parameters that cause target defects in the slab;

[0096] The coefficient determination module 502 is used to determine a plurality of target Pearson correlation coefficients, where the plurality of target Pearson correlation coefficients are Pearson correlation coefficients between a target data and a target defect occurrence frequency corresponding to each influencing parameter;

[0097] The first parameter determination module 503 is configured to determine at least one first target influencing parameter that causes a target defect in the cast billet based on the multiple target Pearson correlation coefficients;

[0098] The P-value determination module 504 is used to determine a P-value, where the P-value is used to represent the significance level of the correlation between any one of the at least one first target influencing parameter and the target defect;

[0099] The second parameter determination module 505 is configured to determine a second target influencing parameter according to the P value, where the second target influencing parameter is the first target influencing parameter corresponding to the P value that is less than the first preset threshold;

[0100] The density determination module 506 is used to determine the density of the ingot with the target defect within the first target data range of the second target influencing parameter;

[0101] The target data range determination module 507 is used to determine a second target data range according to the density situation, where the second target data range is used to indicate that the density of the ingot with the target defect within the second target data range is greater than a second preset threshold.

[0102] In a possible implementation, the apparatus 500 further includes a normalization processing module configured to perform normalization processing on the multiple target data respectively to obtain multiple normalized data.

[0103] In a possible implementation, the coefficient determination module 502 is specifically configured to determine multiple target Pearson correlation coefficients using the following formula:

[0104]

[0105] Among them, Cov(X,Y)=E{[XE(X)][YE(Y)]}, represents the average value of X, X represents the normalized data of the parameter data corresponding to any one of the multiple influencing parameters, represents the average value of Y, Y represents the frequency of occurrence of the target defect, n is the number of parameter data corresponding to an influencing parameter, and k is the sequence number.

[0106] In one possible implementation, the first parameter determination module 503 is specifically used to determine that if the absolute value of any target Pearson correlation coefficient among the multiple target Pearson correlation coefficients is not 0, it indicates that the influencing parameter corresponding to the target Pearson correlation coefficient is at least one first target influencing parameter that causes the target defect in the billet.

[0107] In a possible implementation, the device 500 further includes a production stage determination module, configured to determine the production stage in which the target defect of the cast billet occurs according to the second target influencing parameter.

[0108] In a possible implementation, the target defect is a peeling defect.

[0109] In one possible implementation, the density determination module 506 is specifically used to input the target parameter data of the second target influencing parameter corresponding to each ingot into the origin software, and output the density of the ingot with target defects within the first target data range, and the target parameter data is within the first target data range.

[0110] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple. For the relevant parts, refer to the partial description of the method embodiment. The device embodiment described above is only exemplary, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without making any creative efforts.

[0111] In addition, an embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of any one of the methods in the aforementioned method embodiments are implemented.

[0112] And an electronic device comprising:

[0113] one or more processors; and

[0114] A memory associated with the one or more processors, the memory being used to store program instructions, wherein the program instructions, when read and executed by the one or more processors, execute the steps of any one of the method embodiments described above.

[0115] An embodiment of the present invention further provides a computer program product, comprising a computer program, which implements the steps of any one of the methods described in the aforementioned method embodiments when executed by a processor.

[0116] in, Figure 6The electronic device architecture is shown as an example, and may include a processor 610, a video display adapter 611, a disk drive 612, an input / output interface 613, a network interface 614, and a memory 620. The processor 610, the video display adapter 611, the disk drive 612, the input / output interface 613, the network interface 614, and the memory 620 may be communicatively connected via a communication bus 630.

[0117] The processor 610 may be implemented as a general-purpose CPU, a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and may be used to execute relevant programs to implement the technical solutions provided by the embodiments of the present invention.

[0118] The memory 620 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 620 can store an operating system 621 for controlling the operation of the electronic device 600 and a basic input and output system (BIOS) 622 for controlling the low-level operations of the electronic device 600. In addition, a web browser 623, a data storage management system 624, and a casting quality defect analysis device 625 can also be stored. The casting quality defect analysis device 625 can be an application program that specifically implements the operations of the aforementioned steps in the embodiment of the present invention. In short, when the technical solution provided by the embodiment of the present invention is implemented by software or firmware, the relevant program code is stored in the memory 620 and is called and executed by the processor 610.

[0119] The input / output interface 613 is used to connect to an input / output module to implement information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. Among them, input devices may include a keyboard, mouse, touch screen, microphone, various sensors, etc., and output devices may include a display, speaker, vibrator, indicator light, etc.

[0120] The network interface 614 is used to connect to a communication module (not shown) to enable communication between the device and other devices. The communication module can communicate via a wired method (such as USB, network cable, etc.) or a wireless method (such as mobile network, WiFi, Bluetooth, etc.).

[0121] The bus 630 comprises a pathway for transmitting information between the various components of the device (eg, the processor 610 , the video display adapter 611 , the disk drive 612 , the input / output interface 613 , the network interface 614 , and the memory 620 ).

[0122] It should be noted that although the above device only shows a processor 610, a video display adapter 611, a disk drive 612, an input / output interface 613, a network interface 614, a memory 620, a bus 630, etc., in a specific implementation, the device may also include other components necessary for normal operation. In addition, it will be understood by those skilled in the art that the above device may also include only the components necessary to implement the solution of the present application, and does not necessarily include all the components shown in the figure.

[0123] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0124] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of the present invention, rather than to limit them. Although the embodiments of the present invention have been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for analyzing quality defects of a casting, characterized in that: include: Acquiring a plurality of target data, wherein the plurality of target data are parameter data corresponding to a plurality of influencing parameters in a continuous casting production process of the slab, wherein the influencing parameters are parameters causing target defects in the slab; Determine a plurality of target Pearson correlation coefficients, wherein the plurality of target Pearson correlation coefficients are Pearson correlation coefficients between a target data corresponding to each influencing parameter and a target defect occurrence frequency; determining, based on the multiple target Pearson correlation coefficients, at least one first target influencing parameter that causes a target defect in the cast slab; Determining a P value, where the P value is used to represent a significance level of a correlation between any one of the at least one first target influencing parameter and the target defect; Determining a second target influencing parameter according to the P value, where the second target influencing parameter is the first target influencing parameter corresponding to the P value that is less than the first preset threshold; determining a density of a cast slab in which a target defect occurs within a first target data range of the second target influencing parameter; According to the density situation, a second target data range is determined, where the second target data range is used to indicate that the density of the ingot with the target defect occurring within the second target data range is greater than a second preset threshold.

2. The method according to claim 1, characterized in that After acquiring the multiple target data, the method further includes: Normalization processing is performed on the multiple target data respectively to obtain multiple normalized data.

3. The method according to claim 2, characterized in that The determining of multiple target Pearson correlation coefficients includes: The Pearson correlation coefficient for multiple targets is determined by the following formula: Among them, Cov(X,Y)=E{[XE(X)][YE(Y)]}, represents the average value of X, X represents the normalized data of the parameter data corresponding to any one of the multiple influencing parameters, represents the average value of Y, Y represents the frequency of occurrence of the target defect, n is the number of parameter data corresponding to an influencing parameter, and k is the sequence number.

4. The method according to any one of claims 1 to 3, characterized in that Determining at least one first target influencing parameter causing a target defect in the cast billet based on the multiple target Pearson correlation coefficients includes: If the absolute value of any one of the multiple target Pearson correlation coefficients is not 0, it means that the influencing parameter corresponding to the target Pearson correlation coefficient is at least one first target influencing parameter that causes the target defect in the cast billet.

5. The method according to any one of claims 1 to 3, characterized in that After determining the second target influencing parameter according to the P value, the method further includes: The production stage at which the target defect occurs in the cast billet is determined according to the second target influencing parameter.

6. The method according to any one of claims 1 to 3, characterized in that The target defect is a peeling defect.

7. The method according to any one of claims 1 to 3, characterized in that The determining of the density of the cast slab in which the target defect occurs under the first target data range of the second target influencing parameter includes: The target parameter data of the second target influencing parameter corresponding to each billet is input into the origin software, and the density of the billet with target defects within the first target data range is output, and the target parameter data is within the first target data range.

8. A device for analyzing quality defects of a casting, characterized in that: include: A data acquisition module is used to acquire a variety of target data, wherein the multiple target data are parameter data corresponding to a plurality of influencing parameters in the continuous casting production process of the slab, wherein the influencing parameters are parameters that cause target defects in the slab; A coefficient determination module is used to determine a plurality of target Pearson correlation coefficients, wherein the plurality of target Pearson correlation coefficients are Pearson correlation coefficients between a target data and a target defect occurrence frequency corresponding to each influencing parameter; A first parameter determination module is configured to determine at least one first target influencing parameter causing a target defect in the cast billet based on the multiple target Pearson correlation coefficients; A P-value determination module, configured to determine a P-value, wherein the P-value is used to represent a significance level of a correlation between any one of the at least one first target influencing parameter and the target defect; a second parameter determination module, configured to determine a second target influencing parameter according to the P value, where the second target influencing parameter is the first target influencing parameter corresponding to the P value being less than the first preset threshold; a density determination module, configured to determine the density of the ingot with the target defect occurring within the first target data range of the second target influencing parameter; The target data range determination module is used to determine a second target data range according to the density situation, where the second target data range is used to indicate that the density of the ingot with the target defect within the second target data range is greater than a second preset threshold.

9. An electronic device, characterized in that: include: A memory and a processor, wherein the processor and the memory communicate with each other via a bus; The memory stores program instructions that can be executed by the processor, and the processor can execute the method according to any one of claims 1 to 7 by calling the program instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images