Shrinkage defect prediction method and system for casting side plate casting

Abstract

The invention relates to the technical field of shrinkage defect prediction, in particular to a shrinkage defect prediction method and system for side plate casting casting, and the method comprises the steps: obtaining a temperature drop stable value and a color distribution non-uniform value through the temperature of a thin-wall region in an infrared image, obtaining a shrinkage defect expression evaluation value, and determining a shrinkage defect region; obtaining the temperature of the shrinkage defect area in the infrared image obtained at each moment to form a temperature-moment curve, obtaining a bubble-caused index value according to the temperature-moment curve, and determining a bubble shrinkage defect area; obtaining the coordinates of the to-be-corrected bubble at the next moment according to the bubble moving trend curve; the metal liquid flowing speed of the bubble shrinkage defect area in each infrared image is obtained, and then a metal liquid flowing evaluation value is obtained; and correcting the to-be-corrected bubble coordinate according to the metal liquid flow evaluation value to obtain a corrected bubble coordinate. According to the invention, accurate prediction of the position of the bubble at the next moment can be realized.

Description

Technical Field

[0001] The present invention relates to the technical field of prediction of shrinkage porosity defects, and particularly to a method and system for predicting shrinkage porosity defects in the casting of side plate castings. Background Art

[0002] Side plate castings, as a common and critical casting component, are widely used in multiple fields such as automobile manufacturing, shipbuilding, and construction machinery, and thus have extremely strict quality requirements. Shrinkage porosity defects, as frequent quality problems in the casting process, are characterized by pores and cavities formed inside or on the surface of the casting. This phenomenon usually appears during the solidification stage of the molten metal. Due to the molten metal not fully filling the mold cavity or the temperature gradient being too large during cooling, uneven shrinkage of the metal occurs. Especially in thin-wall regions, due to significant differences in heat conduction and slow temperature recovery, shrinkage porosity defects are prone to be induced. The complex geometric structure of the casting often leads to uneven wall thickness, and the thin-wall regions, where the molten metal is not replenished in time and the shrinkage phenomenon is more significant, become high-incidence areas of shrinkage porosity defects. In addition, during the casting process, the release of gas or the escape of dissolved gas in the molten metal forms bubbles. These bubbles may not only change the fluidity of the molten metal, especially in the thin-wall parts of the casting, but also interfere with the filling process of the metal, causing local insufficient metal filling, further promoting the formation of thin-wall defects or other types of defects, and may exacerbate the defect degree in these regions. The challenge faced by the current technology is that it is difficult to accurately distinguish shrinkage porosity defects caused by the inherent characteristics of the thin-wall regions of the casting from similar defects caused by bubbles, thereby affecting the accuracy of predicting shrinkage porosity defects during the casting process of side plate castings. Summary of the Invention

[0003] In order to solve the technical problem of inaccurate prediction of shrinkage porosity defects during the casting process of side plate castings, the purpose of the present invention is to provide a method for predicting shrinkage porosity defects in the casting of side plate castings, and the specific technical solutions adopted are as follows: Obtain infrared images during the casting process of a preset first number of side plate castings, and distinguish the thick-wall regions and thin-wall regions in the infrared images; Obtain the stable temperature drop value and the uneven color distribution value through the temperature of the thin-wall region, and obtain the evaluation value of the shrinkage porosity defect manifestation according to the stable temperature drop value and the uneven color distribution value. When the evaluation value of the shrinkage porosity defect manifestation is not less than the preset evaluation threshold of the shrinkage porosity defect manifestation, the thin-wall region is regarded as the shrinkage porosity defect region, where the temperature of the thin-wall region is the average value of the temperatures corresponding to each pixel point in the thin-wall region; Obtain the temperatures of the shrinkage porosity defect regions in the infrared images obtained at each moment to form a temperature-time curve, and obtain the bubble-induced index value of the shrinkage porosity defect region according to the temperature-time curve. When the bubble-induced index value is not less than the preset bubble-induced threshold, the shrinkage porosity defect region is a bubble shrinkage porosity defect region; Establish a rectangular coordinate system with the center point of the infrared image as the coordinate origin, use the center point of the bubble shrinkage porosity defect region as the bubble coordinates, construct a bubble movement trend curve, and obtain the bubble coordinates to be corrected at the next moment according to the bubble movement trend curve; Obtain the metal liquid flow velocity in the bubble shrinkage porosity defect region in each of the infrared images, and obtain the metal liquid flow evaluation value of the bubble shrinkage porosity defect region according to the metal liquid flow velocity; Correct the bubble coordinates to be corrected according to the metal liquid flow evaluation value to obtain the corrected bubble coordinates.

[0004] Further, the distinguishing between the thick-wall region and the thin-wall region in the infrared image includes: Divide the infrared image into a preset second number of regions, obtain the first mean value of the brightness of the i-th region and the second mean value of the brightness of the region adjacent to the i-th region, where the value range of i is from 1 to the second number; Add the first mean value and the second mean value to obtain the sum of the mean values, obtain the absolute value of the difference between the first mean value and the second mean value, and then divide by the sum of the mean values to obtain the spectral absorption evaluation value of the i-th region; When the spectral absorption evaluation value is not less than the preset spectral absorption threshold, the i-th region is the thin-wall region, otherwise the i-th region is the thick-wall region.

[0005] Further, the process of obtaining the temperature drop stability value includes: In each of the infrared images, obtain the temperature of the thin-wall region; Obtain the absolute value of the difference in temperature of the thin-wall region between two adjacent infrared images in time, and obtain the average value of the absolute values as the absolute average value; Calculate the average value of the absolute value of the absolute value minus the absolute average value, and take the reciprocal of the average value to obtain the temperature drop stability value.

[0006] Further, the process of obtaining the color distribution non-uniformity value includes: Calculate the variance of the temperatures corresponding to the pixel points in the thin-wall region as the thin-wall region variance; Divide the thin-wall region variance by the temperature of the thin-wall region to obtain the color distribution non-uniformity value.

[0007] Further, the process of obtaining the evaluation value of the shrinkage porosity defect manifestation includes: Multiply the stable temperature drop value by the normalized value of the uneven color distribution value as the evaluation value of the shrinkage porosity defect manifestation.

[0008] Further, the process of obtaining the index value caused by bubbles includes: Obtain the temperature of the m-th shrinkage porosity defect area when the molten metal starts to fill the mold and the average value of the temperature of the shrinkage porosity defect area, and divide the temperature of the m-th shrinkage porosity defect area by the average value of the temperature of the shrinkage porosity defect area to obtain a temperature ratio; Obtain the curvature at each moment in the temperature-time curve corresponding to the m-th shrinkage porosity defect area, and calculate the average value of the curvature; Calculate the average value of the absolute value of the difference between the curvature at each moment and the average value of the curvature as the curvature difference value; Normalize the temperature ratio after dividing it by the curvature difference value to obtain the index value caused by bubbles.

[0009] Further, the process of obtaining the bubble coordinates to be corrected includes: Obtain the bubble coordinates at the current moment, differentiate the bubble coordinates to obtain the velocity vector of the bubble, and differentiate the velocity vector again to obtain the acceleration vector of the bubble; After obtaining the velocity vector and the acceleration vector, use the Euler method to predict the bubble coordinates to be corrected at the next moment.

[0010] Further, the process of obtaining the evaluation value of the molten metal flow includes: Obtain the molten metal flow velocity in each infrared image of the h-th shrinkage porosity defect area of the bubble, and obtain the average value of the molten metal flow velocity as the average molten metal flow velocity; Calculate the average value of the absolute value of the difference between each molten metal flow velocity and the average molten metal flow velocity as the molten metal flow velocity difference value; Divide the molten metal flow velocity difference value by the average molten metal flow velocity to obtain the evaluation value of the molten metal flow.

[0011] Further, the process of obtaining the corrected bubble coordinates includes: Multiply the evaluation value of the molten metal flow by the bubble coordinates to be corrected as the corrected bubble coordinates.

[0012] The embodiment of the present invention also provides a shrinkage porosity defect prediction system for the casting of side plate castings. The system includes: An acquisition module, configured to acquire infrared images during the casting process of a preset first number side plate casting, and distinguish thick-wall regions and thin-wall regions in the infrared images; A shrinkage porosity defect performance evaluation value module, configured to obtain a stable temperature drop value and a non-uniform color distribution value through the temperature of the thin-wall region, and obtain a shrinkage porosity defect performance evaluation value according to the stable temperature drop value and the non-uniform color distribution value. When the shrinkage porosity defect performance evaluation value is not less than a preset shrinkage porosity defect performance evaluation threshold, the thin-wall region is a shrinkage porosity defect region, where the temperature of the thin-wall region is the average value of the temperatures corresponding to each pixel point in the thin-wall region; A bubble-induced index value module, configured to acquire the temperatures of the shrinkage porosity defect regions in the infrared images obtained at each moment to form a temperature-time curve, and obtain a bubble-induced index value of the shrinkage porosity defect regions according to the temperature-time curve. When the bubble-induced index value is not less than a preset bubble-induced threshold, the shrinkage porosity defect region is a bubble shrinkage porosity defect region; A coordinate to be corrected module, configured to establish a rectangular coordinate system with the center point of the infrared image as the coordinate origin, use the center point of the bubble shrinkage porosity defect region as the bubble coordinate, construct a bubble movement trend curve, and obtain the coordinate of the bubble to be corrected at the next moment according to the bubble movement trend curve; A molten metal flow evaluation value module, configured to acquire the molten metal flow velocity in the bubble shrinkage porosity defect regions in each of the infrared images, and obtain a molten metal flow evaluation value of the bubble shrinkage porosity defect regions according to the molten metal flow velocity; A correction module, configured to correct the coordinate of the bubble to be corrected according to the molten metal flow evaluation value to obtain a corrected bubble coordinate.

[0013] The present invention has the following beneficial effects: First, infrared images during the casting process of a preset first number side plate casting are acquired, and thick-wall regions and thin-wall regions in the infrared images are distinguished. The infrared images are the basis for defect detection, and only after the distinction between thick and thin walls can the thin-wall regions be further detected.

[0014] Second, a stable temperature drop value and a non-uniform color distribution value are obtained through the temperature of the thin-wall region, and a shrinkage porosity defect performance evaluation value is obtained according to the stable temperature drop value and the non-uniform color distribution value. When the shrinkage porosity defect performance evaluation value is not less than a preset shrinkage porosity defect performance evaluation threshold, the thin-wall region is a shrinkage porosity defect region, where the temperature of the thin-wall region is the average value of the temperatures corresponding to each pixel point in the thin-wall region. Here, it is to select the shrinkage porosity defect region from the thin-wall region.

[0015] Obtain the temperatures of the shrinkage porosity defect regions in the infrared images obtained at each moment to form a temperature-time curve, and obtain the bubble-induced index value of the shrinkage porosity defect region according to the temperature-time curve. When the bubble-induced index value is not less than the preset bubble-induced threshold value, the shrinkage porosity defect region is a bubble shrinkage porosity defect region. Here, it is to select the bubble shrinkage porosity defect region from the shrinkage porosity defect regions.

[0016] Establish a rectangular coordinate system with the center point of the infrared image as the coordinate origin, take the center point of the bubble shrinkage porosity defect region as the bubble coordinates, construct a bubble movement trend curve, and obtain the bubble coordinates to be corrected at the next moment according to the bubble movement trend curve. The bubble coordinates to be corrected are the preliminary positions of the bubble at the next moment and still need to be corrected.

[0017] Obtain the metal liquid flow velocity of the bubble shrinkage porosity defect region in each of the infrared images, and obtain the metal liquid flow evaluation value of the bubble shrinkage porosity defect region according to the metal liquid flow velocity. The metal liquid flow evaluation value can be used as a correction weight to correct the bubble coordinates to be corrected.

[0018] Correct the bubble coordinates to be corrected according to the metal liquid flow evaluation value to obtain the corrected bubble coordinates. The corrected bubble coordinates are an accurate prediction of the position of the bubble at the next moment, effectively controlling the formation sites of defects, thereby optimizing the casting process, significantly reducing or even eliminating the shrinkage porosity region, preventing bubbles from accumulating at key positions, and thus greatly improving the overall quality of the casting. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 It is a flowchart of a shrinkage porosity defect prediction method for side plate casting provided by the first embodiment of the present invention; Figure 2 It is a flowchart of distinguishing the thick-wall region and the thin-wall region in the infrared image provided by the second embodiment of the present invention; Figure 3 It is a flowchart of the acquisition process of the temperature drop stability value provided by the third embodiment of the present invention; Figure 4 It is a flowchart of the acquisition process of the color distribution unevenness value provided by the fourth embodiment of the present invention; Figure 5 It is a flowchart of the process for obtaining the index value caused by bubbles provided in the fifth embodiment of the present invention; Figure 6 It is a flowchart of the process for obtaining the coordinates of bubbles to be corrected provided in the sixth embodiment of the present invention; Figure 7 It is a flowchart of the process for obtaining the evaluation value of the flow of molten metal provided in the seventh embodiment of the present invention; Figure 8 It is a schematic diagram of a shrinkage cavity defect prediction system for side plate casting provided in the eighth embodiment of the present invention. Detailed Embodiments

[0021] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific embodiments, structures, features, and effects of the shrinkage cavity defect prediction method and system for side plate casting proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0023] It should be noted that to ensure the significance of the calculation results, in the fractional operations in the embodiments of the present invention, when encountering the situation where the denominator is 0, a tuning factor greater than 0 needs to be added to the denominator to prevent the denominator from being 0. The value of the tuning factor is set by the implementer according to the actual situation, and this application does not make special restrictions.

[0024] The following specifically describes the specific solution of the shrinkage cavity defect prediction method for side plate casting provided by the present invention with reference to the accompanying drawings.

[0025] Please refer to Figure 1 , which shows a flowchart of the shrinkage cavity defect prediction method for side plate casting provided in the first embodiment of the present invention. The method includes: S101. Obtain an infrared image during the casting process of a preset first number of side plate castings, and distinguish the thick-walled area and the thin-walled area in the infrared image.

[0026] Using an infrared thermal imager, take an infrared image of the side plate casting every preset time interval, such as 1 second, to obtain the first number of infrared images of the casting from the liquid state to the current moment of shooting.

[0027] The infrared image can capture the critical moments of temperature changes in the casting, such as during the solidification process, in areas with uneven cooling, or at the moment of temperature difference occurrence. The infrared image usually represents temperature in color (or grayscale), with hot parts appearing red or white and cold parts appearing blue or black.

[0028] The process of distinguishing the thick-wall area and the thin-wall area in the infrared image will be described in detail in the second embodiment and will not be elaborated here.

[0029] S102. Obtain the stable value of temperature drop and the uneven value of color distribution through the temperature of the thin-wall area. Obtain the evaluation value of the shrinkage porosity defect manifestation according to the stable value of temperature drop and the uneven value of color distribution. When the evaluation value of the shrinkage porosity defect manifestation is not less than the preset evaluation threshold of the shrinkage porosity defect manifestation, the thin-wall area is the shrinkage porosity defect area, where the temperature of the thin-wall area is the average value of the temperatures corresponding to each pixel point in the thin-wall area.

[0030] Shrinkage porosity defect is a common defect in the side plate casting where, during the solidification process, due to the shrinkage of the molten metal and failure to completely fill the mold cavity, voids or pores are formed inside or on the surface of the casting. The geometric structure of the casting results in inconsistent wall thickness. In the thin-wall area of the casting, due to its smaller mass and larger surface area, heat dissipates rapidly, and the cooling rate is relatively fast, causing the molten metal in this area to start solidifying earlier and the temperature gradient to increase. In the thick-wall area, due to its larger mass and smaller surface area, the cooling rate is relatively slow, less heat is dissipated, and the molten metal can remain in a liquid state until a later stage. This difference makes it likely that the thin-wall area solidifies earlier before the thick-wall area has completely solidified. This asynchronous solidification process causes the molten metal to be unable to timely compensate for the volume loss in the thin-wall area, thus forming voids or pores. These voids are usually called shrinkage porosity defects, which not only affect the mechanical properties of the casting but may also have an adverse impact on the appearance and service life of the product.

[0031] The process of obtaining the stable value of temperature drop will be described in detail in the third embodiment and will not be elaborated here.

[0032] The process of obtaining the uneven value of color distribution will be described in detail in the fourth embodiment and will not be elaborated here.

[0033] The preset evaluation threshold of the shrinkage porosity defect manifestation can be set independently, preferably 0.5.

[0034] When the temperature drop in the thin-wall area during the casting process is more unstable and the color distribution of the hot spots in the current infrared image of the thin-wall area is more uneven, then it is more likely that the thin-wall area has shrinkage porosity defects.

[0035] The process of obtaining the evaluation value of the shrinkage porosity defect manifestation includes: Multiply the stable value of the temperature drop by the normalized value of the non-uniform color distribution as the evaluation value of the porosity defect manifestation.

[0036] The evaluation value of the porosity defect manifestation can be expressed as:

[0037] wherein, the represents the evaluation of the porosity defect manifestation of the th thin-wall region, the represents the stable value of the temperature drop corresponding to the th thin-wall region, the represents the non-uniform value of the color distribution corresponding to the th thin-wall region, and the is a normalization function, preferably a range normalization function.

[0038] The The larger the value, the more likely it is that there is a porosity defect in the th thin-wall region.

[0039] S103. Obtain the temperature of the porosity defect region in the infrared images obtained at each moment to form a temperature-time curve, and obtain the bubble-induced index value of the porosity defect region according to the temperature-time curve. When the bubble-induced index value is not less than a preset bubble-induced threshold, the porosity defect region is a bubble porosity defect region.

[0040] During the casting process, bubbles are formed due to the release of gas or the escape of dissolved gas in the molten metal. The presence of bubbles may change the fluidity of the molten metal. Especially in the thinner parts of the casting, bubbles may affect the filling process of the metal, resulting in incomplete local metal filling and exacerbating the porosity defect in the thin-wall region.

[0041] In the molten metal stage, bubbles are formed, and the temperature of the bubble region is relatively low, and the infrared image shows a darker cold region. During the filling process of the molten metal, the bubbles will flow with the molten metal and gradually distribute inside the casting. The heat conduction in the bubble region is blocked, and the temperature is relatively low, showing a more obvious low-temperature region. As the metal gradually solidifies, the bubbles gradually disappear during the cooling process of the molten metal, the temperature gradually rises, and the brightness of the region gradually increases, but this process is relatively slow. On the contrary, the cooling process of the normal porosity defect region is relatively uniform, and the temperature is relatively low. However, due to the absence of bubble interference, the heat conduction is relatively smooth, and it shows a brighter cold region on the infrared image, with a faster temperature rise and more uniform heat conduction.

[0042] Generally speaking, the shrinkage porosity defect area containing bubbles shows a slower temperature rise and a lower temperature during the cooling process. For the normal shrinkage porosity defect area, the temperature rise changes more evenly and the cooling speed is faster.

[0043] Select the th shrinkage porosity defect area, and obtain the average temperature of all pixel points of the th shrinkage porosity defect area at each moment in the captured infrared image, which is the temperature of the th shrinkage porosity defect area. Taking time as the abscissa and the temperature of the shrinkage porosity defect area as the ordinate, a temperature-time curve of the th shrinkage porosity defect area is formed. Among them, the value of m ranges from 1 to the number of shrinkage porosity defect areas.

[0044] The process of obtaining the index value caused by the bubble will be described in detail in the fifth embodiment and will not be elaborated here.

[0045] The preset threshold value caused by the bubble can be set independently, and is preferably 0.5.

[0046] When the index value caused by the bubble of the th shrinkage porosity defect area is greater than or equal to 0.5, mark the th shrinkage porosity defect area as a bubble shrinkage porosity defect area. When the index value caused by the bubble of the th shrinkage porosity defect area is less than 0.5, mark the th shrinkage porosity defect area as a normal shrinkage porosity defect area.

[0047] S104. Taking the center point of the infrared image as the coordinate origin to establish a rectangular coordinate system, taking the center point of the bubble shrinkage porosity defect area as the bubble coordinate, constructing a bubble movement trend curve, and obtaining the bubble coordinate to be corrected at the next moment according to the bubble movement trend curve.

[0048] After determining the bubble shrinkage porosity defect area, during the subsequent process of the gradual solidification of the molten metal, the temperature field changes. Since the density of the metal increases as the temperature decreases, the molten metal in the unfrozen part is more likely to flow. Therefore, when the molten metal flows, the bubble will be driven and move along the flow direction. In order to better control the possible defects during the casting process and ensure the quality of the casting, it is necessary to predict the movement direction of the bubble.

[0049] Due to the short acquisition interval, the bubble in a certain bubble shrinkage porosity defect area in each infrared image may also appear in the next infrared image. For the th bubble shrinkage porosity defect area, obtain the center point of this area as the bubble center point. Taking the center point of each infrared image as the coordinate origin to establish a rectangular coordinate system, the coordinates of each bubble center point, that is, the bubble coordinates, can be obtained. The bubble coordinates of a shrinkage porosity defect area are marked in the established rectangular coordinate system according to the time series, and all the bubble coordinates are connected by a smooth curve to obtain a bubble movement trend curve, denoted as the th bubble movement trend curve. Among them, the value ranges from 1 to the number of shrinkage porosity defect areas.

[0050] The process of obtaining the bubble coordinates to be corrected will be described in detail in the fifth embodiment and will not be elaborated here.

[0051] S105. Obtain the flow velocity of the molten metal in each of the infrared images of the shrinkage porosity defect area, and obtain the molten metal flow evaluation value of the shrinkage porosity defect area according to the flow velocity of the molten metal.

[0052] The process of obtaining the flow velocity of the molten metal is the prior art.

[0053] The process of obtaining the molten metal flow evaluation value will be described in detail in the sixth embodiment and will not be elaborated here.

[0054] S106. Correct the bubble coordinates to be corrected according to the molten metal flow evaluation value to obtain the corrected bubble coordinates.

[0055] The process of obtaining the corrected bubble coordinates includes: The molten metal flow evaluation value is multiplied by the bubble coordinates to be corrected as the corrected bubble coordinates.

[0056] The corrected bubble coordinates can be expressed as:

[0057] Among them, the represents the molten metal flow evaluation value, and the represents the bubble coordinates to be corrected.

[0058] In the infrared image, regions with different thicknesses will exhibit different thermal radiation characteristics due to differences in material distribution and heat conduction, that is, the absorption characteristics of the infrared spectrum will be different. The thick-walled region has more materials and relatively slower heat conduction, so the absorption of the infrared spectrum may be more significant, manifested as a bright area or a high-absorption area in the image. While the thin-walled region has less materials and faster heat conduction, the absorption of the infrared spectrum is relatively weak, manifested as a dark area or a low-absorption area in the image.

[0059] Use threshold segmentation to divide the infrared image into regions, and then distinguish the thick-walled region and the thin-walled region in the infrared image.

[0060] Figure 2 The flowchart for distinguishing the thick-wall region and the thin-wall region in the infrared image provided by the second embodiment of the present invention. The distinguishing of the thick-wall region and the thin-wall region in the infrared image includes: S201. Divide the infrared image into a preset second number of regions, and obtain the first mean value of the brightness of the i-th region and the second mean value of the brightness of the region adjacent to the i-th region, where the value range of i is from 1 to the second number.

[0061] The first mean value of the brightness of the i-th region refers to the mean value of the brightness corresponding to each pixel point in the i-th region.

[0062] S202. Add the first mean value and the second mean value to obtain the sum of the mean values. After obtaining the absolute value of the difference between the first mean value and the second mean value, divide it by the sum of the mean values to obtain the spectral absorption evaluation value of the i-th region.

[0063] The spectral absorption evaluation value of the i-th region can be expressed as:

[0064] where, represents the spectral absorption evaluation value of the i-th region, represents the first mean value, represents the second mean value, represents the absolute value function.

[0065] The The larger the value of, the more the i-th region appears as a dark area in the infrared image, has a relatively weak absorption of the spectrum, and is more likely to belong to the thin-wall region. the i-th

[0066] S203. When the spectral absorption evaluation value is not less than the preset spectral absorption threshold, the i-th region is the thin-wall region; otherwise, the i-th region is the thick-wall region.

[0067] The preset spectral absorption threshold can be set independently, and is preferably 0.3.

[0068] During the casting process, the normal thin-wall region usually has a relatively uniform temperature distribution because the heat conduction in the thin-wall region is relatively fast, the cooling process is uniform, and the temperature drops smoothly. In the thin-wall region with shrinkage porosity defects, since the molten metal fails to completely fill the mold cavity, it may cause the solidification process in this region to be uneven, the cooling speed to be faster or slower, and the temperature to drop unevenly.

[0069] Figure 3The flowchart of the acquisition process of the stable temperature drop value provided by the third embodiment of the present invention. The acquisition process of the stable temperature drop value includes: S301. In each of the infrared images, obtain the temperature of the thin-wall region.

[0070] The temperature of the thin-wall region is the average value of the temperatures corresponding to each pixel point in the thin-wall region.

[0071] S302. Obtain the absolute value of the difference in the temperature of the thin-wall region between two adjacent infrared images in terms of time, and obtain the average value of the absolute values as the absolute average value.

[0072] It can be represented by to represent the absolute value of the temperature of the th thin-wall region in the th infrared image minus the temperature of the th thin-wall region in the infrared image obtained at the previous moment of the th infrared image.

[0073] There are such absolute values.

[0074] S303. Calculate the average value of the absolute value of the absolute value minus the absolute average value, and take the reciprocal of the average value to obtain the stable temperature drop value.

[0075] The stable temperature drop value can be expressed as:

[0076] Among them, the represents the stable temperature drop value corresponding to the th thin-wall region, the represents the absolute average value corresponding to the th thin-wall region, and the represents the average value.

[0077] The larger the value of the average value, it indicates that the temperature fluctuation degree of the th thin-wall region in all infrared images is greater, and then the temperature drop stability is worse.

[0078] The infrared images of the normal region usually do not show significant differences in too high or too low temperatures. The hot spots present a relatively uniform color distribution, that is, the temperature distribution in this region is uniform. The temperature distribution in the shrinkage porosity defect region is uneven, and there may be phenomena of local overheating or overcooling, manifested as bright (high temperature) or dark (low temperature) regions on the infrared image, and the hot spots present an uneven color distribution.

[0079] Figure 4 Flow chart of the process for obtaining the non-uniform color distribution value provided by the fourth embodiment of the present invention. The process for obtaining the non-uniform color distribution value includes: S401. Calculate the variance of the temperatures corresponding to the pixel points in the thin-wall region as the thin-wall region variance.

[0080] The thin-wall region variance corresponding to the th thin-wall region can be represented by

[0081] S402. Divide the thin-wall region variance by the temperature of the thin-wall region to obtain the non-uniform color distribution value.

[0082] The non-uniform color distribution value can be expressed as:

[0083] wherein, the represents the non-uniform color distribution value corresponding to the th thin-wall region, and the represents the temperature of the th thin-wall region.

[0084] The larger the value, the more uneven the temperature distribution in the region, and the non-uniform color distribution of the hot spot appears.

[0085] Figure 5 Flow chart of the process for obtaining the bubble-induced index value provided by the fifth embodiment of the present invention. The process for obtaining the bubble-induced index value includes: S501. Obtain the temperature of the m-th shrinkage porosity defect region when the molten metal starts to fill the mold and the average value of the temperatures of the shrinkage porosity defect regions. Divide the temperature of the m-th shrinkage porosity defect region by the average value of the temperatures of the shrinkage porosity defect regions to obtain the temperature ratio.

[0086] The temperature ratio can be expressed as: , wherein, the represents the average value of the temperatures of the shrinkage porosity defect regions, and the represents the temperature of the m-th shrinkage porosity defect region.

[0087] The larger the value, the lower the temperature of the th shrinkage porosity defect region compared to the temperatures of the other shrinkage porosity defect regions, and the more likely it is that there are bubbles in this region.

[0088] S502. Obtain the curvature at each moment in the temperature-time curve corresponding to the m-th shrinkage porosity defect region, and calculate the average value of the curvature.

[0089] The average value of the curvature corresponding to the m-th shrinkage porosity defect region can be expressed as: .

[0090] S503. Calculate the average value of the absolute value of the difference between the curvature at each moment and the average value of the curvature as the curvature difference value.

[0091] The curvature difference value can be expressed as:

[0092] Among them, the represents the number of moments in the temperature-time curve corresponding to the m-th shrinkage porosity defect region, and the represents the curvature at the n-th moment in the temperature-time curve corresponding to the m-th shrinkage porosity defect region, and the represents the absolute value function.

[0093] The The smaller the value, the flatter the temperature-time curve of the th shrinkage porosity defect region, the slower the temperature rise, and the more likely there are bubbles in this region.

[0094] S504. After dividing the temperature ratio by the curvature difference value, perform normalization to obtain the bubble-induced index value.

[0095] The bubble-induced index value can be expressed as:

[0096] Among them, the represents the bubble-induced index value, and the is a normalization function, preferably a range normalization function.

[0097] Figure 6 This is the flowchart of the process for obtaining the bubble coordinates to be corrected provided in the sixth embodiment of the present invention. The process for obtaining the bubble coordinates to be corrected includes: S601. Obtain the bubble coordinates at the current moment, differentiate the bubble coordinates to obtain the velocity vector of the bubble, and differentiate the velocity vector again to obtain the acceleration vector of the bubble.

[0098] The bubble coordinates are two-dimensional coordinates, assumed to be (x, y). Differentiating x with respect to time t gives dx / dt, which is the component of the velocity in the x-coordinate direction , differentiating y with respect to time t gives dy / dt, which is the component of velocity in the y - coordinate direction. .

[0099] The value of the velocity vector can be expressed as:

[0100] Similarly, differentiating the velocity vector again, differentiating with respect to time t gives d / dt to obtain the acceleration component in the x - coordinate direction , differentiating with respect to time t gives d / dt to obtain the acceleration component in the y - coordinate direction .

[0101] The value of the acceleration vector can be expressed as:

[0102] S602. After obtaining the velocity vector and the acceleration vector, use the Euler method to predict the coordinates of the bubble to be corrected at the next moment.

[0103] Use the Euler method to predict the position coordinates and velocity of the bubble at the next moment: x(t + Δt), y(t + Δt), v x (t + Δt), v y (t + Δt), where x(t + Δt) is the abscissa of the coordinates of the bubble to be corrected, y(t + Δt) is the ordinate of the coordinates of the bubble to be corrected, t represents the current moment, t + Δt represents the next moment, and Δt represents the time interval between the current moment and the next moment. The moving direction of the bubble can be determined by the unit vector of the velocity vector.

[0104] The flow velocity of the molten metal affects the movement of the bubble. By calculating the molten - metal flow evaluation value of the h - th shrinkage - porosity defect region of the bubble, and using it as the weight of the bubble - center position, the predicted bubble - center position is corrected. Figure

[0105] Figure 7 is a flowchart of the process for obtaining the molten - metal flow evaluation value provided by the seventh embodiment of the present invention. The process for obtaining the molten - metal flow evaluation value includes: S701. Obtain the flow velocity of the molten metal in each infrared image of the h - th shrinkage - porosity defect region of the bubble, and obtain the mean value of the flow velocity of the molten metal as the mean value of the flow velocity of the molten metal.

[0106] The process of obtaining the flow velocity of the molten metal is a prior art. Briefly speaking, it includes: 1. Extract the shrinkage cavity and porosity defect area in the infrared image.

[0107] 2. Match the CFD simulation results (such as temperature field and flow velocity field) with the image data.

[0108] 3. Estimate the flow velocity through the relationship between the temperature gradient and the flow velocity: Utilize the temperature field change in the infrared image and combine it with the temperature field of the CFD simulation. The flow velocity can be estimated by calculating the temperature gradient (rate of temperature change).

[0109] S702. Calculate the average value of the absolute values of the differences between each flow velocity of the molten metal and the average value of the flow velocities of the molten metal as the flow velocity difference value of the molten metal.

[0110] The flow velocity difference value of the molten metal can be expressed as:

[0111] Among them, the represents the number of infrared images, and the represents the th shrinkage cavity and porosity defect area, and the flow velocity of the molten metal in the th infrared image. The represents the average value of the flow velocities of the molten metal.

[0112] S703. Divide the flow velocity difference value of the molten metal by the average value of the flow velocities of the molten metal to obtain the flow evaluation value of the molten metal.

[0113] The flow evaluation value of the molten metal can be expressed as:

[0114] Among them, the represents the flow evaluation value corresponding to the th shrinkage cavity and porosity defect area.

[0115] Figure 8 FIG. is a schematic diagram of a shrinkage cavity and porosity defect prediction system for side plate casting provided by the eighth embodiment of the present invention. The embodiment of the present invention also provides a shrinkage cavity and porosity defect prediction system for side plate casting. The system includes: An acquisition module 801, configured to acquire infrared images during the casting process of a preset first number of side plate castings, and distinguish the thick-wall area and the thin-wall area in the infrared images; The shrinkage porosity defect performance evaluation value module 802 is configured to obtain the stable temperature drop value and the uneven color distribution value through the temperature of the thin-wall region, and obtain the shrinkage porosity defect performance evaluation value according to the stable temperature drop value and the uneven color distribution value. When the shrinkage porosity defect performance evaluation value is not less than the preset shrinkage porosity defect performance evaluation threshold, the thin-wall region is determined as the shrinkage porosity defect region, where the temperature of the thin-wall region is the average value of the temperatures corresponding to each pixel point in the thin-wall region; The bubble-induced index value module 803 is configured to obtain the temperatures of the shrinkage porosity defect region in the infrared images obtained at each moment to form a temperature-time curve, and obtain the bubble-induced index value of the shrinkage porosity defect region according to the temperature-time curve. When the bubble-induced index value is not less than the preset bubble-induced threshold, the shrinkage porosity defect region is the bubble shrinkage porosity defect region; The coordinate to be corrected module 804 is configured to establish a rectangular coordinate system with the center point of the infrared image as the coordinate origin, use the center point of the bubble shrinkage porosity defect region as the bubble coordinate, construct a bubble movement trend curve, and obtain the bubble coordinate to be corrected at the next moment according to the bubble movement trend curve; The molten metal flow evaluation value module 805 is configured to obtain the molten metal flow velocity of the bubble shrinkage porosity defect region in each of the infrared images, and obtain the molten metal flow evaluation value of the bubble shrinkage porosity defect region according to the molten metal flow velocity; The correction module 806 is configured to correct the bubble coordinate to be corrected according to the molten metal flow evaluation value to obtain the corrected bubble coordinate.

[0116] It should be noted that the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0117] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for predicting shrinkage defects in side plate castings, characterized in that: The method comprises: Acquire an infrared image of a preset first number of side plate castings during the casting process, and distinguish a thick-walled area and a thin-walled area in the infrared image; The temperature drop stability value and the color distribution unevenness value are obtained by the temperature of the thin-walled area, and the shrinkage defect performance evaluation value is obtained according to the temperature drop stability value and the color distribution unevenness value. When the shrinkage defect performance evaluation value is not less than a preset shrinkage defect performance evaluation threshold, the thin-walled area is regarded as a shrinkage defect area, wherein the temperature of the thin-walled area is the average value of the corresponding temperature of each pixel point in the thin-walled area; The temperature of the shrinkage defect area in the infrared image obtained at each moment is obtained to form a temperature-time curve, and a bubble-causing index value of the shrinkage defect area is obtained according to the temperature-time curve, and when the bubble-causing index value is not less than a preset bubble-causing threshold value, the shrinkage defect area is a bubble shrinkage defect area; A rectangular coordinate system is established with the center point of the infrared image as the coordinate origin, the center point of the bubble shrinkage defect area is used as the bubble coordinate, a bubble movement trend curve is constructed, and the bubble coordinates to be corrected at the next moment are obtained according to the bubble movement trend curve; Obtaining a metal liquid flow velocity of the bubble shrinkage defect area in each of the infrared images, and obtaining a metal liquid flow evaluation value of the bubble shrinkage defect area according to the metal liquid flow velocity; The bubble coordinates to be corrected are corrected according to the metal liquid flow evaluation value to obtain corrected bubble coordinates.

2. The method for predicting shrinkage defects in side plate casting according to claim 1, characterized in that: The distinguishing between thick-walled areas and thin-walled areas in the infrared image comprises: Divide the infrared image into a preset second number of regions, obtain a first mean value of brightness of the i-th region and a second mean value of brightness of regions adjacent to the i-th region, wherein the value range of i is 1 to the second number; Adding the first mean value to the second mean value to obtain a sum of the mean values, obtaining an absolute value of a difference between the first mean value and the second mean value, and then dividing the difference by the sum of the mean values ​​to obtain a spectral absorption evaluation value of the i-th region; When the spectral absorption evaluation value is not less than a preset spectral absorption threshold, the i-th region is the thin-wall region; otherwise, the i-th region is the thick-wall region.

3. The shrinkage defect prediction method for side plate casting according to claim 1, characterized in that: The process of obtaining the temperature drop stable value includes: In each of the infrared images, obtaining the temperature of the thin-walled area; Obtaining an absolute value of a temperature difference between the thin-walled area in two infrared images adjacent in time, and obtaining an average value of the absolute values ​​as an absolute average value; The temperature drop stable value is obtained by calculating an average value of the absolute value minus the absolute average value, and taking the reciprocal of the average value.

4. The shrinkage defect prediction method for side plate casting according to claim 1, characterized in that: The process of obtaining the color distribution unevenness value includes: Calculating the variance of the temperature corresponding to the pixel points in the thin-wall region as the variance of the thin-wall region; The color distribution unevenness value is obtained by dividing the thin-wall region variance by the temperature of the thin-wall region.

5. The method for predicting shrinkage defects in side plate casting according to claim 1, characterized in that: The process of obtaining the shrinkage defect performance evaluation value includes: The temperature drop stability value is multiplied by the normalized value of the color distribution unevenness value to obtain the shrinkage defect performance evaluation value.

6. The method for predicting shrinkage defects in side plate casting according to claim 1, characterized in that: The process of obtaining the bubble-induced index value includes: Obtaining the temperature of the mth shrinkage defect area and the average of the temperatures of the shrinkage defect area when the metal liquid starts to fill the mold, and dividing the temperature of the mth shrinkage defect area by the average of the temperatures of the shrinkage defect area to obtain a temperature ratio; Obtaining the curvature of each moment in the temperature-time curve corresponding to the m-th shrinkage defect region, and calculating the average value of the curvature; Calculating the average value of the absolute value of the difference between the curvature at each moment and the average value of the curvature as the curvature difference value; The temperature ratio is divided by the curvature difference value and then normalized to obtain the bubble-inducing index value.

7. The method for predicting shrinkage defects in side plate casting according to claim 1, characterized in that: The process of obtaining the coordinates of the bubble to be corrected includes: Acquire the bubble coordinates at the current moment, differentiate the bubble coordinates to obtain the velocity vector of the bubble, and differentiate the velocity vector again to obtain the acceleration vector of the bubble; After obtaining the velocity vector and the acceleration vector, the Euler method is used to predict the bubble coordinates to be corrected at the next moment.

8. The method for predicting shrinkage defects in side plate casting according to claim 1, characterized in that: The process of obtaining the metal liquid flow evaluation value includes: Obtaining the metal liquid flow velocity of the hth bubble shrinkage defect area in each of the infrared images, and obtaining the average of the metal liquid flow velocities as the metal liquid flow velocity average; Calculate the average of the absolute values ​​of the differences between the metal liquid flow velocities and the metal liquid flow velocities mean as the metal liquid flow velocity difference value; The metal liquid flow velocity difference value is divided by the metal liquid flow velocity average value to obtain the metal liquid flow evaluation value.

9. The method for predicting shrinkage defects in side plate casting according to claim 1, characterized in that: The process of obtaining the corrected bubble coordinates includes: The metal liquid flow evaluation value is multiplied by the bubble coordinate to be corrected to obtain the corrected bubble coordinate.

10. A shrinkage defect prediction system for side plate casting, characterized in that: The system comprises: An acquisition module, used for acquiring an infrared image of a preset first number of side plate castings during the casting process, and distinguishing a thick-walled area and a thin-walled area in the infrared image; A shrinkage defect performance evaluation value module is used to obtain a temperature drop stability value and a color distribution unevenness value through the temperature of a thin-walled area, and obtain a shrinkage defect performance evaluation value according to the temperature drop stability value and the color distribution unevenness value. When the shrinkage defect performance evaluation value is not less than a preset shrinkage defect performance evaluation threshold, the thin-walled area is a shrinkage defect area, wherein the temperature of the thin-walled area is the average value of the corresponding temperatures of each pixel in the thin-walled area; A bubble-induced index value module is used to obtain the temperature of the shrinkage defect area in the infrared image obtained at each moment to form a temperature-time curve, and obtain the bubble-induced index value of the shrinkage defect area according to the temperature-time curve. When the bubble-induced index value is not less than a preset bubble-induced threshold value, the shrinkage defect area is a bubble shrinkage defect area; A coordinate module to be corrected is used to establish a rectangular coordinate system with the center point of the infrared image as the coordinate origin, take the center point of the bubble shrinkage defect area as the bubble coordinate, construct a bubble movement trend curve, and obtain the bubble coordinates to be corrected at the next moment according to the bubble movement trend curve; A metal liquid flow evaluation value module, used to obtain the metal liquid flow velocity of the bubble shrinkage defect area in each of the infrared images, and obtain the metal liquid flow evaluation value of the bubble shrinkage defect area according to the metal liquid flow velocity; The correction module is used to correct the bubble coordinates to be corrected according to the metal liquid flow evaluation value to obtain corrected bubble coordinates.

Images