Generation method and system of ladle refractory brick arrangement sequence based on geometric iterative optimization

Abstract

This invention proposes a method and system for generating a sequence of steel ladle refractory bricks based on geometric iterative optimization, relating to the field of data processing technology. The method includes: creating a mathematical model of the working layer lining of the target steel ladle to obtain the ladle lining curve; solving for geometric constraints based on a preset starting point, brick type structural parameters, and the ladle lining curve to determine an initial optimal brick pair; constructing an initial vector using two corner points of the initial optimal brick pair, and generating a candidate point set by combining the key rotation angle and the feature translation distance; preprocessing the candidate point set to obtain a fit evaluation index for each candidate point pair; determining the candidate point pair with the smallest fit evaluation index as the target point pair for this iteration; determining the corresponding brick type based on the distance between the two corner points of the target point pair; iterating from the target point pair as the starting point until the laying point reaches within a preset termination circle, generating a target point pair set.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for generating a sequence of steel ladle refractory bricks based on geometric iterative optimization. Background Technology

[0002] The construction of refractory brick linings for steel ladles is a complex engineering project requiring extremely high precision and reliability. Its core challenge lies in how to rationally arrange hundreds of bricks of different specifications on a complex curved surface of revolution, simultaneously satisfying multiple interdependent engineering objectives such as minimizing brick joints, maintaining overall roundness, and staggering joints between upper and lower layers. Traditionally, this task relied entirely on the experience of craftsmen for on-site trial arrangements, resulting in inefficiency, inconsistent quality, and the inability to optimize globally.

[0003] With the development of intelligent manufacturing, researchers are attempting to introduce digital technologies into this field. One approach involves creating a 3D model of the steel ladle and using a heuristic search algorithm to find feasible brick placement positions on a discrete grid. While this method incorporates a digital model, it essentially searches within a discrete, approximate space, resulting in high computational complexity and difficulty in ensuring the geometric accuracy of the generated continuous masonry path. This can easily lead to accumulated errors, causing uneven brick joints or poor local fit. Another approach compares the current steel ladle size with a template library, selecting the closest template and scaling it. This method is efficient, but its optimization capability relies entirely on a limited template library. It has poor adaptability for non-standard sizes or steel ladles with manufacturing errors, failing to achieve true "tailor-made" optimization, and similarly cannot guarantee the accuracy of the scaled brick joints. Summary of the Invention

[0004] In view of this, the present invention proposes a method and system for generating the arrangement sequence of refractory bricks in steel ladles based on geometric iterative optimization.

[0005] The technical solution of this invention is implemented as follows: The first aspect of this invention provides a method for generating the arrangement sequence of refractory bricks in a steel ladle based on geometric iteration optimization, comprising: A mathematical model of the working layer lining of the target ladle is created to obtain the ladle lining curve; Geometric constraints are solved based on a preset starting point, brick structure parameters, and the ladle lining curve to determine the initial optimal brick position pair; the preset starting point is any point on the ladle lining curve, and the brick structure parameters include the brick bottom edge length, the key rotation angle related to the brick geometry, and the feature translation distance related to the brick feature length; An initial vector is constructed using the two corner points of the initial optimal brick position pair. Combined with the key rotation angle and the feature translation distance, a candidate point set is generated. After preprocessing the candidate point set, the fitting evaluation index of each candidate point pair is obtained. The candidate point pair with the smallest fitting evaluation index is determined as the target point pair for this iteration. The corresponding brick type is determined based on the distance between the two corner points of the target point pair. The iteration is carried out starting from the target point pair until the masonry point reaches the preset termination circle, generating a target point pair set. The fitting evaluation index is the sum of the shortest distances from the two corner points of the optimal brick position pair to the inner lining curve of the steel ladle.

[0006] Based on the above technical solutions, preferably, the mathematical model for creating the target ladle working layer lining, to obtain the ladle lining curve, includes: The masonry scene is scanned to obtain point cloud data containing the masonry boundaries; The point cloud data is input into the mathematical model of the working layer lining of the target ladle to obtain a single-connected closed ladle lining curve; the ladle lining curve is an ellipse, a circle or a higher-order curve.

[0007] Based on the above technical solutions, preferably, the step of determining the initial optimal brick position pair by solving for geometric constraints based on a preset starting point, brick structure parameters, and the steel ladle lining curve includes: An auxiliary circle is created with the preset starting point as the center and the length of the bottom edge of the brick as the radius; The two intersection points of the auxiliary circle and the ladle lining curve are determined as the initial optimal brick position pair.

[0008] Based on the above technical solutions, preferably, the step of constructing an initial vector using two corner points of the initial optimal brick position pair, and generating a candidate point set by combining the key rotation angle and the feature translation distance, includes: The key rotation angle is determined based on the current brick size, and the feature translation distance is determined based on the preset joint width distance; The initial vector is rotated counterclockwise around the vector endpoint by the key rotation angle to obtain the first indicator line, and the first indicator line is translated along the steel ladle lining curve in the normal direction of the vector endpoint by the characteristic translation distance to obtain the target positioning reference line; Geometric transformations are performed based on the target positioning baseline and the brick-shaped structural parameters to generate the candidate point set for the current round.

[0009] Based on the above technical solutions, preferably, the preprocessing of the candidate point set includes: The coordinates of each candidate point in the candidate point set are substituted into the ladle lining curve for verification. If the output result is greater than a preset threshold, the corresponding candidate point is removed from the candidate point set.

[0010] Based on the above technical solutions, preferably, after preprocessing the candidate point set, obtaining the fitting evaluation index for each candidate point pair, and determining the candidate point pair with the smallest fitting evaluation index as the target point pair for this iteration, includes: The sum of the distances from the two corner points in each candidate point pair to the inner lining curve of the steel ladle is obtained, and the sum of the distances is determined as the fitting evaluation index. The candidate point pair with the smallest fit evaluation index is determined as the target point pair for this iteration.

[0011] Based on the above technical solutions, preferably, the step of determining the corresponding brick type based on the distance between the two corner points of the target point includes: Obtain the difference between the Euclidean distance between the two corner points of the target point pair and the preset brick feature length, and determine the corresponding brick type based on the range of the difference.

[0012] More preferably, a second aspect of the present invention provides a system for generating a sequence of steel ladle refractory bricks based on geometric iterative optimization, comprising: a model creation module, an initial solution module, a point set generation module, and an iterative generation module; wherein, The model creation module is configured to create a mathematical model of the inner lining of the target ladle working layer, and obtain the ladle lining curve; The initial solution module is configured to perform geometric constraint solution based on a preset starting point, brick structure parameters, and the ladle lining curve to determine the initial optimal brick position pair; the preset starting point is any point on the ladle lining curve, and the brick structure parameters include the brick bottom edge length, key rotation angles related to the brick geometry, and feature translation distances related to the brick feature length; The point set generation module is configured to construct an initial vector using the two corner points of the initial optimal brick position pair, and generate a candidate point set by combining the key rotation angle and the feature translation distance. The iterative generation module is configured to preprocess the candidate point set, obtain the fitting evaluation index of each candidate point pair, determine the candidate point pair with the smallest fitting evaluation index as the target point pair for this iteration, and determine the corresponding brick type based on the distance between the two corner points in the target point pair. Iteration is performed starting from the target point pair until the masonry point reaches the preset termination circle, thereby generating a set of target point pairs. The fitting evaluation index is the sum of the shortest distances from the two corner points in the optimal brick position pair to the inner lining curve of the steel ladle.

[0013] More preferably, a third aspect of the present invention provides an electronic device, including a processor and a memory; the memory stores a computer program, wherein the computer program, when executed by the processor, implements the method for generating a steel ladle refractory brick arrangement sequence based on geometric iteration optimization as described in the first aspect.

[0014] More preferably, the fourth aspect of the present invention provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method for generating the arrangement sequence of steel ladle refractory bricks based on geometric iteration optimization as described in the first aspect.

[0015] The method and system for generating the arrangement sequence of refractory bricks in steel ladles based on geometric iteration optimization of the present invention have the following advantages over the prior art: 1. By creating a mathematical model of the target ladle working layer lining, the ladle lining curve is obtained, accurately reflecting the actual shape and size of the ladle lining. Based on this, geometric constraints are solved using a preset starting point, brick structure parameters, and the ladle lining curve to determine the initial optimal brick position pair. This fully considers the uniqueness of the ladle lining curve and, combined with the brick structure parameters, ensures that the initial brick position is closely aligned with the actual shape of the ladle lining, further guaranteeing the compatibility of the entire masonry scheme with the ladle lining. An initial vector is constructed using two corner points from the initial optimal brick position pair. A candidate point set is generated by combining key rotation angles and feature translation distances. The candidate point set is then preprocessed, and the fit evaluation index for each candidate point pair is obtained. Based on this, the point pair that best meets the requirements of the ladle lining curve is selected from numerous candidate point pairs, ensuring that the determination of each brick position matches the ladle lining curve as closely as possible, thereby guaranteeing the accuracy of the brick joints. During the iteration process, each round determines a new pair of target points based on precise geometric relationships and fit evaluation indicators, making the entire masonry process a process of gradually and accurately approximating the steel ladle lining curve. The brick joints remain precise at all times, ensuring that the final masonry scheme can accurately and stably realize the masonry of the steel ladle lining.

[0016] 2. By comprehensively considering the preset starting point and brick structure parameters, including the bottom edge length of the brick, key rotation angle, characteristic translation distance, and steel ladle lining curve, the entire scheme can fully cope with various complex situations during the determination of brick positions and the masonry process. This improves the scheme's adaptability to different steel ladles and brick types, thereby enhancing the scheme's reliability and stability.

[0017] 3. By iteratively determining the set of target point pairs, each iteration optimizes the solution based on the previous result, allowing the entire masonry scheme to continuously approach the optimal solution. This enables timely detection and correction of potential deviations, ensuring that the final masonry scheme can accurately and stably achieve the masonry of the steel ladle lining, further improving the overall quality of the scheme. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A flowchart illustrating a method for generating a steel ladle refractory brick arrangement sequence based on geometric iteration optimization, provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of a single geometric iteration calculation process provided in an embodiment of the present invention; Figure 3 A schematic diagram of the parameters of the refractory bricks provided in the embodiments of the present invention; Figure 4 A visualization of the iterative generation of masonry sequences on an elliptic curve, provided by an embodiment of the present invention; Figure 5 A simulation comparison diagram showing the masonry scheme provided in the embodiments of the present invention and the traditional empirical arrangement scheme; Figure 6 This is a schematic diagram of a steel ladle refractory brick arrangement sequence generation system based on geometric iteration optimization, provided in an embodiment of the present invention. Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0020] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0021] In some embodiments, such as Figure 1 As shown, Figure 1 This is a flowchart illustrating a method for generating a ladle refractory brick arrangement sequence based on geometric iterative optimization, provided by an embodiment of the present invention. The method includes: S110, create a mathematical model of the working layer lining of the target ladle and obtain the ladle lining curve.

[0022] Here, a mathematical model can be created by describing the lining profile using parametric equations or NURBS surfaces, based on the actual structure of the steel ladle working layer lining.

[0023] In some embodiments, a mathematical model of the target ladle working layer lining is created to obtain the ladle lining curve, including: The masonry scene is scanned to obtain point cloud data containing the masonry boundaries; Point cloud data is input into the mathematical model of the working layer lining of the target ladle to obtain a simply connected closed ladle lining curve; the ladle lining curve can be an ellipse, a circle, or a higher-order curve.

[0024] In this embodiment, a 3D scanner deployed in the workshop is used to scan the masonry scene, obtaining point cloud data including the masonry boundaries. Here, the mathematical model is a simply connected closed curve equation. The curve can be an ellipse, a circle, or a higher-order curve fitted from the design drawings, which defines the boundary of the masonry on a two-dimensional plane.

[0025] S120, based on the preset starting point, brick structure parameters and steel ladle lining curve, performs geometric constraint solution to determine the initial optimal brick position pair; the preset starting point is any point on the steel ladle lining curve, and the brick structure parameters include the brick bottom edge length, the key rotation angle related to the brick geometry, and the feature translation distance related to the brick feature length.

[0026] In some embodiments, geometric constraints are solved based on a preset starting point, brick structure parameters, and the steel ladle lining curve to determine the initial optimal brick position pair, including: Create an auxiliary circle with the preset starting point as the center and the length of the bottom edge of the brick as the radius; The two intersection points of the auxiliary circle and the inner lining curve of the ladle are determined as the initial optimal brick position pair.

[0027] In this embodiment, based on a preset starting point By combining the inner lining curve C of the ladle and the structural parameters of the brick type, the two key corner points corresponding to the initial optimal brick position pair were calculated. This can be accomplished by solving geometric constraint problems.

[0028] S130: Construct an initial vector using the two corner points of the initial optimal brick position pair, and generate a candidate point set by combining the key rotation angle and feature translation distance.

[0029] In some embodiments, an initial vector is constructed using two corner points of the initial optimal brick pair, and a candidate point set is generated by combining a key rotation angle and a feature translation distance, including: The key rotation angle is determined based on the current brick size, and the feature translation distance is determined based on the preset joint width distance; The initial vector is rotated counterclockwise around the vector endpoint by a key rotation angle to obtain the first indicator line. The first indicator line is then translated along the steel ladle lining curve by a characteristic translation distance in the normal direction of the vector endpoint to obtain the target positioning baseline. Geometric transformations are performed based on the target positioning baseline and brick-shaped structural parameters to generate the candidate point set for the current round.

[0030] In this embodiment, please refer to Figure 2 and Figure 3 , Figure 2 This is a schematic diagram of a single geometric iteration calculation process provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of the parameters of the refractory bricks provided in an embodiment of the present invention; the optimal brick position pair in the first round is... The corresponding initial vector can be represented as Rotate the initial vector counterclockwise by a fixed angle around its endpoint An2. The key rotation angle is used to obtain the first indicator line Ln1. The first indicator line Ln1 is then translated precisely along the normal direction of the steel ladle lining curve C at point An2 by the exact seam width. This refers to the feature translation distance, which ultimately yields the geometric reference for all subsequent calculations in the current round—the target positioning reference line Ln2. The target positioning reference line Ln2 defines the theoretical position where the new brick "closes" to the existing brickwork. Through a series of defined geometric transformations, multiple possible corner points for the next brick position are generated. These transformations simulate the geometric results of placing different brick types in different ways near Ln2. For example... Figure 2 As shown, the generated candidate point set includes 7 candidate points (An3 to An9).

[0031] An3 is the intersection of Ln2 and curve C, and is the point directly aligned with the curve along the baseline. An4 and An5 correspond to brick types A and B, respectively. Using An3 as the rotation center, Ln2 is rotated by the key rotation angle corresponding to each brick type to obtain the indicator line. Then, the characteristic translation distance is shifted along the indicator line, and the intersection point with the parallel line of Ln2 before rotation is An4 or An5. These two points represent the possible position of another corner point when placing brick A or brick B. An6 and An8 correspond to the outer edges ( ) of brick types A and B after placement. or The intersection of curve C and line A represents the contact point between the outer edge of the brick and the inner lining of the steel ladle. An7 and An9 are designed to handle more complex bonding situations, using An6 or An8 as the center, and extending the outer edge... or Reverse rotation by a compensation angle ( , ), obtain the indicator line Ln7 or Ln8, and then find its intersection with Ln2 to obtain An7 or An9.

[0032] S140: After preprocessing the candidate point set, obtain the fitting evaluation index of each candidate point pair. The candidate point pair with the smallest fitting evaluation index is determined as the target point pair for this iteration. The corresponding brick type is determined based on the distance between the two corner points in the target point pair. Iteration is carried out starting from the target point pair until the masonry point reaches the preset termination circle, generating a target point pair set. The fitting evaluation index is the sum of the shortest distances from the two corner points in the optimal brick position pair to the inner lining curve of the steel ladle.

[0033] In some embodiments, preprocessing of the candidate point set includes: The coordinates of each candidate point in the candidate point set are substituted into the ladle lining curve for verification. If the output result is greater than the preset threshold, the corresponding candidate point is removed from the candidate point set.

[0034] In this embodiment, the coordinates of each candidate point are substituted into curve C. If the result is... , If a small positive tolerance is allowed, the point can be considered outside the curve Cd and discarded. The retained points constitute the feasible point set, ensuring that all points considered subsequently are physically constructible.

[0035] In some embodiments, after preprocessing the candidate point set, the fit evaluation index of each candidate point pair is obtained, and the candidate point pair with the smallest fit evaluation index is determined as the target point pair for this iteration, including: The sum of the distances from the two corner points in each candidate point pair to the ladle lining curve is obtained, and the sum of the distances is determined as the fit evaluation index. The candidate point pair with the smallest fit evaluation index is determined as the target point pair for this iteration.

[0036] In this embodiment, for each pair of candidate points Calculate the corresponding fit evaluation index ,in, , The value E represents the shortest distance from the calculation point to curve C. The fit evaluation index directly measures the average gap between the "bottom" of the entire brick and the theoretical inner lining surface, if these two points are taken as the two corner points of the brick. The smaller the E value, the tighter the fit. After calculating the E values ​​for all groups, the pair of points with the smallest E value is selected as the target pair for this iteration, mathematically ensuring that each local selection step is directed towards maximizing the tightest fit between the brick and the inner lining surface.

[0037] In some embodiments, determining the corresponding brick type based on the distance between the two corner points of the target point pair includes: Obtain the difference between the Euclidean distance between the two corner points of the target point and the preset brick feature length, and determine the corresponding brick type based on the range of the difference.

[0038] In this embodiment, the Euclidean distance between two points is calculated based on the determined optimal brick pair. Compare this distance with the preset brick feature length. For example, if... Then the encoding , corresponding to brick type A; if Then the encoding This corresponds to brick type B.

[0039] In one example, see Figure 4 and Figure 5 , Figure 4 A visualization of the iterative generation of masonry sequences on an elliptic curve, provided by an embodiment of the present invention; Figure 5 The above diagram shows a simulation comparison of the masonry scheme provided in this invention and the traditional empirical arrangement scheme. The upper diagram shows the simulation effect of the traditional empirical arrangement scheme, and the lower diagram shows the simulation effect of the arrangement scheme of this application. The brick types are A (165mm) and B (157.5mm).

[0040] Equation of the ladle lining curve: .

[0041] Preset starting point: , is the center of the bottom of the bag.

[0042] Reference seam width Rotation angle Feature translation distance Reverse rotation compensation angle Neighborhood search range: Termination radius .

[0043] Solve for the relationship between ellipse C and circle The intersection point, and take The solution can be obtained numerically, such as through Newton's method: Because the starting point is ,definition Therefore, the initial brick pair is The distance between these points is approximately 165mm, corresponding to the initial placement of a type A brick.

[0044] Taking the first iteration (n=2) as an example, the input is: Construct initial vectors Rotate it counterclockwise around A12. This yields the direction line. The direction line is then translated along this normal direction. The equation of the first indicator line Ln1 is obtained. .

[0045] Based on this, find the intersection point of Ln2 and ellipse C, and constrain the x-coordinate to... Inside, obtained Rotate Ln2 counterclockwise with An3 as the center. We get Ln3, and then translate it. Given Ln4, find the intersection of Ln3 and Ln4. Similarly, rotation We get Ln5, and then translate it. Given Ln6, find the intersection. Find the intersection point of Ln4 and ellipse C, with x constrained to... Inside, get Rotate Ln4 clockwise with An6 as the center. Given Ln7, find the intersection of Ln7 and Ln2. Find the intersection point of Ln6 and ellipse C, with x constrained to... Inside, get Rotate Ln6 clockwise with An8 as the center. Given Ln8, find the intersection of Ln8 and Ln2. .

[0046] All Coordinate substitution Calculations revealed that the F values ​​of An4 and An5 were much larger than the tolerance. This indicates that they are located outside the ellipse, representing the corner points of the brick extension. The F values ​​of An3, An6, An7, An8, and An9 are all close to 0 or negative, and are therefore retained. Therefore, the feasible point set... .

[0047] Grouped by rules: .

[0048] calculate An3 lies on the curve at a distance of 0.

[0049] calculate An6 lies on the curve at a distance of 0.

[0050] calculate An8 lies on the curve at a distance of 0.

[0051] calculate and : , .therefore, , .

[0052] Comparing all E values, the optimal brick pair for this round is: .

[0053] Then calculate .

[0054] Compared with the preset value: .

[0055] Therefore, encoding That is, the brick type is A.

[0056] make ,Will As input for the next round, the above steps are repeated, with each iteration determining a new optimal brick pair and brick type. The point sequence will gradually spread upwards along the elliptic curve. When a certain round of calculation is reached, the coordinates of An2 satisfy... When the algorithm reaches a point near the top of the enclosure wall, the loop terminates, having iterated a total of N=56 times. Ultimately, the algorithm outputs a coordinate sequence containing 57 pairs of points. It contains initial pairs and 56 brick-type codes. For example, the sequence may be... Begin. Compared to conventional methods, the brick joints are even and fit perfectly.

[0057] In some embodiments, please refer to Figure 6 , Figure 6 This is a schematic diagram of a system for generating a sequence of steel ladle refractory bricks based on geometric iterative optimization, provided in an embodiment of the present invention. The present invention provides a system 600 for generating a sequence of steel ladle refractory bricks based on geometric iterative optimization, comprising: a model creation module 610, an initial solution module 620, a point set generation module 630, and an iterative generation module 640; wherein,

[0058] The model creation module 610 is configured to create a mathematical model of the inner lining of the target ladle working layer, and obtain the ladle lining curve; The initial solution module 620 is configured to perform geometric constraint solution based on a preset starting point, brick structure parameters, and steel ladle lining curve to determine the initial optimal brick position pair; the preset starting point is any point on the steel ladle lining curve, and the brick structure parameters include the brick bottom edge length, the key rotation angle related to the brick geometry, and the feature translation distance related to the brick feature length; The point set generation module 630 is configured to construct an initial vector using the two corner points of the initial optimal brick position pair, and generate a candidate point set by combining the key rotation angle and the feature translation distance. The iterative generation module 640 is configured to preprocess the candidate point set, obtain the fitting evaluation index of each candidate point pair, determine the candidate point pair with the smallest fitting evaluation index as the target point pair for this round of iteration, and determine the corresponding brick type based on the distance between the two corner points in the target point pair. Iteration is carried out starting from the target point pair until the masonry point reaches the preset termination circle, generating a set of target point pairs. The fitting evaluation index is the sum of the shortest distances from the two corner points in the optimal brick position pair to the inner lining curve of the steel ladle.

[0059] In some embodiments, the model creation module 610 is specifically configured as follows: The masonry scene is scanned to obtain point cloud data containing the masonry boundaries; Point cloud data is input into the mathematical model of the working layer lining of the target ladle to obtain a simply connected closed ladle lining curve; the ladle lining curve can be an ellipse, a circle, or a higher-order curve.

[0060] In some embodiments, the initial solver module 620 is specifically configured as follows: Create an auxiliary circle with the preset starting point as the center and the length of the bottom edge of the brick as the radius; The two intersection points of the auxiliary circle and the inner lining curve of the ladle are determined as the initial optimal brick position pair.

[0061] In some embodiments, the point set generation module 630 is specifically configured as follows: The key rotation angle is determined based on the current brick size, and the feature translation distance is determined based on the preset joint width distance; The initial vector is rotated counterclockwise around the vector endpoint by a key rotation angle to obtain the first indicator line. The first indicator line is then translated along the steel ladle lining curve by a characteristic translation distance in the normal direction of the vector endpoint to obtain the target positioning baseline. Geometric transformations are performed based on the target positioning baseline and brick-shaped structural parameters to generate the candidate point set for the current round.

[0062] In some embodiments, the ladle refractory brick arrangement sequence generation system based on geometric iteration optimization further includes a preprocessing module, which is specifically configured as follows: The coordinates of each candidate point in the candidate point set are substituted into the ladle lining curve for verification. If the output result is greater than the preset threshold, the corresponding candidate point is removed from the candidate point set.

[0063] In some embodiments, the iterative generation module 640 is specifically configured as follows: The sum of the distances from the two corner points in each candidate point pair to the ladle lining curve is obtained, and the sum of the distances is determined as the fit evaluation index. The candidate point pair with the smallest fit evaluation index is determined as the target point pair for this iteration.

[0064] In some embodiments, the iterative generation module 640 is specifically configured as follows: Obtain the difference between the Euclidean distance between the two corner points of the target point and the preset brick feature length, and determine the corresponding brick type based on the range of the difference.

[0065] It should be noted that the ladle refractory brick arrangement sequence generation system based on geometric iteration optimization provided in this application embodiment and the ladle refractory brick arrangement sequence generation method based on geometric iteration optimization provided in this application embodiment are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned ladle refractory brick arrangement sequence generation method based on geometric iteration optimization, and the repeated parts will not be described again.

[0066] In some embodiments, please refer to Figure 7 , Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 700 provided in this application includes a processor 710 and a memory 720; the memory 720 stores a computer program, wherein the computer program, when executed by the processor, implements the aforementioned method for generating the arrangement sequence of steel ladle refractory bricks based on geometric iteration optimization.

[0067] Specifically, processor 710 may include, for example, a general-purpose microprocessor, an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. Processor 710 may also include onboard memory for caching purposes. Processor 710 may be a single processing unit or multiple processing units for performing different actions of the method flow according to embodiments of this application.

[0068] The memory 720 can be any medium capable of containing, storing, transmitting, propagating, or transmitting instructions. For example, the memory 720 can be, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, apparatus, or propagation medium. Specific examples of the memory 720 include: magnetic storage devices such as magnetic tape or hard disk drives (HDDs); optical storage devices such as optical discs (CD-ROMs); and also random access memory (RAM) or flash memory; and / or wired / wireless communication links.

[0069] This application also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, this program implements the above-described method for generating the arrangement sequence of steel ladle refractory bricks based on geometric iteration optimization. This computer-readable medium may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into that device / apparatus / system. The aforementioned computer-readable medium carries one or more programs, which, when executed, implement the method according to the embodiments of this application.

[0070] According to embodiments of this application, a computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wired, optical fiber, radio frequency signals, etc., or any suitable combination thereof.

[0071] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this application can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly described in this application. In particular, the features described in the various embodiments and / or claims of this application can be combined and / or combined in various ways without departing from the spirit and teachings of this application. All such combinations and / or combinations fall within the scope of this application. Therefore, the scope of this application should not be limited to the above embodiments, but should be defined not only by the appended claims, but also by their equivalents. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this invention should be included within the protection scope of this invention.

Claims

1. A method for generating the arrangement sequence of refractory bricks in a steel ladle based on geometric iterative optimization, characterized in that, include: A mathematical model of the working layer lining of the target ladle is created to obtain the ladle lining curve; Geometric constraints are solved based on a preset starting point, brick structure parameters, and the ladle lining curve to determine the initial optimal brick position pair; the preset starting point is any point on the ladle lining curve, and the brick structure parameters include the brick bottom edge length, the key rotation angle related to the brick geometry, and the feature translation distance related to the brick feature length; An initial vector is constructed using the two corner points of the initial optimal brick position pair. Combined with the key rotation angle and the feature translation distance, a candidate point set is generated. After preprocessing the candidate point set, the fitting evaluation index of each candidate point pair is obtained. The candidate point pair with the smallest fitting evaluation index is determined as the target point pair for this iteration. The corresponding brick type is determined based on the distance between the two corner points of the target point pair. The iteration is carried out starting from the target point pair until the masonry point reaches the preset termination circle, generating a target point pair set. The fitting evaluation index is the sum of the shortest distances from the two corner points of the optimal brick position pair to the inner lining curve of the steel ladle.

2. The method for generating the arrangement sequence of refractory bricks in a steel ladle based on geometric iterative optimization as described in claim 1, characterized in that, The mathematical model for creating the target ladle working layer lining is used to obtain the ladle lining curve, including: The masonry scene is scanned to obtain point cloud data containing the masonry boundaries; The point cloud data is input into the mathematical model of the working layer lining of the target ladle to obtain a single-connected closed ladle lining curve; the ladle lining curve is an ellipse, a circle or a higher-order curve.

3. The method for generating the arrangement sequence of refractory bricks in a steel ladle based on geometric iterative optimization as described in claim 1, characterized in that, The process of determining the initial optimal brick position pair by solving for geometric constraints based on a preset starting point, brick structure parameters, and the steel ladle lining curve includes: An auxiliary circle is created with the preset starting point as the center and the length of the bottom edge of the brick as the radius; The two intersection points of the auxiliary circle and the ladle lining curve are determined as the initial optimal brick position pair.

4. The method for generating the arrangement sequence of refractory bricks in a steel ladle based on geometric iterative optimization as described in claim 1, characterized in that, The process of constructing an initial vector from two corner points of the initial optimal brick pair, and generating a candidate point set by combining the key rotation angle and the feature translation distance, includes: The key rotation angle is determined based on the current brick size, and the feature translation distance is determined based on the preset joint width distance; The initial vector is rotated counterclockwise around the vector endpoint by the key rotation angle to obtain the first indicator line, and the first indicator line is translated along the steel ladle lining curve in the normal direction of the vector endpoint by the characteristic translation distance to obtain the target positioning reference line; Geometric transformations are performed based on the target positioning baseline and the brick-shaped structural parameters to generate the candidate point set for the current round.

5. The method for generating the arrangement sequence of refractory bricks in a steel ladle based on geometric iterative optimization as described in claim 1, characterized in that, The preprocessing of the candidate point set includes: The coordinates of each candidate point in the candidate point set are substituted into the ladle lining curve for verification. If the output result is greater than a preset threshold, the corresponding candidate point is removed from the candidate point set.

6. The method for generating the arrangement sequence of refractory bricks in a steel ladle based on geometric iterative optimization as described in claim 1, characterized in that, After preprocessing the candidate point set, a fitting evaluation index is obtained for each candidate point pair. The candidate point pair with the smallest fitting evaluation index is determined as the target point pair for this iteration, including: The sum of the distances from the two corner points in each candidate point pair to the inner lining curve of the steel ladle is obtained, and the sum of the distances is determined as the fitting evaluation index. The candidate point pair with the smallest fit evaluation index is determined as the target point pair for this iteration.

7. The method for generating the arrangement sequence of refractory bricks in a steel ladle based on geometric iterative optimization as described in claim 1, characterized in that, The step of determining the corresponding brick type based on the distance between the two corner points of the target point includes: Obtain the difference between the Euclidean distance between the two corner points of the target point pair and the preset brick feature length, and determine the corresponding brick type based on the range of the difference.

8. A system for generating a sequence of refractory bricks for steel ladles based on geometric iterative optimization, characterized in that, include: The system comprises a model creation module, an initial solution module, a point set generation module, and an iterative generation module; among which... The model creation module is configured to create a mathematical model of the inner lining of the target ladle working layer, and obtain the ladle lining curve; The initial solution module is configured to perform geometric constraint solution based on a preset starting point, brick structure parameters, and the ladle lining curve to determine the initial optimal brick position pair; the preset starting point is any point on the ladle lining curve, and the brick structure parameters include the brick bottom edge length, key rotation angles related to the brick geometry, and feature translation distances related to the brick feature length; The point set generation module is configured to construct an initial vector using the two corner points of the initial optimal brick position pair, and generate a candidate point set by combining the key rotation angle and the feature translation distance. The iterative generation module is configured to preprocess the candidate point set, obtain the fitting evaluation index of each candidate point pair, determine the candidate point pair with the smallest fitting evaluation index as the target point pair for this iteration, and determine the corresponding brick type based on the distance between the two corner points in the target point pair. Iteration is performed starting from the target point pair until the masonry point reaches the preset termination circle, thereby generating a set of target point pairs. The fitting evaluation index is the sum of the shortest distances from the two corner points in the optimal brick position pair to the inner lining curve of the steel ladle.

9. An electronic device comprising a processor and a memory; said memory storing a computer program, wherein, When the computer program is executed by the processor, it implements the method for generating the arrangement sequence of steel ladle refractory bricks based on geometric iteration optimization as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that, It stores a computer program, wherein when the computer program is executed by a processor, it implements the method for generating the arrangement sequence of steel ladle refractory bricks based on geometric iteration optimization as described in any one of claims 1 to 7.

Images