A method and system for additive manufacturing distributed equalization scanning

Abstract

This invention relates to a distributed balanced scanning system and method for additive manufacturing, belonging to the field of additive manufacturing technology. The method includes: acquiring data information of the part to be processed, including data information of multiple slice layers; processing the data information to obtain initial graphic partition data; adjusting the initial graphic partition data, provided that the initial graphic partition data meets adjustment conditions, to obtain first target graphic partition data; re-estimating the total scanning time of each laser based on the first target graphic partition data, until the time difference between the total scanning times of the lasers is less than a time threshold or the number of iterations reaches a preset number, and obtaining second target graphic partition data; and allocating the second target graphic partition data to each laser for scanning and printing. This method achieves precise balancing of scanning time among multiple lasers, avoiding waiting and efficiency losses caused by uneven load, and significantly improving parallel processing efficiency.

Description

Technical Field

[0001] This invention belongs to the field of additive manufacturing technology, and particularly relates to a distributed equalization scanning method and system for additive manufacturing. Background Technology

[0002] Rapid additive manufacturing (RAM) is a collective term for a series of rapid prototyping technologies that directly drive the rapid fabrication of arbitrarily complex three-dimensional physical entities driven by digital models. With the rapid development of laser additive manufacturing technology in aerospace, medical devices, and high-end manufacturing, higher efficiency and quality requirements have been placed on the construction of large and complex parts. Traditional single-laser scanning methods face many limitations when processing large-sized parts or highly complex structures, such as long scanning times, uneven heat accumulation, and high defect rates. Therefore, how to better achieve additive manufacturing scanning has become an urgent problem to be solved. Summary of the Invention

[0003] In view of the shortcomings of the prior art, the purpose of the invention is to provide a distributed equalization scanning method and system for additive manufacturing.

[0004] A first aspect of the present invention provides a distributed equalization scanning method for additive manufacturing, comprising: acquiring data information of a part to be processed, the data information including data information of multiple slice layers, wherein a three-dimensional model of the part to be processed is sliced ​​to obtain data information of multiple slice layers; processing the data information to obtain initial graphic partition data; and adjusting the initial graphic partition data, wherein if the initial graphic partition data is determined to meet adjustment conditions, to obtain first target graphic partition data; re-estimating the total scanning time of each laser based on the first target graphic partition data, until the time difference of the total scanning time between the lasers is less than a time threshold or the number of iterations reaches a preset number, and obtaining second target graphic partition data; and allocating the second target graphic partition data to each of the lasers for scanning and printing.

[0005] Further, the data information is processed to obtain initial graphic partition data, including: discretizing the region of each slice layer into squares; determining the region type of each square based on the position coordinates of each square, and obtaining the initial graphic partition data of each slice layer. Each square includes a set of scan lines and records the estimated scan time, the position coordinates and the region type. The region type includes a laser region or an overlapping region.

[0006] Further, determining that the initial graphic partition data meets the adjustment conditions includes: determining the total estimated scanning time for each laser and determining the time difference between the total estimated scanning times of the lasers; determining that the initial graphic partition data meets the adjustment conditions if the time difference between the total estimated scanning times of the lasers is greater than a first preset time; and / or determining the size of each square, determining that the initial graphic partition data meets the adjustment conditions if the size of the square is greater than a first size threshold; and / or determining that the initial graphic partition data meets the adjustment conditions if the size of the square is less than a second size threshold.

[0007] Further, determining the total estimated scanning time of the laser includes: inputting the initial graphic partition data, process parameters, and historical graphic partition data into the trained time prediction model to predict the scanning time, thereby obtaining the total estimated scanning time of the slice layer; and determining the total estimated scanning time of each laser based on the total estimated scanning time of the slice layer and the region type to which the square belongs.

[0008] Further, adjusting the initial graphic partition data to obtain the first target graphic partition data includes: when the time difference of the total estimated scanning time between the lasers is greater than the first preset threshold, obtaining the scanning time of the squares in the overlapping area, and sorting the squares in the overlapping area according to the scanning time to obtain a sorting result; based on the sorting result, assigning the squares in the overlapping area to lasers with a total estimated scanning time less than a second preset time, until the total estimated scanning time of each laser is balanced; and / or when the size of the square is greater than the first size threshold, dividing the squares larger than the first size threshold into sub-squares, and assigning the sub-squares to lasers with a total estimated scanning time less than the second preset time, until the total estimated scanning time of each laser is balanced; and / or when the size of the square is less than the second size threshold, traversing the adjacent areas of the squares smaller than the second size threshold, and merging the squares smaller than the second size threshold into the smallest area in the adjacent areas to obtain the first target graphic partition data.

[0009] Furthermore, it also includes: when the second target graphic partition data is allocated to each of the lasers for scanning and printing, monitoring the scanning time of each laser in real time; when one of the lasers completes scanning earlier than the other lasers, dividing the remaining tasks of the other lasers and allocating the scanning units to the laser that has completed scanning; when one of the lasers completes scanning earlier and the overlapping area has been scanned, adjusting the load factor of the next layer according to the time difference of the scanning time of the lasers, wherein the load factor is used to adjust the estimated time ratio of the lasers during initial allocation.

[0010] A second aspect of the present invention provides an additive manufacturing distributed equalization scanning system, comprising: a data acquisition module for acquiring data information of a part to be processed, the data information including data information of multiple slice layers, wherein the three-dimensional model of the part to be processed is sliced ​​to obtain the data information of multiple slice layers; a determination module for processing the data information to obtain initial graphic partition data, and adjusting the initial graphic partition data to obtain first target graphic partition data when it is determined that the initial graphic partition data meets the adjustment conditions; an acquisition module for re-estimating the total scanning time of each laser based on the first target graphic partition data until the time difference of the total scanning time between the lasers is less than a time threshold or the number of iterations reaches a preset number, and acquiring second target graphic partition data; and an allocation module for allocating the second target graphic partition data to each of the lasers for scanning and printing.

[0011] A third aspect of the present invention provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method described in any one of the first aspects of the present invention.

[0012] A fourth aspect of the present invention provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to perform the method described in any one of the first aspects of the present invention.

[0013] The beneficial effects of this invention are as follows: The additive manufacturing distributed balanced scanning method and system of this invention collects data information of the part to be processed, including data information of multiple slice layers. Specifically, the three-dimensional model of the part to be processed is sliced ​​to obtain data information of multiple slice layers. The data information is processed to obtain initial graphic partition data. If the initial graphic partition data meets the adjustment conditions, it is adjusted to obtain first target graphic partition data. Based on the first target graphic partition data, the total scanning time of each laser is re-estimated until the time difference between the total scanning times of the lasers is less than a time threshold or the number of iterations reaches a preset number, at which point second target graphic partition data is obtained. The second target graphic partition data is then allocated to each laser for scanning and printing. This method achieves precise balancing of scanning time among multiple lasers through iterative optimization of partitioning and dynamic task scheduling, effectively avoiding waiting and efficiency losses caused by uneven load, and significantly improving parallel processing efficiency. Attached Figure Description

[0014] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts. It is obvious that the drawings described below are merely some embodiments of the present invention, and those skilled in the art can obtain other drawings based on these drawings.

[0015] Figure 1 This is a flowchart of an additive manufacturing distributed equalization scanning method according to an embodiment of the present invention; Figure 2 This is a flowchart of an additive manufacturing distributed equalization scanning method according to a specific embodiment of the present invention; Figure 3 This is a schematic diagram of graphical partitioning according to an embodiment of the present invention; Figure 4 This is a schematic diagram of laser partitioning according to an embodiment of the present invention; Figure 5 This is a schematic diagram of the critical partition according to an embodiment of the present invention; Figure 6 This is a schematic diagram of dynamic partitioning according to an embodiment of the present invention; Figure 7 This is a schematic diagram of an additive manufacturing distributed equalization scanning system according to an embodiment of the present invention; Figure 8 This is a structural block diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0016] To enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. It should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0017] Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts disclosed in this invention.

[0018] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. The terms "installed," "connected," and "linked" should be interpreted broadly; for example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0019] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of methods and systems consistent with some aspects of the invention as detailed in the appended claims.

[0020] Rapid additive manufacturing (RAM) is a collective term for a series of rapid prototyping technologies that directly drive the rapid fabrication of arbitrarily complex three-dimensional physical entities driven by digital models. With the rapid development of laser additive manufacturing technology in aerospace, medical devices, and high-end manufacturing, higher efficiency and quality requirements have been placed on the construction of large and complex parts. Traditional single-laser scanning methods face many limitations when processing large-sized parts or highly complex structures, such as long scanning times, uneven heat accumulation, and high defect rates. To address these issues, multi-laser collaborative scanning systems have emerged, allowing multiple lasers to operate simultaneously in the same build layer, significantly improving processing efficiency. However, in practical applications, multi-laser systems still face many challenges. For example, improper scanning area division can lead to some lasers being overloaded and some areas experiencing excessive heat input; unbalanced task scheduling can result in some lasers operating under overload while others remain idle, reducing parallel efficiency. Inappropriate division of labor among multiple lasers can cause repeated melting of adjacent areas, uneven boundary overlap, and in severe cases, warping, cracking, and voids.

[0021] To this end, the present invention proposes a distributed equalization scanning method, system and related equipment for additive manufacturing. Specifically, the distributed equalization scanning method, system and related equipment for additive manufacturing according to embodiments of the present invention are described below with reference to the accompanying drawings.

[0022] Figure 1 This is a flowchart of an additive manufacturing distributed equalization scanning method according to an embodiment of the present invention. It should be noted that the additive manufacturing distributed equalization scanning method of this embodiment can be applied to the additive manufacturing distributed equalization scanning system of this embodiment. This additive manufacturing distributed equalization scanning system can be configured on an electronic device or in a server. This application does not limit the scope of the application.

[0023] like Figure 1 As shown, the additive manufacturing distributed equalization scanning method includes: S110: Collect data information of the part to be processed. The data information includes data information of multiple slice layers. Specifically, the three-dimensional model of the part to be processed is sliced ​​to obtain data information of multiple slice layers.

[0024] In an embodiment of the present invention, data information of the parts to be processed can be collected based on the acquisition module in the device.

[0025] In this process, the part to be processed can be sliced ​​using a 3D model. The outline of each slice layer is a precise description of the geometry of that layer, thus obtaining the 2D outline of each slice layer.

[0026] The process involves generating initial scanning path planning information based on a two-dimensional contour and preset process rules, which determines the laser's trajectory. The estimated unit scanning heat input is then calculated based on this initial scanning path planning information and process parameters. These process parameters include, but are not limited to, power and scanning speed.

[0027] S120: Process the data information to obtain initial graphic partition data, and adjust the initial graphic partition data if it is determined that the initial graphic partition data meets the adjustment conditions to obtain the first target graphic partition data.

[0028] In embodiments of the present invention, when data information from multiple slice layers is obtained, the data information can be processed to obtain initial graphic partition data. Furthermore, if the initial graphic partition data is determined to meet adjustment conditions, the initial graphic partition data can be adjusted to obtain first target graphic partition data. Specific implementation details can be found in subsequent embodiments.

[0029] S130, based on the first target graphic partition data, re-estimate the total scanning time of each laser until the time difference of the total scanning time between lasers is less than the time threshold or the number of iterations reaches the preset number, and obtain the second target graphic partition data.

[0030] In an embodiment of the present invention, after obtaining the first target graphic partition data, the total scanning time of each laser can be re-estimated based on the first target graphic partition data until the time difference of the total scanning time between lasers is less than the time threshold or the number of iterations reaches the preset number, and then the second target graphic partition data is obtained, that is, the final target graphic partition data is obtained.

[0031] S140, the second target graphic partition data is allocated to each laser for scanning and printing.

[0032] In an embodiment of the present invention, when the second target graphic partition data is obtained, the second target graphic partition data can be allocated to each laser for scanning and printing.

[0033] According to an embodiment of the additive manufacturing distributed balanced scanning method of the present invention, data information of the part to be processed is collected, including data information of multiple slice layers. Specifically, the three-dimensional model of the part to be processed is sliced ​​to obtain data information of multiple slice layers. The data information is processed to obtain initial graphic partition data. If the initial graphic partition data meets the adjustment conditions, it is adjusted to obtain first target graphic partition data. Based on the first target graphic partition data, the total scanning time of each laser is re-estimated until the time difference between the total scanning times of the lasers is less than a time threshold or the number of iterations reaches a preset number, and second target graphic partition data is obtained. The second target graphic partition data is then allocated to each laser for scanning and printing. This method achieves precise balancing of scanning time among multiple lasers through iterative optimization of partitioning and dynamic task scheduling, effectively avoiding waiting and efficiency loss caused by uneven load, and significantly improving parallel processing efficiency.

[0034] To enable those skilled in the art to more readily understand the present invention, Figure 2 This is an additive manufacturing distributed equalization scanning method according to a specific embodiment of the present invention, such as... Figure 2 As shown, the additive manufacturing distributed equalization scanning method includes: S210: Collect data information of the part to be processed. The data information includes data information of multiple slice layers. Specifically, the three-dimensional model of the part to be processed is sliced ​​to obtain data information of multiple slice layers.

[0035] In the embodiments of the present invention, the implementation of step S210 can refer to the implementation of step S110 described above, and the present invention will not repeat it here.

[0036] S220 processes the data to obtain initial graphic partition data.

[0037] In an embodiment of the present invention, the region of each slice layer is discretized into squares; based on the position coordinates of each square, the region type of each square is determined to obtain the initial graphic partition data of each slice layer. Each square includes a set of scan lines and records the estimated scan time, position coordinates and region type. The region type includes laser region or overlapping region.

[0038] One approach is to use a graph partitioning method to intelligently partition the slice layer regions, thereby discretizing each slice layer region into squares.

[0039] The graph partitioning method considers factors such as geometric complexity and thermal load prediction. For example, the sliced ​​layer region is discretized into small square cells (e.g., 1mm × 1mm squares), with each square serving as a node. If two squares are spatially adjacent (four-connected or eight-connected), an edge is established between them, typically set as the reciprocal of the geometric distance or the thermal interaction intensity (i.e., edge weight). The thermal interaction intensity can be estimated based on a heat conduction model or historical data, reflecting the degree of thermal impact when adjacent squares are scanned by different lasers simultaneously. Each node has the following attributes: scan time (estimated based on fill line length and process parameters), thermal input (energy input per unit area), coordinates (xi, yi), and laser range marker (e.g., laser region 1, laser region 2, overlapping region). Each node is ultimately assigned to a specific laser.

[0040] S230, Determine that the initial graphic partition data meets the adjustment conditions.

[0041] In embodiments of the present invention, the total estimated scanning time of each laser and the time difference between the total estimated scanning times of the lasers are determined; if the time difference between the total estimated scanning times of the lasers is greater than a first preset time, the initial graphic partition data is determined to meet the adjustment conditions; and / or the size of each square is determined, and if the size of the square is greater than a first size threshold, the initial graphic partition data is determined to meet the adjustment conditions; and / or if the size of the square is less than a second size threshold, the initial graphic partition data is determined to meet the adjustment conditions.

[0042] In an embodiment of the present invention, initial graphic partition data, process parameters, and historical graphic partition data are input into a trained time prediction model to predict the scanning time, thereby obtaining the total estimated scanning time of the slice layer; based on the total estimated scanning time of the slice layer and the region type to which the square belongs, the total estimated scanning time of each laser is determined.

[0043] The specific implementation method for inputting initial graphic partition data, process parameters, and historical graphic partition data into the trained time prediction model to predict the scan time and obtain the total estimated scan time of the slice layer is as follows: 1. For each slice layer, construct a feature vector containing three types of information: Geometric load features: total scan line length of all squares, total solid area, total perimeter of the contour, etc. (reflecting the total workload). Region distribution features: scan line length ratio of laser zone 1, laser zone 2, and overlapping zone (reflecting the initial partitioning). Process and history features: process parameters such as scanning speed, laser power, and fill spacing, as well as the actual and estimated time deviation of the previous layer (used to correct for changes in equipment status). Finally, each slice layer becomes a fixed-dimensional numerical vector (e.g., 17-dimensional), which serves as the input to the SVM model.

[0044] 2. Using historical printing data, with the aforementioned feature vectors as input and the actual scan time as output, train a support vector regression model. For example, use the RBF kernel function to handle non-linear relationships. Optimize the hyperparameters (C, γ, ε) through cross-validation. After training, the model can accurately predict the total scan time of the current layer based on its feature vectors.

[0045] 3. The SVM model only outputs the total estimated scan time for the slice layer, but the solution requires knowledge of the individual scan time for each laser. The decomposition method is as follows: Based on the region type of the square, calculate the scan line length ratio and thermal interaction intensity for each region. Using a simple weighted allocation or an auxiliary SVR model, the total time is broken down into the time for laser region 1, laser region 2, and the overlapping region.

[0046] S240, if the initial graphic partition data meets the adjustment conditions, the initial graphic partition data is adjusted to obtain the first target graphic partition data.

[0047] In an embodiment of the present invention, when it is determined that the initial graphic partition data meets the adjustment conditions, and when it is determined that the time difference of the total estimated scanning time between lasers is greater than a first preset threshold, the scanning time of the squares in the overlapping area is obtained, and the squares in the overlapping area are sorted according to the scanning time to obtain a sorting result; based on the sorting result, the squares in the overlapping area are assigned to lasers with a total estimated scanning time less than a second preset time, until the total estimated scanning time of each laser is balanced; and / or when it is determined that the size of the square is greater than a first size threshold, the squares greater than the first size threshold are divided into sub-squares, and the sub-squares are assigned to lasers with a total estimated scanning time less than the second preset time, until the total estimated scanning time of each laser is balanced; and / or when it is determined that the size of the square is less than the second size threshold, the adjacent areas of the squares smaller than the second size threshold are traversed, and the squares smaller than the second size threshold are merged into the smallest area in the adjacent areas to obtain the first target graphic partition data.

[0048] In other words, when the time difference between the total estimated scanning time of the lasers exceeds a first preset threshold, the squares in the overlapping area are sorted by scanning time. Squares are preferentially assigned to the laser with the shorter current total time. Positional factors are also considered; for example, when there are two lasers (e.g., laser 1 and laser 2), squares with coordinates closer to laser 1 are preferentially assigned to laser 1, and those closer to laser 2 are preferentially assigned to laser 2. This minimizes laser skipping while ensuring time balance.

[0049] If the size of a square exceeds a first size threshold, the square is further divided into smaller sub-units (e.g., A1, A2). If there are two lasers (e.g., laser 1 and laser 2), the sub-units are allocated as needed to the laser with the shorter total estimated scanning time. This fine-grained adjustment prevents overall imbalance caused by a single large square, achieving time balance among the lasers.

[0050] If a square's size is less than a second size threshold, all adjacent regions of that square are traversed. These regions are then merged into the smallest adjacent region to avoid overloading larger areas. This reduces fragmented scanning paths and improves scanning efficiency.

[0051] S250, based on the first target graphic partition data, re-estimate the total scanning time of each laser until the time difference of the total scanning time between lasers is less than the time threshold or the number of iterations reaches the preset number, and obtain the second target graphic partition data.

[0052] In an embodiment of the present invention, after obtaining the first target graphic partition data, the total scanning time of each laser can be re-estimated based on the first target graphic partition data until the time difference of the total scanning time between lasers is less than the time threshold or the number of iterations reaches the preset number, and then the second target graphic partition data is obtained, that is, the final target graphic partition data is obtained.

[0053] The shapes of the graphic partitions include, but are not limited to, triangles, hexagons, etc. For example, graphic partitions include, but are not limited to... Figure 3 (a), (b), (c), (d).

[0054] S260 distributes the second target graphic partition data to each laser for scanning and printing.

[0055] In an embodiment of the present invention, when the second target graphic partition data is obtained, the second target graphic partition data is allocated to each laser for scanning and printing.

[0056] In the case where the second target graphic partition data is allocated to each laser for scanning and printing, the scanning time of each laser is monitored in real time. If one of the multiple lasers completes scanning ahead of the others, the scanning units are divided from the remaining tasks of the other lasers and allocated to the laser that has completed scanning. If one of the multiple lasers completes scanning ahead of the others and the overlapping area has been scanned, the load factor of the next layer is adjusted according to the time difference of the laser scanning time. The load factor is used to adjust the estimated time ratio of the laser during the initial allocation.

[0057] For example, such as Figure 4As shown, taking two lasers as an example, the solid-lined box represents the maximum scanning range of laser 1, the dashed-lined box represents the maximum scanning range of laser 2, Q3 is the area that can only be scanned by laser 1, Q5 is the area that can only be scanned by laser 2, and Q4 is the area that both laser 1 and laser 2 scan. The scanning order for each laser is from bottom to top. That is, laser 2 scans area Q5 first, and then scans area Q4; laser 1 scans area Q4 first, and then scans area Q3, avoiding the two lasers scanning adjacent areas. Laser 2, which scans its own area first, is allocated more time during area allocation. Where T2 is the estimated scanning time of laser 2, and T1 is the estimated scanning time of laser 1. The default value is 0.05. Due to potential errors in laser scanning and prediction, if laser 1 completes its scan first, then laser 2 will allocate a unit from the scanned stitching area to laser 1. If laser 2 completes its scan first, the stitching area is already complete, indicating a large prediction error by the system. Based on the recorded scanning time of laser 1... and the scanning time of laser 2 Adjust the load factor of the next layer ,Right now ,in It is the load factor value of the previous layer, thereby ensuring that the laser's working time is balanced.

[0058] In embodiments of the present invention, during multi-laser collaborative scanning, a slice layer is typically divided into regions handled by different lasers. If each slice layer uses a fixed straight line as the dividing line, the seam will always appear in the same position, creating a "weak surface" inside the part to be processed, which is prone to cracking or strength reduction under stress. Therefore, to avoid the seam always being on the same straight line, square wave or sawtooth-shaped dividing lines are used instead of simple straight lines. The wave pattern of the dividing line changes between adjacent slice layers, so that the seam is staggered between slice layers, avoiding the formation of a through-thin weak surface. Staggered layers are created in both the X and Y directions. In the Y direction, the wave amplitude or starting position of the dividing line is changed by adjusting the height H1 of the square wave; in the X direction, the dividing unit is translated in the X direction, for example, by half a square width, further staggering the splicing position. ,in, This indicates the maximum amplitude of the fluctuation in the Y direction, layer represents the slice layer, and mod represents the number of slice layers.

[0059] In other words, when most of the workpiece falls within a certain laser area, from the perspective of time equalization, the dividing line may be pushed to a certain extreme position; however, if each layer is divided in this fixed way, it will affect the strength of the workpiece. Therefore, the dividing line should be square wave shaped, and each layer should be different in the Y and X directions; where H1 is a parameter used to control the misalignment of layers in the Y direction.

[0060] For example, such as Figure 5 As shown, the shapes of the parts to be processed vary. If most of the parts fall within the area of ​​laser 2, from a time perspective, laser 1 should use its maximum area, meaning the segmentation position should be set at the critical line L1. However, if each layer is segmented at the critical line, the performance of the parts will be affected. To avoid all segments being on the same straight line, automatic fine-tuning into a square wave shape is required, with each layer having a different position. The height H1 in the Y direction can be set, differing between adjacent layers. The segmented units will also shift in the X direction, also differing between adjacent layers. The H1 value for each layer is then obtained. Figure 5 In the middle, L2 is the height line in the Y direction, that is, the height of L2-L1 is H1. Figure 5 In this context, X1 represents the grid width in the X direction. Preferably, the next layer's segmentation unit is translated in the X direction by (X1) / 2, but other values ​​can also be used for the X-direction translation.

[0061] In one embodiment of the invention, if the division is directly done evenly based on time or area, for example, using a straight line, the dividing line will always be in the same position, leading to a decrease in print strength. If there are fluctuations based on the straight dividing line, there will be losses and reduced efficiency. Therefore, using a checkerboard pattern, the dividing line is not a straight line, which achieves even division while avoiding the dividing line of each layer being in a different position. Figure 6 As shown, the non-shaded areas are scanned by laser 1, and the shaded areas are scanned by laser 2. The line separating the non-shaded and shaded areas is not a straight line, but a line similar to a square wave. The dividing lines of adjacent slice layers are different, thus improving the printing intensity of the parts at the splicing position. If, after partitioning, the area of ​​a certain region Q1 is found to be less than 10% of the regular area Sn, it needs to be merged into the adjacent partition Q2. This process is repeated for each adjacent partition, merging into the partition with the smallest area. If the square scanning time exceeds a threshold, the square is further divided into two parts, A2 and A1. A1 is assigned to laser 2 for scanning, ensuring that the scanning times of laser 1 and laser 2 are consistent. The position of the dividing line between A2 and A1 is determined based on the difference in scanning time between laser 1 and laser 2.

[0062] In one embodiment of the present invention, taking four galvanometers as an example, the area within each dividing line is divided into several small squares. The time of each small square and its position are recorded. The area is divided into laser 1, laser 2, laser 3, laser 4, and overlapping areas 1, 2, and 3. The time for laser 1, laser 2, laser 3, and laser 4 is calculated separately. Then, the time for each square is calculated and sorted, with shorter times allocated first. Coordinates closer to laser 1 are prioritized for laser 1, closer to laser 2, closer to laser 3, and closer to laser 4. Based on the scanning time of each square and the total scanning time, time balance among the lasers is achieved. Due to the increased number of lasers and the varying shapes of the parts, it may not be possible to achieve completely consistent scanning times for all four lasers. Therefore, priority is given to minimizing the maximum scanning time among the four lasers. Based on this, the scanning times of the remaining lasers are evenly distributed to balance the load on each laser.

[0063] In the embodiments of the present invention, the present invention is applicable to various types of additive manufacturing, such as laser galvanometer additive manufacturing, coaxial wire (powder) feeding additive manufacturing, and non-galvanometer ring cladding printing.

[0064] According to the additive manufacturing distributed equalization scanning method of the present invention, the abstract load balancing is transformed into a specific numerical target by introducing an estimated scanning time and a time difference threshold (a first preset time). Through iterative adjustment (S250) until the time difference converges, the workload of each laser in each slice is ensured to be highly synchronized. Large squares (greater than the first size threshold) are segmented and small squares (less than the second size threshold) are merged, avoiding the problem of a large area dragging down the overall speed or too many fragmented areas increasing the idle travel caused by improper discretization granularity, thereby maximizing the efficiency of multi-laser parallel operation. In the initial graph partitioning stage (S220), the scheme not only considers the geometric position, but also introduces the thermal interaction intensity as the edge weight and calculates the unit scan thermal input. This allows the partitioning results to effectively isolate high-heat input areas, preventing the heat from concentrating and accumulating in adjacent areas due to simultaneous scanning. When time differences occur, overlapping squares are prioritized for lasers with shorter scan times, balancing time and avoiding forced contour fragmentation in non-overlapping areas, thus maintaining the continuity of heat distribution. When a laser finishes early, the system can compensate by dividing scanning units from the remaining tasks of other lasers. This online compensation mechanism effectively addresses small deviations between actual scanning speed and theoretical predictions. Adjusting the load factor of the next layer based on the actual time difference of the previous layer (S260) gives this scheme a capability similar to feedforward control. As the number of printing layers increases, the system's accuracy in time prediction becomes increasingly higher, achieving cross-layer global optimization.

[0065] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0066] According to one aspect of the present invention, a distributed equalization scanning system for additive manufacturing is also proposed. Figure 7 This is a schematic diagram of an additive manufacturing distributed equalization scanning system according to an embodiment of the present invention; as shown. Figure 7 As shown, it includes: The acquisition module 710 is used to acquire data information of the part to be processed, the data information including data information of multiple slice layers, wherein the three-dimensional model of the part to be processed is sliced ​​to obtain the data information of multiple slice layers; The determining module 720 is used to process the data information to obtain initial graphic partition data, and to adjust the initial graphic partition data to obtain first target graphic partition data when it is determined that the initial graphic partition data meets the adjustment conditions. The acquisition module 730 is used to re-estimate the total scanning time of each laser based on the first target graphic partition data until the time difference of the total scanning time between the lasers is less than the time threshold or the number of iterations reaches the preset number, and then acquire the second target graphic partition data. The allocation module 740 is used to allocate the second target graphic partition data to each of the lasers for scanning and printing.

[0067] According to an embodiment of the additive manufacturing distributed equalization scanning system of the present invention, data information of the part to be processed is acquired, including data information of multiple slice layers. Specifically, the three-dimensional model of the part to be processed is sliced ​​to obtain data information of multiple slice layers. The data information is processed to obtain initial graphic partition data. If the initial graphic partition data meets the adjustment conditions, it is adjusted to obtain first target graphic partition data. Based on the first target graphic partition data, the total scanning time of each laser is re-estimated until the time difference between the total scanning times of the lasers is less than a time threshold or the number of iterations reaches a preset number, at which point second target graphic partition data is obtained. The second target graphic partition data is then allocated to each laser for scanning and printing. Thus, through iterative optimization of partitioning and dynamic task scheduling, precise equalization of scanning time among multiple lasers is achieved, effectively avoiding waiting and efficiency losses caused by uneven load, and significantly improving parallel processing efficiency.

[0068] Optionally, the determining module is specifically used to: discretize the region of each slice layer into squares; determine the region type of each square based on the position coordinates of each square, and obtain the initial graphic partition data of each slice layer, wherein each square includes a set of scan lines, and records the estimated scan time, the position coordinates and the region type, wherein the region type includes a laser region or an overlapping region.

[0069] Optionally, the determining module 720 is specifically configured to determine the total estimated scanning time of each of the lasers and the time difference between the total estimated scanning times of the lasers; if the time difference between the total estimated scanning times of the lasers is greater than a first preset time, determine that the initial graphic partition data meets the adjustment conditions; and / or determine the size of each square, if the size of the square is greater than a first size threshold, determine that the initial graphic partition data meets the adjustment conditions; and / or if the size of the square is less than a second size threshold, determine that the initial graphic partition data meets the adjustment conditions.

[0070] Optionally, the determining module 720 is specifically used to input the initial graphic partition data, process parameters, and historical graphic partition data into the trained time prediction model to predict the scanning time and obtain the total estimated scanning time of the slice layer; based on the total estimated scanning time of the slice layer and the region type to which the square belongs, the total estimated scanning time of each laser is determined.

[0071] Optionally, the determining module 720 is specifically configured to, when determining that the time difference between the total estimated scanning times of the lasers is greater than the first preset threshold, obtain the scanning time of the squares in the overlapping area, and sort the squares in the overlapping area according to the scanning time to obtain a sorting result; based on the sorting result, assign the squares in the overlapping area to the lasers whose total estimated scanning time is less than the second preset time, until the total estimated scanning time of each laser is balanced; and / or, when determining that the size of the square is greater than the first size threshold, divide the squares larger than the first size threshold into sub-squares, and assign the sub-squares to the lasers whose total estimated scanning time is less than the second preset time, until the total estimated scanning time of each laser is balanced; and / or, when determining that the size of the square is less than the second size threshold, traverse the adjacent areas of the squares smaller than the second size threshold, and merge the squares smaller than the second size threshold into the smallest area in the adjacent areas to obtain the first target graphic partition data.

[0072] Optionally, it also includes a monitoring module for real-time monitoring of the scanning time of each laser when the second target graphic partition data is allocated to each laser for scanning and printing; if one of the lasers completes scanning earlier than the other lasers, the scanning unit is divided from the remaining tasks of the other lasers and allocated to the laser that has completed scanning; if one of the lasers completes scanning earlier and the overlapping area has been scanned, the load factor of the next layer is adjusted according to the time difference of the scanning time of the lasers, and the load factor is used to adjust the estimated time ratio of the lasers during initial allocation.

[0073] According to one aspect of the present invention, an electronic device is provided.

[0074] Figure 8 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Figure 8 As shown, an electronic device may include one or more ( Figure 8 Only one is shown in the image. A processor 102 (which may include, but is not limited to, a microprocessor unit (MPU) or a programmable logic device (PLD)) and a memory 104 for storing data are also shown. In one exemplary embodiment, the electronic device may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 8The structure shown is for illustrative purposes only and does not limit the structure of the terminal device described above. For example, the terminal device may also include components that are more... Figure 8 The more or fewer components shown, or having the same Figure 8 Equivalent functions or ratios shown Figure 8 The functions shown have more different configurations.

[0075] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the additive manufacturing distributed equalization scanning method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to terminal devices via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0076] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the switching device. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0077] This invention proposes a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute an additive manufacturing distributed equalization scanning method.

[0078] The applicant of this invention has provided a detailed description of the embodiments of the invention in conjunction with the accompanying drawings. However, those skilled in the art should understand that the above embodiments are merely preferred embodiments of the invention. The detailed description is only intended to help readers better understand the spirit of the invention and is not intended to limit the scope of protection of the invention. On the contrary, any improvements or modifications made based on the inventive spirit of the invention should fall within the scope of protection of the invention.

[0079] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0080] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

[0081] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the embodiments of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the protection scope of the present invention.

Claims

1. A method of additive manufacturing distributed equalization scanning, characterized in that, include: Data information of the part to be processed is collected, including data information of multiple slice layers, wherein the three-dimensional model of the part to be processed is sliced ​​to obtain data information of multiple slice layers; The data information is processed to obtain initial graphic partition data, and if the initial graphic partition data meets the adjustment conditions, the initial graphic partition data is adjusted to obtain the first target graphic partition data. Based on the first target graphic partition data, the total scanning time of each laser is re-estimated until the time difference of the total scanning time between the lasers is less than the time threshold or the number of iterations reaches the preset number, and then the second target graphic partition data is obtained. The second target graphic partition data is allocated to each of the lasers for scanning and printing.

2. The additive manufacturing distributed equalization scanning method of claim 1, wherein, The data information is processed to obtain initial graphic partition data, including: Discretize the region of each slice layer into squares; Based on the position coordinates of each square, the region type of each square is determined, and the initial graphic partition data of each slice layer is obtained. Each square includes a set of scan lines and records the estimated scan time, the position coordinates and the region type. The region type includes laser region or overlapping region.

3. The additive manufacturing distributed equalization scanning method of claim 2, wherein, Determining that the initial graphic partition data meets the adjustment conditions includes: Determine the total estimated scan time for each of the lasers and determine the time difference between the total estimated scan times of the lasers; If the time difference between the total estimated scanning time of the lasers is greater than a first preset time, it is determined that the initial graphic partition data meets the adjustment conditions; and / or Determine the size of each of the squares, and if the size of a square is greater than a first size threshold, determine that the initial graphic partition data meets the adjustment conditions; and / or If the size of the square is determined to be less than the second size threshold, the initial graphic partition data is determined to meet the adjustment conditions.

4. The additive manufacturing distributed equalization scanning method of claim 3, wherein, Determining the total estimated scan time of the laser includes: The initial graphic partition data, process parameters and historical graphic partition data are input into the trained time prediction model to predict the scanning time and obtain the total estimated scanning time of the slice layer. The total estimated scan time for each laser is determined based on the total estimated scan time of the slice layer and the region type to which the square belongs.

5. The additive manufacturing distributed equalization scanning method of claim 3, wherein, The initial graphic partition data is adjusted to obtain the first target graphic partition data, including: If the time difference between the total estimated scanning time of the lasers is greater than the first preset threshold, the scanning time of the squares in the overlapping area is obtained, and the squares in the overlapping area are sorted according to the scanning time to obtain the sorting result; Based on the sorting results, the squares in the overlapping area are assigned to lasers whose total estimated scanning time is less than a second preset time, until the total estimated scanning time of each laser is balanced; and / or If the size of the square is determined to be greater than the first size threshold, the square larger than the first size threshold is divided into sub-squares, and the sub-squares are assigned to lasers whose total estimated scanning time is less than a second preset time, until the total estimated scanning time of all lasers is balanced; and / or If the size of the square is determined to be less than the second size threshold, the adjacent regions of the squares smaller than the second size threshold are traversed, and the squares smaller than the second size threshold are merged into the smallest region among the adjacent regions to obtain the first target graphic partition data.

6. The additive manufacturing distributed equalization scanning method according to claim 1, characterized in that, Also includes: When the second target graphic partition data is allocated to each of the lasers for scanning and printing, the scanning time of each of the lasers is monitored in real time. If one of the lasers completes scanning before the others, a scanning unit will be allocated from the remaining tasks of the other lasers to the laser that has completed scanning; If one of the lasers completes scanning of the overlapping area ahead of schedule, the load factor of the next layer is adjusted according to the time difference of the laser's scanning time. The load factor is used to adjust the estimated time ratio of the laser during initial allocation.

7. A distributed equalization scanning system for additive manufacturing, characterized in that, include: The acquisition module is used to acquire data information of the part to be processed. The data information includes data information of multiple slice layers. The three-dimensional model of the part to be processed is sliced ​​to obtain the data information of multiple slice layers. The determining module is used to process the data information to obtain initial graphic partition data, and to adjust the initial graphic partition data to obtain first target graphic partition data when it is determined that the initial graphic partition data meets the adjustment conditions. The acquisition module is used to re-estimate the total scanning time of each laser based on the first target graphic partition data until the time difference of the total scanning time between the lasers is less than the time threshold or the number of iterations reaches the preset number, and then acquire the second target graphic partition data. The allocation module is used to allocate the second target graphic partition data to each of the lasers for scanning and printing.

8. The additive manufacturing distributed equalization scanning system according to claim 7, characterized in that, The determining module is specifically used for: Discretize the region of each slice layer into squares; Based on the position coordinates of each square, the region type of each square is determined, and the initial graphic partition data of each slice layer is obtained. Each square includes a set of scan lines and records the estimated scan time, the position coordinates and the region type. The region type includes laser region or overlapping region.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 6.

10. A non-transitory computer-readable storage medium storing computer instructions, characterized in that, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 6.

Images