Laser cutting method based on visual positioning and laser plate splitting machine

Abstract

The invention provides a laser cutting method and a laser plate splitting machine based on visual localization, and the method comprises the steps: determining a laser cutting path based on a standard image template and a current image; analyzing the historical cutting effect to obtain an analysis result; and the laser cutting path is adjusted based on the analysis result. According to the laser cutting method based on visual positioning and the laser plate splitting machine, the historical cutting effect is analyzed, cutting adjustment is conducted according to the analysis result, and then more accurate and effective visual positioning cutting is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of machine vision, and particularly to a laser cutting method and a laser board splitting machine based on visual positioning. Background Art

[0002] The laser cutting PCB board splitting machine is an advanced PCB board splitting and processing equipment, which can achieve high-precision, high-speed, high-efficiency and high-quality board splitting processing. It is widely used in the fields of electronics, communication, computer, automobile, etc. In the existing laser cutting machines, products and product carriers are transferred by a roller shaft method, and the laser cutting head moves above the roller shaft table, and the PCB board is cut by calibrating the position through a vision module. However, the calibration of the vision module is generally carried out before cutting, and the position is calibrated according to a standard calibration image template. In the actual application process, due to the influence of mechanisms, etc., there are situations of partial or overall offset. How to achieve more accurate and effective visual positioning cutting is a technical problem that needs to be solved urgently. Summary of the Invention

[0003] One of the purposes of the present invention is to provide a laser cutting method and a laser board splitting machine based on visual positioning. By analyzing the historical cutting effect and making cutting adjustments based on the analysis result, more accurate and effective visual positioning cutting is realized.

[0004] A laser cutting method based on visual positioning provided by an embodiment of the present invention includes: Determine a laser cutting path based on a standard image template and a current image; Analyze the historical cutting effect to obtain an analysis result; Adjust the laser cutting path based on the analysis result.

[0005] Preferably, determining a laser cutting path based on a standard image template and a current image includes: Map the standard image template to the current image and translate it; During the translation process, compare the positioning area in the standard image template with the corresponding area in the current image; When the comparison is in line, determine the cutting trajectory in the current image according to the preset trajectory line in the standard image template; Determine the trajectory data of the cutting trajectory according to the coordinate system corresponding to the current image; According to the coordinate system conversion rule, convert the trajectory data of the cutting trajectory into the laser cutting path of the laser cutting head.

[0006] Preferably, analyzing the historical cutting effect to obtain an analysis result includes: Determine the expected trajectory and the actual trajectory corresponding to the cutting path of the first preset number of times; Perform point sampling on the expected trajectory and the actual trajectory to determine a plurality of associated point groups; Based on the deviations between each point in each point group, a deviation array of the cutting path is constructed; Arranging the deviation arrays of each cutting in order to form a deviation analysis data set; The deviation analysis data set is analyzed using a pre-configured deviation analysis library to obtain analysis results.

[0007] Preferably, the laser cutting path is adjusted, including: Analyze the analysis results, determine the point sampling rules and the deviation correction values ​​of each point; Based on the point sampling rules, the laser cutting path is sampled and the sampling points are corrected according to the deviation correction values ​​of each point; The corrected sampling points are refitted to obtain the adjusted laser cutting path.

[0008] Preferably, the laser cutting method based on visual positioning further includes: Determine the expected trajectory and the actual trajectory corresponding to the cutting path of the first second preset number of times; Perform point sampling on the expected trajectory and the actual trajectory to determine a plurality of associated point groups; Based on the deviations between each point in each point group, a deviation array of the cutting path is constructed; The risk assessment library configured in advance is used to perform risk assessment on the deviation array of all cutting times within the second preset number of times. When the risk assessment meets the trigger condition, the adjustment of the laser cutting path is triggered.

[0009] The present invention also provides a laser panel splitter, comprising a main body, a conveying mechanism, at least one image acquisition mechanism, at least one laser cutting mechanism and a main controller; the conveying mechanism is used to convey the plate to be cut; the image acquisition mechanism and the laser cutting mechanism are associated one-to-one and are configured above the conveying mechanism, and the laser cutting mechanism can cut different plates separately or collaboratively cut the same plate; a laser cutting system based on visual positioning is configured in the main controller, and the laser cutting system includes: a path planning module, an analysis module and an adjustment module; wherein the path planning module determines the laser cutting path based on a standard image template and a current image; the analysis module analyzes the historical cutting effects and obtains the analysis results; the adjustment module adjusts the laser cutting path based on the analysis results.

[0010] Preferably, the path planning module performs the following operations: Map the standard image template to the current image and translate it; During the translation process, the positioning area in the standard image template is compared with the corresponding area in the current image; When the comparison is consistent, the cutting trajectory in the current image is determined according to the preset trajectory line in the standard image template; Determine the trajectory data of the cutting trajectory according to the coordinate system corresponding to the current image; According to the coordinate system conversion rules, the trajectory data of the cutting trajectory is converted into a laser cutting path of the laser cutting head.

[0011] Preferably, the analysis module performs the following operations: Determine the expected trajectory and the actual trajectory corresponding to the cutting path of the first preset number of times; Perform point sampling on the expected trajectory and the actual trajectory to determine a plurality of associated point groups; Based on the deviations between each point in each point group, a deviation array of the cutting path is constructed; Arranging the deviation arrays of each cutting in order to form a deviation analysis data set; The deviation analysis data set is analyzed using a pre-configured deviation analysis library to obtain analysis results.

[0012] Preferably, the adjustment module performs the following operations: Analyze the analysis results, determine the point sampling rules and the deviation correction values ​​of each point; Based on the point sampling rules, the laser cutting path is sampled and the sampling points are corrected according to the deviation correction values ​​of each point; The corrected sampling points are refitted to obtain the adjusted laser cutting path.

[0013] Preferably, the laser panel separator further comprises: a risk trigger module; The risk trigger module performs the following operations: Determine the expected trajectory and the actual trajectory corresponding to the cutting path of the first second preset number of times; Perform point sampling on the expected trajectory and the actual trajectory to determine a plurality of associated point groups; Based on the deviations between each point in each point group, a deviation array of the cutting path is constructed; The risk assessment library configured in advance is used to perform risk assessment on the deviation array of all cutting times within the second preset number of times. When the risk assessment meets the trigger condition, the adjustment of the laser cutting path is triggered.

[0014] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0015] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings: Figure 1 Schematic diagram of a laser cutting method based on visual positioning in an embodiment of the present invention; Figure 2 A schematic diagram of a laser panel separator according to an embodiment of the present invention; Figure 3 Schematic diagram of a laser cutting system based on vision positioning in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0018] The embodiment of the present invention provides a laser cutting method based on visual positioning, such as Figure 1 As shown, including: Step 1: Determine the laser cutting path based on the standard image template and the current image; The existing visual positioning laser cutting methods all use an image acquisition device to acquire an image of the working area corresponding to the laser cutting head, and then analyze the current image. Generally, a standard image template is used to compare with the current image to locate the real-time position of the board to be cut in the working area, and then the board is fitted according to the position where it needs to be cut to obtain the laser cutting path; that is, based on the standard image template and the current image, the laser cutting path is determined, including: mapping the standard image template to the current image and translating; comparing the positioning area in the standard image template with the corresponding area in the current image during the translation process; when the comparison is consistent, the cutting trajectory in the current image is determined according to the preset trajectory line in the standard image template; according to the coordinate system corresponding to the current image, the trajectory data of the cutting trajectory is determined; according to the coordinate system conversion rules, the trajectory data of the cutting trajectory is converted into the laser cutting path of the laser cutting head; Step 2: Analyze the historical cutting effects and obtain the analysis results; This application considers the effect of actual application to improve cutting accuracy; specifically: the effect of cutting before the current cutting operation is analyzed, and the results of the analysis are used to guide the current cutting, which can effectively consider the coordination of various parts of the machine, and the cutting deviation under the influence of environmental factors, thereby achieving improved cutting accuracy; Step 3: Adjust the laser cutting path based on the analysis results. The analysis results mainly indicate whether there is an offset in each cut before the current cutting operation. If an offset occurs, determine whether to make adjustments. For example, if the first cut is offset to the left and the second cut is offset to the right, both are offset to the left and right at the expected position, and the center of the offset is at the expected position, indicating that no adjustment is required. If each time the offset is to the left or right, then adjustment is required. In order to analyze the historical cutting effect, the historical cutting effect is analyzed and the analysis result is obtained, including: Determine the expected trajectory and the actual trajectory corresponding to the cutting path of the first preset number of times; wherein the first preset number of times can be any value between 2 and 1; The expected trajectory and the actual trajectory are sampled to determine multiple associated point groups; the point sampling rule is that the number of sampled points on the expected trajectory and the actual trajectory is the same, and then equidistant sampling is performed to obtain each point; the points are associated according to the same sequence number after being sorted on the expected trajectory or the actual trajectory to obtain an associated point group; Based on the deviations between the points in each point group, a deviation array of the cutting path is constructed; the deviations are sorted according to the sequence numbers of the points in the point group to obtain a deviation array; The deviation arrays of each cutting are arranged in order to form a deviation analysis data set; that is, each row in the deviation analysis data set corresponds to a deviation array, and the arrays are arranged in chronological order from top to bottom; The deviation analysis data set is analyzed with a pre-configured deviation analysis library to obtain the analysis result. The deviation analysis library is a pre-analysis configuration, and the deviation analysis data set is associated with the analysis result in a one-to-one correspondence in the library.

[0019] In order to achieve accurate adjustment of the laser cutting path of the laser cutting head, the laser cutting path is adjusted, including: Analyze the analysis results to determine the point sampling rules and the deviation correction values ​​of each point; the point sampling rules actually specify the number of points for equal-interval sampling; the analysis results contain the data corresponding to the point sampling rules and the deviation correction values ​​of each point; the analysis process is to obtain the point sampling rules and the deviation correction values ​​of each point by understanding this part of the data; Based on the point sampling rules, the laser cutting path is sampled and the sampling points are corrected according to the deviation correction values ​​of each point; The corrected sampling points are refitted to obtain the adjusted laser cutting path.

[0020] Since calculation and adjustment need to be performed each time according to historical analysis, it is troublesome and unnecessary. In order to determine when historical analysis is needed for adjustment, in one embodiment, the laser cutting method based on visual positioning further includes: Determine the expected trajectory and the actual trajectory corresponding to the cutting path of the second preset number of times; the second preset number is set smaller than the first preset number; for example: the first preset number is set to 5, and the second preset number is set to 2; Perform point sampling on the expected trajectory and the actual trajectory to determine a plurality of associated point groups; Based on the deviations between each point in each point group, a deviation array of the cutting path is constructed; The risk assessment is performed on the deviation array of all cutting times within the second preset number of times using a pre-configured risk assessment library. When the risk assessment meets the trigger condition, the adjustment of the laser cutting path is triggered. The risk assessment library is also configured for pre-analysis. The deviation array in the library is associated with the assessment value in a one-to-one correspondence. The assessment value of the corresponding number of times is obtained through the deviation array of each cutting. Then, based on the weight coefficient corresponding to each number of times, the sum of the product of the assessment value of each cutting and the corresponding weight coefficient is used as the total risk assessment value. The risk assessment value is used as the basis for trigger judgment. When the risk assessment value is greater than or equal to the risk threshold configured in the trigger condition, the laser cutting path is adjusted.

[0021] When an adjustment is triggered, it indicates that the cutting path needs to be adjusted. Therefore, how to make prior adjustments to subsequent cutting is the guarantee for ensuring the accuracy of subsequent cutting. In one embodiment, the laser cutting method based on visual positioning further includes: configuring a pre-adjustment array, where pre-adjustment values for each point on the trajectory are configured in the pre-adjustment array; in the initial stage (when the software just runs), all the values in the pre-adjustment array are set to zero; at this time, after the first adjustment is triggered, the deviation correction values of each point used for adjustment are calculated with a preset pre-adjustment coefficient (any one of 0.1 to 0.9) to obtain the corresponding values for each point in the pre-adjustment array; when the second adjustment is triggered, according to the number of cuts between the two adjustments, query the preset coefficient distribution table to determine the coefficients corresponding to the first adjustment and the second adjustment; based on the sum of the products of the deviation correction values of each point used for the first adjustment and the second adjustment and their respective corresponding coefficients, as the corresponding values for each point in the pre-adjustment array; thereafter, after each adjustment, according to the preset coefficient distribution table, query the coefficient and use the sum of the products of the deviation correction values of each point used for each adjustment and their respective corresponding coefficients, as the corresponding values for each point in the pre-adjustment array; however, with the increase in the number of adjustments, the amount of data for previous adjustments that need to be analyzed is increasing. At this time, the analysis volume is large, there is a large delay for cutting, and the improvement in accuracy is not significant. Therefore, a number threshold can be configured. When the historical cuts exceeding this number threshold are not considered, that is, the data of historical cuts with the number of adjustments between the historical cut and the current cut greater than the number threshold are not within the consideration range; At each update and reset, a zero adjustment is made to the pre-adjustment array. To extend the time when the first adjustment occurs, the pre-adjustment coefficient can be configured. By analyzing the pre-adjustment coefficient after each historical reset and the last pre-adjustment array, a configuration analysis data set is constructed, and then the corresponding configuration value is retrieved from the pre-configured configuration library to configure the pre-adjustment coefficient; the configuration library is pre-analyzed and constructed, and the configuration values in the library are in one-to-one correspondence with the configuration analysis data set; each row of data in the configuration analysis data set corresponds to the pre-adjustment coefficient after an update and reset and the data in the last pre-adjustment array; however, this configuration rule requires a large amount of data. Therefore, a number threshold can be configured, and when the number of update and reset times reaches the number threshold, the configuration adjustment of the pre-adjustment coefficient is carried out.

[0022] Under normal circumstances, the number of cuts increases between each adjustment. If there is a trend of decreasing number of cuts, it is necessary to reset the pre-adjustment array to zero and reduce the pre-adjustment coefficient. The trend of decreasing number of cuts can be determined by analyzing at least 3 to 5 adjustments. When the number of cuts decreases in sequence, it can be determined as a trend of decreasing number of cuts. The adjustment of the pre-adjustment coefficient can be configured with a reduction step or an increase step. Each reduction or adjustment is adjusted according to the reduction step or the increase step. The reduction step or the increase step is the difference between the adjusted value and the value before the adjustment.

[0023] The present invention also provides a laser board splitter, comprising: a main body, a conveying mechanism, at least one image acquisition mechanism, at least one laser cutting mechanism and a main controller; the conveying mechanism is used to convey the board to be cut; the image acquisition mechanism and the laser cutting mechanism are associated one by one and are arranged above the conveying mechanism, and the laser cutting mechanism can cut different boards respectively or cooperate to cut the same board; Figure 2 As shown, it is a laser panel separator using two image acquisition mechanisms and two laser cutting mechanisms, and the laser panel separator includes: a main body 10, a conveying mechanism 11, two image acquisition mechanisms 12, two laser cutting mechanisms 13 and a main controller 14; the two image acquisition mechanisms 12 and the two laser cutting mechanisms 13 form two cutting stations; when cutting the same plate, the conveying mechanism conveys the plate to be cut to the bottom of the image acquisition mechanism, and the two image acquisition mechanisms scan and shoot from both sides of the plate respectively, and the controller splices and analyzes the images, and then controls the laser cutting mechanism to perform coordinated cutting; when cutting different plates, the conveying mechanism conveys two plates at the same time, and conveys them to the bottom of each laser cutting mechanism respectively, and then the corresponding image acquisition mechanism performs image scanning, plans cutting, and then the laser cutting mechanism performs separate cutting; The main controller is equipped with a laser cutting system based on visual positioning, such as Figure 3 As shown, the laser cutting system includes: a path planning module 1, an analysis module 2 and an adjustment module 3; wherein the path planning module 1 determines the laser cutting path based on the standard image template and the current image; the analysis module 2 analyzes the historical cutting effects and obtains the analysis results; the adjustment module 3 adjusts the laser cutting path based on the analysis results. The laser cutting system adopts a parallel processing mode when the laser cutting mechanism cuts different plates, that is, path planning and adjustment are performed separately; when the laser cutting mechanism cuts the same plate, the current image is obtained by splicing the images collected by each image acquisition mechanism; Among them, the path planning module performs the following operations: Map the standard image template to the current image and translate it; During the translation process, the positioning area in the standard image template is compared with the corresponding area in the current image; When the comparison is consistent, the cutting trajectory in the current image is determined according to the preset trajectory line in the standard image template; Determine the trajectory data of the cutting trajectory according to the coordinate system corresponding to the current image; According to the coordinate system conversion rules, the trajectory data of the cutting trajectory is converted into a laser cutting path of the laser cutting head.

[0024] The analysis module performs the following operations: Determine the expected trajectory and the actual trajectory corresponding to the cutting path of the first preset number of times; Perform point sampling on the expected trajectory and the actual trajectory to determine a plurality of associated point groups; Based on the deviations between each point in each point group, a deviation array of the cutting path is constructed; Arranging the deviation arrays of each cutting in order to form a deviation analysis data set; The deviation analysis data set is analyzed using a pre-configured deviation analysis library to obtain analysis results.

[0025] The adjustment module performs the following operations: Analyze the analysis results, determine the point sampling rules and the deviation correction values ​​of each point; Based on the point sampling rules, the laser cutting path is sampled and the sampling points are corrected according to the deviation correction values ​​of each point; The corrected sampling points are refitted to obtain the adjusted laser cutting path.

[0026] In one embodiment, the laser panel separator further includes: a risk trigger module; The risk trigger module performs the following operations: Determine the expected trajectory and the actual trajectory corresponding to the cutting path of the first second preset number of times; Perform point sampling on the expected trajectory and the actual trajectory to determine a plurality of associated point groups; Based on the deviations between each point in each point group, a deviation array of the cutting path is constructed; The risk assessment library configured in advance is used to perform risk assessment on the deviation array of all cutting times within the second preset number of times. When the risk assessment meets the trigger condition, the adjustment of the laser cutting path is triggered.

[0027] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A laser cutting method based on visual positioning, characterized in that: include: Determine the laser cutting path based on the standard image template and the current image; Analyze the historical cutting effects and obtain the analysis results; Based on the analysis results, the laser cutting path is adjusted.

2. The laser cutting method based on visual positioning according to claim 1, characterized in that: Determine the laser cutting path based on the standard image template and the current image, including: Map the standard image template to the current image and translate it; During the translation process, the positioning area in the standard image template is compared with the corresponding area in the current image; When the comparison is consistent, the cutting trajectory in the current image is determined according to the preset trajectory line in the standard image template; Determine the trajectory data of the cutting trajectory according to the coordinate system corresponding to the current image; According to the coordinate system conversion rules, the trajectory data of the cutting trajectory is converted into a laser cutting path of the laser cutting head.

3. The laser cutting method based on visual positioning according to claim 1, characterized in that: Analyze the historical cutting effects and obtain the analysis results, including: Determine the expected trajectory and the actual trajectory corresponding to the cutting path of the first preset number of times; Perform point sampling on the expected trajectory and the actual trajectory to determine multiple associated point groups; Based on the deviations between each point in each point group, a deviation array of the cutting path is constructed; Arranging the deviation arrays of each cutting in order to form a deviation analysis data set; The deviation analysis data set is analyzed using a pre-configured deviation analysis library to obtain analysis results.

4. The laser cutting method based on visual positioning according to claim 1, characterized in that: Based on the analysis results, the laser cutting path is adjusted, including: Analyze the analysis results, determine the point sampling rules and the deviation correction values ​​of each point; Based on the point sampling rules, the laser cutting path is sampled and the sampling points are corrected according to the deviation correction values ​​of each point; The corrected sampling points are refitted to obtain the adjusted laser cutting path.

5. A laser panel splitter, comprising a main body, a conveying mechanism, at least one image acquisition mechanism, at least one laser cutting mechanism and a main controller; characterized in that: The conveying mechanism is used to convey the plates to be cut; the image acquisition mechanism and the laser cutting mechanism are associated one-to-one and are configured above the conveying mechanism, and the laser cutting mechanism can cut different plates separately or collaboratively cut the same plate; a laser cutting system based on visual positioning is configured in the main controller, and the laser cutting system includes: a path planning module, an analysis module and an adjustment module; wherein the path planning module determines the laser cutting path based on a standard image template and a current image; the analysis module analyzes the historical cutting effects and obtains the analysis results; the adjustment module adjusts the laser cutting path based on the analysis results.

6. The laser panel separator according to claim 5, characterized in that: The path planning module performs the following operations: Map the standard image template to the current image and translate it; During the translation process, the positioning area in the standard image template is compared with the corresponding area in the current image; When the comparison is consistent, the cutting trajectory in the current image is determined according to the preset trajectory line in the standard image template; Determine the trajectory data of the cutting trajectory according to the coordinate system corresponding to the current image; According to the coordinate system conversion rules, the trajectory data of the cutting trajectory is converted into a laser cutting path of the laser cutting head.

7. The laser panel separator according to claim 5, characterized in that: The analysis module performs the following operations: Determine the expected trajectory and the actual trajectory corresponding to the cutting path of the first preset number of times; Perform point sampling on the expected trajectory and the actual trajectory to determine a plurality of associated point groups; Based on the deviations between each point in each point group, a deviation array of the cutting path is constructed; Arranging the deviation arrays of each cutting in order to form a deviation analysis data set; The deviation analysis data set is analyzed using a pre-configured deviation analysis library to obtain analysis results.

8. The laser panel separator according to claim 5, characterized in that: The adjustment module performs the following operations: Analyze the analysis results, determine the point sampling rules and the deviation correction values ​​of each point; Based on the point sampling rules, the laser cutting path is sampled and the sampling points are corrected according to the deviation correction values ​​of each point; The corrected sampling points are refitted to obtain the adjusted laser cutting path.

9. The laser panel separator according to claim 5, characterized in that: Also includes: Risk trigger module; The risk trigger module performs the following operations: Determine the expected trajectory and the actual trajectory corresponding to the cutting path of the first second preset number of times; Perform point sampling on the expected trajectory and the actual trajectory to determine a plurality of associated point groups; Based on the deviations between each point in each point group, a deviation array of the cutting path is constructed; The risk assessment library configured in advance is used to perform risk assessment on the deviation array of all cutting times within the second preset number of times. When the risk assessment meets the trigger condition, the adjustment of the laser cutting path is triggered.

Images