Workpiece digital model alignment method, apparatus, equipment and computer-readable storage medium

Abstract

This specification relates to a method, apparatus, device, and computer-readable storage medium for aligning digital models of workpieces. The alignment method includes: determining initial values ​​for preset weight function parameters; determining a first template point element corresponding to a workpiece point element; defining a first distance between the first template point element and its corresponding workpiece point element; substituting the first distance into the preset weight function, and re-determining a second template point element corresponding to the workpiece point element based on the obtained first weight data; defining a second distance between the second template point element and its corresponding workpiece point element; if a first convergence condition is met based on the second distance, adjusting the initial parameter values; repeating the above steps until the second convergence condition is met, obtaining a target correspondence between the workpiece point element and the second template point element; and performing an alignment operation using the target correspondence. The embodiments in this specification can effectively suppress the influence of noise and improve the alignment accuracy of workpiece point elements and model point elements.

Description

Technical Field

[0001] This specification relates to the field of industrial automation technology, and in particular to a method, apparatus, device, and computer-readable storage medium for aligning digital models of workpieces. Background Technology

[0002] In industries such as workpiece manufacturing and processing, workpiece production relies on a pre-designed workpiece model. After workpiece manufacturing is completed, it is typically necessary to match, inspect, or measure the model's point cloud data with the acquired workpiece point cloud data to evaluate the workpiece's processing quality. With technological advancements, the most common method currently is to use computers to automatically align the acquired workpiece data with the model data. However, due to the influence of the production environment, the acquired workpiece data may contain a significant amount of noise, resulting in a need to improve alignment accuracy. Summary of the Invention

[0003] This specification aims to address, at least to some extent, one of the technical problems in the related art. To this end, one objective of this specification is to propose a workpiece digital model alignment method that, by iteratively adjusting the parameters of a preset weighting function, continuously reduces the error distance between workpiece point elements and template point elements, effectively suppressing the influence of noise and improving the alignment accuracy of workpiece point elements and model point elements.

[0004] The second objective of this specification is to provide a workpiece digital model alignment device.

[0005] The third objective of this specification is to provide a computer-readable storage medium.

[0006] The fourth objective of this specification is to provide an electronic device.

[0007] To achieve the above objectives, a workpiece digital model alignment method is proposed in the first aspect of this specification. The workpiece corresponds to a template. The workpiece digital model alignment method includes: determining the parameter range of a preset weight function and determining initial parameter values ​​within the parameter range; identifying a first template point element in the template point cloud data that satisfies a preset distance condition with a workpiece point element in the workpiece point cloud data; wherein the distance between the first template point element and its corresponding workpiece point element is a first distance; substituting the first distance into the preset weight function to obtain first weight data, and re-determining a second template point element corresponding to the workpiece point element based on the first weight data; wherein the distance between the second template point element and its corresponding workpiece point element is a second distance; if the correspondence between the workpiece point element and the second template point element satisfies a first convergence condition based on the second distance, adjusting the initial parameter value and using the adjusted initial parameter value as the initial parameter value; repeating the above steps until the adjusted initial parameter value satisfies the second convergence condition, thereby obtaining a target correspondence between the workpiece point element and the second template point element; and performing alignment operations between the workpiece and the template using the target correspondence.

[0008] According to the workpiece digital model alignment method of the embodiments of this specification, firstly, within a predetermined parameter range, a value is determined as the initial value of the preset weight function parameter for one iteration cycle. In the template point cloud data of the template, a first template point element corresponding to the workpiece point element is first determined based on a preset distance condition. Then, the first template point element is adjusted using the preset weight function, and a second template point element corresponding to the workpiece point element is re-determined in the template point cloud data. When the correspondence between the workpiece point element and the second template point element satisfies the first convergence condition based on the second distance between the second template point element and the workpiece point element, the initial value of the preset weight function parameter is adjusted, and the next iteration cycle begins. This process is iterated continuously until the adjusted initial parameter value satisfies the second convergence condition, thus obtaining the target correspondence between the workpiece point element and the second template point element. Based on the target correspondence, alignment operations can be performed between the workpiece and the template. The workpiece digital model alignment method in this specification continuously reduces the determination range between the second template point elements corresponding to the workpiece point elements by iterating the parameters of the preset weight function. This effectively suppresses the influence of noise in the workpiece point cloud data and improves the accuracy of the second template point elements corresponding to the workpiece point elements, thereby achieving the effect of improving the alignment accuracy between the workpiece point elements and the template point elements.

[0009] In some embodiments of this specification, re-determining the second template point element corresponding to the workpiece point element based on the first weight data includes: when the first weight data is within a preset weight range, using the first template point element as the second template point element; when the first weight data is not within the preset weight range, determining the second template point element that satisfies a preset distance condition from other template point cloud data besides the first template point element.

[0010] In some embodiments of this specification, the preset weighting function is an exponential function with a preset constant as the base. Substituting the first distance into the preset weighting function to obtain the first weight data may include: determining the ratio between the square of the first distance and the square of the initial parameter value; using the negative value of the ratio as the exponent of the preset constant to obtain the first weight data.

[0011] In some embodiments of this specification, the initial value of the parameter is the maximum value of the parameter range. Adjusting the initial value of the parameter and using the adjusted initial value as the initial value of the parameter includes: decreasing the initial value of the parameter and using the decreased initial value as the initial value of the parameter.

[0012] In some embodiments of this specification, the following method is used to determine whether the adjusted initial value of the parameter satisfies the second convergence condition: if the reduced initial value of the parameter is less than or equal to the minimum value of the parameter range, it is determined that the second convergence condition is satisfied.

[0013] In some embodiments of this specification, determining that the correspondence between workpiece point elements and second template point elements satisfies a first convergence condition based on a second distance may include: determining a first transformation matrix between workpiece point elements and second template point elements based on the second distance and a preset error function; performing a rigid transformation on the workpiece point elements using the first transformation matrix to obtain transformed point elements; determining a target distance between the transformed point elements and second template point elements; and determining that the correspondence between the workpiece point elements and second template point elements satisfies the first convergence condition when the target distance is less than a preset distance threshold.

[0014] In some embodiments of this specification, there is a correspondence between the transformation point element and the workpiece point element. The second template point element corresponding to the transformation point element is determined by the correspondence between the workpiece point element and the second template point element. Determining the target distance between the transformation point element and the second template point element includes: determining the average distance between the transformation point element and the corresponding second template point element. The average distance is used as the target distance.

[0015] In some embodiments of this specification, the correspondence between workpiece point elements and second template point elements is determined using any of the following methods: if the matrix change data between adjacent iteration cycles meets a preset change threshold, the correspondence between workpiece point elements and second template point elements is determined to meet the first convergence condition. Here, the matrix change data is the change data between the first transformation matrix of the current iteration cycle and the first transformation matrix of the previous iteration cycle. If the current iteration cycle reaches a preset iteration count threshold, the correspondence between workpiece point elements and second template point elements is determined to meet the first convergence condition.

[0016] In some embodiments of this specification, alignment between the workpiece and the template is performed using a target correspondence, including: determining a second transformation matrix between workpiece point elements and second template point elements based on the target correspondence and a preset error function; and then performing a rigid transformation on the workpiece point elements using the second transformation matrix to align the workpiece point elements with the second template point elements, thereby completing the alignment operation between the workpiece and the template.

[0017] To achieve the above objectives, a workpiece digital model alignment device is proposed in a second aspect of this specification. The workpiece corresponds to a template. The workpiece digital model alignment device includes: a parameter determination module, used to determine the parameter range of a preset weight function and determine initial parameter values ​​within the parameter range; a first template point element determination module, used to determine, in the template point cloud data of the template, a first template point element that satisfies a preset distance condition with a workpiece point element in the workpiece point cloud data. The distance between the first template point element and its corresponding workpiece point element is a first distance; a second template point element determination module, used to substitute the first distance into the preset weight function to obtain first weight data, and re-determine the second template point element corresponding to the workpiece point element based on the first weight data. The distance between the second template point element and its corresponding workpiece point element is a second distance; and a parameter adjustment module, used to adjust the initial parameter values ​​if, based on the second distance, the correspondence between the workpiece point element and the second template point element satisfies a first convergence condition, and use the adjusted initial parameter values ​​as the initial parameter values. The iteration module is used to repeatedly execute the above steps until the adjusted initial parameter values ​​satisfy the second convergence condition, thereby obtaining the target correspondence between the workpiece point elements and the second template point elements. The alignment module is used to perform alignment operations between the workpiece and the template using the target correspondence.

[0018] According to the workpiece alignment device of this specification embodiment, firstly, within a predetermined parameter range, a value is determined as the initial value of a preset weight function parameter for one iteration cycle. In the template point cloud data of the template, a first template point element corresponding to the workpiece point element is first determined based on a preset distance condition. Then, the first template point element is adjusted using the preset weight function, and a second template point element corresponding to the workpiece point element is re-determined in the template point cloud data. When the correspondence between the workpiece point element and the second template point element satisfies a first convergence condition based on a second distance between them, the initial value of the preset weight function parameter is adjusted, and the next iteration cycle begins. This process is iterated continuously until the adjusted initial parameter value satisfies a second convergence condition, thus obtaining the target correspondence between the workpiece point element and the second template point element. Alignment operations can then be performed between the workpiece and the template based on this target correspondence. The workpiece digital model alignment method in this specification continuously reduces the determination range between the second template point elements corresponding to the workpiece point elements by iterating the parameters of the preset weight function. This effectively suppresses the influence of noise in the workpiece point cloud data and improves the accuracy of the second template point elements corresponding to the workpiece point elements, thereby achieving the effect of improving the alignment accuracy between the workpiece point elements and the template point elements.

[0019] To achieve the above objectives, a third aspect of this specification provides a computer-readable storage medium storing a workpiece digital model alignment program, which, when executed by a processor, implements the workpiece digital model alignment method as described in any of the above embodiments.

[0020] According to embodiments of this specification, when a workpiece digital model alignment program is executed by a processor, the error between workpiece point elements and second template point elements can be reduced by continuously iterating the parameters of a preset weight function, effectively suppressing the influence of noise in the workpiece point cloud data, thereby improving the alignment accuracy between workpiece point elements and template point elements.

[0021] To achieve the above objectives, a fourth aspect of this specification provides an electronic device, including a memory, a processor, and a workpiece digital model alignment program stored in the memory and executable on the processor. When the processor executes the workpiece digital model alignment program, it implements the workpiece digital model alignment method of any of the above embodiments.

[0022] According to the embodiments of this specification, when the processor executes the workpiece digital model alignment program, it can reduce the error between the workpiece point elements and the second template point elements by continuously iterating the parameters of the preset weight function, effectively suppressing the influence of noise in the workpiece point cloud data, thereby improving the alignment accuracy between the workpiece point elements and the template point elements.

[0023] Additional aspects and advantages of this specification will be set forth in part in the description which follows, and in part will be obvious from the description or may be learned by practice of this specification. Attached Figure Description

[0024] Figure 1 This is a flowchart of the workpiece digital model alignment method according to an embodiment of this specification.

[0025] Figure 2 This is a schematic diagram of the preset weighting function of one embodiment of this specification.

[0026] Figure 3 This is a flowchart illustrating the determination of the first convergence condition according to one embodiment of this specification.

[0027] Figure 4 This is a flowchart of a workpiece digital model alignment method according to one embodiment of this specification.

[0028] Figure 5 This is a structural block diagram of the workpiece digital model alignment device according to an embodiment of this specification.

[0029] Figure 6 This is a structural block diagram of the electronic device according to an embodiment of this specification. Detailed Implementation

[0030] The embodiments of this specification are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this specification, and should not be construed as limiting this specification.

[0031] In industries such as workpiece manufacturing and processing, workpiece models are typically designed in advance using CAD or other design software. The corresponding workpieces are then manufactured based on these models. For the manufactured workpieces, a quality inspection process is usually implemented to check the processing quality. Manual quality inspection, due to its limited measurement range, slow efficiency, and difficulty in measuring certain areas, is gradually being replaced by machine quality inspection. Machine quality inspection primarily uses sensors to collect workpiece point cloud data and uploads it to a computer. The computer then matches and aligns the workpiece point cloud data with the model's point cloud data to complete the quality inspection. However, due to the influence of the workpiece's manufacturing environment, the workpiece point cloud data collected by the sensors may contain a significant amount of noise, resulting in low alignment accuracy between the workpiece point cloud data and the model point cloud data, affecting the quality inspection results. Therefore, given the presence of high noise in the workpiece point cloud data, a digital-model alignment method is urgently needed to improve the alignment accuracy between the workpiece point cloud data and the model point cloud data.

[0032] See Figure 1This specification provides an embodiment of a workpiece digital model alignment method. The workpiece corresponds to a template. The workpiece digital model alignment method includes:

[0033] S110, determine the parameter range of the preset weight function, and determine the initial value of the parameter within the parameter range.

[0034] Specifically, a preset weight function can be used to determine the distance between two point elements. By pre-determining an appropriate parameter range, the distance between workpiece point elements and template point elements can be continuously reduced to obtain an accurate correspondence. The parameter range can be arbitrarily selected by referring to previous application data of the preset weight function. Alternatively, the parameter range can be adaptively calculated using relevant features such as the workpiece point cloud data to be aligned, the model point cloud data, and the distance between model point elements. An appropriate value is selected from the determined parameter range as the initial parameter value for the first iteration cycle.

[0035] S120, in the template point cloud data of the template, determine the first template point element that satisfies the preset distance condition with the workpiece point element in the workpiece point cloud data.

[0036] The distance between the first template point element and the workpiece point element corresponding to the first template point element is the first distance.

[0037] In some cases, the determination process between workpiece point cloud data and template point cloud data can be based on the same coordinate system. Since the relative distance between workpiece point elements and corresponding template point elements is closest when the orientation of the workpiece contour displayed in the workpiece point cloud data and the template contour displayed in the template point cloud data are roughly the same within the same coordinate system, the process can reduce iteration cycles and improve alignment accuracy by pre-setting distance conditions for initial template point element selection.

[0038] Specifically, the preset distance condition can be set to the nearest or lower than a set distance threshold. In the template point cloud data of the template, the distance between each template point element and the workpiece point element is calculated. The template point element whose distance to the workpiece point element meets the preset distance condition is taken as the first template point element corresponding to the workpiece point element. Alternatively, the first template point element that meets the preset distance condition can be determined using methods such as Open3D. The distance between the workpiece point element and the corresponding first template point element is the first distance.

[0039] S130, Substitute the first distance into the preset weight function to obtain the first weight data, and redetermine the second template point element corresponding to the workpiece point element based on the first weight data.

[0040] The distance between the second template point element and the workpiece point element corresponding to the second template point element is the second distance.

[0041] Since the accuracy of the first template point element corresponding to the workpiece point element determined by the preset distance condition is not high, a preset weight function can be used to determine whether the first template point element needs to be replaced.

[0042] Among them, the workpiece point element p i With the corresponding first template point element q i The first distance D between them can be determined in the following way: First, determine the workpiece point element p. i With the first template point element q i In the same coordinate system, calculate the distance D = |q| between two coordinates. i -p i |, as the workpiece point element p i With the first template point element q i The first distance. Secondly, the first template point element q. i The above uses a preset direction as the method vector, and the normal vector is related to the workpiece point element p. i It is perpendicular to a certain face. Using the first template point element q... i The distance to that surface is used as the workpiece point element p. i With the first template point element q i The first distance.

[0043] Substituting the first distance into a preset weight function yields the first weight data. Based on this first weight data, the accuracy of the correspondence between the first template point element and the workpiece point element can be determined. If inaccurate, a second template point element corresponding to the workpiece point element is redefined in the template point cloud data. The distance between the second template point element and its corresponding workpiece point element is the second distance. The determination method for the second distance is the same as that for the first distance, and will not be repeated here.

[0044] S140, if the correspondence between the workpiece point element and the second template point element is determined based on the second distance and satisfies the first convergence condition, adjust the initial value of the parameter and use the adjusted initial value of the parameter as the initial value of the parameter.

[0045] Specifically, the correspondence between workpiece point elements and second template point elements can be determined based on the second distance to see if it satisfies the conditions defined by the first convergence condition. The first convergence condition can be the accuracy of the correspondence between workpiece point elements and second template point elements. If the correspondence between workpiece point elements and their corresponding second template point elements satisfies the first convergence condition based on the second distance between them, the current iteration cycle is stopped. The initial values ​​of the preset weight function parameters are adjusted, increasing or decreasing them according to the actual iteration situation, to proceed to the next iteration cycle.

[0046] If the correspondence between the workpiece point element and the second template point element determined based on the second distance does not meet the first convergence condition, steps S120 and S130 are repeated; alternatively, only the process of re-determining the second template point element corresponding to the workpiece point element using a preset weight function in step S130 is repeated. Iteration stops when the correspondence between the workpiece point element and the second template point element determined based on the second distance between them meets the first convergence condition.

[0047] For example, assume that the workpiece point cloud data P includes four workpiece point elements p1, p2, p3, and p4. The template point cloud data Q includes four template point elements q1, q2, q3, and q4. Taking the determination of the second template point element corresponding to workpiece point element p1 as an example, q1 and q2 are identified in the template point cloud data Q that satisfy a preset distance condition with p1. Either point, such as q1, can be arbitrarily selected as the first template point element corresponding to workpiece point element p1. The distance between p1 and q1 is the first distance. The first distance is substituted into a preset weight function to obtain the first weight data. If the first weight data conforms to a preset data range, then the template point element q1 is determined as the second template point element q1 corresponding to workpiece point element p1. Therefore, the first distance between template point element q1 and workpiece point element p1 is also the second distance.

[0048] When the correspondence between the workpiece point element and the second template point element determined based on the second distance does not meet the first convergence condition, the second template point element corresponding to the workpiece point element p1 can be re-determined based on a preset weight function. Therefore, in the template point cloud data Q, among the other three template point elements q2, q3, and q4 (excluding q1), a new template point element can be determined as the second template point element corresponding to the workpiece point element p1. When re-determining the template point element, a preset distance condition can also be used. If the template point element q2 is re-determined based on the preset distance condition, the first distance between the workpiece point element p1 and the template point element q2 is substituted into the preset weight function. If the obtained first weight data does not conform to the preset data range, the second template point element corresponding to the workpiece point element p1 is re-determined among the template point elements q3 and q4.

[0049] Assume that the second template point element corresponding to the workpiece point element p1 is determined to be q3. Based on the second distance between the second template point element q3 and the workpiece point element p1, if the correspondence between the workpiece point element and the second template point element satisfies the first convergence condition, the iteration stops, and the initial values ​​of the parameters of the preset weight function are adjusted.

[0050] S150, repeat the above steps until the adjusted initial values ​​of the parameters meet the second convergence condition, and obtain the target correspondence between the workpiece point elements and the second template point elements.

[0051] Specifically, determining whether the adjusted initial parameter values ​​satisfy the second convergence condition can be done by checking whether the adjusted initial parameter values ​​are still within the aforementioned parameter range. If the adjusted initial parameter values ​​exceed the parameter range, then the second convergence condition can be determined to be satisfied.

[0052] After adjusting the initial parameter values, steps 120 to 140 are repeated using a preset weight function for adjusting the initial parameter values. Iteration continues until the adjusted initial parameter values ​​satisfy the second convergence condition, at which point the iteration stops. The preset weight function after adjusting the initial parameter values ​​can continuously reduce the determination range of the second template point elements. Therefore, by adjusting the initial parameter values ​​and iterating continuously, the accuracy of the second template point elements corresponding to the workpiece point elements can be gradually improved, achieving noise suppression. Therefore, it can be determined that the second template point elements corresponding to the workpiece point elements determined in the last iteration have the highest accuracy, thus obtaining the target correspondence between the workpiece point elements and the second template point elements.

[0053] S160, aligns the workpiece and template using the target correspondence.

[0054] After obtaining the target correspondence between the workpiece point elements and the second template point elements, the one-to-one correspondence between the point elements in the workpiece point cloud data and the template point cloud data is determined. Based on the target correspondence, the workpiece point elements can be aligned to the template point elements, completing the alignment operation between the workpiece and the template.

[0055] According to the workpiece digital model alignment method of the embodiments of this specification, firstly, within a predetermined parameter range, a value is determined as the initial value of the preset weight function parameter for one iteration cycle. In the template point cloud data of the template, a first template point element corresponding to the workpiece point element is first determined based on a preset distance condition. Then, the first template point element is adjusted using the preset weight function, and a second template point element corresponding to the workpiece point element is re-determined in the template point cloud data. When the correspondence between the workpiece point element and the second template point element satisfies the first convergence condition based on the second distance between the second template point element and the workpiece point element, the initial value of the preset weight function parameter is adjusted, and the next iteration cycle begins. This process is iterated continuously until the adjusted initial parameter value satisfies the second convergence condition, thus obtaining the target correspondence between the workpiece point element and the second template point element. Based on the target correspondence, alignment operations can be performed between the workpiece and the template. The workpiece digital model alignment method in this specification continuously reduces the determination range between the second template point elements corresponding to the workpiece point elements by iterating the parameters of the preset weight function. This effectively suppresses the influence of noise in the workpiece point cloud data and improves the accuracy of the second template point elements corresponding to the workpiece point elements, thereby achieving the effect of improving the alignment accuracy between the workpiece point elements and the template point elements.

[0056] In some embodiments of this specification, the preset weighting function is an exponential function with a preset constant as the base. Substituting the first distance into the preset weighting function to obtain first weight data includes: determining the ratio between the square of the first distance and the square of the initial parameter value. Using the negative value of this ratio as the exponent of the preset constant, the first weight data is obtained.

[0057] In the embodiments of this specification, the preset weighting function can be set as an exponential function with base e, using the distance value as the independent variable. Specifically, the preset weighting function... Where x represents distance and v represents parameter. The value of v is the initial value of the parameter. Substituting the first distance as x into the preset weight function w(x) yields the first weight data.

[0058] In some embodiments of this specification, the initial value of the parameter is the maximum value of the parameter range. Adjusting the initial value of the parameter and using the adjusted initial value as the initial value of the parameter includes: decreasing the initial value of the parameter and using the decreased initial value as the initial value of the parameter.

[0059] like Figure 2 The curve shown is a preset weight function. A schematic diagram of the curves under three parameter conditions. (From...) Figure 2 It is evident that the closer the absolute value of the distance x is to 0, the larger the value of w(x), with a maximum value of 1. Furthermore, the smaller the initial parameter value, the faster the value of w(x) converges. Therefore, the maximum value within the parameter range can be used as the initial parameter value for the first iteration. When the first convergence condition is met, the initial parameter value is reduced to increase the convergence speed of w(x), thereby narrowing the defined range between the second template point elements corresponding to the workpiece point elements and effectively suppressing the noise influence in the workpiece point cloud data.

[0060] In some embodiments of this specification, re-determining the second template point element corresponding to the workpiece point element based on the first weight data may include: when the first weight data is within a preset weight range, using the first template point element as the second template point element; when the first weight data is not within the preset weight range, determining the second template point element that satisfies a preset distance condition from other template point cloud data besides the first template point element.

[0061] Continue to refer to Figure 2The preset weight function w(x) reduces the range of the second template point element by continuously converging the first distance. Therefore, the preset weight range can be set to a range where 1 ≥ w(x) ≥ y. For example, setting the preset weight range to [1, 0.5] means that when the first weight data obtained by substituting the first distance into the preset weight function is within the range of [1, 0.5], it indicates that the distance between the current first template point element and the workpiece point element is small. The first template point element can be considered as a template point element with higher accuracy corresponding to the workpiece point element, and therefore, the currently determined first template point element can be directly used as the second template point element. When the first weight data obtained by substituting the first distance into the preset weight function is not within the range of [1, 0.5], it indicates that the distance between the current first template point element and the workpiece point element is large. Therefore, template point elements that meet the preset distance condition can be re-determined from other template point cloud data besides the first template point element as the second template point element.

[0062] In some embodiments of this specification, the following method is used to determine whether the adjusted initial value of the parameter satisfies the second convergence condition: if the reduced initial value of the parameter is less than or equal to the minimum value of the parameter range, it is determined that the second convergence condition is satisfied.

[0063] In the embodiments of this specification, since a predetermined parameter range is defined, if the iteration continues when the reduced initial parameter value is less than or equal to the minimum value of the parameter range, the reduced initial parameter value will exceed the preset parameter range. Therefore, iteration can be stopped when the reduced initial parameter value is less than or equal to the minimum value of the parameter range.

[0064] In some embodiments described herein, a maximum number of iterations may be preset as one of the second convergence conditions. The iteration process can be stopped when the number of iterations is greater than or equal to the preset maximum number of iterations.

[0065] In some embodiments of this specification, such as Figure 3 As shown, determining the correspondence between workpiece point elements and second template point elements based on the second distance to satisfy the first convergence condition can include:

[0066] S310, determine the first transformation matrix between the workpiece point element and the second template point element based on the second distance and the preset error function.

[0067] S320, use the first transformation matrix to perform a rigid transformation on the workpiece point elements to obtain the transformed point elements.

[0068] S330, determine the target distance between the transformed point element and the second template point element.

[0069] S340, when the target distance is less than the preset distance threshold, determine that the correspondence between the workpiece point element and the second template point element satisfies the first convergence condition.

[0070] Specifically, the preset error function is used to represent distance. If the second distance is obtained based on the distance between two points, then the preset error function can be ∑ i ((M·q i -p i )) 2 , where M represents the transformation matrix; if the second distance is the point-to-surface distance obtained based on the normal vector, then the preset error function can be ∑ i ((M·q i -p i )·n i ), where M represents matrix transformation, n i The normal vector is represented by a vector. If the determined second template point element corresponds to the actual workpiece point element, then the workpiece point element after transformation by the transformation matrix will coincide with the second template point element, so the ideal value of the error function is 0. However, since the determined second template point element corresponding to the workpiece point element may not be the actual corresponding point during the iteration process, given the workpiece point element and its corresponding second template point element, the first transformation matrix between the workpiece point element and the second template point element can be determined by minimizing the value of the error function. When calculating the first transformation matrix based on the preset error function, general methods such as least squares or SVD decomposition can be used.

[0071] After rigidly transforming the workpiece point elements using the first transformation matrix, transformed point elements are obtained. Theoretically, each transformed point element corresponds one-to-one with a second template point element and their positions coincide. However, due to potential errors or insufficient accuracy in the determined second template point elements, some transformed point elements may not coincide with their corresponding second template point elements. The distance between the transformed point elements and the second template point elements can be used to reflect the accuracy of the second template point elements. Therefore, a target distance between the transformed point elements and the second template point elements can be used as the first convergence condition. When the target distance is less than a preset distance threshold, it indicates that the accuracy of the second template point elements determined in this iteration has reached the expected level, and the first convergence condition is satisfied.

[0072] In some embodiments of this specification, there is a correspondence between the transformation point element and the workpiece point element. The second template point element corresponding to the transformation point element is determined by the correspondence between the workpiece point element and the second template point element. Determining the target distance between the transformation point element and the second template point element includes: determining the average distance between the transformation point element and the corresponding second template point element. The average distance is used as the target distance.

[0073] Since the transformed point elements are obtained by rigidly transforming the workpiece point elements based on the transformation matrix, there is a one-to-one correspondence between the transformed point elements and the workpiece point elements. Furthermore, there is a one-to-one correspondence between the workpiece point elements and the second template point elements. Therefore, the second template point elements corresponding to the transformed point elements can be determined using the workpiece point elements as a bridge. The distances between the transformed point elements and their corresponding second template point elements are determined, and the average distance obtained by averaging these distances is taken as the target distance.

[0074] In some embodiments of this specification, the correspondence between workpiece point elements and second template point elements is determined to satisfy the first convergence condition using any of the following methods: if the matrix change data between adjacent iteration cycles satisfies a preset change threshold, the first convergence condition is satisfied. Here, the matrix change data is the change data between the first transformation matrix of the current iteration cycle and the first transformation matrix of the previous iteration cycle. If the current iteration cycle reaches a preset iteration count threshold, the correspondence between workpiece point elements and second template point elements is determined to satisfy the first convergence condition.

[0075] In some cases, the first convergence condition can include multiple conditions. Since the matrix transformation data between adjacent iteration cycles can represent the changes in the elements of the second template points obtained in two consecutive iterations, and when the repetition rate of the second template point elements determined in adjacent iteration cycles is large, the change data between the first transformation matrices of two iteration cycles will not be significant. Therefore, whether the matrix transformation data between adjacent iteration cycles meets a preset change threshold can be used as one criterion for whether the first convergence condition is met.

[0076] In some cases, improperly set conditions may prevent accurate results from being obtained even after multiple iterations. Therefore, an iteration threshold can be preset. When the iteration cycle reaches the preset threshold, and the target distance is not less than the preset distance threshold or the matrix change data between adjacent iteration cycles does not meet the preset conditions, the iteration can be stopped directly.

[0077] Similarly, the satisfaction of the second convergence condition can be determined based on whether the matrix change data between adjacent iteration cycles meets a preset change threshold. The preset change threshold in the second convergence condition should be less than the preset change threshold in the first convergence condition.

[0078] In some embodiments of this specification, alignment operations between a workpiece and a template are performed using a target correspondence, including: determining a second transformation matrix between workpiece point elements and second template point elements based on the target correspondence and a preset error function; and performing a rigid transformation on the workpiece point elements using the second transformation matrix to align the workpiece point elements with the second template point elements, thereby completing the alignment operation between the workpiece and the template.

[0079] Specifically, after obtaining the second template point element corresponding to the workpiece point element in the last iteration cycle, the second transformation moment between the workpiece point element and the second template point element can be determined based on the aforementioned preset error function. By rigidly transforming the workpiece point element using the second transformation matrix, the workpiece point element and the second template point element can be aligned, thus completing the alignment operation between the workpiece and the template.

[0080] It should be noted that the workpiece digital model alignment method in the embodiments of this specification includes two iterations. The first convergence condition is the judgment condition for the first iteration, in which the parameter values ​​of the preset weight function are the same during the iteration cycle of this layer. The second convergence condition is the judgment condition for the second iteration, in which the parameter values ​​of the preset weight function are different during the iteration cycle of this layer.

[0081] In some embodiments of this specification, such as Figure 4 As shown, the workpiece digital model alignment method may also include:

[0082] S402, determine the parameter range of the preset weight function, and determine the maximum value within the parameter range as the initial value of the parameter.

[0083] S404, in the template point cloud data of the template, determine the first template point element that satisfies the preset distance condition with the workpiece point element in the workpiece point cloud data. The distance between the first template point element and the corresponding workpiece point element is the first distance.

[0084] S406, the first distance is substituted into a preset weight function to obtain first weight data, and the second template point element corresponding to the workpiece point element is re-determined based on the first weight data. The distance between the second template point element and the corresponding workpiece point element is the second distance.

[0085] S408, determine the first transformation matrix between the workpiece point element and the second template point element based on the second distance and the preset error function.

[0086] S410, use the first transformation matrix to perform a rigid transformation on the workpiece point elements to obtain the transformed point elements.

[0087] S412, determine the target distance between the transformed point element and the second template point element.

[0088] S414, determine whether the correspondence between the workpiece point element and the second template point element satisfies the first convergence condition based on the target distance.

[0089] S416 If the first convergence condition is met, adjust the initial value of the parameter and use the adjusted initial value of the parameter as the initial value of the parameter.

[0090] S418, repeat the above steps until the adjusted initial values ​​of the parameters meet the second convergence condition, and obtain the target correspondence between the workpiece point elements and the second template point elements.

[0091] S420, determine the second transformation matrix between the workpiece point elements and the second template point elements based on the target correspondence and the preset error function.

[0092] S422, use the second transformation matrix to perform a rigid transformation on the workpiece point elements, align the workpiece point elements with the second template point elements, and complete the alignment operation between the workpiece and the template.

[0093] Corresponding to the above embodiments, this specification also proposes a workpiece digital model alignment device. The workpiece corresponds to a template. For example... Figure 5 As shown, the workpiece digital model alignment device includes:

[0094] The parameter determination module 510 is used to determine the parameter range of the preset weight function and determine the initial value of the parameter within the parameter range.

[0095] The first template point element determination module 520 is used to determine, in the template point cloud data of the template, a first template point element that satisfies a preset distance condition with the workpiece point element in the workpiece point cloud data. The distance between the first template point element and its corresponding workpiece point element is defined as the first distance.

[0096] The second template point element determination module 530 is used to input the first distance into a preset weight function to obtain first weight data, and to redetermine the second template point element corresponding to the workpiece point element based on the first weight data. The distance between the second template point element and the corresponding workpiece point element is the second distance.

[0097] The parameter adjustment module 540 is used to adjust the initial value of the parameter if the correspondence between the workpiece point element and the second template point element is determined based on the second distance and satisfies the first convergence condition, and to use the adjusted initial value of the parameter as the initial value of the parameter.

[0098] The iteration module 550 is used to repeatedly execute the above steps until the adjusted initial value of the parameters satisfies the second convergence condition, thereby obtaining the target correspondence between the workpiece point elements and the second template point elements.

[0099] Alignment module 560 is used to perform alignment operations between the workpiece and the template using the target correspondence relationship.

[0100] According to the workpiece alignment device of this specification embodiment, firstly, within a predetermined parameter range, a value is determined as the initial value of a preset weight function parameter for one iteration cycle. In the template point cloud data of the template, a first template point element corresponding to the workpiece point element is first determined based on a preset distance condition. Then, the first template point element is adjusted using the preset weight function, and a second template point element corresponding to the workpiece point element is re-determined in the template point cloud data. When the correspondence between the workpiece point element and the second template point element satisfies a first convergence condition based on a second distance between them, the initial value of the preset weight function parameter is adjusted, and the next iteration cycle begins. This process is iterated continuously until the adjusted initial parameter value satisfies a second convergence condition, thus obtaining the target correspondence between the workpiece point element and the second template point element. Alignment operations can then be performed between the workpiece and the template based on this target correspondence. The workpiece digital model alignment method in this specification continuously reduces the determination range between the second template point elements corresponding to the workpiece point elements by iterating the parameters of the preset weight function. This effectively suppresses the influence of noise in the workpiece point cloud data and improves the accuracy of the second template point elements corresponding to the workpiece point elements, thereby achieving the effect of improving the alignment accuracy between the workpiece point elements and the template point elements.

[0101] In some embodiments of this specification, the second template point element determination module 530 is further configured to: use the first template point element as the second template point element when the first weight data is within a preset weight range; and determine the second template point element that satisfies a preset distance condition from other template point cloud data besides the first template point element when the first weight data is not within the preset weight range.

[0102] In some embodiments of this specification, the preset weighting function is an exponential function with a preset constant as the base. The second template point element determination module 530 is further configured to: determine the ratio between the square of the first distance and the square of the initial parameter value. The negative value of the ratio is used as the exponent of the preset constant to obtain the first weight data.

[0103] In some embodiments of this specification, the initial value of the parameter is the maximum value of the parameter range. The parameter adjustment module 540 is also used to: decrease the initial value of the parameter, and use the decreased initial value as the initial value of the parameter.

[0104] In some embodiments of this specification, the following method is used to determine whether the adjusted initial value of the parameter satisfies the second convergence condition: if the reduced initial value of the parameter is less than or equal to the minimum value of the parameter range, it is determined that the second convergence condition is satisfied.

[0105] In some embodiments of this specification, the parameter adjustment module 540 is further configured to: determine a first transformation matrix between workpiece point elements and second template point elements based on a second distance and a preset error function; perform a rigid transformation on the workpiece point elements using the first transformation matrix to obtain transformed point elements; determine a target distance between the transformed point elements and the second template point elements; and determine that a first convergence condition is met when the target distance is less than a preset distance threshold.

[0106] In some embodiments of this specification, there is a correspondence between the transformation point element and the workpiece point element. The second template point element corresponding to the transformation point element is determined by the correspondence between the workpiece point element and the second template point element. The parameter adjustment module 540 is further configured to: determine the average distance between the transformation point element and the corresponding second template point element; and use the average distance as the target distance.

[0107] In some embodiments of this specification, the correspondence between workpiece point elements and second template point elements is determined using any of the following methods: if the matrix change data between adjacent iteration cycles meets a preset change threshold, the correspondence between workpiece point elements and second template point elements is determined to meet the first convergence condition. Here, the matrix change data is the change data between the first transformation matrix of the current iteration cycle and the first transformation matrix of the previous iteration cycle. If the current iteration cycle reaches a preset iteration count threshold, the correspondence between workpiece point elements and second template point elements is determined to meet the first convergence condition.

[0108] In some embodiments of this specification, the alignment module 560 is further configured to: determine a second transformation matrix between workpiece point elements and second template point elements based on the target correspondence and a preset error function. The workpiece point elements are then rigidly transformed using the second transformation matrix to align the workpiece point elements with the second template point elements, thereby completing the alignment operation between the workpiece and the template.

[0109] It should be noted that for details not disclosed in the workpiece model alignment device of this embodiment, please refer to the details disclosed in the embodiments of the workpiece model alignment method in this specification, which will not be repeated here.

[0110] Corresponding to the above embodiments, this specification also proposes a computer-readable storage medium storing a workpiece digital model alignment program thereon, which, when executed by a processor, implements the workpiece digital model alignment method of any of the above embodiments.

[0111] According to embodiments of this specification, when a workpiece digital model alignment program is executed by a processor, the error between workpiece point elements and second template point elements can be reduced by continuously iterating the parameters of a preset weight function, effectively suppressing the influence of noise in the workpiece point cloud data, thereby improving the alignment accuracy between workpiece point elements and template point elements.

[0112] Corresponding to the above embodiments, this specification also provides an electronic device.

[0113] Figure 6 This is a structural block diagram of an electronic device according to one embodiment of this specification, such as... Figure 6 As shown, the electronic device 600 includes a memory 604, a processor 602, and a workpiece digital model alignment program 606 stored in the memory 604 and executable on the processor 602. When the processor 602 executes the workpiece digital model alignment program 606, it implements the workpiece digital model alignment method of any of the above embodiments.

[0114] According to the embodiments of this specification, when the processor 602 executes the workpiece digital model alignment program 606, it can reduce the error between the workpiece point elements and the second template point elements by continuously iterating the parameters of the preset weight function, effectively suppressing the influence of noise in the workpiece point cloud data, thereby improving the alignment accuracy between the workpiece point elements and the template point elements.

[0115] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0116] It should be understood that various parts of this specification can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0117] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this specification. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0118] In the description of this specification, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this specification and for 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. Therefore, they should not be construed as limitations on this specification.

[0119] Furthermore, the terms "first," "second," etc., used in the embodiments of this specification are for descriptive purposes only and should not be construed as indicating or implying relative importance, or implicitly specifying the number of technical features indicated in this embodiment. Therefore, features defined with terms such as "first" and "second" in the embodiments of this specification can explicitly or implicitly indicate that the embodiment includes at least one of those features. In the description of this specification, the word "multiple" means at least two or more, such as two, three, four, etc., unless otherwise explicitly specified in the embodiments.

[0120] In this specification, unless otherwise explicitly specified or limited in the embodiments, the terms "installation," "connection," "joining," and "fixing," etc., appearing in the embodiments, should be interpreted broadly. For example, a connection can be a fixed connection, a detachable connection, or an integral part; it can also be a mechanical connection, an electrical connection, etc. Of course, it can also be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication between two components, or the interaction between two components. Those skilled in the art will be able to understand the specific meaning of the above terms in this specification based on the specific implementation.

[0121] In this specification, unless otherwise expressly specified and limited, "above" or "below" the second feature can mean that the first and second features are in direct contact, or that the first and second features are in indirect contact through an intermediate medium. Furthermore, "above," "over," and "on top" of the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0122] Although embodiments of this specification have been shown and described above, it is to be understood that the above embodiments are exemplary and should not be construed as limiting this specification. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this specification.

Claims

1. A method for aligning digital models of workpieces, characterized in that, The workpiece corresponds to a template; the method includes: Determine the parameter range of the preset weight function, and determine the initial values ​​of the parameters within the parameter range; In the template point cloud data of the template, a first template point element is identified that satisfies a preset distance condition with the workpiece point element in the workpiece point cloud data; wherein, the distance between the first template point element and the workpiece point element corresponding to the first template point element is the first distance; The first distance is substituted into the preset weight function to obtain the first weight data, and the second template point element corresponding to the workpiece point element is re-determined based on the first weight data; wherein, the distance between the second template point element and the workpiece point element corresponding to the second template point element is the second distance; If the correspondence between the workpiece point element and the second template point element is determined to satisfy the first convergence condition based on the second distance, the initial value of the parameter is adjusted, and the adjusted initial value of the parameter is used as the initial value of the parameter. Repeat the above steps until the adjusted initial value of the parameter satisfies the second convergence condition, and obtain the target correspondence between the workpiece point element and the second template point element; The alignment operation between the workpiece and the template is performed using the target correspondence; The step of re-determining the second template point element corresponding to the workpiece point element based on the first weight data includes: when the first weight data is within a preset weight range, using the first template point element as the second template point element; when the first weight data is not within the preset weight range, determining the second template point element that satisfies the preset distance condition from other template point cloud data besides the first template point element. The following method is used to determine whether the adjusted initial value of the parameter satisfies the second convergence condition: if the reduced initial value of the parameter is less than or equal to the minimum value of the parameter range, it is determined that the second convergence condition is satisfied; Determining that the correspondence between the workpiece point element and the second template point element satisfies the first convergence condition based on the second distance includes: determining a first transformation matrix between the workpiece point element and the second template point element based on the second distance and a preset error function; performing a rigid transformation on the workpiece point element using the first transformation matrix to obtain transformed point elements; determining a target distance between the transformed point elements and the second template point element; and determining that the correspondence between the workpiece point element and the second template point element satisfies the first convergence condition when the target distance is less than a preset distance threshold. The alignment operation between the workpiece and the template using the target correspondence includes: determining a second transformation matrix between the workpiece point elements and the second template point elements based on the target correspondence and a preset error function; performing a rigid transformation on the workpiece point elements using the second transformation matrix to align the workpiece point elements with the second template point elements, thereby completing the alignment operation between the workpiece and the template.

2. The method according to claim 1, characterized in that, The preset weighting function is an exponential function with a preset constant as the base; the step of substituting the first distance into the preset weighting function to obtain the first weight data includes: Determine the ratio between the square of the first distance and the square of the initial value of the parameter; The first weight data is obtained by using the negative value of the ratio as the exponent of the preset constant.

3. The method according to claim 1, characterized in that, The initial value of the parameter is the maximum value of the parameter range; adjusting the initial value of the parameter, and using the adjusted initial value as the initial value of the parameter, includes: Decrease the initial value of the parameter, and use the decreased initial value as the initial value of the parameter.

4. The method according to claim 1, characterized in that, There is a correspondence between the transformation point element and the workpiece point element; the second template point element corresponding to the transformation point element is determined by the correspondence between the workpiece point element and the second template point element. Determining the target distance between the transformed point element and the second template point element includes: Determine the average distance between the transformed point element and the corresponding second template point element; The average distance is taken as the target distance.

5. The method according to claim 1, characterized in that, The correspondence between the workpiece point element and the second template point element is determined using any of the following methods to determine whether it satisfies the first convergence condition: If the matrix change data between adjacent iteration cycles meets a preset change threshold, it is determined that the correspondence between the workpiece point element and the second template point element meets the first convergence condition; wherein, the matrix change data is the change data between the first transformation matrix of the current iteration cycle and the first transformation matrix of the previous iteration cycle of the current iteration cycle; If the current iteration cycle reaches the preset iteration number threshold, it is determined that the correspondence between the workpiece point element and the second template point element satisfies the first convergence condition.

6. A workpiece digital model alignment device, implementing the workpiece digital model alignment method as described in any one of claims 1-5, characterized in that, The workpiece corresponds to a template; the device includes: The parameter determination module is used to determine the parameter range of the preset weight function and determine the initial value of the parameter within the parameter range; The first template point element determination module is used to determine, in the template point cloud data of the template, a first template point element that satisfies a preset distance condition with the workpiece point element in the workpiece point cloud data; wherein, the distance between the first template point element and the workpiece point element corresponding to the first template point element is the first distance. The second template point element determination module is used to input the first distance into the preset weight function to obtain the first weight data, and to redetermine the second template point element corresponding to the workpiece point element based on the first weight data; wherein, the distance between the second template point element and the workpiece point element corresponding to the second template point element is the second distance. The parameter adjustment module is used to adjust the initial value of the parameter if the correspondence between the workpiece point element and the second template point element determined based on the second distance satisfies the first convergence condition, and to use the adjusted initial value of the parameter as the initial value of the parameter. The iteration module is used to repeatedly execute the above steps until the adjusted initial value of the parameter satisfies the second convergence condition, thereby obtaining the target correspondence between the workpiece point element and the second template point element. An alignment module is used to perform alignment operations between the workpiece and the template using the target correspondence.

7. A computer-readable storage medium, characterized in that, It stores a workpiece digital model alignment program, which, when executed by the processor, implements the workpiece digital model alignment method as described in any one of claims 1-5.

8. An electronic device, characterized in that, The device includes a memory, a processor, and a workpiece digital model alignment program stored in the memory and executable on the processor. When the processor executes the workpiece digital model alignment program, it implements the workpiece digital model alignment method according to any one of claims 1-5.

Images