Method and system for detecting product quality of molded case circuit breaker

Abstract

The invention relates to the technical field of image data processing, in particular to a molded case circuit breaker product quality detection method and system, and the method comprises the steps: obtaining the point cloud data of a molded case circuit breaker to be detected; obtaining the local density of each point cloud data according to the change condition of the local geometric features of each point cloud data and all point cloud data in the local range and the spatial distance; performing principal component analysis on each point cloud data and all point cloud data in the neighborhood space, and combining the local density to obtain a local form index of each point cloud data; and adjusting an error function in the ICP algorithm based on the local form index difference between the point cloud data of the molded case circuit breaker to be detected and the point cloud data of the standard molded case circuit breaker, and obtaining a molded case circuit breaker product quality detection result through point cloud registration. The invention aims to improve the matching precision between the point cloud data, thereby meeting the high-precision and high-efficiency detection requirements of the molded case circuit breaker.

Description

Technical Field

[0001] The present application relates to the technical field of image data processing, and in particular to a method and system for detecting the product quality of a molded case circuit breaker. Background Art

[0002] Molded case circuit breakers are important protective components in electrical systems, with multiple protection functions such as overload and short circuit. The plastic shell provides good insulation, and the internal integrated thermal magnetic or electromagnetic tripping mechanism can quickly cut off the circuit when the current is abnormal to protect the equipment from damage. It is widely used in household, commercial and industrial power distribution systems to ensure circuit safety and stability. The quality of molded case circuit breakers directly affects the operational safety of power equipment, that is, operational safety is the basis of reliability, and reliability is the basis of circuit breaker performance.

[0003] With the continuous development of molded case circuit breaker production technology, the requirements for molded case circuit breaker quality inspection during the production process are becoming higher and higher. However, due to factors such as manufacturing errors and assembly processes, there may be assembly deviations between components, affecting the overall performance and safety of the circuit breaker. In practical applications, due to the complex structure of molded case circuit breakers, point cloud data of molded case circuit breakers can be obtained through three-dimensional models, and assembly quality problems between different components of molded case circuit breakers can be detected based on iterative closest point (ICP) point cloud data matching technology. However, when searching for corresponding points, the ICP algorithm usually assumes that the point with the closest Euclidean distance is the corresponding point. This assumption often leads to mismatching in complex scenarios, and it is difficult to meet the high-precision and high-efficiency detection requirements of molded case circuit breakers. Summary of the invention

[0004] In view of the above, it is necessary to provide a molded case circuit breaker product quality detection method and system to solve the above problems.

[0005] The first aspect of the present application provides a method for detecting the quality of a molded case circuit breaker product, the method comprising: Obtain point cloud data of the molded case circuit breaker to be tested; Preset the neighborhood space of each point cloud data, extract the eigenvector of each point cloud data in its neighborhood space; perform singular value decomposition on the matrix composed of the eigenvectors of each point cloud data and all point cloud data in its neighborhood space, obtain the singular distribution index of each point cloud data based on the distribution of singular values, and obtain the local density of each point cloud data in combination with the spatial distance; Principal component analysis is performed on each point cloud data and all point cloud data in its neighborhood space to obtain the curvature of each point cloud data, and local morphological index of each point cloud data is obtained by combining the local density; Based on the difference in local morphological index between the point cloud data of the molded case circuit breaker to be tested and the standard molded case circuit breaker, the error function in the ICP algorithm is adjusted, and the product quality inspection result of the molded case circuit breaker is obtained through point cloud registration.

[0006] The process of extracting the feature vector of each point cloud data in its neighborhood space is as follows: The point cloud data and all the point cloud data in its neighborhood space are used as the input of the fast point feature histogram algorithm to obtain the feature vector of each point cloud data in its neighborhood space.

[0007] Wherein, the step of obtaining the singular distribution index of each point cloud data is: The disorder degree of all singular values ​​of the matrix of each point cloud data is obtained, and the result of fusing the disorder degree with all singular values ​​of each point cloud data is used as the singular distribution index of each point cloud data.

[0008] The local density of each point cloud data is obtained as follows: Negative correlation mapping is performed on the distance between each point cloud data and each point cloud data in its neighborhood space; Based on the average level of the negative correlation mapping results between each point cloud data and all point cloud data in its neighborhood space, combined with the singular distribution index, the local density of each point cloud data is obtained; wherein the local density is positively correlated with the average level and the singular distribution index.

[0009] The local morphological index of each point cloud data is obtained as follows: The discrete degree of curvature of each point cloud data and all point cloud data in its neighborhood space is calculated; the discrete degree is merged with the local density to obtain the local morphological index of each point cloud data.

[0010] The error function in the ICP algorithm is adjusted as follows: in, represents the error value, represents the rotation matrix, represents the translation vector, represents the number of point pairs, Standard molded case circuit breaker The coordinates of the point cloud data, For the molded case circuit breaker to be tested The point cloud data coordinates with the closest Euclidean distance, Indicates the standard molded case circuit breaker The local morphological index of point cloud data, Indicates the molded case circuit breaker to be tested The local morphology index of the point cloud data with the closest Euclidean distance.

[0011] The process of obtaining the molded case circuit breaker product quality test results is specifically as follows: Perform surface fitting on the registered point cloud data of the standard molded case circuit breaker and the point cloud data of the molded case circuit breaker to be tested, respectively, to obtain the corresponding surface model; According to the coordinate change between the surface model of the standard molded case circuit breaker and the molded case circuit breaker to be tested, the overall deviation of the molded case circuit breaker to be tested is obtained; When the overall deviation is greater than a preset error threshold, the quality is determined to be unqualified; otherwise, the quality is qualified.

[0012] The overall deviation of the molded case circuit breaker to be tested is obtained as follows: A preset number of coordinate points are uniformly selected on the surface model of the standard molded case circuit breaker, and a corresponding calibration point is selected in the surface model of the molded case circuit breaker to be tested according to the position of each coordinate point; The cumulative sum of the Euclidean distances between all coordinate points and the corresponding calibration points is obtained as the overall deviation of the molded case circuit breaker to be detected.

[0013] The corresponding calibration point is specifically a point which is closest to the corresponding coordinate point in the surface model of the molded case circuit breaker to be detected.

[0014] In a second aspect, an embodiment of the present application further provides a molded case circuit breaker product quality detection system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above methods when executing the computer program.

[0015] In the above scheme, by collecting the point cloud data set of the molded case circuit breaker, the geometric relationship between each point cloud data and other point cloud data in its local range is analyzed to construct the local density. The beneficial effect is that the feature differences between the point clouds in the local range are taken into account, and the geometric features of different positions of the molded case circuit breaker can be better distinguished; secondly, based on the density distribution and curvature distribution of the point cloud data, a local morphological index is constructed. The beneficial effect is that the distribution density of the point cloud data at different positions of the molded case circuit breaker and the surface morphology of the molded case circuit breaker are taken into account, and the geometric and physical characteristics of the molded case circuit breaker are fully utilized. By combining the local morphological index with the Euclidean distance, the registration process of the point cloud data of the molded case circuit breaker to be detected and the point cloud data of the standard molded case circuit breaker can be better completed, reducing the mismatching problem caused by matching only relying on the Euclidean distance, and improving the matching accuracy between the point cloud data of the molded case circuit breaker to be detected and the point cloud data of the standard molded case circuit breaker, thereby meeting the high-precision and high-efficiency detection requirements of the molded case circuit breaker. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1A flowchart of a method for detecting the quality of a molded case circuit breaker product provided in one embodiment of the present application; Figure 2 A schematic diagram of point cloud data before denoising provided by an embodiment of the present application; Figure 3 A schematic diagram of denoised point cloud data provided by an embodiment of the present application; Figure 4 A schematic diagram of the curvature distribution of point cloud data a and all point cloud data in its neighborhood space provided in one embodiment of the present application; Figure 5 A schematic diagram of the curvature distribution of point cloud data b and all point cloud data in its neighborhood space provided in one embodiment of the present application; Figure 6 A point cloud matching effect diagram provided for one embodiment of the present application. DETAILED DESCRIPTION

[0017] In the description of the embodiments of the present application, words such as "exemplary", "or", "for example" and the like are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary", "or", "for example" and the like is intended to present related concepts in a concrete manner.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art in the present application. The terms used in the specification of the present application are only for the purpose of describing specific embodiments and are not intended to limit the present application.

[0019] It should also be noted that the terms "first" and "second" in this application and the accompanying drawings are used to distinguish similar objects, rather than to describe a specific order or sequence. The method disclosed in the embodiments of the present application or the method shown in the flow chart includes one or more steps for implementing the method. Without departing from the scope of protection of the present application, the execution order of multiple steps can be interchanged with each other, and some steps can also be deleted.

[0020] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0021] The specific scheme of a molded case circuit breaker product quality detection method and system provided by the present application is described in detail below with reference to the accompanying drawings.

[0022] See also Figure 1, which shows a flow chart of the steps of a molded case circuit breaker product quality detection method provided by an embodiment of the present application, the method comprising the following steps: The first step: obtain the point cloud data of the molded case circuit breaker to be tested.

[0023] This application mainly detects the quality problems of molded case circuit breaker products through point cloud data. This application uses a Trimble 3D scanner to scan molded case circuit breaker products: place the molded case circuit breaker to be tested with the panel cover opened on the workbench, and ensure that its surface is unobstructed, and use a Trimble 3D scanner to comprehensively scan the molded case circuit breaker from different angles to obtain complete point cloud data. Due to the influence of environmental factors and the equipment itself, in addition to the molded case circuit breaker point cloud, the acquired three-dimensional point cloud data also contains a large number of irrelevant environmental point clouds and random noise. In this embodiment, a radius outlier denoising algorithm is used to pre-process the acquired three-dimensional point cloud data. The radius outlier denoising algorithm is a well-known technology, and this application will not repeat its specific implementation process. The implementer can select a suitable method to denoise the point cloud data, and this application does not limit this.

[0024] Among them, the schematic diagram of the point cloud data before denoising is as follows: Figure 2 As shown; Schematic diagram of point cloud data after denoising, as shown Figure 3 shown.

[0025] It should be noted that the point cloud data used for subsequent analysis are all processed point cloud data; in addition, the point cloud data set of the molded case circuit breaker to be tested is recorded as the actual point cloud data set. At the same time, the three-dimensional point cloud data of the standard molded case circuit breaker is obtained under the same conditions and in the same way, which is recorded as the reference point cloud data set.

[0026] The second step: according to the change of local geometric features of each point cloud data and all point cloud data in the local range and the spatial distance, the local density of each point cloud data is obtained.

[0027] This application matches the actual point cloud data set with the reference point cloud data set, and judges the quality of the molded case circuit breaker based on the matching results. When using the ICP algorithm to match the point cloud of the molded case circuit breaker, the traditional ICP algorithm only relies on the Euclidean distance to match the corresponding points, and fails to fully utilize the unique geometric and physical characteristics of the molded case circuit breaker, which often causes the algorithm to fall into the local optimal solution and produce mismatches, thereby reducing the matching accuracy between the actual point cloud data set and the reference point cloud data set. In the point cloud data of the molded case circuit breaker, some data points contain key descriptive information of the molded case circuit breaker, such as the corner points of the molded case circuit breaker and the connection points between components. Therefore, this application considers the actual scene characteristics in the selection of corresponding points of the ICP algorithm to improve the matching accuracy and matching efficiency of the ICP point cloud matching algorithm in the quality detection of molded case circuit breakers.

[0028] Generally, point clouds are scattered in three-dimensional space. In the registration process, it is impossible to obtain good registration results based only on the information of a single point in the point cloud. Therefore, a neighborhood space is established for each point in the three-dimensional point cloud data set to obtain more information. Since the relative positions of different components in the molded case circuit breaker are relatively fixed, the point cloud data of different components in the collected point cloud data of the molded case circuit breaker still retain consistent geometric relationships, especially the geometric relationships between the point cloud data connected between different components are more significant.

[0029] Based on this, the neighborhood space of each point cloud data is preset, and the feature vector of each point cloud data in its neighborhood space is extracted: In this embodiment, the nearest neighbor search algorithm is first used to search the neighborhood points of each point cloud data. In this embodiment, the number of neighborhood points is set to 27; the implementer can adjust it according to the actual situation. Among them, the nearest neighbor search algorithm is an existing public technology and is not elaborated in this application; further, the Fast Point Feature Histograms (FPFH) algorithm is used to obtain the feature vector of each point cloud data in the neighborhood space.

[0030] Perform singular value decomposition on the matrix composed of the eigenvectors of each point cloud data and all the point cloud data in its neighborhood space, and obtain the singular distribution index of each point cloud data based on the distribution of singular values: obtain the degree of confusion of all singular values ​​of the matrix of each point cloud data, and fuse the degree of confusion with all singular values ​​of each point cloud data as the singular distribution index of each point cloud data.

[0031] In acquiring the singular distribution index of this embodiment, information entropy is used to measure the degree of confusion of a set of data, and multiple variables are mixed using addition and multiplication operations, that is, the singular distribution index is specifically: calculating the sum of squares of all singular values ​​of each point cloud data and the information entropy, and taking the product of the sum of squares and the information entropy as the singular distribution index of each point cloud data.

[0032] It should be understood that when the point cloud data is at a position where the molded case circuit breaker has obvious geometric features, the difference between the calculated eigenvectors of the point cloud data and other point cloud data in its neighborhood space is more obvious, and thus the difference between the singular values ​​of the matrix composed of the eigenvectors is greater, that is, the information entropy of all singular values ​​of the matrix corresponding to each point cloud data is greater. At the same time, the difference between the eigenvector of the point cloud data and the eigenvectors of other point cloud data in its neighborhood space is more obvious, the possibility of an increase in the sum of squares of singular values ​​is greater, and thus the singular distribution index of the point cloud data is greater.

[0033] Density is an important attribute of point cloud data. Areas with high point cloud density usually contain more geometric details. For example, a flatter surface may reflect less light or laser beams, resulting in a lower point cloud density in that area. On the other hand, a rough or textured surface may reflect more light or laser beams, thereby increasing the point cloud density in that area. Therefore, in the point cloud dataset of the molded case circuit breaker, the area with a larger point cloud density can better describe the local details of the molded case circuit breaker.

[0034] Based on this, based on the spatial distance between each point cloud data and all the point cloud data in its neighborhood space, combined with the singular distribution index, the local density of each point cloud data is obtained: a negative correlation mapping is performed on the distance between each point cloud data and each point cloud data in its neighborhood space; based on the average level of the negative correlation mapping results between each point cloud data and all the point cloud data in its neighborhood space, combined with the singular distribution index, the local density of each point cloud data is obtained; wherein the local density is positively correlated with the average level and the singular distribution index.

[0035] In the process of obtaining the local density of this embodiment, the distance between the point cloud data is the Euclidean distance; the average level of multiple variables is measured by the average value calculation method; the negative correlation mapping of a variable is specifically the reciprocal of a variable; the formula form of the local density is specifically: ;in, Represents the local density of the i-th point cloud data; Represents the singular distribution index of the i-th point cloud data; Represents the number of all point cloud data in the neighborhood space of the i-th point cloud data; Represents the Euclidean distance between the i-th point cloud data and the j-th point cloud data in its neighborhood space.

[0036] It should be understood that the more complex the surface of the molded case circuit breaker is, the more obvious the characteristic information of the surface is, and thus the larger the singular distribution index of the point cloud data is; at the same time, the more complex the surface is, the denser the point cloud data in the neighborhood space of the point cloud data is, that is, the smaller the distance to the point cloud data in the neighborhood space is, and thus the greater the local density of the point cloud data is.

[0037] The third step: principal component analysis is performed on each point cloud data and all point cloud data in its neighborhood space to obtain the curvature of each point cloud data, and combined with the local density to obtain the local morphological index of each point cloud data.

[0038] Molded case circuit breakers have rich geometric information. The surface features of molded case circuit breakers can be accurately captured through the curvature of point cloud data. Based on this, principal component analysis is used for each point cloud data and all point cloud data in its neighborhood space to obtain the eigenvalues ​​of each point cloud data, and the curvature of each point cloud data is calculated based on the eigenvalues; it should be noted that the use of principal component analysis to obtain the curvature of each point cloud data is an existing known technology, and this application will not elaborate on this in detail.

[0039] Among them, the curvature distribution diagram of point cloud data a and all point cloud data in its neighborhood space is as follows: Figure 4 As shown; the curvature distribution diagram of point cloud data b and all point cloud data in its neighborhood space is as follows: Figure 5 As shown, the point cloud data a and the point cloud data b are located at different positions.

[0040] However, in practical applications, due to the complex shape and structure of the molded case circuit breaker, the curvature of a single point cloud data can only reflect the local curvature at the corresponding position of the point cloud data, and it is difficult to ensure the matching accuracy with the reference point cloud. According to the distribution of the curvature of each point cloud data and its neighborhood space, combined with the local density, the local morphological index of each point cloud data is obtained: the discrete degree of the curvature of each point cloud data and all point cloud data in its neighborhood space is calculated; the discrete degree is merged with the local density to obtain the local morphological index of each point cloud data.

[0041] In this embodiment, the degree of discreteness refers to the variance of the curvature of each point cloud data and all point cloud data in its neighborhood space; multiple variables are added by multiplication, that is, the local morphological index is specifically the product of the local density of each point cloud data and the variance.

[0042] It should be understood that in the complex area of ​​the molded case circuit breaker surface, the curvature of the point cloud data and the point cloud data in its neighborhood space is quite different, so that the larger the variance of the curvature, the larger the local morphological index of the point cloud data, indicating that the point cloud data contains more information.

[0043] The fourth step: Based on the difference in local morphological index between the point cloud data of the molded case circuit breaker to be tested and the standard molded case circuit breaker, the error function in the ICP algorithm is adjusted, and the molded case circuit breaker product quality inspection result is obtained through point cloud registration.

[0044] The local morphological index of each point cloud data in the actual point cloud data set and the reference point cloud data set is obtained; the local morphological index takes into account the local geometric features in the neighborhood space of the point cloud data. Based on the local morphological index, the error function in the ICP algorithm is adjusted: in, represents the error value, represents the rotation matrix, represents the translation vector, represents the number of point pairs, The reference point cloud dataset The coordinates of the point cloud data, The actual point cloud data set The point cloud data coordinates with the closest Euclidean distance, Indicates the first The local morphological index of point cloud data, Indicates the actual point cloud data set The local morphological index of the point cloud data with the closest Euclidean distance. It should be noted that n in the ICP error function is obtained by the number of point pairs found in the registration process. This number is dynamic and depends on the iteration process of the algorithm and the density of the point cloud data. By minimizing the error function, the rotation matrix and translation vector are optimized. These two parameters are updated in each iteration until the error value reaches the minimum or converges.

[0045] Among them, the point cloud matching effect diagram is as follows: Figure 6 As shown, the bar graph with diagonal texture is the registration error using the traditional ICP algorithm, and the solid color bar graph represents the registration error using the adjusted ICP algorithm.

[0046] According to the adjusted error function, the actual point cloud dataset and the reference point cloud dataset are aligned, and surface fitting is performed to obtain the corresponding surface model; according to the difference between the corresponding positions of the surface models of the actual point cloud dataset and the reference point cloud dataset, the quality inspection results of the molded case circuit breaker product are obtained.

[0047] Specifically, a preset number of coordinate points are uniformly selected on the surface model of the reference point cloud data set, and in the surface model of the actual point cloud data set, the point closest to each coordinate point is selected as the calibration point; in this embodiment, the preset number is 300, and the Euclidean distance between each coordinate point and the calibration point is obtained. After the position deviation between each coordinate point and the calibration point is obtained, the position deviation is accumulated and summed to quantify the overall quality of the molded case circuit breaker, and the overall deviation of the molded case circuit breaker is obtained. The error threshold is set in this application When the calculated overall deviation is greater than the error threshold, an alarm is issued, indicating that the quality of the molded case circuit breaker is unqualified; otherwise, it means that the quality of the molded case circuit breaker is qualified. The error threshold can be adjusted by the implementer.

[0048] Based on the same inventive concept as the above method, an embodiment of the present application also provides a molded case circuit breaker product quality detection system, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, the steps of any one of the above-mentioned molded case circuit breaker product quality detection methods are implemented.

[0049] To summarize, the embodiment of the present application collects a point cloud data set of a molded case circuit breaker, analyzes the geometric relationship between each point cloud data and other point cloud data in its local range, and constructs a local density. The beneficial effect is that the feature differences between the point clouds in the local range are taken into account, and the geometric features of different positions of the molded case circuit breaker can be better distinguished; secondly, based on the density distribution and curvature distribution of the point cloud data, a local morphological index is constructed. The beneficial effect is that the distribution density of the point cloud data at different positions of the molded case circuit breaker and the surface morphology of the molded case circuit breaker are taken into account, and the geometric and physical characteristics of the molded case circuit breaker are fully utilized. By combining the local morphological index with the Euclidean distance, the registration process of the point cloud data of the molded case circuit breaker to be detected and the point cloud data of the standard molded case circuit breaker can be better completed, the mismatching problem caused by relying only on the Euclidean distance for matching is reduced, and the matching accuracy between the point cloud data of the molded case circuit breaker to be detected and the point cloud data of the standard molded case circuit breaker is improved, thereby meeting the high-precision and high-efficiency detection requirements of the molded case circuit breaker.

[0050] The flowchart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to the embodiment of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two continuous boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. In the description corresponding to the flowchart and the block diagram in the accompanying drawings, the operations or steps corresponding to different boxes can also occur in a different order from the order disclosed in the description, and sometimes there is no specific order between different operations or steps. For example, two continuous operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, which can depend on the functions involved. Each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs the specified functions or actions, or may be implemented by a combination of dedicated hardware and computer instructions.

[0051] For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the basic features of the present application. Therefore, no matter from which point of view, the above embodiments of the present application should be regarded as exemplary and non-restrictive; the technical solutions recorded in the above embodiments are modified, or some of the technical features are replaced by equivalents, which does not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application.

Claims

1. A method for detecting the quality of molded case circuit breakers, characterized in that: The method comprises the following steps: Obtain point cloud data of the molded case circuit breaker to be tested; Preset the neighborhood space of each point cloud data, extract the eigenvector of each point cloud data in its neighborhood space; perform singular value decomposition on the matrix composed of the eigenvectors of each point cloud data and all point cloud data in its neighborhood space, obtain the singular distribution index of each point cloud data based on the distribution of singular values, and obtain the local density of each point cloud data in combination with the spatial distance; Principal component analysis is performed on each point cloud data and all point cloud data in its neighborhood space to obtain the curvature of each point cloud data, and local morphological index of each point cloud data is obtained by combining the local density; Based on the difference in local morphological index between the point cloud data of the molded case circuit breaker to be tested and the standard molded case circuit breaker, the error function in the ICP algorithm is adjusted, and the product quality inspection result of the molded case circuit breaker is obtained through point cloud registration.

2. A method for detecting product quality of molded case circuit breakers according to claim 1, characterized in that: The process of extracting the feature vector of each point cloud data in its neighborhood space is as follows: The point cloud data and all the point cloud data in its neighborhood space are used as the input of the fast point feature histogram algorithm to obtain the feature vector of each point cloud data in its neighborhood space.

3. A method for testing the quality of molded case circuit breakers according to claim 1, characterized in that: The steps of obtaining the singular distribution index of each point cloud data are: The disorder degree of all singular values ​​of the matrix of each point cloud data is obtained, and the result of fusing the disorder degree with all singular values ​​of each point cloud data is used as the singular distribution index of each point cloud data.

4. A method for testing the quality of molded case circuit breakers according to claim 1, characterized in that: The local density of each point cloud data is obtained as follows: Negative correlation mapping is performed on the distance between each point cloud data and each point cloud data in its neighborhood space; Based on the average level of the negative correlation mapping results between each point cloud data and all point cloud data in its neighborhood space, combined with the singular distribution index, the local density of each point cloud data is obtained; wherein the local density is positively correlated with the average level and the singular distribution index.

5. A method for testing the quality of molded case circuit breakers according to claim 1, characterized in that: The local morphological index of each point cloud data is obtained as follows: The discrete degree of curvature of each point cloud data and all point cloud data in its neighborhood space is calculated; the discrete degree is merged with the local density to obtain the local morphological index of each point cloud data.

6. A method for testing the quality of molded case circuit breakers according to claim 1, characterized in that: The error function in the ICP algorithm is adjusted as follows: in, represents the error value, represents the rotation matrix, represents the translation vector, represents the number of point pairs, Standard molded case circuit breaker The coordinates of the point cloud data, For the molded case circuit breaker to be tested The point cloud data coordinates with the closest Euclidean distance, Indicates the standard molded case circuit breaker The local morphological index of point cloud data, Indicates the molded case circuit breaker to be tested The local morphology index of the point cloud data with the closest Euclidean distance.

7. A method for testing the quality of molded case circuit breakers according to claim 1, characterized in that: The process of obtaining the molded case circuit breaker product quality test results is specifically as follows: Perform surface fitting on the registered point cloud data of the standard molded case circuit breaker and the point cloud data of the molded case circuit breaker to be tested, respectively, to obtain the corresponding surface model; According to the coordinate change between the surface model of the standard molded case circuit breaker and the molded case circuit breaker to be tested, the overall deviation of the molded case circuit breaker to be tested is obtained; When the overall deviation is greater than a preset error threshold, the quality is determined to be unqualified; otherwise, the quality is qualified.

8. A method for testing the quality of molded case circuit breakers according to claim 7, characterized in that: The overall deviation of the molded case circuit breaker to be tested is obtained as follows: A preset number of coordinate points are uniformly selected on the surface model of the standard molded case circuit breaker, and a corresponding calibration point is selected in the surface model of the molded case circuit breaker to be tested according to the position of each coordinate point; The cumulative sum of the Euclidean distances between all coordinate points and the corresponding calibration points is obtained as the overall deviation of the molded case circuit breaker to be detected.

9. A method for testing the quality of molded case circuit breakers according to claim 8, characterized in that: The corresponding calibration point is specifically a point in the surface model of the molded case circuit breaker to be detected that is closest to the corresponding coordinate point.

10. A molded case circuit breaker product quality detection system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

Images