A deformation detection method for an integrally formed photovoltaic inverter box

Abstract

The present application relates to the technical field of deformation measurement, in particular to a deformation detection method for an integrally formed photovoltaic inverter box, which solves the technical problem of misjudgment of box deformation detection caused by position distortion due to external interference in the prior art. The method comprises: scanning to obtain sample point cloud data of a box to be detected and standard point cloud data of a new box; determining an abnormal area according to the offset degree of the sample point cloud data relative to the standard point cloud data; identifying a deformation area without interference and a suspected deformation area with interference in the abnormal area according to the data distribution of the abnormal area; correcting the data distribution according to the offset degree and signal reflection intensity of the suspected deformation area, and identifying a deformation area with interference and an interference distortion area without deformation in the suspected deformation area; determining the deformation degree of the box to be detected and taking corresponding maintenance measures according to the proportion of the deformation area in the scanning area and the data distribution of the deformation area.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of deformation measurement, and in particular to a deformation detection method for an integrally formed photovoltaic inverter box. BACKGROUND

[0002] The integrally formed photovoltaic inverter generally adopts an efficient integrated design, so that all functional modules (such as direct current input, alternating current output, control module, heat dissipation device, etc.) of the inverter are completed in a unified box, thereby improving the overall efficiency, reducing the installation complexity, and enhancing the stability and reliability of the equipment.

[0003] During transportation, installation or maintenance, the box may be subjected to external impact or vibration, causing local deformation of the box structure. However, when the laser scanning method is used to detect the deformation of the box, the point cloud data of the measured object is generally obtained for evaluation. However, due to external interference (surface characteristics, ambient light) during the acquisition of the point cloud data, position distortion may occur, which may cause the above-mentioned non-deformation region to be misjudged as a deformation region, affecting the accuracy and reliability of the laser scanning or other measurement techniques. SUMMARY

[0004] In order to solve the technical problem of misjudgment of the deformation detection of the box due to position distortion caused by external interference in the prior art, the purpose of the present application is to provide a deformation detection method for an integrally formed photovoltaic inverter box, and the technical solution adopted is as follows:

[0005] In a first aspect, a deformation detection method for an integrally formed photovoltaic inverter box is provided, comprising: scanning the three-dimensional point cloud data of the outer surface of the box to obtain sample point cloud data of the box to be detected and standard point cloud data of a new box; determining abnormal regions on the box to be detected according to the offset degree of the sample point cloud data relative to the standard point cloud data; identifying deformation regions without interference and suspected deformation regions with interference in the abnormal regions according to the data distribution of the sample point cloud data in the abnormal regions; correcting the data distribution according to the offset degree and signal reflection intensity of the sample point cloud data in the suspected deformation regions, and identifying deformation regions with interference and interference distortion regions without deformation in the suspected deformation regions; determining the degree of deformation of the box to be detected according to the proportion of the deformation regions in the scanning area in the box to be detected, and the data distribution of the deformation regions, and taking corresponding maintenance measures.

[0006] Based on the above technical scheme, in the deformation detection method of the integrally formed photovoltaic inverter box provided by the application, first, the abnormal area is located through offset degree analysis to distinguish potential deformation and interference. Then, the data distribution characteristics are used to distinguish the interference-free deformation and the suspected area with interference, and the point cloud data interfered by the interference is preliminarily isolated. Finally, the data distribution is corrected in combination with the double indexes of offset degree and signal reflection intensity to clearly distinguish the real deformation with interference and the pure interference distortion, and the interference identification and exclusion mechanism is established from the method flow, and the problem of interference in the detection accuracy of the box deformation area caused by surface dust, rust, light and the like during the laser scanning detection of the box deformation is optimized.

[0007] In combination with the first aspect, in a possible implementation manner, the method for determining the abnormal area on the box to be detected according to the offset degree of the sample point cloud data relative to the standard point cloud data specifically includes: comparing the sample point cloud data and the standard point cloud data to obtain an abnormal data point set of the offset standard position; clustering the data points in the abnormal data point set based on the offset degree of each data point in the abnormal data point set to obtain a plurality of data point clusters; and determining the abnormal area in the box region corresponding to the abnormal data point set according to the offset degree and the number of the data points in each data point cluster.

[0008] In combination with the first aspect, in a possible implementation manner, the method for comparing the sample point cloud data and the standard point cloud data to obtain the abnormal data point set of the offset standard position specifically includes: determining the offset degree of the data point in the sample point cloud data from the offset standard position according to the Euclidean distance between the data point in the sample point cloud data and the data point in the standard point cloud data and the distance between the data point in the sample point cloud data and the point cloud plane; and determining the data point in the sample point cloud data with the offset degree greater than a preset offset degree threshold as an abnormal data point.

[0009] In combination with the first aspect, in a possible implementation manner, the method for determining the abnormal area in the box region corresponding to the abnormal data point set according to the offset degree and the number of the data points in each data point cluster specifically includes: determining the detection confidence of each data point cluster according to the offset degree and the number of the data points in each data point cluster; and identifying the box region corresponding to the data point cluster with the detection confidence greater than a preset confidence threshold as the abnormal area.

[0010] In combination with the first aspect, in a possible implementation manner, the method for identifying the interference-free deformation area and the suspected deformation area with interference in the abnormal area according to the data distribution of the sample point cloud data in the abnormal area specifically includes: analyzing the data distribution of the sample point cloud data in the abnormal area to obtain a first distribution coefficient; identifying the abnormal area as the interference-free deformation area if the first distribution coefficient is greater than a preset coefficient threshold; and identifying the abnormal area as the suspected deformation area with interference if the first distribution coefficient is less than or equal to the preset coefficient threshold.

[0011] In a possible implementation manner of the first aspect, the method of analyzing the data distribution of the sample point cloud data in the abnormal region to obtain the first distribution coefficient comprises: analyzing the sample point cloud density of the plurality of data points in the abnormal region, comparing the sample point cloud density of the plurality of data points in the abnormal region with the standard point cloud density of the plurality of data points in the corresponding region of the new box, and determining a point cloud density difference coefficient of the abnormal region; comparing and analyzing the offset direction of the plurality of data points in the abnormal region, and determining a data point continuity coefficient in the abnormal region; and determining the first distribution coefficient according to the point cloud density difference coefficient and the data point continuity coefficient.

[0012] In a possible implementation manner of the first aspect, the method of correcting the data distribution according to the offset degree and the signal reflection intensity of the sample point cloud data in the suspected deformation region, and identifying the deformation region with interference and the interference distortion region without deformation in the suspected deformation region comprises: determining a deformation screening factor of the suspected deformation region according to the offset degree and the signal reflection intensity of the sample point cloud data; correcting the first distribution coefficient based on the deformation screening factor to obtain a second distribution coefficient; if the second distribution coefficient is greater than a preset coefficient threshold, identifying the suspected deformation region as the deformation region with interference; and if the second distribution coefficient is less than or equal to the preset coefficient threshold, identifying the suspected deformation region as the interference distortion region without deformation.

[0013] In a possible implementation manner of the first aspect, the method of determining the deformation screening factor of the suspected deformation region according to the offset degree and the signal reflection intensity of the sample point cloud data comprises: determining a signal reflection coefficient of each suspected deformation region according to the average signal reflection intensity of the sample point cloud data in each suspected deformation region; determining an offset degree coefficient of each suspected deformation region according to the average offset degree of the sample point cloud data in the plurality of suspected deformation regions; and determining the deformation screening factor according to the signal reflection coefficient and the offset degree coefficient.

[0014] In a possible implementation manner of the first aspect, the method further comprises: visually displaying the sample point cloud data of the to-be-detected box and identifying the deformation region.

[0015] In a possible implementation manner of the first aspect, the method of taking corresponding maintenance measures comprises: when the deformation degree is severe deformation, determining a processing strategy according to the functional attribute of the deformation region; and sending an alarm message to a maintenance terminal, wherein the alarm message comprises the deformation region, the deformation degree, and the processing strategy.

[0016] In a second aspect, a deformation detection device for an integrally formed photovoltaic inverter box is provided, including a processor and a storage medium; the storage medium includes instructions, and the processor is configured to execute the instructions to implement the actions described in the first aspect and any possible implementation manner of the first aspect. The deformation detection device for the integrally formed photovoltaic inverter box can be an electronic device or a chip in the electronic device.

[0017] In a third aspect, a computer-readable storage medium is provided, and the computer-readable storage medium stores instructions, which, when executed on a deformation detection device for an integrally formed photovoltaic inverter box, cause the deformation detection device for the integrally formed photovoltaic inverter box to perform the actions described in the first aspect and any possible implementation manner of the first aspect.

[0018] In a fourth aspect, a computer program product is provided, and the computer program product includes instructions, which, when executed on a deformation detection device for an integrally formed photovoltaic inverter box, cause the deformation detection device for the integrally formed photovoltaic inverter box to perform the actions described in the first aspect and any possible implementation manner of the first aspect.

[0019] The present application has the following beneficial effects:

[0020] First, the abnormal area is located by offset degree analysis to distinguish potential deformation and interference. Then, the data distribution characteristics are used to distinguish the non-interference deformation and the suspected area with interference, and the point cloud data affected by interference is preliminarily isolated. Finally, the data distribution is corrected in combination with the double indexes of offset degree and signal reflection intensity to clearly distinguish the real deformation with interference and the pure interference distortion, and the interference identification and exclusion mechanism is established from the method flow, and the detection accuracy problem of the box deformation area caused by surface dust, rust, light and the like during laser scanning detection of the box deformation is optimized. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0022] Figure 1 A method flowchart of a deformation detection method for an integrally formed photovoltaic inverter box is provided for an embodiment of the present application;

[0023] Figure 2 An equipment appearance schematic diagram of an integrally formed photovoltaic inverter box is provided for an embodiment of the present application;

[0024] Figure 3 A three-dimensional point cloud schematic diagram of an integrally formed photovoltaic inverter box is provided for an embodiment of the present application.

[0025] Figure 4 A method flow chart of another deformation detection method of an integrally formed photovoltaic inverter box is provided for an embodiment of the present application.

[0026] Figure 5 A method flow chart of another deformation detection method of an integrally formed photovoltaic inverter box is provided for an embodiment of the present application.

[0027] Figure 6 A method flow chart of another deformation detection method of an integrally formed photovoltaic inverter box is provided for an embodiment of the present application.

[0028] Figure 7 A method flow chart of another deformation detection method of an integrally formed photovoltaic inverter box is provided for an embodiment of the present application.

[0029] Figure 8 A method flow chart of another deformation detection method of an integrally formed photovoltaic inverter box is provided for an embodiment of the present application.

[0030] Figure 9 A method flow chart of another deformation detection method of an integrally formed photovoltaic inverter box is provided for an embodiment of the present application.

[0031] Figure 10 A method flow chart of another deformation detection method of an integrally formed photovoltaic inverter box is provided for an embodiment of the present application.

[0032] Figure 11 A method flow chart of another deformation detection method of an integrally formed photovoltaic inverter box is provided for an embodiment of the present application.

[0033] Figure 12 A method flow chart of another deformation detection method of an integrally formed photovoltaic inverter box is provided for an embodiment of the present application.

[0034] Figure 13 A hardware structure schematic diagram of a deformation detection device of an integrally formed photovoltaic inverter box is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to further illustrate the technical means and effects taken by the present application to achieve the predetermined inventive objectives, the following describes in detail the specific implementation, structure, features and effects of a deformation detection method for an integrally formed photovoltaic inverter box according to the present application, in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0036] Unless otherwise defined, 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.

[0037] The specific scheme of the deformation detection method for an integrally formed photovoltaic inverter box provided by the present application is described in detail below in conjunction with the accompanying drawings.

[0038] Referring to Figure 1 , a method flowchart of a deformation detection method for an integrally formed photovoltaic inverter box according to an embodiment of the present application is shown. The deformation detection method for an integrally formed photovoltaic inverter box includes:

[0039] S1, scanning the three-dimensional point cloud data of the outer surface of the box to obtain sample point cloud data of the box to be detected and standard point cloud data of a brand new box.

[0040] The principle of using a laser scanning method to detect the deformation of the box is based on non-contact three-dimensional measurement technology. A laser scanner emits a laser beam to scan the surface of the box. The laser scanner emits a laser beam to the surface of the box. The laser is reflected back to the scanner after encountering the box. The distance traveled by the laser from emission to return is calculated to obtain the three-dimensional coordinates of the corresponding points in space, and a three-dimensional point cloud about the box is established. For example, as shown in Figure 2 , the inverter box, the point cloud data obtained by laser scanning is as shown in Figure 3 . The three-dimensional point cloud data of the box can be used to represent the true geometric shape and deformation of the box surface, and is suitable for geometric precision detection of large containers / boxes.

[0041] In some implementations, the scanning device can use a high-precision laser scanner (scanning accuracy ±0.1mm, point cloud density ≥100 points / mm²), configure a 360° rotary scanning platform, and ensure that there is no scanning dead angle on the outer surface of the box. The scanning environment is carried out in a closed detection space to avoid direct sunlight, air flow disturbance and vibration (such as setting an anti-vibration workbench), the temperature is stabilized at 25±2℃, and the temporary influence of thermal expansion and contraction on the box is reduced.

[0042] In some implementations, three new and unused boxes of the same batch can be selected, scanned three times respectively, and nine groups of data can be fused by a point cloud registration algorithm to generate a standard point cloud model that eliminates individual differences, serving as a reference.

[0043] The to-be-detected box is scanned three times repeatedly, and noise points are removed, for example, isolated points deviating from the mean by three times the standard deviation are removed by statistical filtering to obtain a denoised sample point cloud.

[0044] Further, the two types of point clouds are unified in the coordinate system, for example, a three-dimensional coordinate system is established with the center of the box bottom mounting hole as the origin, and the iterative closest points (ICP) algorithm is used to complete the coarse registration to ensure the spatial position alignment of the two.

[0045] In some implementations, while obtaining the point cloud data of the to-be-detected integrated inverter box by laser scanning, the reflection intensity and fitting residual of different data points are recorded, and the standard point cloud data and indicators of a new or surface-smooth box of the same type are obtained by scanning.

[0046] S2, according to the offset degree of the sample point cloud data relative to the standard point cloud data, determine the abnormal area on the to-be-detected box.

[0047] In some implementations, the abnormal points deviating from the standard position can be marked first, and the spatial connectivity analysis (such as dividing the space region by octree) is performed on the abnormal points, and the connected regions are merged into abnormal regions. This method is suitable for box structures with more curved surfaces, and can better handle the offset detection of complex geometric shapes.

[0048] In other implementations, the spatial gradient change of the offset degree can also be used to identify abnormal regions, including grid processing (such as 1mm x 1mm three-dimensional grid) of the sample point cloud and the standard point cloud, and calculating the average offset degree of each grid. Calculate the offset degree gradient (i.e. offset change rate) between adjacent grids to generate a gradient field distribution map. When the gradient value in a certain region continuously exceeds the threshold value and the direction is consistent, it is marked as a potential abnormal region, and the average offset degree in the region is combined, such as an average offset degree greater than 0.3mm, to finally determine the abnormal region. This method can effectively distinguish between continuous deformation (such as bending) and local protrusions / recesses, and is suitable for detecting structural deformation of the box.

[0049] S3, according to the data distribution of the sample point cloud data in the abnormal region, identify the deformation region without interference and the suspected deformation region with interference in the abnormal region.

[0050] In some implementations, since the point cloud normal vectors (reflecting surface orientation) of the real deformation region present a continuous change trend, while the point cloud offset caused by interference is often accompanied by disordered jumping of normal vectors, such as the confusion of normal vectors of local noise points, the normal vector of each point in the abnormal region can be fitted to a local plane by least squares, then the included angle of the normal vectors of adjacent points is calculated, and the average absolute value and standard deviation of the included angles in the region are calculated. The determination rules include: if the average included angle is < 10° and the standard deviation is < 5°, it is determined that there is no interference deformation region (the normal vector changes continuously, which is consistent with the physical deformation characteristics); if the average included angle is > 30° or the standard deviation is > 15°, it is determined that there is an interference suspected region (the normal vector changes suddenly, which may be caused by point cloud disorder caused by interference).

[0051] In other implementations, since the point cloud of the real deformation region remains continuous connection in spatial topology (such as the integrity of the triangular mesh), while the point cloud of the interference region often appears topological fracture or isolated fragments, a triangular mesh (topological connection of adjacent points in three-dimensional space) can be constructed for the point cloud of the abnormal region, the proportion of narrow triangles (minimum angle < 10°) in the triangular mesh, and the number of isolated points (connection edge number < 3) are calculated. The determination rules include: if the proportion of narrow triangles is < 10% and the number of isolated points is < 5%, it is determined that there is no interference deformation region (the topological structure is continuous and complete); if the proportion of narrow triangles is > 30% or the number of isolated points is > 15%, it is determined that there is an interference suspected region (the topological structure is broken, which may be caused by point cloud missing or disorder caused by interference).

[0052] S4、According to the offset degree and signal reflection intensity of the sample point cloud data in the suspected deformation region, the data distribution is corrected, and the deformation region with interference and the interference distortion region without deformation in the suspected deformation region are identified.

[0053] In some implementations, the laser reflection intensity value of each data point (scanner built-in parameter, reflecting the light reflection characteristics of the surface material) is extracted, and the mean and standard deviation of the reflection intensity in the region are calculated. By comparing the mean reflection intensity of the corresponding region in the standard point cloud, if the difference between the mean reflection intensity of the sample point cloud and the standard point cloud in the corresponding region is greater than 2 times the reflection intensity standard deviation of the standard region, it indicates that there is surface interference (such as oil stains, scratches causing abnormal reflectivity) in the region. For the points with abnormal reflection intensity in the suspected region, the weight of the offset degree in the region evaluation is reduced, for example, multiplied by a correction coefficient of 0.3, and the spatial continuity and offset consistency are recalculated.

[0054] The deformation region with interference can be defined as: the corrected spatial continuity > 0.7 and the standard deviation of the offset direction < 10°, which is determined to be interfered but still exists real deformation (such as deformation region surface with stains);

[0055] The interference distortion region without deformation can be defined as: the corrected spatial continuity < 0.5, and the offset degree mainly comes from the point of abnormal reflection intensity, which is determined as the distortion caused by pure interference (such as dust blocking during scanning).

[0056] S5, according to the proportion of the deformation region in the scanning area in the to-be-detected box body and the data distribution of the deformation region, the deformation degree of the to-be-detected box body is determined, and corresponding maintenance measures are taken.

[0057] In some implementations, for any deformation region, the data distribution determines the severity of the local deformation degree, which can be represented by the average distribution coefficient of the deformation region , which represents the local deformation degree. The larger the average distribution coefficient , the greater the local deformation degree, and vice versa. At the same time, the size of the abnormal region corresponds to the deformation area. Based on the above characteristics, the calculation formula for comprehensively evaluating the deformation degree of the box body sample is as follows:

[0058]

[0059] In the formula, is the total scanning area of the to-be-detected box body.

[0060] is the area of the deformation region in the to-be-detected box body.

[0061] represents the proportion of the deformation region in the scanning area, and the larger the value, the larger the deformation region.

[0062] is the average distribution coefficient of all local deformation regions.

[0063] is a normalization function for normalizing the numerical value to the range of [0, 1].

[0064] is the deformation degree of the to-be-detected box body. Among them, the proportion of the deformation region in the scanning area is larger, and the severity of the deformation is larger, which means that the deformation of the to-be-detected box body is more serious, and it needs to be repaired more.

[0065] Since the integrated inverter box body integrates many functional components, if the box body is severely deformed, it may affect the change of the functional components. Here, the value of corresponds to the box body sample with severe deformation, and is replaced. If necessary, the functions of the internal components can be detected one by one, and the box body structure, internal electrical components, heat dissipation system, etc. are focused on to ensure the stable operation of the inverter function.​

[0066] Based on the above technical solution, first, the abnormal area is located by offset degree analysis, and potential deformation and interference are distinguished. Then, the data distribution characteristics are used to distinguish the non-interference deformation and the suspected area with interference, and the point cloud data interfered is preliminarily isolated. Finally, the data distribution is corrected in combination with the double indexes of offset degree and signal reflection intensity, and the real deformation with interference and the pure interference distortion are clearly distinguished. The interference recognition and exclusion mechanism is established from the method flow, and the problem of detection accuracy of the box deformation area interfered by surface dust, rust, light and the like during laser scanning detection of the box deformation is optimized.

[0067] In a possible implementation manner, the method S2 is implemented in combination with Figure 1 As shown in Figure 4 The method S2 can be implemented through the following S21 to S23, which will be described in detail below.

[0068] S21, compare the sample point cloud data and the standard point cloud data to obtain an abnormal data point set of offset standard positions.

[0069] The sample point cloud data can contain the local deformation characteristics of the box, and the standard point cloud data represents the normal box shape. Then, the point cloud shapes corresponding to the two are superimposed and coincided through the coordinate system. If the data points at the corresponding positions are different from the positions of the standard points, it means that the box position corresponding to the data points may have deformed, which is an abnormal data point.

[0070] In some implementation manners, the standard point cloud can be converted into a three-dimensional distance field (the shortest distance from each space point to the surface of the standard point cloud), and then the distance value distribution of the sample point cloud in the distance field is calculated. When the distance value of the sample point exceeds a threshold value (such as 0.5 mm), it is marked as an abnormal point.

[0071] S22, cluster the data points in the abnormal data point set based on the offset degrees of the data points in the abnormal data point set to obtain a plurality of data point clusters.

[0072] Since the interference point cloud data generally corresponds to a large offset degree and the local number scale is small, the adaptive clustering based on the offset degree size is performed on all abnormal data points. Then, the data points with similar offset degrees can be classified into a cluster. Since the interference point cloud has poor concentration, the scale of the corresponding data point cluster will be smaller, and therefore the point cloud can be screened based on different data point clusters.

[0073] In some implementations, the density-based spatial clustering of applications with noise (DBSCAN) algorithm can be used. This algorithm does not require a preset number of clusters and can adaptively identify point clusters of arbitrary shapes, making it suitable for irregular deformation areas that may occur on the surface of the container. The core parameter is set as follows: the neighborhood radius is determined based on the point cloud density. For example, when the point cloud density is 100 points / mm², the neighborhood radius is 0.8 mm, ensuring that adjacent outliers can be grouped into the same cluster.

[0074] Traverse the set of outlier data points. For each unclassified point, search for all other outlier points within its neighborhood radius. If the number of points in the neighborhood is greater than or equal to the minimum threshold within the cluster (e.g., 10), then set that point as the core point and recursively expand the points in its neighborhood to form a data point cluster.

[0075] For non-core points (i.e., the number of points in their neighborhood is less than the minimum threshold within the cluster), if they are in the neighborhood of a core point, they are assigned to the cluster of that core point; otherwise, they are marked as noise points and can be directly removed.

[0076] The result is multiple data point clusters, each representing a spatially contiguous region of outlier aggregation.

[0077] S23. Based on the offset and number of data points in each data point cluster, determine the abnormal area in the box area corresponding to the abnormal data point set.

[0078] In some implementations, dual filtering conditions are set, including: filtering by offset to ensure that the overall offset of the region is significant and to exclude point clusters with slight fluctuations; and filtering by the actual area corresponding to the size of the point cluster to exclude local interference areas that are too small.

[0079] For point clusters that meet the conditions, the region boundary is determined in the following way: calculate the minimum circumscribed cuboid of the point cluster, and use the boundary of the cuboid as the initial boundary of the abnormal region; smooth the boundary (e.g., by using Gaussian filtering) to remove the sharp corners to fit the continuous features of the actual deformed region.

[0080] Based on the above technical solution, by directly comparing the sample with the standard point cloud, all outlier points deviating from the standard position can be quickly screened out, avoiding the omission of potential deformation areas. Offset-based clustering analysis can aggregate outlier points with similar spatial locations and offset characteristics, effectively isolating the influence of noise points on the results. Combining offset and data point quantity as dual indicators to determine outlier regions makes the region boundaries clearer, providing structured data support for subsequent deformation judgment. It can effectively identify both continuous deformation (such as large-area depressions) and local deformation (such as bulges), and is applicable to different types of box deformation detection scenarios.

[0081] In one possible implementation, combining Figure 4 ,like Figure 5 As shown, the method in S21 above can be specifically implemented through the following S211 to S212, which are explained in detail below:

[0082] S211. Based on the Euclidean distance between the data points in the sample point cloud data and the data points in the standard point cloud data, and the distance between the data points in the sample point cloud data and the point cloud plane, determine the offset degree of the data points in the sample point cloud data from the standard position.

[0083] In some implementations, data points The formula for calculating the offset from the standard position is as follows:

[0084]

[0085] In the formula, For data points coordinate data, For standard point cloud and data points The coordinates of the nearest point.

[0086] Represents data points The larger the Euclidean distance relative to the standard point, the higher the value of the corresponding data point. The greater the offset, the more abnormal the data points.

[0087] For data points With its point cloud plane The straight-line distance, at the same time Represents data points Relative to the plane The offset value is larger, and the greater the unevenness of the point position, the more likely it is to be an abnormal data point. By constraining the plane distance of the point cloud, it is possible to effectively distinguish between true deformation points (deviating from the corresponding standard point and also deviating from the overall surface trend) and local interference points (only a single point deviates without destroying the overall surface trend).

[0088] For data points The offset from the standard position, when averaged, is a quantification of the balance between local and overall trend offsets. Specifically, the greater the Euclidean distance of a data point relative to the standard point... At the same time, combined with data points Relative to the plane offset ,Right now The larger the value, the greater the deviation of the data point from the standard position.

[0089] Among them, the Euclidean distance reflects the direct position deviation of point to point, which can capture local subtle deviation; the point cloud plane distance (usually the vertical distance of the sample point to the local fitting plane of the standard point cloud) reflects the deviation degree of the point to the overall surface trend, which is more in line with the overall characteristics of physical deformation (such as the bending of the box surface will cause the overall deviation of the local area from the original plane, rather than the deviation of a single discrete point). The combination of the two makes the deviation degree not only include the absolute position deviation, but also include the deviation of the relative overall trend, which can more accurately quantify the difference between the real deformation (such as concave and convex) and the normal surface fluctuation.

[0090] In S212, data points with a deviation degree greater than a preset deviation degree threshold in the sample point cloud data are determined as abnormal data points.

[0091] In some implementations, the threshold value can be dynamically adjusted according to factors such as the stiffness difference of the box material (such as metal / plastic), the environmental interference difference of the use scene (such as outdoor / indoor), and the device accuracy, so as to balance flexibility and standardization. For example, the basic device can set the threshold value to 0.5mm, and the precise device can set the threshold value to 0.

[0092] The deviation degree based on the double distance calculation itself contains the overall trend deviation information, so the threshold screening can more accurately frame the points that truly deviate from the normal structure, avoiding over-screening (missed detection) or under-screening (false detection) caused by a single distance threshold.

[0093] Based on the above technical solutions, by fusing the deviation degree calculated by double distance and the threshold screening, the accuracy of deviation quantification is improved while the anti-interference ability is enhanced, which effectively distinguishes the real deformation from the local interference, provides high-quality basic data for subsequent abnormal area recognition, and finally improves the overall reliability of the box deformation detection.

[0094] In a possible implementation, the method of S23 can be implemented by combining the following S231 and S232. Figure 4 As shown in the following S231 and S232, the method of S23 can be implemented by combining the following S231 and S232. Figure 6 The method of S23 can be implemented by the following S231 and S232, which will be described in detail below.

[0095] In S231, the detection confidence of each data point cluster is determined according to the deviation degree and the number of data points in each data point cluster.

[0096] In some implementations, the calculation formula of the detection confidence of the data point cluster is as follows:

[0097]

[0098] In the formula, is the data point cluster The average offset degree of all data points. Since the offset of the real deformation is usually structural and continuous, the offset degree is not extremely large, and the interference points (such as noise and surface stains) often show local and discrete large offset. Therefore, the data point cluster The larger the average offset degree of all data points in the cluster, the larger the offset degree, and the more likely the data points in the cluster are interference point cloud data points.

[0099] The data size of the data point cluster , that is, the number of data points, The maximum size of all data point clusters.

[0100] The relative size of the data point cluster . Since the real deformation is a physical change of the box structure, it usually shows a large number of continuous area points and a large size; and the interference points (such as isolated noise) are usually distributed discretely, with a small number of points and a small size. Therefore, the smaller the relative size, the fewer data points the cluster contains, which meets the discreteness of the interference point cloud.

[0101] The detection confidence of a certain data point cluster , the association between the offset degree and the size is normalized to a confidence in the interval [0, 1] by a normalization function , realizing the fusion judgment of multi-dimensional features.

[0102] S232, the data point cluster corresponding to the box region whose detection confidence is greater than the preset confidence threshold is marked as an abnormal region.

[0103] The adaptive differentiation of the deformation cluster and the interference cluster is realized, and the threshold screening (such as ) of the quantitative confidence is used to reduce the false detection of mistaking the interference as the deformation and avoid the missed detection of mistaking the deformation as the interference, and finally output the accurate abnormal region annotation.

[0104] Based on the above technical solution, the confidence is calculated by multi-dimensional feature fusion, and the threshold screening is used to locate the abnormal region, which solves the core problem that the interference cluster and the real deformation cluster are difficult to distinguish in laser scanning detection.

[0105] In one possible implementation, in combination with Figure 1 , as shown in Figure 7 , the method of S3 can be implemented by the following S31 to S33, which will be described in detail below:

[0106] S31, analyze the data distribution of the sample point cloud data in the abnormal region to obtain a first distribution coefficient.

[0107] Since the point cloud offset will generate the above abnormal area, and the point cloud distortion will also cause the point cloud offset in the corresponding area, that is, the abnormal area not only contains the box deformation area but also contains the area where these interference factors exist. Here, the point cloud corresponding to the abnormal area is screened based on the difference in the point cloud distribution of both.

[0108] In some implementations, the DBSCAN clustering algorithm is used to cluster the region point cloud, and the proportion of the number of points in the largest cluster to the total number of points in the region is counted. The closer the proportion is to 1, the stronger the spatial continuity of the point cloud.

[0109] For each point in the region, the offset vector (spatial position difference) of the point relative to the standard point cloud is calculated, principal component analysis is performed on all offset vectors, and the variance contribution rate of the first principal component is calculated. The closer the variance contribution rate of the first principal component is to 1, the more concentrated the offset direction is.

[0110] The density of the point cloud in the region is calculated, and the coefficient of variation (standard deviation / mean) of the density is calculated. The closer the coefficient of variation is to 0, the more uniform the point cloud density is.

[0111] The multi-dimensional indicators are fused by using a weighted formula (the weights can be adjusted according to the scene), for example:

[0112] The first distribution coefficient = 0.4 x the proportion of the number of points in the largest cluster to the total number of points in the region + 0.3 x the variance contribution rate of the first principal component + 0.3 x (1 - the coefficient of variation of the density).

[0113] At this time, the first distribution coefficient ranges from 0 to 1, and the closer to 1 indicates that the distribution is more in line with the true deformation characteristics.

[0114] S32, if the first distribution coefficient is greater than a preset coefficient threshold, the abnormal area is identified as a deformation area without interference.

[0115] In some implementations, the preset coefficient threshold can be set according to the box material and detection accuracy, for example, the metal box threshold is set to 0.7, and the plastic box threshold is set to 0.6.

[0116] S33, if the first distribution coefficient is less than or equal to the preset coefficient threshold, the abnormal area is identified as a suspected deformation area with interference.

[0117] Not all anomalous regions that do not meet this threshold condition originate from external interference factors (such as point cloud distortion caused by ambient light). In actual detection, some anomalous regions may simultaneously exhibit a mixture of local deformation of the box and surface interference. For example, if the box bulges or depressions while its surface has high light reflection intensity, it will cause point cloud distortion. In such mixed scenarios, surface interference will significantly alter the microscopic distribution characteristics of the point cloud, specifically manifesting as abnormally sparse point cloud density, deviating from the standard density, or reduced data point continuity, leading to an underestimation of the first distribution coefficient, with its value falling below the threshold.

[0118] If only this threshold is used for screening, such mixed areas will be incorrectly classified as non-deformation areas, resulting in missed deformation detections and thus reducing the reliability of the detection results. In other words, the above screening steps will produce errors. Therefore, it is necessary to analyze the reflection intensity and regional change characteristics of the remaining abnormal areas for accurate screening.

[0119] Based on the above technical solution, since the point cloud of real deformation has characteristics such as spatial continuity, consistency of offset direction, and uniform density, by quantifying the distribution characteristics of point cloud data and setting a threshold, it is possible to effectively distinguish between two types of regions: non-interference deformation regions and interference-suspected deformation regions, thereby reducing the risk of misjudging interference as deformation or missing deformation as interference.

[0120] In one possible implementation, combining Figure 7 ,like Figure 8 As shown, the method in S31 above can be specifically implemented through the following S311 to S313, which are explained in detail below:

[0121] S311. Analyze the sample point cloud density of multiple data points in the abnormal area and compare it with the standard point cloud density of multiple data points in the corresponding area of ​​the new box to determine the point cloud density difference coefficient of the abnormal area.

[0122] Generally, local deformation of the box can present surface shapes such as bulges, depressions, and bends. The point cloud data anomalies caused by these have microscopic continuity. At the same time, the point cloud distribution density in the anomaly area remains unchanged. However, due to the discontinuity of point cloud anomalies caused by point cloud distortion, the distribution density of the point cloud becomes sparser.

[0123] In some implementations, the formula for calculating the point cloud density difference coefficient is as follows:

[0124]

[0125] In the formula, Abnormal area Point cloud density, This represents the point cloud density under normal standard conditions.

[0126] Real deformation (e.g. bulge, depression) is a physical change of the box structure, which does not change the point cloud density (0 ≈ ), therefore tends to 0, and its reciprocal tends to a maximum value.

[0127] Point cloud distortion (e.g. point cloud anomaly caused by interference, noise) makes the point cloud density more sparse (0 ), therefore is significantly greater than 0, and its reciprocal is significantly less than the real deformation area.

[0128] is a very small positive number, such as 0.001, because there may be a case of 0, by increasing the very small positive number, to avoid the case of meaningless reciprocal, in addition, the influence of the very small value on the calculation result can be ignored.

[0129] The point cloud density difference coefficient is screened by density proximity, effectively suppressing the interference of point cloud distortion (density sparsity), and highlighting the feature of constant density of real deformation.

[0130] S312, compare and analyze the displacement direction of multiple data points in the abnormal area to determine the data point continuity coefficient in the abnormal area.

[0131] In some implementations, the calculation formula of the data point continuity coefficient is as follows:

[0132]

[0133] In the formula, and are the maximum and minimum principal component vectors in the principal component analysis (PCA) of the abnormal area .

[0134] The point cloud of real deformation has microscopic continuity (e.g. the point cloud of the bulge area is continuously distributed along the deformation direction), therefore the angle between the PCA principal component vectors is small, and the cosine value tends to 1.

[0135] Point cloud distortion (e.g. point cloud disorder caused by interference) does not have continuity, and the angle between the PCA principal component vectors is large, and the cosine value is significantly less than 1.

[0136] The data point continuity coefficient is screened by spatial continuity, effectively suppressing the interference of point cloud distortion (non-continuity), and highlighting the feature of continuous distribution of real deformation.

[0137] S313, determine the first distribution coefficient according to the point cloud density difference coefficient and the data point continuity coefficient. ​

[0138] In some implementations, the first distribution coefficient The calculation formula is as follows:

[0139]

[0140] In the formula, For a certain abnormal region The data point distribution coefficient.

[0141] The true deformation region simultaneously satisfies the conditions of near-normal density and continuous point cloud, therefore The value is significantly larger than expected.

[0142] The interference area either has large density differences or poor continuity. The value is significantly smaller than expected.

[0143] Furthermore, the normalized value can be adjusted by applying a threshold. Perform threshold filtering (e.g., setting a normalized threshold) (For true deformation), it can achieve quantitative differentiation between the two types of regions.

[0144] Based on the above technical solution, the essential difference between real deformation and interference areas is accurately characterized by multi-dimensional fusion of density features and continuity features. This provides a quantitative basis for the classification of abnormal areas (deformation without interference / suspected interference), effectively solving the technical pain point of difficulty in distinguishing between deformation and interference in laser scanning, and improving the accuracy and reliability of box deformation detection.

[0145] In one possible implementation, combining Figure 8 ,like Figure 9 As shown, the method in S4 above can be specifically implemented through the following steps S41 to S44, which are explained in detail below:

[0146] S41. Determine the deformation screening factor for suspected deformation areas based on the offset and signal reflection intensity of the sample point cloud data.

[0147] In some implementations, the spatial offset (Euclidean distance) of all sample points within the suspected deformation area relative to the standard point cloud is calculated, and the average value is taken to reflect the intensity of physical deformation in the area.

[0148] Extract the laser reflection intensity (a built-in parameter of the scanner, reflecting the light reflection characteristics of the surface material) from all points within the suspected area, and calculate the average reflection intensity of the area. Simultaneously, obtain the average reflection intensity of the standard area (a normal, undisturbed box area). Calculate the reflection intensity difference rate.

[0149] The design incorporates a fusion formula that combines offset and reflection intensity difference rate to obtain the deformation screening factor.

[0150] S42, correct the first distribution coefficient based on the deformation screening factor to obtain a second distribution coefficient.

[0151] The deformation screening factor corresponding to the interference deformation region is significantly larger than that of the pure deformation region, so the distribution coefficient of all abnormal regions that do not meet the condition can be corrected based on the screening factor, so that the size of the distribution coefficient can more accurately reflect the deformation characteristics of the abnormal region, thereby improving the accuracy of the deformation region screening.

[0152] In some implementations, the calculation formula of the second distribution coefficient is as follows:

[0153]

[0154] In the formula, is the first distribution coefficient of the suspected deformation region .

[0155] is the deformation screening factor of the suspected deformation region , and the value range is [0, 1].

[0156] is the second distribution coefficient of the suspected deformation region . Since the deformation screening factor highlights the significant features of the mixed abnormal region, weighting the distribution coefficient with it can make the features of the mixed abnormal region more obvious (larger), while the pure dust or oil stain covered region has no obvious change. The larger the deformation screening factor (the higher the possibility of real deformation), the greater the correction amplitude of the first distribution coefficient, making more consistent with the real deformation characteristics.

[0157] According to the description in S5, when calculating the average distribution coefficient of the deformation region, the first distribution coefficient is used for the deformation region without interference, and the corrected second distribution coefficient is used for the deformation region with interference.

[0158] S43, if the second distribution coefficient is greater than a preset coefficient threshold, the suspected deformation region is identified as a deformation region with interference.

[0159] Further, the normalized can be subjected to the same threshold screening as the first distribution coefficient , so as to realize the quantitative differentiation of the two types of regions, the deformation region with interference and the non-deformation interference distortion region.

[0160] If the second distribution coefficient is greater than the preset coefficient threshold, it indicates that the region has real deformation, and the surface interference does not completely cover the deformation characteristics, so it is determined as a deformation region with interference.

[0161] ​S44. If the second distribution coefficient is less than or equal to the preset coefficient threshold, the suspected deformation area is marked as an interference distortion area without deformation.

[0162] If the second distribution coefficient is less than or equal to the preset coefficient threshold, it means that the point cloud anomaly in the region is entirely caused by surface interference (such as stains or reflections) and there is no real deformation. In this case, it is determined to be an interference distortion region without deformation.

[0163] Based on the above technical solution, a deformation screening factor is obtained through the fusion analysis of offset (reflecting deformation intensity) and reflection intensity (reflecting the degree of surface interference). This effectively distinguishes between two types of scenarios: those with surface interference but actual deformation (such as depressions covered by stains) and those with point cloud anomalies caused by pure interference (such as false offsets caused by reflections). This avoids misjudging real deformation as interference or pure interference as deformation. The first distribution coefficient may be underestimated due to surface interference (such as stains causing a deterioration in the continuity of point cloud features). After correction by the deformation screening factor, the second distribution coefficient more closely matches the true deformation attributes of the region, making the judgment results more reliable and significantly reducing the misjudgment rate in interference scenarios.

[0164] In one possible implementation, combining Figure 9 ,like Figure 10 As shown, the method in S41 described above can be specifically implemented through the following steps S411 to S413, which are explained in detail below:

[0165] S411. Determine the signal reflection coefficient of each suspected deformation region based on the average signal reflection intensity of the sample point cloud data in each suspected deformation region.

[0166] The deformation region itself may cause changes in the laser scanning angle, which may lead to attenuation of the reflected signal, thus reducing the reflection intensity of the region. In the case of a mixture of deformation and distortion, the two may work together, resulting in a severe weakening of the reflected signal. At the same time, the superposition of distortions will lead to more severe thickness shifts, resulting in a larger fitting residual (offset) when fitting the point cloud of the corresponding region.

[0167] In some implementations, the signal reflection coefficient The calculation formula is as follows:

[0168]

[0169] In the formula, This refers to the average reflection intensity of all data points within the anomalous region.

[0170] Actual deformation (such as bulges or depressions) will change the laser scanning angle, causing attenuation of the reflected signal. reduce, The larger the value, the more likely it is to be a mixed anomaly region.

[0171] S412, determine the offset degree coefficient of each suspected deformation region according to the average offset degree of the sample point cloud data in the plurality of suspected deformation regions.

[0172] In some implementations, the offset degree coefficient The calculation formula is as follows:

[0173]

[0174] In the formula, is the average data point offset degree of all data points in the suspected deformation region.

[0175] is the smallest average data point offset degree in all suspected deformation regions.

[0176] The significance of the region offset is quantified by the ratio of the region offset degree to the minimum offset degree. The larger the ratio, the greater the degree of data point offset of the corresponding abnormal region. Since the offset degree of the real deformation is usually significantly greater than the false offset caused by the interference (such as the random offset of the noise point), it is more likely to be a mixed abnormal region.

[0177] S413, determine the deformation screening factor according to the signal reflection coefficient and the offset degree coefficient.

[0178] In some implementations, the calculation formula of the deformation screening factor is as follows:

[0179]

[0180] In the formula, is the deformation screening factor of a certain abnormal region, which combines the two core features of reflection attenuation degree and offset significance.

[0181] The mixed abnormal region (both deformation and interference) will exhibit reflection intensity attenuation and offset degree significance at the same time, so the value is significantly larger. The pure interference region (without real deformation) is only abnormal in reflection intensity or small in offset degree, the value is significantly smaller. Through threshold screening of , the quantitative differentiation of mixed abnormal regions and pure interference regions can be realized.

[0182] Based on the above technical solution, the essential difference between the real deformation region with interference and the pure interference region is accurately described through the multi-dimensional fusion of reflection intensity attenuation and offset degree significance, which provides a quantitative basis for the secondary screening of abnormal regions (distinguishing between deformation with interference and pure interference), effectively solves the misjudgment problem caused by the superposition of deformation and interference in laser scanning, and improves the accuracy and reliability of the box deformation detection.

[0183] In a possible implementation, the method can further include the following S6, which is described below in detail: Figure 1 As shown in Figure 11 The method can further include the following S6, which is described below in detail:

[0184] S6, visualizing sample point cloud data of the to-be-detected box body and identifying a deformation region.

[0185] In some implementations, a professional point cloud visualization software (such as CloudCompare or ParaView) or a self-developed three-dimensional visualization module is used, which needs to support point cloud rendering, region labeling, interactive operation, and multi-data layer superposition.

[0186] Different region types are distinguished by color coding, for example:

[0187] The non-interference deformation region is rendered in red, and the point cloud density is set to high to highlight the spatial continuity;

[0188] The interference deformation region is rendered in orange, with a 50% transparency superimposed, to indicate that there is surface interference;

[0189] The interference distortion region is rendered in gray, and the point cloud density is reduced to visually distinguish it from the effective deformation region.

[0190] Further, interactive function design can also be supported, including:

[0191] Multi-view control: supports free rotation, zooming, and panning, and can switch between preset perspectives of top view, side view, and overhead view at one click, for comprehensive observation of the deformation region;

[0192] Information query: clicking any point or region pops up an attribute panel to display key parameters such as average offset, reflection intensity, and distribution coefficient of the region;

[0193] Multi-data layer comparison: supports superimposed display of sample point cloud and standard point cloud (standard point cloud is set to semi-transparent blue), to intuitively compare the differences between the deformation region and the normal region.

[0194] Based on the above technical solutions, complex point cloud data and deformation regions are converted into intuitive three-dimensional graphics, so that technical personnel can quickly understand the deformation position, range, and degree without analyzing numerical values, reducing the technical threshold. At the same time, it is convenient for subsequent physical inspection, maintenance, or cause tracing, and improves the problem handling efficiency.

[0195] In a possible implementation, the method can further include the following S5, which is described below in detail: Figure 1 As shown in Figure 12 The method of taking corresponding maintenance measures in S5 can be implemented through the following S51 to S52, which is described below in detail:

[0196] S51, when the deformation degree is severe deformation, a treatment strategy is determined according to the functional attribute of the deformation region.

[0197] In some implementations, the photovoltaic inverter box is divided into functional regions in advance, and the criticality and failure influence of each region are determined, including:

[0198] Electrical component mounting area: contains inverter core module, wiring terminal, etc., deformation is easy to cause electrical connection loose, insulation failure;

[0199] Heat dissipation functional area: contains heat dissipation fins, ventilation openings, etc., deformation is easy to block the heat dissipation channel and cause equipment overheating;

[0200] Structural support area: contains box frame, fixing hole, etc., deformation is easy to damage the stability of the overall structure, leading to box collapse or component shedding.

[0201] The regional treatment strategy includes:

[0202] Severe deformation of the electrical component mounting area, immediately remove the electrical components in this area, replace the same specification box module; simultaneously detect the insulation and conductivity of the components, and if the components are damaged, replace them together.

[0203] Severe deformation of the heat dissipation functional area, after cleaning the heat dissipation channel, repair the heat dissipation structure using sheet metal technology; test the heat dissipation efficiency after repair, if it is less than 80% of the design value, replace the heat dissipation module.

[0204] Severe deformation of the structural support area, if the structural safety factor is less than 0.8, directly replace the box; if the safety factor is between 0.8 and 1.0, retest the structural strength after reinforcing with carbon fiber, and continue to use after meeting the standard.

[0205] S52, send an alarm message to the maintenance terminal.

[0206] The alarm message includes: deformation region, deformation degree and treatment strategy.

[0207] In some implementations, mobile and PC terminal management systems can be supported for dual-end collaboration. At the same time, permission levels are classified, for example: technical expert end can view full data and strategy configuration interface, front-line maintenance personnel end only shows execution level operation process and real-time alarm.

[0208] Based on the above technical solution, through functional attribute differentiation decision and real-time alarm reaching, special treatment strategies are developed for severe deformation of different functional areas of the box (electrical area, heat dissipation area, structural area), which not only prevents short circuit, leakage and other risks caused by delayed processing in key functional areas (such as electrical component area), but also avoids over maintenance of non-critical areas, improves resource utilization and maintenance effectiveness, and realizes precise maintenance and efficient response in severe deformation scenarios.

[0209] It is to be noted that the above-mentioned sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0210] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each of the embodiments focuses on the difference from other embodiments.

[0211] The embodiments of the present application can divide the functional units of the deformation detection device of the integrally formed photovoltaic inverter box according to the above-mentioned method examples. For example, each functional unit can be divided according to each function, or two or more functions can be integrated in one processing unit. The above-mentioned integrated unit can be realized in the form of hardware or in the form of software functional unit. It should be noted that the division of the unit in the embodiments of the present application is illustrative, and is only a logical function division. In actual implementation, there can be another division manner.

[0212] The embodiments of the present application also provide a hardware structure diagram of the deformation detection device of the integrally formed photovoltaic inverter box, referring to Figure 13 The deformation detection device 1300 of the integrally formed photovoltaic inverter box includes a processor 1301, and optionally, further includes a memory 1302 connected with the processor 1301.

[0213] In the first possible implementation manner, referring to Figure 13 The deformation detection device 1300 of the integrally formed photovoltaic inverter box further includes a transceiver 1303. The processor 1301, the memory 1302 and the transceiver 1303 are connected through a bus. The transceiver 1303 is used for communicating with other devices or communication networks. Optionally, the transceiver 1303 can include a transmitter and a receiver. The device for realizing the receiving function in the transceiver 1303 can be regarded as a receiver, and the receiver is used for executing the receiving steps in the embodiments of the present application. The device for realizing the sending function in the transceiver 1303 can be regarded as a transmitter, and the transmitter is used for executing the sending steps in the embodiments of the present application.

[0214] Based on the first possible implementation manner, Figure 13 The structure diagram shown can be used to illustrate the structure of the deformation detection device of the integrally formed photovoltaic inverter box involved in the above-mentioned embodiments.

[0215] Among them, Figure 13The system chip in the deformation detection device of the integrated photovoltaic inverter box can also be shown. In this case, the actions performed by the deformation detection device of the integrated photovoltaic inverter box described above can be implemented by the system chip, and the specific actions performed can be referred to above and will not be described here again.

[0216] In the implementation process, the steps in the method provided by the embodiment can be completed by integrated logic circuits of hardware in the processor or instructions in the form of software. The steps of the method disclosed by the embodiment of the application can be directly embodied as hardware processor execution completion, or executed by a combination of hardware and software modules in the processor.

[0217] The processor in the application can include but is not limited to at least one of the following: a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a micro controller unit (MCU), or various types of computing devices running software, each of which can include one or more cores for executing software instructions to perform operations or processing. The processor can be a separate semiconductor chip, or can be integrated with other circuits to form a semiconductor chip, for example, it can form a SoC (system on chip) with other circuits (such as coding and decoding circuits, hardware acceleration circuits or various bus and interface circuits), or it can be integrated as an internal processor in an ASIC. The ASIC integrated with the processor can be packaged separately or packaged together with other circuits. In addition to including cores for executing software instructions to perform operations or processing, the processor can further include necessary hardware accelerators, such as field programmable gate arrays (FPGA), PLDs (programmable logic devices), or logic circuits for implementing special logic operations.

[0218] The memory in the embodiments of the present application can include at least one of the following types: read-only memory (ROM) or other types of static storage devices that can store static information and instructions, random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, and can also be electrically erasable programmable read-only memory (EEPROM). In some scenarios, the memory can also be a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and capable of being accessed by a computer, but not limited thereto.

[0219] The embodiments of the present application also provide a computer readable storage medium including instructions, which, when executed on a computer, cause the computer to perform any of the above methods.

[0220] The embodiments of the present application also provide a computer program product including instructions, which, when executed on a computer, cause the computer to perform any of the above methods.

[0221] The embodiments of the present application also provide a chip, which includes a processor and an interface circuit, the interface circuit is coupled with the processor, the processor is used to run a computer program or instructions to implement the above method, and the interface circuit is used to communicate with other modules outside the chip.

[0222] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present application are generated. The computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transferred from one website, computer, server or data center to another website, computer, server or data center through wired (such as coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode. The computer readable storage medium can be any available medium that can be accessed by a computer or data storage device including one or more servers, data centers, etc. integrated with the medium. The available medium can be magnetic medium (such as floppy disk, hard disk, magnetic tape), optical medium (such as DVD), or semiconductor medium (such as solid state disk (solid state disk, SSD)) and the like.

[0223] Although the present application is described herein in conjunction with various embodiments, it is understood that other variations of the disclosed embodiments can be understood and effected by those skilled in the art in practicing the claimed application, from an inspection of the drawings, the disclosure, and the appended claims. In the present application, the word "comprising" does not exclude other components or steps, and the indefinite article "a" or "an" does not exclude a plurality. A single processor or other unit can implement several of the functions recited in the present application.

[0224] Although the present application is described herein in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations can be made thereto, without departing from the spirit and scope of the application. Accordingly, the description and drawings are to be regarded simply as illustrative of the present application and are to be construed in accordance with the scope of the present application as encompassing any and all modifications, variations, combinations or equivalents that fall within the scope of the present application. Obviously, various modifications and changes can be made to the present application by those skilled in the art without departing from the spirit and scope of the present application. Thus, it is intended that the present application cover modifications and variations of this application provided they come within the scope of the appended claims and their equivalents.

Claims

1. A method for detecting the deformation of an integrally molded photovoltaic inverter housing, characterized in that, The method comprises the following steps: scanning the outer surface of the box to obtain sample point cloud data of the box to be detected and standard point cloud data of a new box; determining an abnormal area on the box to be detected according to the offset degree of the sample point cloud data relative to the standard point cloud data; identifying a deformation area without interference and a suspected deformation area with interference in the abnormal area according to the data distribution of the sample point cloud data in the abnormal area; correcting the data distribution according to the offset degree and signal reflection intensity of the sample point cloud data in the suspected deformation area, identifying a deformation area with interference and a distortion area without deformation in the suspected deformation area; determining the deformation degree of the box to be detected according to the proportion of the deformation area in the scanning area and the data distribution of the deformation area, and taking corresponding maintenance measures; the method comprises the following steps: comparing the sample point cloud data and the standard point cloud data to obtain an abnormal data point set of the offset standard position; clustering the data points in the abnormal data point set based on the offset degree of each data point in the abnormal data point set to obtain a plurality of data point clusters; determining the abnormal area in the box area corresponding to the abnormal data point set according to the offset degree and the number of data points in each data point cluster; the method comprises the following steps: analyzing the data distribution of the sample point cloud data in the abnormal area to obtain a first distribution coefficient; if the first distribution coefficient is greater than a preset coefficient threshold, identifying the abnormal area as a deformation area without interference; if the first distribution coefficient is less than or equal to the preset coefficient threshold, identifying the abnormal area as a suspected deformation area with interference.

2. The method of claim 1, wherein the method further comprises: the method comprises the following steps: determining the offset degree of the data points in the sample point cloud data offset from the standard position according to the Euclidean distance between the data points in the sample point cloud data and the data points in the standard point cloud data, and the distance between the data points in the sample point cloud data and the point cloud plane; determining the data points in the sample point cloud data with an offset degree greater than a preset offset degree threshold as abnormal data points.

3. The method of claim 1, wherein the method further comprises: the method comprises the following steps: determining the detection confidence of each data point cluster according to the offset degree and the number of data points in each data point cluster; identifying the box area corresponding to the data point cluster with a detection confidence greater than a preset confidence threshold as an abnormal area.

4. The method of claim 1, wherein the method further comprises: the method comprises the following steps: Comparing the sample point cloud density of the plurality of data points in the abnormal area with the standard point cloud density of the plurality of data points in the corresponding area of the new box, a point cloud density difference coefficient of the abnormal area is determined; Comparing and analyzing the offset direction of the plurality of data points in the abnormal area, a data point continuity coefficient of the abnormal area is determined; According to the point cloud density difference coefficient and the data point continuity coefficient, the first distribution coefficient is determined.

5. The method of claim 4, wherein the method further comprises: The method for correcting the data distribution according to the offset degree and the signal reflection intensity of the sample point cloud data in the suspected deformation area, identifying the deformation area with interference and the interference distortion area without deformation in the suspected deformation area, comprises: According to the offset degree and the signal reflection intensity of the sample point cloud data, a deformation screening factor of the suspected deformation area is determined; Based on the deformation screening factor, the first distribution coefficient is corrected to obtain a second distribution coefficient; If the second distribution coefficient is greater than the preset coefficient threshold, the suspected deformation area is identified as the deformation area with interference; If the second distribution coefficient is less than or equal to the preset coefficient threshold, the suspected deformation area is identified as the interference distortion area without deformation.

6. The method of claim 5, wherein the method further comprises: The method for determining the deformation screening factor of the suspected deformation area according to the offset degree and the signal reflection intensity of the sample point cloud data, comprises: According to the average signal reflection intensity of the sample point cloud data in each suspected deformation area, a signal reflection coefficient of each suspected deformation area is determined; According to the average offset degree of the sample point cloud data in a plurality of suspected deformation areas, an offset degree coefficient of each suspected deformation area is determined; According to the signal reflection coefficient and the offset degree coefficient, the deformation screening factor is determined.

7. The method of claim 1, wherein the method further comprises: Further comprising: Visualizing and displaying the sample point cloud data of the box to be detected, and identifying the deformation area.

8. The method of claim 1, wherein the method further comprises: The method for taking corresponding maintenance measures, comprises: When the deformation degree is severe deformation, a processing strategy is determined according to the functional attribute of the deformation area; An alarm message is sent to a maintenance terminal, and the alarm message comprises the deformation area, the deformation degree and the processing strategy.

Images