Detection method and system at the edge of battery housing

Abstract

The present invention discloses a detection method and system for the edge of a battery shell. During the detection process of the battery shell, the battery shell is scanned in a circular direction, and a point cloud corresponding to the edge of the battery shell is collected; the edge feature is constructed based on the point cloud at the edge of the battery shell, and the abnormal area of ​​the edge feature is marked, so that the fixed-point detection is triggered based on the position of the abnormal area, and the targeted detection of the abnormal area of ​​the edge feature is realized, so that the abnormal area is used to perform abnormal evaluation, and repeated detection of the edge feature is avoided. At the same time, the deformation level is determined according to the deformation amount of the abnormal feature, and the risk parameter of the edge is determined based on multiple deformation levels and corresponding positions, so that the qualified level of the edge of the battery shell is determined by the risk parameter of the edge, and the qualified evaluation of the edge of the battery shell is determined, so as to realize the refined and precise measurement of the edge of the battery shell.

Description

Technical Field

[0001] The present invention relates to the technical field of detecting the edge of a battery shell, and in particular to a method and a system for detecting the edge of a battery shell. Background Art

[0002] With the development of science and technology, the battery shell, as a part of the battery equipment, needs to be inspected before assembly. In the prior art, the image of the battery shell is collected and the image of the battery shell is inspected as a whole. However, the defects of the battery shell are mainly concentrated at the edge of the battery shell, and the overall inspection of the image of the battery shell takes a lot of time. The prior art cannot perform fine and precise measurement on the edge of the battery shell. Summary of the invention

[0003] The purpose of the present invention is to overcome the shortcomings of the prior art. The present invention provides a detection method and system for the edge of a battery shell, introduces edge features, and marks abnormal areas of the edge features, thereby triggering fixed-point detection based on the location of the abnormal area, and realizing targeted detection of abnormal areas of the edge features, thereby using the abnormal area to perform abnormal assessment and avoiding repeated detection of the edge features. At the same time, the deformation level is determined according to the deformation amount of the abnormal feature, and the risk parameters at the edge are determined based on multiple deformation levels and corresponding positions, so as to determine the qualified level of the edge of the battery shell through the risk parameters at the edge, thereby realizing the qualified assessment of the edge of the battery shell, so as to realize the refined and precise measurement of the edge of the battery shell.

[0004] In order to solve the above technical problems, an embodiment of the present invention provides a detection method at the edge of a battery housing, which is applied to the detection scenario at the edge of a battery housing; the detection method at the edge of a battery housing includes:

[0005] During the detection of the battery shell, the battery shell is scanned circumferentially, and a point cloud corresponding to the edge of the battery shell is collected;

[0006] Construct edge features based on the point cloud at the edge of the battery shell;

[0007] Traverse the edge features and mark the abnormal areas in the edge features;

[0008] Trigger fixed-point detection based on the location of the abnormal area and determine the abnormal characteristics;

[0009] Collecting the deformation amount of the abnormal feature, and determining the deformation level according to the deformation amount of the abnormal feature;

[0010] In each battery case, a risk parameter at the edge is determined based on a plurality of deformation levels and corresponding positions, and a qualified level at the edge of the battery case is determined according to the risk parameter at the edge.

[0011] Optionally, during the detection process of the battery shell, the battery shell is circumferentially scanned, and a point cloud corresponding to the edge of the battery shell is collected, including:

[0012] Acquire a battery shell, and trigger shell detection based on the battery shell;

[0013] During the inspection of the battery housing, locating the edge of the battery housing;

[0014] Determine a scanning direction based on an edge of the battery housing and an orientation of the battery housing;

[0015] Performing a circular scan on the edge of the battery shell along the scanning direction, at this time, adjusting the width of the circular scan according to the width of the edge of the battery shell;

[0016] In the circumferential scanning at the edge of the battery housing, a point cloud corresponding to the edge of the battery housing is collected.

[0017] Optionally, constructing edge features based on the point cloud at the edge of the battery housing includes:

[0018] Freeze the point cloud at the edge of the battery housing;

[0019] Locate the dense point cloud at the edge of the battery housing, and collect multiple dense points;

[0020] Perform point cloud inspection based on multiple dense locations and collect the number of point clouds at each dense location;

[0021] The point cloud difference is constructed based on the number of point clouds in each dense location, and the point cloud optimization in the dense location is triggered according to the point cloud difference to balance the number of point clouds in each dense location. At this time, the optimization level is triggered based on the point cloud difference;

[0022] When the number of point clouds at each dense location is in a balanced state, the first feature is constructed according to the point clouds at each dense location, and the framework direction of the first feature is defined;

[0023] Constructing a second feature along the point cloud at the non-dense location, and optimizing the second feature based on the frame direction of the first feature;

[0024] The plurality of second features and the plurality of first features are connected to construct features at the edge, and at this time, the frame direction of the first feature overlaps with the frame direction of the second feature.

[0025] Optionally, traversing the edge features and marking abnormal areas in the edge features include:

[0026] Identify the features at the edge and define the edge type based on the identification of the features at the edge;

[0027] The traversal method is defined according to the edge type and the area of ​​the feature at the edge. The traversal methods include circular traversal, regional traversal, and hierarchical traversal.

[0028] During the traversal of the edge features, the runout difference of the edge features at various positions is collected;

[0029] Define the runout difference variation based on two adjacent positions;

[0030] Comparing the jitter difference variation with a preset jitter difference variation threshold;

[0031] If the jitter difference variation is greater than a preset jitter difference variation threshold, an abnormal region in the edge feature is defined, and the position of the abnormal region is marked.

[0032] Optionally, triggering fixed-point detection based on the location of the abnormal area and determining abnormal features include:

[0033] The location of the abnormal area is collected;

[0034] If there are multiple abnormal areas, multiple locations are collected, and the priorities among the multiple locations are defined according to the abnormal states of the multiple abnormal areas;

[0035] The detection sequence of multiple locations is triggered according to the priority among the multiple locations.

[0036] Optionally, triggering fixed-point detection based on the location of the abnormal area and determining abnormal features further includes:

[0037] In the process of fixed-point detection of the location where the abnormal area is located, the abnormal area is divided;

[0038] Based on the division of the abnormal area, a plurality of sub-abnormal areas are formed;

[0039] defining an abnormal pattern according to the identification of the sub-abnormal region, and collecting a plurality of abnormal patterns;

[0040] Anomaly signatures are constructed based on multiple anomaly graphs.

[0041] Optionally, collecting the deformation amount of the abnormal feature and determining the deformation level according to the deformation amount of the abnormal feature includes:

[0042] Freeze abnormal features;

[0043] Traverse the abnormal features and define the abnormal parts;

[0044] Calculate the area of ​​the abnormal part and determine the deformation amount according to the appearance of the abnormal feature;

[0045] Determine the deformation amount of abnormal features;

[0046] The deformation level is determined according to the deformation amount of the abnormal feature.

[0047] Optionally, in each battery housing, determining a risk parameter at the edge based on a plurality of deformation levels and corresponding positions, and determining a qualified level at the edge of the battery housing according to the risk parameter at the edge, comprises:

[0048] In each battery housing, mark each deformation level;

[0049] Construct the coordinate system of the battery shell and mark each deformation level;

[0050] Collect the location of the deformation level and associate the deformation level with the corresponding location;

[0051] Position levels are determined according to the positions and features at the edges, and position parameters are determined based on the position levels.

[0052] Optionally, in each battery housing, determining the risk parameter at the edge based on a plurality of deformation levels and corresponding positions, and determining the qualified level at the edge of the battery housing according to the risk parameter at the edge, further includes:

[0053] determining a risk parameter at the edge based on a plurality of deformation levels and position parameters;

[0054] The acceptance level at the edge of the battery housing is determined based on the risk parameter at the edge.

[0055] Optionally, a detection system at the edge of a battery shell is provided, wherein the detection system at the edge of the battery shell is applied to the above-mentioned detection method at the edge of the battery shell, and the detection system at the edge of the battery shell comprises:

[0056] The acquisition module is used to perform a circumferential scan on the battery shell and acquire a point cloud corresponding to the edge of the battery shell during the detection process of the battery shell;

[0057] An edge feature module, used to construct edge features based on a point cloud at the edge of a battery housing;

[0058] An abnormal region module, used to traverse the edge features and mark the abnormal regions in the edge features;

[0059] Anomaly feature module, used to trigger fixed-point detection based on the location of the abnormal area and determine the abnormal features;

[0060] A deformation level module is used to collect the deformation amount of the abnormal feature and determine the deformation level according to the deformation amount of the abnormal feature;

[0061] The qualified detection module is used to determine the risk parameters at the edge of each battery shell based on multiple deformation levels and corresponding positions, and determine the qualified level at the edge of the battery shell according to the risk parameters at the edge.

[0062] In an embodiment of the present invention, through the method in the embodiment of the present invention, during the detection process of the battery shell, the battery shell is scanned in a circular direction, and the point cloud at the edge of the corresponding battery shell is collected; the edge feature is constructed based on the point cloud at the edge of the battery shell; the edge feature is traversed, and the abnormal area in the edge feature is marked; the fixed-point detection is triggered based on the position of the abnormal area, and the abnormal feature is determined; the deformation amount of the abnormal feature is collected, and the deformation level is determined according to the deformation amount of the abnormal feature; in each battery shell, the risk parameter at the edge is determined based on multiple deformation levels and corresponding positions, and the edge of the battery shell is determined according to the risk parameter at the edge At this time, the edge feature is introduced, and the abnormal area of ​​the edge feature is marked, so that the fixed-point detection is triggered based on the position of the abnormal area, and the targeted detection of the abnormal area of ​​the edge feature is realized, so that the abnormal area is used for abnormal evaluation, and repeated detection of the edge feature is avoided. At the same time, the deformation level is determined according to the deformation amount of the abnormal feature, and the risk parameters at the edge are determined based on multiple deformation levels and corresponding positions, so as to determine the qualified level of the edge of the battery shell through the risk parameters at the edge, and the qualified evaluation of the edge of the battery shell is realized, so as to realize the refined and precise measurement of the edge of the battery shell. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0064] Figure 1 is a schematic flow chart of a method for detecting the edge of a battery housing in an embodiment of the present invention;

[0065] Figure 2 is a schematic flow chart of S11 in the method for detecting the edge of the battery housing in the embodiment of the present invention;

[0066] Figure 3is a schematic flow chart of S12 in the method for detecting the edge of the battery housing in the embodiment of the present invention;

[0067] Figure 4 is a flow chart of S13 in the method for detecting the edge of the battery housing in the embodiment of the present invention;

[0068] Figure 5 is a flow chart of S14 in the method for detecting the edge of the battery housing in the embodiment of the present invention;

[0069] Figure 6 is a flow chart of S15 in the method for detecting the edge of the battery housing in the embodiment of the present invention;

[0070] Figure 7 is a schematic flow chart of S16 in the method for detecting the edge of the battery housing in the embodiment of the present invention;

[0071] Figure 8 Schematic diagram of the structure of the detection system at the edge of the battery housing in an embodiment of the present invention;

[0072] Fig. 9 The figure is a hardware diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0073] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0074] Example

[0075] See also Figures 1 to 9 A method for detecting the edge of a battery shell is applied to the detection scenario of the edge of the battery shell; the method for detecting the edge of the battery shell comprises:

[0076] Step S11: during the detection process of the battery shell, the battery shell is circumferentially scanned, and a point cloud corresponding to the edge of the battery shell is collected;

[0077] Step S12: constructing edge features based on the point cloud at the edge of the battery housing;

[0078] Step S13: traverse the edge features and mark abnormal areas in the edge features;

[0079] Step S14: triggering fixed-point detection based on the location of the abnormal area and determining abnormal features;

[0080] Step S15: collecting the deformation amount of the abnormal feature, and determining the deformation level according to the deformation amount of the abnormal feature;

[0081] Step S16: in each battery housing, determine risk parameters at the edge based on a plurality of deformation levels and corresponding positions, and determine a qualified level at the edge of the battery housing according to the risk parameters at the edge.

[0082] In an embodiment of the present invention, through the method in the embodiment of the present invention, features at the edge are introduced, and abnormal areas of the features at the edge are marked, so that fixed-point detection is triggered based on the location of the abnormal area, and targeted detection of abnormal areas of the features at the edge is achieved, so that abnormal areas are used for abnormal assessment, avoiding repeated detection of the features at the edge. At the same time, the deformation level is determined according to the deformation amount of the abnormal feature, and the risk parameters at the edge are determined based on multiple deformation levels and corresponding positions, so that the qualified level of the edge of the battery shell can be determined through the risk parameters at the edge, and the qualified assessment of the edge of the battery shell can be determined, so as to achieve refined and precise measurement of the edge of the battery shell.

[0083] In step S11, during the detection process of the battery shell, the battery shell is circumferentially scanned, and a point cloud corresponding to the edge of the battery shell is collected;

[0084] In the specific implementation process of the present invention, the specific steps may be:

[0085] S111: Acquire a battery shell, and trigger shell detection based on the battery shell;

[0086] S112: During the detection of the battery housing, locating the edge of the battery housing;

[0087] S113: determining a scanning direction based on an edge of the battery housing and a direction of the battery housing;

[0088] S114: performing a circular scan on the edge of the battery shell along the scanning direction, and at this time, adjusting the width of the circular scan according to the width of the edge of the battery shell;

[0089] S115: In the circumferential scanning at the edge of the battery housing, a point cloud corresponding to the edge of the battery housing is collected.

[0090] In an embodiment of the present application, a battery shell is obtained, and shell detection is triggered based on the battery shell. At this time, targeted detection is performed on the edge of the battery shell instead of performing an overall detection on the battery shell to ensure detection efficiency. At this time, during the detection process of the battery shell, the edge of the battery shell is located, and the scanning direction is determined based on the edge of the battery shell and the orientation of the battery shell to facilitate directional scanning according to the scanning direction.

[0091] At this time, the edge of the battery shell is scanned in a circular manner along the scanning direction. At this time, the width of the circular scan is adjusted according to the width of the edge of the battery shell, so that the adjustment of the width of the circular scan is triggered according to the width of the edge, thereby achieving compatibility with the edges of battery shells of different models. At the same time, in the circular scan at the edge of the battery shell, the point cloud at the edge of the battery shell is collected, so as to facilitate subsequent forming based on the point cloud at the edge of the battery shell, further facilitating the construction of features at the edge.

[0092] In step S12, edge features are constructed based on the point cloud at the edge of the battery housing;

[0093] In the specific implementation process of the present invention, the specific steps may be:

[0094] S121: freeze the point cloud at the edge of the battery housing;

[0095] S122: locating a dense point cloud at the edge of the battery housing, and collecting multiple dense points;

[0096] S123: performing point cloud inspection based on multiple dense locations, and collecting the number of point clouds at each dense location;

[0097] S124: constructing a point cloud difference amount based on the number of point clouds at each dense location, and triggering point cloud optimization at the dense location according to the point cloud difference amount to balance the number of point clouds at each dense location. At this time, triggering an optimization level based on the point cloud difference amount;

[0098] S125: When the number of point clouds at each dense location is in a balanced state, a first feature is constructed according to the point clouds at each dense location, and a framework direction of the first feature is defined;

[0099] S126: constructing a second feature along the point cloud at the non-dense location, and optimizing the second feature based on the frame direction of the first feature;

[0100] S127: Connect the plurality of second features and the plurality of first features to construct edge features. At this time, the frame direction of the first feature overlaps with the frame direction of the second feature.

[0101] In an embodiment of the present application, the point cloud at the edge of the battery shell is frozen, and the dense position of the point cloud at the edge of the battery shell is determined, so as to collect multiple dense places, so as to facilitate point cloud investigation based on multiple dense places, and collect the number of point clouds at each dense place, so as to further regulate the number of point clouds at each dense place.

[0102] At this time, the point cloud difference is constructed based on the number of point clouds in each dense location, so as to introduce the point cloud difference, thereby triggering the point cloud optimization in the dense location according to the point cloud difference to balance the number of point clouds in each dense location. At this time, the optimization level is triggered based on the point cloud difference, so as to optimize the point cloud to different degrees based on different optimization levels, thereby ensuring the balance of the number of point clouds in each dense location.

[0103] Furthermore, when the number of point clouds at each dense location is in a balanced state, a first feature is constructed according to the point clouds at each dense location, and a frame direction of the first feature is defined; a second feature is constructed along the point cloud at a non-dense location, and the second feature is optimized based on the frame direction of the first feature; the second feature is associated with the first feature so as to sort the second feature and the first feature in sequence along the scanning direction, thereby connecting multiple second features and multiple first features to construct features at the edge. At this time, there is an overlap between the frame direction of the first feature and the frame direction of the second feature, thereby improving the accuracy of the features at the edge.

[0104] In step S13, the edge features are traversed and abnormal areas in the edge features are marked;

[0105] In the specific implementation process of the present invention, the specific steps may be:

[0106] S131: freeze the features at the edge, and define the edge type based on the recognition of the features at the edge;

[0107] S132: defining a traversal method according to the edge type and the area of ​​the feature at the edge, wherein the traversal method includes a circular traversal, a region-based traversal, or a hierarchical traversal;

[0108] S133: during the traversal of the edge feature, collecting the runout difference of the edge feature at each position;

[0109] S134: defining a jitter difference variation based on two adjacent positions;

[0110] S135: comparing the jitter difference variation with a preset jitter difference variation threshold;

[0111] S136: If the jitter difference variation is greater than a preset jitter difference variation threshold, an abnormal region in the edge feature is defined, and a position mark is performed on the position of the abnormal region.

[0112] In an embodiment of the present application, the features at the edge are frozen, and the edge type is defined based on the identification of the features at the edge, so as to determine the edge type of the features at the edge, and then define the traversal method according to the edge type and the area of ​​the features at the edge. The traversal method includes circular traversal, regional traversal, and hierarchical traversal, so as to use the corresponding traversal method to trigger the traversal of the features at the edge, and then perform refined detection on the features at the edge.

[0113] At this time, in the process of traversing the edge feature, the jitter difference of the edge feature at each position is collected; the jitter difference change is defined based on two adjacent positions to introduce the jitter difference change, thereby comparing the jitter difference change with the preset jitter difference change threshold; if the jitter difference change is greater than the preset jitter difference change threshold, the abnormal area in the edge feature is defined, and the position of the abnormal area is marked to ensure subsequent control of the abnormal area.

[0114] S14: triggering fixed-point detection based on the location of the abnormal area and determining abnormal features;

[0115] In the specific implementation process of the present invention, the specific steps may be:

[0116] S141: collecting the location of the abnormal area;

[0117] S142: if there are multiple abnormal areas, collect multiple positions, and define priorities among the multiple positions according to the abnormal states of the multiple abnormal areas;

[0118] S143: triggering a detection sequence of the multiple locations according to the priorities among the multiple locations;

[0119] S144: In the process of fixed-point detection of the location where the abnormal area is located, the abnormal area is divided;

[0120] S145: forming a plurality of sub-abnormal regions based on the division of the abnormal region;

[0121] S146: defining an abnormal graph according to the identification of the sub-abnormal region, and collecting a plurality of abnormal graphs;

[0122] S147: Construct an abnormal feature according to the plurality of abnormal graphics.

[0123] In an embodiment of the present application, the location of the abnormal area is collected and the number of abnormal areas is counted. If there are multiple abnormal areas, multiple locations are collected, and the priorities between the multiple locations are defined according to the abnormal states of the multiple abnormal areas, so as to sort the priorities of the multiple locations, thereby triggering the detection order of the multiple locations according to the priorities between the multiple locations, thereby realizing orderly detection of the multiple locations in the detection order, so as to trigger the fixed-point detection of the location where the abnormal area is located.

[0124] In the process of fixed-point detection of the location of the abnormal area, the abnormal area is divided; multiple sub-abnormal areas are formed based on the division of the abnormal area; abnormal graphics are defined according to the identification of the sub-abnormal areas, and multiple abnormal graphics are collected; abnormal features are constructed according to the multiple abnormal graphics, thereby ensuring the accuracy of the abnormal features.

[0125] S15: collecting the deformation amount of the abnormal feature, and determining the deformation level according to the deformation amount of the abnormal feature;

[0126] In the specific implementation process of the present invention, the specific steps may be:

[0127] S151: freeze abnormal features;

[0128] S152: traverse the abnormal features and define the abnormal part;

[0129] S153: Calculate the area of ​​the abnormal part and determine the deformation amount according to the appearance of the abnormal feature;

[0130] S154: Deformation of the freeze-frame abnormal feature;

[0131] S155: Determine the deformation level according to the deformation amount of the abnormal feature.

[0132] In an embodiment of the present application, the abnormal features are frozen and controlled. At this time, the abnormal features are traversed and the abnormal parts are defined to facilitate area measurement of the abnormal parts, thereby defining the area of ​​the abnormal parts.

[0133] At this time, the area of ​​the abnormal part is measured, and the deformation amount is determined according to the appearance of the abnormal feature; the deformation amount of the abnormal feature is fixed; and the deformation level is determined according to the deformation amount of the abnormal feature, so that the deformation degree can be presented using the deformation level.

[0134] S16: In each battery housing, determining a risk parameter at the edge based on a plurality of deformation levels and corresponding positions, and determining a qualified level at the edge of the battery housing according to the risk parameter at the edge;

[0135] In the specific implementation process of the present invention, the specific steps may be:

[0136] S161: Mark each deformation level in each battery housing;

[0137] S162: constructing a coordinate system of the battery housing and marking each deformation level;

[0138] S163: collecting the position of the deformation level, and associating the deformation level and the corresponding position;

[0139] S164: Locate the position level according to the position and the edge feature, and determine the position parameter based on the position level;

[0140] S165: determining a risk parameter at the edge based on a plurality of deformation levels and position parameters;

[0141] S166: Determine the qualified level at the edge of the battery housing according to the risk parameters at the edge.

[0142] In an embodiment of the present application, risk parameters at the edge are determined based on multiple deformation levels and corresponding positions, so that the qualified level at the edge of the battery shell can be determined through the risk parameters at the edge, thereby achieving a qualified assessment of the edge of the battery shell, so as to achieve refined and precise measurement of the edge of the battery shell.

[0143] At this time, the location of the deformation level is collected, and the deformation level and the corresponding position are associated; the position level is located according to the position and the features at the edge, and the position parameters are determined based on the position level; the risk parameters at the edge are determined based on multiple deformation levels and position parameters, so as to determine the qualified level at the edge of the battery shell according to the risk parameters at the edge, and then targeted detection is carried out on the edge of the battery shell, avoiding comprehensive detection of the battery shell, thereby improving the detection efficiency of the battery shell.

[0144] In an embodiment of the present invention, through the method in the embodiment of the present invention, during the detection process of the battery shell, the battery shell is scanned in a circular direction, and the point cloud at the edge of the corresponding battery shell is collected; the edge feature is constructed based on the point cloud at the edge of the battery shell; the edge feature is traversed, and the abnormal area in the edge feature is marked; the fixed-point detection is triggered based on the position of the abnormal area, and the abnormal feature is determined; the deformation amount of the abnormal feature is collected, and the deformation level is determined according to the deformation amount of the abnormal feature; in each battery shell, the risk parameter at the edge is determined based on multiple deformation levels and corresponding positions, and the edge of the battery shell is determined according to the risk parameter at the edge At this time, the edge feature is introduced, and the abnormal area of ​​the edge feature is marked, so that the fixed-point detection is triggered based on the position of the abnormal area, and the targeted detection of the abnormal area of ​​the edge feature is realized, so that the abnormal area is used for abnormal evaluation, and repeated detection of the edge feature is avoided. At the same time, the deformation level is determined according to the deformation amount of the abnormal feature, and the risk parameters at the edge are determined based on multiple deformation levels and corresponding positions, so as to determine the qualified level of the edge of the battery shell through the risk parameters at the edge, and the qualified evaluation of the edge of the battery shell is realized, so as to realize the refined and precise measurement of the edge of the battery shell.

[0145] Example

[0146] See also Figure 8 , Figure 8 It is a schematic diagram of the structural composition of the detection system at the edge of the battery housing in an embodiment of the present invention.

[0147] like Figure 8 As shown, a detection system at the edge of a battery housing, the detection system at the edge of the battery housing comprises:

[0148] The acquisition module 21 is used to perform a circumferential scan on the battery shell and acquire a point cloud corresponding to the edge of the battery shell during the detection process of the battery shell;

[0149] An edge feature module 22, used for constructing edge features based on a point cloud at the edge of the battery housing;

[0150] An abnormal region module 23, used for traversing the edge features and marking abnormal regions in the edge features;

[0151] The abnormal feature module 24 is used to trigger the fixed-point detection based on the location of the abnormal area and determine the abnormal features;

[0152] The deformation level module 25 is used to collect the deformation amount of the abnormal feature and determine the deformation level according to the deformation amount of the abnormal feature;

[0153] The qualified detection module 26 is used to determine the risk parameters at the edge of each battery housing based on multiple deformation levels and corresponding positions, and determine the qualified level at the edge of the battery housing according to the risk parameters at the edge.

[0154] Example

[0155] See also Fig. 9 , refer to the following Fig. 9 The electronic device 40 according to this embodiment of the present invention will be described. Fig. 9 The electronic device 40 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0156] like Fig. 9 As shown, the electronic device 40 is in the form of a general computing device. The components of the electronic device 40 may include but are not limited to: at least one processing unit 41, at least one storage unit 42, and a bus 43 connecting different system components (including the storage unit 42 and the processing unit 41).

[0157] The storage unit stores program codes, which can be executed by the processing unit 41, so that the processing unit 41 executes the steps according to various exemplary embodiments of the present invention described in the above “Embodiment Method” section of this specification.

[0158] The storage unit 42 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit 421 and / or a cache storage unit 422 , and may further include a read-only storage unit (ROM) 423 .

[0159] The storage unit 42 may also include a program / utility 424 having a set (at least one) of program modules 425, such program modules 425 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0160] Bus 43 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0161] The electronic device 40 may also communicate with one or more external devices (e.g., keyboards, pointing devices, Bluetooth devices, etc.), one or more devices that enable a user to interact with the electronic device 40, and / or any device that enables the electronic device 40 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 44. Furthermore, the electronic device 40 may also communicate with one or more networks (e.g., local area networks, wide area networks, and / or public networks, such as the Internet) via a network adapter 45. Fig. 9 As shown, the network adapter 45 communicates with other modules of the electronic device 40 via the bus 43. It should be understood that although Fig. 9 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 40, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, tape drives, and data backup planning systems.

[0162] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0163] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: a read-only memory, a random access memory, a disk or an optical disk, etc. In addition, it stores computer program instructions, and when the computer program instructions are executed by a computer, the computer executes the above method.

[0164] In addition, the detection method and system for the edge of the battery shell provided by the embodiment of the present invention are introduced in detail above. Specific examples are used herein to illustrate the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for detecting the edge of a battery housing, characterized in that: Applicable to the detection scenario at the edge of the battery shell; the detection method at the edge of the battery shell includes: During the detection of the battery shell, the battery shell is scanned circumferentially, and a point cloud corresponding to the edge of the battery shell is collected; Construct edge features based on the point cloud at the edge of the battery shell; Traverse the edge features and mark the abnormal areas in the edge features; Trigger fixed-point detection based on the location of the abnormal area and determine the abnormal characteristics; Collecting the deformation amount of the abnormal feature, and determining the deformation level according to the deformation amount of the abnormal feature; In each battery housing, a risk parameter at an edge is determined based on a plurality of deformation levels and corresponding positions, and a qualified level at the edge of the battery housing is determined according to the risk parameter at the edge; The method of constructing edge features based on the point cloud at the edge of the battery shell includes: freezing the point cloud at the edge of the battery shell; locating the dense points of the point cloud at the edge of the battery shell, and collecting multiple dense points; checking the point cloud based on the multiple dense points, and collecting the number of point clouds at each dense point; constructing a point cloud difference based on the number of point clouds at each dense point, and triggering point cloud optimization at the dense points according to the point cloud difference to balance the number of point clouds at each dense point, at this time, triggering the optimization level based on the point cloud difference; when the number of point clouds at each dense point is in a balanced state, constructing a first feature according to the point clouds at each dense point, and defining the frame direction of the first feature; constructing a second feature along the point cloud at a non-dense point, and optimizing the second feature based on the frame direction of the first feature; connecting multiple second features and multiple first features to construct edge features, at this time, the frame direction of the first feature overlaps with the frame direction of the second feature.

2. The detection method at the edge of the battery housing according to claim 1, characterized in that: In the process of detecting the battery shell, the battery shell is circumferentially scanned, and a point cloud corresponding to the edge of the battery shell is collected, including: Acquire a battery shell, and trigger shell detection based on the battery shell; During the inspection of the battery housing, locating the edge of the battery housing; Determine a scanning direction based on an edge of the battery housing and an orientation of the battery housing; Performing a circular scan on the edge of the battery shell along the scanning direction, at this time, adjusting the width of the circular scan according to the width of the edge of the battery shell; In the circumferential scanning at the edge of the battery housing, a point cloud corresponding to the edge of the battery housing is collected.

3. The detection method at the edge of the battery housing according to claim 1, characterized in that: The traversing the edge features and marking abnormal areas in the edge features include: Identify the features at the edge and define the edge type based on the identification of the features at the edge; The traversal method is defined according to the edge type and the area of ​​the feature at the edge. The traversal methods include circular traversal, regional traversal, and hierarchical traversal. During the traversal of the edge features, the runout difference of the edge features at various positions is collected; Define the runout difference variation based on two adjacent positions; Comparing the jitter difference variation with a preset jitter difference variation threshold; If the jitter difference variation is greater than a preset jitter difference variation threshold, an abnormal region in the edge feature is defined, and the position of the abnormal region is marked.

4. The detection method at the edge of the battery housing according to claim 3, characterized in that: The triggering of fixed-point detection based on the location of the abnormal area and determining the abnormal features include: The location of the abnormal area is collected; If there are multiple abnormal areas, multiple locations are collected, and the priorities among the multiple locations are defined according to the abnormal states of the multiple abnormal areas; The detection sequence of multiple locations is triggered according to the priority among the multiple locations.

5. The method for detecting the edge of a battery housing according to claim 4, characterized in that: The method of triggering fixed-point detection based on the location of the abnormal area and determining abnormal features also includes: In the process of fixed-point detection of the location where the abnormal area is located, the abnormal area is divided; Based on the division of the abnormal area, a plurality of sub-abnormal areas are formed; defining an abnormal pattern according to the identification of the sub-abnormal region, and collecting a plurality of abnormal patterns; Anomaly features are constructed based on multiple anomaly graphs.

6. The method for detecting the edge of a battery housing according to claim 5, characterized in that: The step of collecting the deformation amount of the abnormal feature and determining the deformation level according to the deformation amount of the abnormal feature includes: Freeze abnormal features; Traverse the abnormal features and define the abnormal parts; Calculate the area of ​​the abnormal part and determine the deformation amount according to the appearance of the abnormal feature; Determine the deformation amount of abnormal features; The deformation level is determined according to the deformation amount of the abnormal feature.

7. The method for detecting the edge of a battery casing according to claim 6, characterized in that: The step of determining risk parameters at the edge of each battery housing based on a plurality of deformation levels and corresponding positions, and determining a qualified level at the edge of the battery housing according to the risk parameters at the edge, comprises: In each battery housing, mark each deformation level; Construct the coordinate system of the battery shell and mark each deformation level; Collect the location of the deformation level and associate the deformation level with the corresponding location; Position levels are determined according to the positions and features at the edges, and position parameters are determined based on the position levels.

8. The method for detecting the edge of a battery casing according to claim 7, characterized in that: The method of determining the risk parameters at the edge of each battery housing based on a plurality of deformation levels and corresponding positions, and determining the qualified level at the edge of the battery housing according to the risk parameters at the edge, further includes: determining a risk parameter at the edge based on a plurality of deformation levels and position parameters; The acceptance level at the edge of the battery housing is determined based on the risk parameter at the edge.

9. A detection system for the edge of a battery housing, characterized in that: The detection system at the edge of the battery housing is applied to the detection method at the edge of the battery housing as claimed in any one of claims 1 to 8, and the detection system at the edge of the battery housing comprises: The acquisition module is used to perform a circumferential scan on the battery shell and acquire a point cloud corresponding to the edge of the battery shell during the detection process of the battery shell; An edge feature module, used to construct edge features based on a point cloud at the edge of a battery housing; An abnormal region module, used to traverse the edge features and mark the abnormal regions in the edge features; Anomaly feature module, used to trigger fixed-point detection based on the location of the abnormal area and determine the abnormal features; A deformation level module is used to collect the deformation amount of the abnormal feature and determine the deformation level according to the deformation amount of the abnormal feature; A qualified detection module, used to determine the risk parameters at the edge of each battery housing based on a plurality of deformation levels and corresponding positions, and determine the qualified level at the edge of the battery housing according to the risk parameters at the edge; The method of constructing edge features based on the point cloud at the edge of the battery shell includes: freezing the point cloud at the edge of the battery shell; locating the dense points of the point cloud at the edge of the battery shell, and collecting multiple dense points; checking the point cloud based on the multiple dense points, and collecting the number of point clouds at each dense point; constructing a point cloud difference based on the number of point clouds at each dense point, and triggering point cloud optimization at the dense points according to the point cloud difference to balance the number of point clouds at each dense point, at this time, triggering the optimization level based on the point cloud difference; when the number of point clouds at each dense point is in a balanced state, constructing a first feature according to the point clouds at each dense point, and defining the frame direction of the first feature; constructing a second feature along the point cloud at a non-dense point, and optimizing the second feature based on the frame direction of the first feature; connecting multiple second features and multiple first features to construct edge features, at this time, the frame direction of the first feature overlaps with the frame direction of the second feature.

Images