CN115805397B - Photovoltaic module battery piece welding detection system - Google Patents
Photovoltaic module battery piece welding detection system Download PDFInfo
- Publication number
- CN115805397B CN115805397B CN202310119777.9A CN202310119777A CN115805397B CN 115805397 B CN115805397 B CN 115805397B CN 202310119777 A CN202310119777 A CN 202310119777A CN 115805397 B CN115805397 B CN 115805397B
- Authority
- CN
- China
- Prior art keywords
- image information
- product
- area
- sub
- module
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 128
- 238000003466 welding Methods 0.000 title claims abstract description 126
- 229910000679 solder Inorganic materials 0.000 claims description 19
- 230000002950 deficient Effects 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 9
- 238000003062 neural network model Methods 0.000 claims description 8
- 238000004519 manufacturing process Methods 0.000 claims description 5
- 230000010365 information processing Effects 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 claims description 4
- 230000005856 abnormality Effects 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 8
- 230000000694 effects Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 7
- 238000012549 training Methods 0.000 description 7
- 238000012360 testing method Methods 0.000 description 5
- 238000005520 cutting process Methods 0.000 description 4
- 238000013519 translation Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 3
- RSWGJHLUYNHPMX-UHFFFAOYSA-N Abietic-Saeure Natural products C12CCC(C(C)C)=CC2=CCC2C1(C)CCCC2(C)C(O)=O RSWGJHLUYNHPMX-UHFFFAOYSA-N 0.000 description 2
- KHPCPRHQVVSZAH-HUOMCSJISA-N Rosin Natural products O(C/C=C/c1ccccc1)[C@H]1[C@H](O)[C@@H](O)[C@@H](O)[C@@H](CO)O1 KHPCPRHQVVSZAH-HUOMCSJISA-N 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 239000003550 marker Substances 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- KHPCPRHQVVSZAH-UHFFFAOYSA-N trans-cinnamyl beta-D-glucopyranoside Natural products OC1C(O)C(O)C(CO)OC1OCC=CC1=CC=CC=C1 KHPCPRHQVVSZAH-UHFFFAOYSA-N 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 229910000838 Al alloy Inorganic materials 0.000 description 1
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000003703 image analysis method Methods 0.000 description 1
- 239000000741 silica gel Substances 0.000 description 1
- 229910002027 silica gel Inorganic materials 0.000 description 1
- 238000005476 soldering Methods 0.000 description 1
- 239000005341 toughened glass Substances 0.000 description 1
- 230000004304 visual acuity Effects 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The application relates to a photovoltaic module battery piece welding detection system belongs to the technical field that photovoltaic module detected, the method, a photovoltaic module battery piece welding detection system includes: the wire scanning device comprises a receiving frame arranged at the downstream of an outlet of the converging welding machine, a conveyor belt is arranged on the receiving frame, a bracket is fixed above the outlet of the converging welding machine, a wire scanning camera and a wire scanning light source are arranged on the bracket, and the wire scanning light source and a camera of the wire scanning camera are downward; the bracket is also provided with a universal bracket, the universal bracket is provided with a code scanning gun, and a product is provided with a coded label which can be scanned and identified by the code scanning gun; the device comprises a code scanning gun, a line scanning camera and a code scanning gun, and is characterized by further comprising a detection device, wherein the line scanning camera and the code scanning gun are connected with the detection device, and the detection device is used for receiving image information obtained by a pixel line sent by the line scanning camera and receiving product information sent by the code scanning gun. The application has the effect of improving detection efficiency.
Description
Technical Field
The application relates to the technical field of photovoltaic module detection, in particular to a photovoltaic module battery piece welding detection system.
Background
The photovoltaic module is the minimum effective power generation unit and mainly comprises core parts such as a battery piece, an interconnection bar, a bus bar, toughened glass, EVA, a back plate, aluminum alloy, silica gel, a junction box and the like. The single-chip power generation amount of the photovoltaic cell is limited, and the photovoltaic cell can be used as a power supply only by being connected in series and packaged into a component. In the manufacturing process, the welding strips are required to be welded on the battery pieces side by side, so that the battery pieces are connected in series, and the ends of the welding strips are welded with the bus bars, so that a complete photovoltaic assembly is formed.
However, because there is an error between the position of the battery piece, the position of the welding strip or the position of the bus bar and the preset position, there may be problems such as continuous welding, deviation of the welding strip, overlap joint of the welding strip and the bus bar or deviation of the position of the bus bar after welding, so that the welding position needs to be detected after welding is completed, and a defective product needs to be found out for repair. Most of the detection is performed manually, and the detection efficiency is low.
Disclosure of Invention
In order to improve detection efficiency, the application provides a photovoltaic module battery piece welding detection system.
The application provides a photovoltaic module battery piece welding detection system, adopts following technical scheme:
a photovoltaic module cell welding detection system, comprising: the wire scanning device comprises a receiving frame arranged at the downstream of an outlet of the converging welding machine, a conveyor belt is arranged on the receiving frame, a bracket is fixed above the outlet of the converging welding machine, a wire scanning camera and a wire scanning light source are arranged on the bracket, and the wire scanning light source and a camera of the wire scanning camera are downward;
the bracket is also provided with a universal bracket, the universal bracket is provided with a code scanning gun, and a product is provided with a coded label which can be scanned and identified by the code scanning gun;
the device comprises a code scanning gun, a line scanning camera and a code scanning gun, and is characterized by further comprising a detection device, wherein the line scanning camera and the code scanning gun are connected with the detection device, and the detection device is used for receiving image information obtained by a pixel line sent by the line scanning camera and receiving product information sent by the code scanning gun.
Through adopting above-mentioned technical scheme, the product is passed to the accepting frame from the export of converging the welding machine, the product is passed through from line scanning light source and line scanning camera below, the line is swept the light source and is shone the product surface, the line is swept the camera and is shot light place, along with the removal of product, shoot and obtain a plurality of pixel lines, a plurality of pixel lines can be processed through detection device and obtain image information, sweep the code rifle and scan the code label of product, obtain product information, detection device carries out the analysis according to image information and product information, carry out automated inspection product, realize automated inspection.
Further, the detection device includes:
the acquisition module is used for acquiring image information of the product;
a dividing module for dividing the image information into a plurality of sub-image information, each of the sub-image information corresponding to a block area of a product;
the analysis module is used for analyzing the sub-image information and determining whether the area corresponding to each sub-image information is qualified or not;
the determining module is used for determining the detection result of the product according to the result of whether each area is qualified or not, and comprises any one of the following steps:
if the unqualified area exists, determining that the detection result of the product is a defective product;
if no unqualified area exists, determining that the detection result of the product is good.
By adopting the technical scheme, after the acquisition processing module detection device acquires the image information of the product, the image information is divided to obtain a plurality of sub-image information, the analysis module analyzes each sub-image information, so that whether the corresponding area is qualified or not is determined, when the unqualified area exists in the product, the determination module determines that the corresponding product is a defective product, and when each area of the product is qualified, the determination module determines that the product is a good product, therefore, the product is automatically detected by an image analysis method, and the working efficiency is improved.
Further, the area failure includes a cold joint, a strap overlap with the bus bar, a strap offset, and a bus bar offset, and the analysis module includes:
the first comparison sub-module is used for comparing the sub-image information with the problem of overlap joint of the cold joint, the welding strip and the bus bar in the big data in sequence, and determining that the region corresponding to the sub-image information is unqualified when any comparison is consistent;
the first marked sub-image generation sub-module is used for inputting the sub-image information into a trained neural network model, identifying bus bars and/or welding strips in the sub-image information, and marking the bus bars and the welding strips in the sub-image information respectively to generate first marked sub-image information;
the second marked image information generation sub-module is used for splicing the first marked sub-image information according to the actual position of the corresponding area to generate second marked image information;
the second comparison sub-module is used for comparing the second marked image information with standard products and judging whether the area corresponding to each sub-image information has the problem of welding strip offset and/or bus bar offset; if yes, determining that the region corresponding to the sub-image information is unqualified.
Through adopting above-mentioned technical scheme, first contrast sub-module detection device confirms whether there is the rosin joint in the region that sub-image information corresponds, weld the problem of area and busbar overlap joint through big data, realize automated inspection, on the other hand, first mark sub-image generation sub-module detection device passes through neural network model, the busbar and/or welding rod in the sub-image information are discerned, and carry out the mark, second mark image information generation sub-module splice into second mark image information with first sub-image information of mark, the second contrast sub-module of being convenient for compares second mark image information with standard image information, thereby confirm whether every region has the problem of welding area skew and/or busbar skew, in sum, analysis module detection device can intelligent analysis sub-image information, the problem that each region exists is judged to the pertinence.
Further, the second contrast sub-module includes:
the coordinate determining unit is used for establishing a coordinate system, wherein in the second marked image information, one corner of a product is overlapped with an origin in the coordinate system, and two right-angle sides adjacent to one corner of the product are respectively overlapped with an abscissa and an ordinate of the coordinate system;
the standard image information processing unit is used for generating standard image information of a standard product in the coordinate system, wherein in the standard image information, one corner of the standard product coincides with an origin in the coordinate system, and two right-angle sides adjacent to one corner of the standard product coincide with an abscissa and an ordinate of the coordinate system respectively;
a transparency setting unit for increasing the transparency of the standard image information to a transparency preset value;
the judging unit is used for judging whether the coincidence rate of each bus bar and each welding strip in the second mark image information and the standard image information reaches a preset value;
if yes, determining that the region corresponding to each piece of sub-image information is qualified;
if the bus bar coincidence rate of the current bus bar in the second marked image information and the bus bar coincidence rate of the corresponding position in the standard image information does not reach a preset value, determining that the current bus bar is deviated, and determining that the area corresponding to the current sub-image information is unqualified;
if the welding strip superposition rate of the current welding strip in the second marked image information and the welding strip superposition rate of the corresponding position in the standard image information does not reach the preset value, determining that the current welding strip is deviated, and determining that the area corresponding to the current sub-image information is unqualified.
By adopting the technical scheme, the coordinate determining unit, the standard image information processing unit and the transparency setting unit detection device overlap the second marked image information and the products in the standard image information in the same coordinate system, the judging unit judges the coincidence rate of the welding strip and the bus bar in the second marked image and the standard welding strip and the bus bar, if the coincidence rate reaches a preset value, the region corresponding to the sub-image information is judged to be qualified, the positions of the welding strip and the bus bar can be basically correct, if the coincidence rate does not reach the preset value, the region corresponding to the sub-image is judged to be unqualified due to the deviation of the welding strip and the bus bar, and the region welding result can be rapidly and accurately detected.
Further, the judging unit includes:
a first acquisition subunit configured to acquire a plurality of first areas of the bus bar and a plurality of second areas of the solder strip in the standard image information;
a second acquiring subunit configured to acquire a plurality of third areas of the bus bar and a plurality of fourth areas of the solder strip in the second mark image information;
a first processing subunit, configured to determine a superposition area of the third area and the first area at a corresponding position, calculate a first ratio of the superposition area to a total area of the first area, and determine, according to the first ratio, whether a superposition ratio of the second mark image information and the bus bar in the standard image information reaches a preset value;
a second processing subunit, configured to determine a superposition area of the fourth area and the second area at the corresponding position, calculate a second ratio of the superposition area to a total area of the second area, and determine whether a superposition ratio of the second mark image information and the welding strip in the standard image information reaches a preset value according to the second ratio
By adopting the technical scheme, the first acquisition subunit, the second acquisition subunit and the first processing subunit detection device determine the superposition area of the third area and the first area of the same bus bar, a first ratio is obtained by calculating according to the superposition area and the total area of the first area, and the first ratio is the superposition ratio, so that the superposition ratio can be compared with a preset value to judge whether the superposition ratio of the bus bar reaches the preset value, and likewise, the second processing subunit detection device can determine whether the superposition ratio of the welding strip reaches the preset value.
Further, the detection device further includes:
the product information acquisition module is used for acquiring product information obtained by scanning the bar code corresponding to the product, wherein the product information comprises a product batch, a product number and a production date;
the identification image information generation module is used for identifying the reasons of disqualification of the corresponding areas of each sub-image in the image information to generate identification image information;
the storage module is used for storing the image information or the identification image information of the product and the detection result corresponds to the product information;
and the sending module is used for sending the product information of the defective products to the repairing end.
By adopting the technical scheme, the product information acquisition module detection device stores product information according to the bar code, the identification image information generation module correspondingly stores the image information and the product information, so that archiving and recording are facilitated, automatic archiving is realized, and detection convenience is improved.
Further, the detection device further includes:
the repeated monitoring module is used for repeatedly acquiring image information of the product for a plurality of times, analyzing the image information and determining detection results of the product to obtain a plurality of detection results of the product;
the repeated judging module is used for judging whether the detection results comprise the detection results of defective products or not;
if yes, determining the possibility of disqualification of each area according to the ratio of the number of times that each area is determined to be disqualified to the total number of times of detection;
otherwise, determining that the detection result of the product is good.
By adopting the technical scheme, after the detection device detects defective products, repeated monitoring is carried out for a plurality of times, and the repeated judgment module rechecks the detection result according to the proportion of the defective products in the detection result, so that the misjudgment rate is reduced, and the detection accuracy is improved.
Further, the detection device further includes:
the problem judging module is used for judging whether the problem of welding strip deviation or bus bar deviation exists in the current area;
if yes, generating error information, wherein the error information comprises welding equipment abnormality corresponding to the current area;
if not, generating feedback information, wherein the feedback information comprises that the welding equipment corresponding to the current area is normal.
Through adopting above-mentioned technical scheme, when the current region has the rosin joint or weld area and busbar overlap joint problem, problem judging module judges whether the current region has the problem of weld area skew or busbar skew, if so, the unusual possibility of welding equipment is bigger, can reverse infer the condition of welding equipment according to the testing result of product from this.
In summary, the present application includes at least one of the following beneficial technical effects:
1. the product is transmitted to the bearing frame from the outlet of the converging welding machine, the product passes through the line scanning light source and the lower part of the line scanning camera, the line scanning light source irradiates the surface of the product, the line scanning camera shoots the position of light, along with the movement of the product, a plurality of pixel lines are shot to obtain the image information, the pixel lines can be processed by the detection device to obtain the image information, the code scanning gun scans the code label of the product to obtain the product information, the detection device analyzes according to the image information and the code label, the product is automatically detected, the automatic detection is realized, and the working efficiency is improved;
2. the detection device determines whether the region corresponding to the sub-image information has the problems of cold joint and lap joint of the welding strip and the bus bar through big data, so that automatic detection is realized, and on the other hand, the detection device determines whether each region has the problems of welding strip offset and/or bus bar offset through a neural network model, and the problems of each region are judged in a targeted manner.
Drawings
Fig. 1 is a schematic structural diagram of a welding detection system for a photovoltaic module battery piece in an embodiment of the application.
Fig. 2 is a block diagram of the detection apparatus in the embodiment of the present application.
Fig. 3 is a schematic structural view of a product in an embodiment of the present application.
A in fig. 4 is a schematic diagram of sub-image information including a battery panel and a solder ribbon; b is a schematic diagram of sub-image information including solder strips and bus bars.
5-1 in FIG. 5 is a schematic illustration of a weld well; 5-2 is a schematic illustration of a dummy solder joint; 5-3 are schematic diagrams of the overlap of the solder strip and the bus bar.
FIG. 6-1 is a schematic illustration of bus bar translation; 6-2 is a schematic view of the inclination of the bus bar.
Reference numerals: 1. a bearing frame; 2. a conveyor belt; 3. a confluence welding machine; 4. a bracket; 5. a camera fixing member; 6. a line scan camera; 7. a line scanning light source; 8. a universal bracket; 9. a code scanning gun; 10. a battery sheet; 11. welding a belt; 12. a bus bar; 200. a detection device; 201. an acquisition module; 202. dividing the module; 203. analysis module, 204, determination module.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
In addition, the term "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In this context, unless otherwise specified, the term "/" generally indicates that the associated object is an "or" relationship.
The embodiment of the application discloses photovoltaic module battery piece welding detection system, refer to fig. 1 and 2, photovoltaic module battery piece welding detection system is including accepting frame 1, is provided with conveyer belt 2 on accepting frame 1, accepts frame 1 and sets up the export low reaches at conflux welding machine 3, and after the product after the welding is accomplished was released from conflux welding machine 3's export, accept frame 1 accepts the product.
A bracket 4 is fixed above the outlet of the confluence welding machine 3, a camera fixing piece 5 is fixed on the bracket 4, a line scanning camera 6 and a line scanning light source 7 are arranged on the camera fixing piece 5, and the cameras of the line scanning light source 7 and the line scanning camera 6 are downward.
The line scanning light source 7 generates a light ray perpendicular to the moving direction of the product, the light ray illuminates the product, one end of the product starts to move from the lower side of the line scanning camera 6 until the other end of the product leaves from the lower side of the line scanning camera 6, when the product passes through the front of the line scanning camera 6, the line scanning camera 6 scans the illuminated position of the light ray, a new pixel line is acquired, and along with the continuous movement of the product, the line scanning camera 6 shoots a plurality of continuous pixel lines.
The bracket 4 is also provided with a universal bracket 8, and the universal bracket 8 is provided with a code scanning gun 9. The code is arranged on the product, the position of the universal bracket 8 is adjusted, the code scanning gun 9 is opposite to the position of the code, and when the code moves to the position below the code scanning gun 9, the code scanning gun 9 scans the code, so that the product information corresponding to the code is obtained.
The photovoltaic module battery piece welding detection system further comprises a detection device 200, the line scanning camera 6 and the code scanning gun 9 are connected with the detection device 200, the detection device 200 receives pixel lines sent by the line scanning camera 6 and product information sent by the code scanning gun 9, an image acquisition card is connected to the detection device 200, the image acquisition card processes a plurality of pixel lines, and the lines are gathered to form a surface to obtain image information of a product.
The detection device 200 performs analysis and detection on the image information, and stores the detection result in association with the product information.
Referring to fig. 2, the detection apparatus 200 includes:
an acquisition module 201, configured to acquire image information of a product.
Specifically, the line scan camera may perform real-time transmission, so that the detection device 200 automatically acquires image information of the product.
The dividing module 202 is configured to divide the image information into a plurality of sub-image information, each of the sub-image information corresponding to a block area of the product.
Specifically, referring to fig. 3, the product includes a plurality of columns of battery cells 10, and a plurality of welding strips 11 are welded to each column of battery cells 10, so that the battery cells 10 are connected in series, and both ends of the welding strips 11 are welded to one bus bar 12. Therefore, the number of welding points on the product is large and complex, and the detection device 200 divides the image information for rapid analysis of the image information.
When the detection device 200 acquires the image information, according to a preset cutting rule, a plurality of sub-image information are automatically obtained by cutting, and each sub-image corresponds to a region of the product. At least one welding spot is arranged in each sub-image obtained by cutting according to a preset cutting rule.
For example, referring to fig. 3 and 4, the detecting device 200 may divide sub-image areas a and B, where a is sub-image information of an area corresponding to each battery piece, a plurality of welding strips are welded on the battery piece, and B is sub-image information corresponding to bus bars, and only one bus bar, one welding strip, and a welding point between the bus bar and the welding strip are included in the sub-image information corresponding to each bus bar.
Further, the detecting device 200 may further be further subdivided, such as C, and each sub-image information includes a solder strip.
After the detection device 200 divides the plurality of sub-image information, the sub-image information is stored in one-to-one correspondence with the areas of the product.
And the analysis module 203 is configured to analyze the sub-image information and determine whether the area corresponding to each sub-image information is qualified.
Specifically, the area failure includes a cold joint, a lap joint of the bonding tape and the bus bar, a shift of the bonding tape, and a shift of the bus bar. Taking fig. 5 as an example, 5-1 is good welding, namely, a welding spot completely covers two welded objects; 5-2 is virtual welding, and the welding point is incomplete; 5-3, overlapping the welding strip with the bus bar, namely connecting the welding strip with the bus bar without welding spots; the welding strip offset comprises two conditions of welding strip inclination and welding strip translation; bus bar deflection includes both bus bar tilting and bus bar translation.
An analysis module 203 comprising:
and the first comparison sub-module is used for comparing the sub-image information with the problems of cold joint, welding strip and bus bar overlap joint in the big data in sequence, and determining that the region corresponding to the sub-image information is unqualified when any comparison is consistent.
The first marked sub-image generation sub-module is used for inputting sub-image information into the trained neural network model, identifying bus bars and/or welding strips in the sub-image information, and marking the bus bars and the welding strips in the sub-image information respectively to generate first marked sub-image information.
Specifically, when training the neural network model for identifying the bus bar and/or the welding strip, the detection device 200 respectively forms a training data set, a verification set and a test set through sample data with the bus bar and/or the welding strip, applies the training data and trains the model, and adjusts parameters of the model in the training process so that the output of the model is as close to the sample data in the training data set as possible and fits the data in the training data set as possible. And then, judging the fitting degree of the model by using a verification set, determining whether to modulate the super parameters, and finally, verifying the resolving power of the trained model by using a test data set, so that the neural network model is obtained by training, sub-image information is input, and bus bars and/or welding strips in the sub-image information are automatically identified.
Further, the detecting device 200 may mark the bus bar and the solder ribbon in the sub-image information with different colors, respectively.
And the second mark image information generation sub-module is used for splicing the first mark sub-image information according to the actual position of the corresponding area to generate second mark image information.
Specifically, the detection device 200 reduces the area of the image for analysis by identifying the bus bars and the solder strips in the sub-image information, and reduces the time taken compared to when analysis is performed by the entire image information.
The second comparison sub-module is used for comparing the second marked image information with standard products and judging whether the area corresponding to each sub-image information has the problem of welding strip offset and/or bus bar offset; if yes, determining that the region corresponding to the sub-image information is unqualified.
The second contrast sub-module includes:
the coordinate determining unit is used for establishing a coordinate system, enabling one corner of the product in the second marked image information to coincide with an origin in the coordinate system, and enabling two right-angle sides adjacent to one corner of the product to coincide with an abscissa and an ordinate of the coordinate system respectively.
Specifically, due to the imprecise position of the product entering the receiving rack, the four sides of the product in the second mark image information may not be parallel to the four sides of the second mark image information, respectively, and for facilitating further analysis, the detecting device 200 establishes a coordinate system and identifies one corner of the product.
The detecting device 200 may use the mark at the most edge as one corner of the product in the second mark image information. For example, the lower left corner in the second marker image is marked with a bus bar, and then a point of the leftmost end of the bus bar is determined as one corner of the product.
And then, a corner of the product determined in the second marked image information is overlapped with the original point, and further, two right-angle sides are overlapped with the horizontal coordinate and the vertical coordinate respectively.
And the standard image information processing unit is used for generating standard image information of the standard product in the coordinate system, enabling one corner of the standard product in the standard image information to coincide with an origin in the coordinate system, and enabling two right-angle sides adjacent to one corner of the standard product to coincide with an abscissa and an ordinate of the coordinate system respectively.
Specifically, the welding positions of the welding strips, the bus bars and the battery plates in the standard product are standard, so that the standard product can be used as a reference for comparison. Further, the detection device 200 also places the standard picture information of the standard product in the coordinate system, and the second mark image information and the standard image information are superimposed in the coordinate system.
And a transparency setting unit for raising the transparency of the standard image information to a transparency preset value.
Specifically, when the detection device 200 increases the transparency of the standard image information to the preset transparency value, the standard image information reaches the semitransparent state.
The judging unit is used for judging whether the coincidence rate of each bus bar and each welding strip in the second mark image information and the standard image information reaches a preset value; if yes, determining that the area corresponding to each piece of sub-image information is qualified;
otherwise, if the bus bar coincidence rate of the current bus bar in the second marked image information and the bus bar coincidence rate of the corresponding position in the standard image information does not reach a preset value, determining that the current bus bar is deviated, and determining that the area corresponding to the current sub-image information is unqualified;
if the welding strip superposition rate of the current welding strip in the second mark image information and the welding strip superposition rate of the corresponding position in the standard image information does not reach the preset value, determining that the current welding strip is deviated, and determining that the area corresponding to the current sub-image information is unqualified.
The preset value is a value preset by the detection device 200, and is used for judging whether the bus bar or the welding strip is deviated or not.
Further, the judging unit includes:
and the first acquisition subunit is used for acquiring a plurality of first areas of the bus bar and a plurality of second areas of the welding strip in the standard image information.
Specifically, the detection device 200 inputs standard image information into the above trained neural network model, recognizes the solder strips and the bus bars, and generates the identification. Further, the detection device 200 determines the area of the identification bus bar as a first area and the area of the identification ribbon as a second area.
And the second acquisition subunit is used for acquiring a plurality of third areas of the bus bar and a plurality of fourth areas of the welding strip in the second marked image information.
Specifically, the detection device 200 determines the region of the second marker image information based on the identification bus bar as the third region, and determines the fourth region based on the region identified as the solder strip.
The first processing subunit is used for determining the superposition area of the third area and the first area at the corresponding position, calculating a first ratio of the superposition area to the total area of the first area, and determining whether the superposition ratio of the bus bars in the second mark image information and the standard image information reaches a preset value or not according to the first ratio.
Specifically, the detection device 200 calculates a first ratio of the overlapping area to the area of the first area, judges the overlapping rate of the third area and the first area at the corresponding position, and when the overlapping rate reaches a preset value, the current bus bar slightly translates or rotates with the preset position, so that the deviation is negligible; if the overlap ratio does not reach the preset value, the deviation is larger, and the possibility of generating the false welding and the missing welding is larger.
For example, 6-1 in fig. 6 is a schematic diagram of the bus bar translating with the preset position, a is a first area, b is a third area, a first ratio of the area of the shadow portion to the area of the first area a is the coincidence rate, and if the preset coincidence rate is 90% and the current coincidence rate is 92%, the coincidence rate is judged to reach the preset value.
Fig. 6-2 is a schematic diagram of the bus bar being inclined with respect to the preset position, a is a first area, b is a second area, a first ratio of the area of the shadow portion to the area of the first area a is a coincidence rate, and if the preset coincidence rate is 90%, and the current coincidence rate is 88%, it is determined that the coincidence rate does not reach the preset value.
And the second processing subunit is used for determining the superposition area of the fourth area and the second area at the corresponding position, calculating a second ratio of the superposition area to the total area of the second area, and determining whether the superposition rate of the welding strip in the second mark image information and the standard image information reaches a preset value or not according to the second ratio.
Specifically, the detection device 200 calculates a second ratio of the overlapping area to the area of the second area, determines an overlapping ratio of the fourth area to the second area at the corresponding position, and when the overlapping ratio reaches a preset value, generates tiny translation or rotation between the current welding strip and the preset position, and the deviation is negligible, so that the overlapping of the second mark image information and the current welding strip in the standard image information can be determined; if the overlapping rate does not reach the preset value, the deviation is larger, the possibility of generating the false welding and the missing welding is larger, and the fact that the second mark image information is not overlapped with the current welding strip in the standard image information is determined.
A determining module 204, configured to determine a detection result of the product according to a result of whether each area is qualified, where the detection result includes any one of the following:
if the unqualified area exists, determining that the detection result of the product is a defective product;
if no unqualified area exists, determining that the detection result of the product is good.
Specifically, in order to ensure the quality of the product, when an unqualified area exists in the product, repair is required, so that the unqualified product can be accurately screened out.
In another possible implementation manner, the detection device 200 further includes:
the product information acquisition module is used for acquiring product information obtained by scanning the bar code corresponding to the product, wherein the product information comprises a product batch, a product number and a production date.
Specifically, after the product is produced, the detection device 200 generates a bar code according to the product batch, the product number and the production diary after encryption, and the bar code is attached to a certain position of the product, so that the detection device 200 obtains the product information sent by the code scanning gun.
The identification image information generation module is used for identifying the reasons of disqualification of the corresponding areas of each sub-image in the image information and generating identification image information.
Specifically, after the detection device 200 completes detection of the product, the image information of the product is saved, and the position identifier is corresponding to the failed area. The method for identifying the detection device 200 can adopt different colors to distinguish unqualified reasons, and can also identify characters on corresponding areas, so that repair personnel can quickly find and identify the unqualified reasons.
In another possible implementation, the detection device 200 may also identify the qualified area.
And the storage module is used for storing the image information or the identification image information of the product and the detection result corresponds to the product information.
Specifically, the detection device 200 stores the detection results in a one-to-one correspondence manner, so that the follow-up check is facilitated.
And the sending module is used for sending the product information of the defective products to the repairing end.
Specifically, the detection results are automatically classified, and the product information of defective products is stored in an independent folder and sent to a repair end.
In another possible implementation manner, in order to reduce the false detection rate, after the determining module 204 determines that the detection result of the product is a defective product, the detecting device 200 further includes:
and the repeated monitoring module is used for repeatedly acquiring the image information of the product for a plurality of times, analyzing the image information and determining the detection result of the product to obtain a plurality of detection results of the product.
Specifically, after any product is determined as defective, the detecting device 200 repeatedly detects the current product a plurality of times, to obtain a plurality of detection results, and analyzes whether the conclusion that the current product is determined as defective is authentic or not through the plurality of detection results.
The repeated judging module is used for judging whether the detection results comprise defective products or not;
if yes, determining the possibility of disqualification of each area according to the ratio of the number of times that each area is determined to be disqualified to the total number of times of detection;
specifically, if the number of times of failure of the current area is greater in the case of testing a plurality of times, the probability of failure is greater. For example, the detecting device 200 repeatedly detects three times, wherein the number of times that the area a is determined to be failed is two times, and the probability that the area a is failed is 66.7%; if the number of times that the area B is determined to be failed is three, the probability of failure of the area B is 100%.
Otherwise, determining that the detection result of the product is good.
Specifically, in the case of repeated tests, no reject condition occurs in each region, and the first reject may be a false judgment, so that the detection result of the current product is determined to be good.
Further, the reasons for the disqualification of the product are related to the welding equipment, and when the welding equipment is abnormal, the welding point may be incomplete, so as to check whether the welding equipment has a problem, the detection device 200 further analyzes the detection result of the product.
In another possible implementation, if the failure cause of the current area includes welding or overlapping the welding ribbon with the bus bar, the detecting device 200 further includes:
and the problem judging module is used for judging whether the problem of welding strip deviation or bus bar deviation exists in the current area.
If yes, generating error information, wherein the error information comprises welding equipment abnormality corresponding to the current area.
If not, generating feedback information, wherein the feedback information comprises that the welding equipment corresponding to the current area is normal.
Specifically, the solder strips or bus bars where they are offset may cause problems with the partial area soldering in which the dummy solder or solder strips overlap the bus bars. On the contrary, when the current area has the problem of the lap joint of the dummy solder or the solder ribbon and the bus bar, but does not have the problem of the offset of the solder ribbon or the offset of the bus bar, the welding equipment is likely to be abnormal, so that error information is generated to prompt the user.
The foregoing are all preferred embodiments of the present application, and are not intended to limit the scope of the present application in any way, therefore: all equivalent changes in structure, shape and principle of this application should be covered in the protection scope of this application.
In addition, it is to be understood that relational terms such as first and second are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
Claims (6)
1. The welding detection system for the photovoltaic module battery piece is characterized by comprising a carrying frame (1) arranged at the downstream of an outlet of a converging welding machine (3), wherein a conveyor belt (2) is arranged on the carrying frame (1), a support (4) is fixed above the outlet of the converging welding machine (3), a wire scanning camera (6) and a wire scanning light source (7) are arranged on the support (4), and the wire scanning light source (7) and a camera of the wire scanning camera (6) are downward;
the universal bracket (8) is further arranged on the bracket (4), the code scanning gun (9) is arranged on the universal bracket (8), and the coded label which can be scanned and identified by the code scanning gun (9) is arranged on a product;
the device also comprises a detection device (200), wherein the line scanning camera (6) and the code scanning gun (9) are connected with the detection device (200), and the detection device (200) is used for receiving the pixel lines sent by the line scanning camera (6) to obtain image information and receiving the product information sent by the code scanning gun (9);
the detection device (200) comprises:
an acquisition module (201) for acquiring image information of a product;
a dividing module (202) for dividing the image information into a plurality of sub-image information, each of the sub-image information corresponding to a block area of a product;
an analysis module (203) for analyzing the sub-image information and determining whether the area corresponding to each sub-image information is qualified;
a determining module (204) for determining a detection result of the product according to the result of whether each area is qualified, wherein the detection result comprises any one of the following steps:
if the unqualified area exists, determining that the detection result of the product is a defective product;
if no unqualified area exists, determining that the detection result of the product is good;
the area failure includes a cold joint, a strap overlap with a bus bar, a strap offset, and a bus bar offset, the analysis module (203) includes:
the first comparison sub-module is used for comparing the sub-image information with the problem of overlap joint of the cold joint, the welding strip and the bus bar in the big data in sequence, and determining that the region corresponding to the sub-image information is unqualified when any comparison is consistent;
the first marked sub-image generation sub-module is used for inputting the sub-image information into a trained neural network model, identifying bus bars and/or welding strips in the sub-image information, and marking the bus bars and the welding strips in the sub-image information respectively to generate first marked sub-image information;
the second marked image information generation sub-module is used for splicing the first marked sub-image information according to the actual position of the corresponding area to generate second marked image information;
the second comparison sub-module is used for comparing the second marked image information with standard products and judging whether the area corresponding to each sub-image information has the problem of welding strip offset and/or bus bar offset; if yes, determining that the region corresponding to the sub-image information is unqualified.
2. The system of claim 1, wherein the second contrast sub-module comprises:
the coordinate determining unit is used for establishing a coordinate system, wherein in the second marked image information, one corner of a product is overlapped with an origin in the coordinate system, and two right-angle sides adjacent to one corner of the product are respectively overlapped with an abscissa and an ordinate of the coordinate system;
the standard image information processing unit is used for generating standard image information of a standard product in the coordinate system, wherein in the standard image information, one corner of the standard product coincides with an origin in the coordinate system, and two right-angle sides adjacent to one corner of the standard product coincide with an abscissa and an ordinate of the coordinate system respectively;
a transparency setting unit for increasing the transparency of the standard image information to a transparency preset value;
the judging unit is used for judging whether the coincidence rate of each bus bar and each welding strip in the second mark image information and the standard image information reaches a preset value;
if yes, determining that the region corresponding to each piece of sub-image information is qualified;
if the bus bar coincidence rate of the current bus bar in the second marked image information and the bus bar coincidence rate of the corresponding position in the standard image information does not reach a preset value, determining that the current bus bar is deviated, and determining that the area corresponding to the current sub-image information is unqualified;
if the welding strip superposition rate of the current welding strip in the second marked image information and the welding strip superposition rate of the corresponding position in the standard image information does not reach the preset value, determining that the current welding strip is deviated, and determining that the area corresponding to the current sub-image information is unqualified.
3. The system according to claim 2, wherein the judging unit includes:
a first acquisition subunit configured to acquire a plurality of first areas of the bus bar and a plurality of second areas of the solder strip in the standard image information;
a second acquiring subunit configured to acquire a plurality of third areas of the bus bar and a plurality of fourth areas of the solder strip in the second mark image information;
a first processing subunit, configured to determine a superposition area of the third area and the first area at a corresponding position, calculate a first ratio of the superposition area to a total area of the first area, and determine, according to the first ratio, whether a superposition ratio of the second mark image information and the bus bar in the standard image information reaches a preset value;
and the second processing subunit is used for determining the superposition area of the fourth area and the second area at the corresponding position, calculating a second ratio of the superposition area to the total area of the second area, and determining whether the superposition rate of the welding strip in the second mark image information and the standard image information reaches a preset value according to the second ratio.
4. The system of claim 1, wherein the detection device (200) further comprises:
the product information acquisition module is used for acquiring product information obtained by scanning the bar code corresponding to the product, wherein the product information comprises a product batch, a product number and a production date;
the identification image information generation module is used for identifying the reasons of disqualification of the corresponding areas of each sub-image in the image information to generate identification image information;
the storage module is used for storing the image information or the identification image information of the product and the detection result corresponds to the product information;
and the sending module is used for sending the product information of the defective products to the repairing end.
5. The system of claim 1, wherein the detection device (200) further comprises:
the repeated monitoring module is used for repeatedly acquiring image information of the product for a plurality of times, analyzing the image information and determining detection results of the product to obtain a plurality of detection results of the product;
the repeated judging module is used for judging whether the detection results comprise the detection results of defective products or not;
if yes, determining the possibility of disqualification of each area according to the ratio of the number of times that each area is determined to be disqualified to the total number of times of detection;
otherwise, determining that the detection result of the product is good.
6. The system according to claim 2, wherein the detection device (200) further comprises:
the problem judging module is used for judging whether the problem of welding strip deviation or bus bar deviation exists in the current area;
if yes, generating error information, wherein the error information comprises welding equipment abnormality corresponding to the current area;
if not, generating feedback information, wherein the feedback information comprises that the welding equipment corresponding to the current area is normal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310119777.9A CN115805397B (en) | 2023-02-16 | 2023-02-16 | Photovoltaic module battery piece welding detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310119777.9A CN115805397B (en) | 2023-02-16 | 2023-02-16 | Photovoltaic module battery piece welding detection system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115805397A CN115805397A (en) | 2023-03-17 |
| CN115805397B true CN115805397B (en) | 2023-07-04 |
Family
ID=85487869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310119777.9A Active CN115805397B (en) | 2023-02-16 | 2023-02-16 | Photovoltaic module battery piece welding detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115805397B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115971598B (en) * | 2023-03-20 | 2023-06-27 | 广东联塑班皓新能源科技集团有限公司 | Intelligent assembly system based on photovoltaic panel |
| CN117330576B (en) * | 2023-11-01 | 2024-05-03 | 融韵光电科技(苏州)有限公司 | Poor welding detection equipment and method for junction box bus bar |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101275823B1 (en) * | 2011-04-28 | 2013-06-18 | (주) 에투시스템 | Device for detecting 3d object using plural camera and method therefor |
| CN105312707A (en) * | 2015-06-14 | 2016-02-10 | 常州天合光能有限公司 | Welding machine capable of automatically sorting and discharging |
| CN208929519U (en) * | 2018-10-29 | 2019-06-04 | 无锡先导智能装备股份有限公司 | Welding equipment |
| CN112150455A (en) * | 2020-09-30 | 2020-12-29 | 王海 | Method and system for judging visual angle deviation of photovoltaic camera based on artificial intelligence |
| CN112712149B (en) * | 2020-12-30 | 2022-12-02 | 盛泰光电科技股份有限公司 | Production information management system based on two-dimensional code recognition |
| CN114289945B (en) * | 2021-12-31 | 2024-07-05 | 北京博清科技有限公司 | Welding equipment, control method thereof and welding system |
| CN115274481A (en) * | 2022-07-28 | 2022-11-01 | 江苏博阳智能装备有限公司 | Battery string detection method |
| CN115578321A (en) * | 2022-09-19 | 2023-01-06 | 北京珞安科技有限责任公司 | Finished product detection system and method for industrial production |
| CN115457119B (en) * | 2022-09-21 | 2023-10-27 | 正泰集团研发中心(上海)有限公司 | Bus bar labeling method, device, computer equipment and readable storage medium |
-
2023
- 2023-02-16 CN CN202310119777.9A patent/CN115805397B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115805397A (en) | 2023-03-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115805397B (en) | Photovoltaic module battery piece welding detection system | |
| CN103134809B (en) | Welded line defect detection method | |
| CN106825958A (en) | Integrated welding is agreed to play and takes the photograph structure and battery core automatic welding detection means and method | |
| CN107478979A (en) | A kind of defects detection maintenance system, method and maintenance unit | |
| WO2020199660A1 (en) | Method for processing photovoltaic module | |
| CN114022436B (en) | Detection method, device and detection equipment for printed circuit board | |
| CN109000564A (en) | A kind of keycap assembling method for testing performance and automatic detection device | |
| CN115131268A (en) | Automatic welding system based on image feature extraction and three-dimensional model matching | |
| CN106903069A (en) | A kind of X-ray detection equipment | |
| CN113743311B (en) | Device and method for detecting welding spots of battery and connecting sheet based on machine vision | |
| CN113469991B (en) | Visual online detection method for laser welding spot of lithium battery tab | |
| CN207008009U (en) | A kind of defects detection maintenance system and maintenance unit | |
| CN115047015A (en) | Online X-ray nondestructive flaw detection method and system | |
| CN105212264B (en) | A kind of glue heap detection means of cigarette rolling up and connecting machine | |
| CN117990705A (en) | Intelligent part detection device and method based on industrial vision technology | |
| CN114581368A (en) | Bar welding method and device based on binocular vision | |
| CN108878194A (en) | A kind of keyboard automated assembly line | |
| CN106526448A (en) | Automatic detecting system and detection method for power supply drive board | |
| US20060034506A1 (en) | Machine vision analysis system and method | |
| CN114273245B (en) | Continuous mixing detection method and system for various workpieces of automotive interior parts | |
| CN212322301U (en) | Internet artificial intelligence electron accessories discernment and detecting system | |
| CN213181294U (en) | Graphite electrode surface detection system | |
| CN209841170U (en) | Device for improving weighing reliability | |
| CN210572040U (en) | Device for online detection of cover plate glass stripes | |
| CN117862624B (en) | Wave-soldering welding repair method and wave-soldering welding repair integrated machine |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20240710 Address after: No. 3 Weisi Road, Beiping Park, Pinglu District, Shuozhou City, Shanxi Province 036800 Patentee after: Haitai New Energy Shuozhou Co.,Ltd. Country or region after: China Address before: 063000 Yutai Industrial Zone, Yutian County, Tangshan City, Hebei Province Patentee before: TANGSHAN HAITAI NEW ENERGY TECHNOLOGY CO.,LTD. Country or region before: China |
|
| TR01 | Transfer of patent right |