A factory quality inspection method and system for direct-insertion LED lamp beads
Through the intelligent factory quality inspection system combining historical statistical information and quality inspection impact information, the inspection focuses on distribution list, and the factory quality inspection of direct insertion of LED lamp beads is solved by solving the inaccurate quality inspection in the existing technology. The problem has achieved efficient and accurate quality inspection and early warning functions.
Patent Information
- Application Number
- CN202211179342.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-09-27
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2042-09-27
AI Technical Summary
The prior art cannot accurately conduct quality inspection based on production characteristics during the factory quality inspection of LED lamp beads with direct insertion, resulting in inaccurate quality inspection.
Through the intelligent factory quality inspection system, combined with historical inspection statistical information and quality inspection product impact information, the inspection focuses on distribution list, and the image acquisition and temperature acquisition device are used to perform data acquisition and sampling inspection to achieve targeted quality inspection.
It improves the accuracy and efficiency of quality inspection, saves the workload of quality inspection, can conduct factory inspections intelligently and targetedly, and provides factory warnings.
Smart Images

Figure CN115575322B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field related to intelligent detection of LED lamp beads, and in particular to a factory quality inspection method and system for direct-insertion LED lamp beads. Background Art
[0002] Direct-plug LED refers to plug-in light-emitting diodes, which are energy-saving and environmentally friendly lighting semiconductor devices that convert electrical energy into visible light. During the production and manufacturing process of direct-plug LED lamp beads, it is necessary to conduct factory quality inspection on the produced LED lamp beads to ensure the quality of the LED lamp beads supplied.
[0003] However, in the process of implementing the technical solution of the invention in this application, it is found that the above technology has at least the following technical problems:
[0004] In the process of factory quality inspection of direct-plug LED lamp beads, the prior art has a technical problem that accurate factory quality inspection cannot be performed according to the production characteristics of the direct-plug LED lamp beads. Summary of the invention
[0005] The present application provides a factory quality inspection method and system for direct-plug LED lamp beads, thereby solving the technical problem that in the prior art, accurate factory quality inspection cannot be performed according to the production characteristics of direct-plug LED lamp beads during the factory quality inspection. The application achieves the technical effect of combining the production characteristics of direct-plug LED lamp beads to perform intelligent and targeted factory sampling, saving quality inspection workload and improving quality inspection accuracy.
[0006] In view of the above problems, the present application provides a factory quality inspection method and system for direct-plug LED lamp beads.
[0007] In a first aspect, the present application provides a factory quality inspection method for direct-plug LED lamp beads, the method is applied to an intelligent factory quality inspection system, the intelligent factory quality inspection system is communicatively connected with an image acquisition device and a temperature acquisition device, the method comprising: obtaining first historical detection statistical information, wherein the first historical detection statistical information is the historical production statistical information of a first company; obtaining second historical detection statistical information, wherein the second historical detection statistical information is the historical production statistical information of a second company, and obtaining a first detection focus distribution list according to the first historical detection statistical information and the second historical detection statistical information; obtaining a first focus compensation parameter set according to quality inspection product impact information, and modifying the first detection focus distribution list based on the first focus compensation parameter set to obtain a second detection focus distribution list; performing data acquisition based on the image acquisition device and the temperature acquisition device through the second detection focus distribution list to obtain a first image set and a first temperature acquisition set; performing a factory random inspection test of the direct-plug LED lamp beads based on the first image set and the first temperature acquisition set to obtain a first random inspection result; and performing a factory warning for the direct-plug LED lamp beads according to the first random inspection result.
[0008] On the other hand, the present application also provides a factory quality inspection system for plug-in LED lamp beads, the system comprising: a first acquisition unit, the first acquisition unit is used to obtain first historical detection statistical information, wherein the first historical detection statistical information is the historical production statistical information of the first company; a second acquisition unit, the second acquisition unit is used to obtain second historical detection statistical information, wherein the second historical detection statistical information is the historical production statistical information of the second company, and a first detection focus distribution list is obtained according to the first historical detection statistical information and the second historical detection statistical information; a third acquisition unit, the third acquisition unit is used to obtain the first focus distribution list according to the quality inspection product impact information A compensation parameter set, which modifies the first detection focus distribution list based on the first detection focus compensation parameter set to obtain a second detection focus distribution list; a fourth acquisition unit, which is used to acquire data based on an image acquisition device and a temperature acquisition device through the second detection focus distribution list to obtain a first image set and a first temperature acquisition set; a fifth acquisition unit, which is used to perform factory random inspection tests on direct-plug LED lamp beads based on the first image set and the first temperature acquisition set to obtain first random inspection results; a first early warning unit, which is used to perform factory early warning on direct-plug LED lamp beads based on the first random inspection results.
[0009] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the methods described in the first aspect when executing the program.
[0010] In a fourth aspect, the present application provides a computer program product, comprising a computer program and / or instructions, which, when executed by a processor, implement the steps of any method described in the first aspect.
[0011] One or more technical solutions provided in this application have at least the following technical effects or advantages:
[0012] By adopting the method of obtaining the first historical detection statistical information, wherein the first historical detection statistical information is the historical production statistical information of the first company; obtaining the second historical detection statistical information, wherein the second historical detection statistical information is the historical production statistical information of the second company, and performing detection focus distribution of the company's problems and other companies' common problems based on the first historical detection statistical information and the second historical detection statistical information, to obtain a first detection focus distribution list; obtaining a first focus compensation parameter set based on the quality inspection product impact information, and correcting the first detection focus distribution list based on the first focus compensation parameter set to obtain a second detection focus distribution list; performing data acquisition based on the image acquisition device and the temperature acquisition device through the second detection focus distribution list to obtain a first image set and a first temperature acquisition set; performing factory sampling test of direct-plug LED lamp beads based on the first image set and the first temperature acquisition set to obtain a first sampling result; and performing factory warning of direct-plug LED lamp beads based on the first sampling result, the technical effect of combining the production characteristics of direct-plug LED lamp beads, performing intelligent and targeted factory sampling, saving quality inspection workload, and improving quality inspection accuracy is achieved.
[0013] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] Figure 1 This is a flow chart of a factory quality inspection method for direct-plug LED lamp beads in this application;
[0015] Figure 2 A schematic diagram of a flow chart for determining the first sampling inspection parameter of a factory quality inspection method for direct-plug LED lamp beads in this application;
[0016] Figure 3 A schematic diagram of the process of image matching and recognition for a factory quality inspection method of direct-plug LED lamp beads in this application;
[0017] Figure 4A flowchart of constructing an abnormal feature recognition list for a factory quality inspection method of a plug-in LED lamp bead in this application;
[0018] Figure 5 This is a schematic diagram of the structure of a factory quality inspection system for direct-plug LED lamp beads in this application;
[0019] Figure 6 This is a structural schematic diagram of an electronic device of the present application.
[0020] Explanation of the reference numerals: first obtaining unit 11 , second obtaining unit 12 , third obtaining unit 13 , fourth obtaining unit 14 , fifth obtaining unit 15 , first early warning unit 16 , electronic device 50 , processor 51 , memory 52 , input device 53 , output device 54 . DETAILED DESCRIPTION
[0021] This application solves the technical problem that the prior art cannot accurately perform factory quality inspection according to the production characteristics of direct-plug LED lamp beads during the factory quality inspection of direct-plug LED lamp beads by providing a factory quality inspection method and system for direct-plug LED lamp beads, thereby achieving the technical effect of combining the production characteristics of direct-plug LED lamp beads to conduct intelligent and targeted factory sampling inspections, saving quality inspection workload, and improving quality inspection accuracy. The embodiments of this application are described below in conjunction with the accompanying drawings. It is known to those skilled in the art that with the development of technology and the emergence of new scenarios, the technical solutions provided by this application are also applicable to similar technical problems.
[0022] The terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchanged under appropriate circumstances. This is merely a way of distinguishing objects with the same properties when describing the embodiments of the present application. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, so that a process, method, system, product, or device that includes a series of units is not necessarily limited to those units, but may include other units that are not explicitly listed or inherent to these processes, methods, products, or devices.
[0023] Application Overview
[0024] In the process of manufacturing LED lamp beads, in order to ensure product quality, it is necessary to conduct factory inspection of the products. However, in the prior art, there is a technical problem that accurate factory inspection cannot be conducted according to the production characteristics of direct-plug LED lamp beads during the factory inspection.
[0025] In response to the above technical problems, the overall idea of the technical solution provided by this application is as follows:
[0026] The present application provides a factory quality inspection method for direct-plug LED lamp beads, the method is applied to an intelligent factory quality inspection system, the intelligent factory quality inspection system is communicatively connected with an image acquisition device and a temperature acquisition device, the method comprises: obtaining first historical detection statistical information, wherein the first historical detection statistical information is historical production statistical information of a first company; obtaining second historical detection statistical information, wherein the second historical detection statistical information is historical production statistical information of a second company, and obtaining a first detection focus distribution list according to the first historical detection statistical information and the second historical detection statistical information; obtaining a first focus compensation parameter set according to quality inspection product impact information, and modifying the first detection focus distribution list based on the first focus compensation parameter set to obtain a second detection focus distribution list; performing data acquisition based on the image acquisition device and the temperature acquisition device through the second detection focus distribution list to obtain a first image set and a first temperature acquisition set; performing a factory random inspection test of the direct-plug LED lamp beads based on the first image set and the first temperature acquisition set to obtain a first random inspection result; and performing a factory warning of the direct-plug LED lamp beads according to the first random inspection result.
[0027] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically described below in conjunction with the drawings in the specification.
[0028] Embodiment 1
[0029] like Figure 1 As shown, the present application provides a factory quality inspection method for direct-plug LED lamp beads, the method is applied to an intelligent factory quality inspection system, the intelligent factory quality inspection system is communicatively connected with an image acquisition device and a temperature acquisition device, and the method includes:
[0030] Step S100: obtaining first historical detection statistical information, wherein the first historical detection statistical information is historical production statistical information of a first company;
[0031] Step S200: obtaining second historical detection statistical information, wherein the second historical detection statistical information is historical production statistical information of the second company, and obtaining a first detection focus distribution list according to the first historical detection statistical information and the second historical detection statistical information;
[0032] Specifically, the intelligent factory quality inspection system is a system that focuses on sampling inspection in combination with the production inspection characteristics of the product. The image acquisition device is an electronic device that can perform high-definition image sampling of the product, generally a CCD camera. The temperature acquisition device is a device for temperature acquisition and monitoring of direct-plug LED lamp beads, with a built-in temperature sensor, which can perform real-time temperature acquisition. The intelligent factory quality inspection system is connected to the image acquisition device and the temperature acquisition device in communication, and can exchange information with each other. The first company is the current production company of direct-plug LED lamp beads, that is, the target company for intelligent factory inspection, and the second company is other companies excluding the first company. With the permission of the first company's cooperative customers, combined with the first company's historical inspection records, the first historical inspection statistical information is obtained, and the first historical inspection statistical information includes the problem points, problem quantity, problem ratio of the products sampled by the first company during the historical factory inspection, and the quality problems reported by the cooperative company after being sent to the cooperative company. The first historical inspection statistical information reflects the focus of the first company's production inspection. The second historical detection statistical information is statistical information on the quality inspection results of LED lamp beads produced by companies that produce direct-plug LED lamp beads, excluding the first company, with the permission of other companies to publish. The second historical detection statistical information reflects the common quality characteristics of production inspection of direct-plug LED lamp beads. The distribution of emphasis of inspection items for quality inspection sampling is based on the first historical detection statistical information and the second historical detection statistical information. For example, the detection features of the non-emphasis list have a first sampling quantity for detection, and the detection items in the emphasis list are determined according to the processing sampling ratio plus the emphasis ratio according to different emphasis ratios. The first detection emphasis distribution list is determined, so that the factory random inspection is more targeted at LED lamp bead production inspection, and the detection results are more accurate.
[0033] Step S300: obtaining a first emphasis compensation parameter set according to the quality inspection product impact information, and modifying the first detection emphasis distribution list based on the first emphasis compensation parameter set to obtain a second detection emphasis distribution list;
[0034] Specifically, the quality inspection product information is information on the characteristic quantity distribution of quality problems in the production quality inspection of the direct-plug LED lamp beads by the first company during the production process. The quality inspection product impact information is obtained by calling the production records of the first company in the production of direct-plug LED lamp beads. According to the frequency of occurrence of each quality feature of the quality inspection product impact information, combined with the influence coefficient of the quality feature itself on the product, the first emphasis compensation parameter set is obtained, and the first detection emphasis distribution list is corrected based on the first emphasis compensation parameter set, and the second detection emphasis distribution list is obtained according to the correction result. By obtaining the first emphasis compensation parameter set, the quality of the direct-plug LED lamp beads produced by the first company is further deeply analyzed, so that the obtained second detection emphasis distribution list is more in line with the product, and thus the technical effect of more comprehensive and accurate detection of factory products can be achieved with less detection resources.
[0035] Step S400: performing data acquisition based on the image acquisition device and the temperature acquisition device through the second detection focus distribution list to obtain a first image set and a first temperature acquisition set;
[0036] Step S500: performing a factory sampling test of the plug-in LED lamp beads based on the first image set and the first temperature collection set to obtain a first sampling test result;
[0037] Specifically, according to the second detection focus distribution list, the image acquisition device and the temperature acquisition device are controlled by the intelligent factory quality inspection system to perform sampling and acquisition of factory products. The first image set and the first temperature set are obtained by performing corresponding image acquisition and temperature acquisition on the sampled samples.
[0038] Furthermore, in the process of sampling samples based on the second detection emphasis distribution list, it is necessary to analyze the factory quantity and factory batch of the current factory products before determining the number of samples. When the proportion of factory batches in the factory samples is higher than the proportion of factory quantity, the number of samples for factory delivery is determined according to the sampling standard of factory batches; when the proportion of factory quantity in the factory samples is higher than the proportion of factory batches, the number of samples for factory delivery is determined according to the sampling standard of factory quantity. After determining the basic sample sampling number according to the factory quantity, the sample detection expansion is performed based on the second detection emphasis distribution list, and the detection items are allocated according to the expansion results. Based on the item allocation results, the image acquisition device and the temperature acquisition device are used to perform corresponding quality detection data acquisition to obtain the first image set and the first temperature acquisition set, and the corresponding item image feature analysis is performed according to the first image set to obtain the image quality sampling result; the first temperature set is subjected to temperature analysis to obtain the temperature test result. The first sampling result is obtained according to the test result.
[0039] Step S600: issuing a factory warning for the direct-plug LED lamp beads according to the first random inspection result.
[0040] Specifically, according to the quality sampling results in the first sampling inspection, a factory warning is issued for the products leaving the factory. For example, when there are no samples with abnormal quality in the factory sampling samples, but a characteristic parameter of multiple sampling samples is close to the abnormal value, it is necessary to issue a warning for re-sampling and testing of the corresponding characteristics. When there are samples with abnormal quality in the factory sampling samples, it is necessary to locate the batch of the products and issue a warning for comprehensive quality testing of the products in the same batch. Through the detection and warning of the samples, the production characteristics of the direct-plug LED lamp beads are combined to achieve intelligent and targeted factory sampling, saving the workload of quality inspection and improving the accuracy of quality inspection.
[0041] Furthermore, if Figure 2 As shown, step S400 of the present application also includes:
[0042] Step S410: Obtaining first quantity information of factory-produced direct-plug LED lamp beads;
[0043] Step S420: Obtaining the first production batch information through the production parameters of the direct-insertion LED lamp beads;
[0044] Step S430: determining a first sample sampling constraint parameter according to the first quantity information and the first production batch information;
[0045] Step S440: obtaining first sampling parameters based on the first sample sampling constraint parameters and the second detection emphasis distribution list;
[0046] Step S450: obtaining the first image set and the first temperature acquisition set based on the first sampling parameter.
[0047] Specifically, the first quantity information is the quantity information of the current products shipped by the first company. When the first company ships the products, the intelligent factory quality inspection system is used to obtain the product information shipped. The product information includes the product number, the batch of the product, and the total amount of the product. The first quantity information and the first production batch information are obtained through the intelligent factory quality inspection system. According to the sample quantity sampling constraint rule, the sample sampling quantity information is obtained according to the first quantity information; the batch sample sampling quantity distribution information is obtained according to the batch sample sampling standard of the same batch of samples under the production batch. The first sample sampling constraint parameter is determined according to the sampling quantity information and the batch sample sampling quantity distribution information, and the actual sample sampling parameters are redistributed based on the first sample sampling constraint parameter and the second detection focus distribution list to obtain the first sampling parameter. After the sample is selected according to the first sampling parameter, the corresponding data is collected by the image acquisition device and the temperature acquisition device to obtain the first image set and the first temperature acquisition set.
[0048] Furthermore, if Figure 3 As shown, step S500 of the present application also includes:
[0049] Step S510: obtaining a first sampled product according to the first sampling parameter;
[0050] Step S520: acquiring multi-angle images of the first sampled product by the image acquisition device to obtain the first image set;
[0051] Step S530: constructing an abnormal feature recognition list of direct-plug LED lamp beads;
[0052] Step S540: performing feature matching and recognition on the first image set based on the abnormal feature recognition list to obtain a first matching and recognition result;
[0053] Step S550: Obtain the first sampling result through the first matching recognition result.
[0054] Specifically, the product is sampled according to the first sampling parameter to obtain the first sampled product, and the first sampled product has multiple items to be tested. The abnormal feature recognition list includes multiple features, for example, including: bubble features, stain features, poor appearance features, burr features, poor pin length features, etc. The abnormal feature recognition list is constructed according to the above features. The image acquisition device is used to capture the image of the first sampled product, and the image acquisition is multi-angle image acquisition, and the images of the multi-angle image acquisition have position identification features that are mutually associated. The abnormal feature recognition list is used to match the abnormal features of the first image set, and the sampling test of the first sampled product is completed according to the matching degree information and the matched abnormal feature information. After the feature matching of the corresponding assigned features is performed on all the sampled products of the factory products, the first sampling result is obtained according to the matching result. Through the multi-angle image acquisition of the image acquisition device, feature recognition is performed on the image acquisition result, so that the sampling inspection of the product is more intelligent and automated, so as to achieve intelligent product sampling inspection, and thus achieve the technical effect of improving the accuracy and efficiency of the factory inspection of the product.
[0055] Further, such as Figure 4 As shown, step 530 of the present application also includes:
[0056] Step S531: Collect bubble images of the direct-insertion LED lamp beads through big data to obtain a first collection result;
[0057] Step S532: performing artificial bubble level identification on the first collection result to obtain a first identification result;
[0058] Step S533: collecting the sealing glue pictures of the direct-insertion LED lamp beads through big data to obtain a second collection result;
[0059] Step S534: performing manual sealing grade identification on the second collection result to obtain a second identification result;
[0060] Step S535: construct the abnormal feature recognition list through the first identification result and the second identification result.
[0061] Specifically, in the process of constructing the abnormal feature identification list, it is necessary to collect and identify abnormal features as comprehensively as possible to ensure the accuracy, reliability and comprehensiveness of the abnormal feature identification list. Data collection is carried out through the data that is allowed to circulate, and the bubble picture set and the sealing glue picture set of the direct-plug LED lamp beads are obtained. The collected images are graded with the assistance of intelligent devices and dominated by manual identification. The first identification result and the second identification result are obtained according to the identification results. The first identification result is the result of the bubble grade identification of the first collection result, and the second identification result is the result of the sealing glue grade identification of the second collection result. By constructing the recognition image features of multiple features, multiple features are graded and identified, so that the features in the image recognition process are richer, and the feature recognition and matching of the image can be made more accurate, so as to achieve the technical effect of improving the accuracy of factory quality inspection.
[0062] Furthermore, the feature matching and identification of the first image set based on the abnormal feature identification list, step S540 of the present application also includes:
[0063] Step S541: performing feature matching and recognition on the first image set based on the abnormal feature recognition list to obtain a first matching degree list of first matching features;
[0064] Step S542: sorting the first matching degree list in order to obtain a first sorting result;
[0065] Step S543: performing an association analysis of adjacent matching degrees on the first matching degree in the first sorting result to obtain a first association analysis result;
[0066] Step S544: performing matching degree distribution of the first sorting result based on the first association analysis result, and obtaining a first matching identification result according to the matching degree distribution result.
[0067] Specifically, when the image features are matched through the abnormal feature recognition list, the intelligent factory quality inspection system performs feature matching based on the abnormal feature recognition list according to the detection features selected by the predetermined sample. For example, when the feature matching is performed, the first bubble feature is matched, and the sample determines that there is a feature of abnormal bubble quality inspection. According to the multiple bubbles in the abnormal feature recognition list, the bubbles of the sample are compared according to type and size, and the features of the existing bubbles are sorted in order according to the similarity with the bubbles of the sample according to the matching degree to obtain the first sorting result.
[0068] Further, each matching bubble feature in the first sorting result is further analyzed. First, the bubble level corresponding to the feature with the highest matching degree and its adjacent matching degree (second matching degree) in the first sorting result is extracted, and the first matching degree and the second matching degree are subjected to correlation analysis, wherein the correlation analysis is to determine whether the matching degree difference between the first matching degree and the second matching degree meets the expected threshold value. When the difference between the first matching degree and the second matching degree does not meet the expected threshold value, it indicates that the matching of the second matching degree is not within the expected analysis range. At this time, the first matching recognition result is calculated only based on the first matching degree and the bubble level feature corresponding to the first matching degree; when the difference between the first matching degree and the second matching degree meets the expected threshold value, it indicates that the first matching degree and the second matching degree need to be further analyzed at the same time. At this time, the third matching degree is obtained according to the first sorting result, and it is determined whether the matching results of the second matching degree and the third matching degree meet the expected threshold value. When it does not meet the threshold value, the matching degree is allocated through the first matching degree, the second matching degree, and the feature levels corresponding to the first matching degree and the second matching degree, and the first matching recognition result is obtained based on the allocation result. By conducting a detailed analysis of the correlation between the matching degree, the matching analysis results of the features can be made more accurate, thereby laying a solid foundation for obtaining more accurate factory quality inspection results and providing data support.
[0069] Furthermore, step S544 of the present application also includes:
[0070] Step S5441: obtaining a first matching degree associated with a preset threshold;
[0071] Step S5442: determining whether the first matching degree and the second matching degree satisfy a preset threshold associated with the first matching degree, wherein the second matching degree is an adjacent matching degree of the first matching degree in the first sorting result;
[0072] Step S5443: When the first matching degree and the second matching degree satisfy a preset threshold associated with the first matching degree, the first matching recognition result is obtained based on the first matching degree and the second matching degree and corresponding matching features.
[0073] Specifically, the first matching degree association preset threshold is a condition for determining the correlation between matching degrees. In the first sorting result, the matching degrees are sorted from high to low, namely, the first matching degree, the second matching degree, the third matching degree, etc. First, the first matching degree and the second matching degree are determined according to the first matching degree association preset threshold. When the correlation between the first matching degree and the second matching degree does not meet the first matching degree association preset threshold, the judgment is not continued, and the first matching recognition result is determined only according to the feature level and matching degree corresponding to the first matching degree. When the correlation between the first matching degree and the second matching degree meets the first matching degree association preset threshold, it is necessary to continue to determine the correlation between the second matching degree and the third matching degree, and so on, until it is determined that the matching degree does not meet the first matching degree association preset threshold or meets the expected number. The first matching recognition result is obtained according to the matching degree that meets the first matching degree association preset threshold and the corresponding feature level of the match. By performing a detailed analysis of the matching degree, the final matching recognition result obtained is made more intelligent and accurate, thereby achieving the technical effect of improving the accuracy of the early warning of the factory quality inspection.
[0074] Furthermore, step S400 of the present application also includes:
[0075] Step S460: obtaining a first temperature control parameter;
[0076] Step S470: Perform a sampling direct-insertion LED lamp bead test using the first temperature control parameter, collect data using the temperature collection device, and obtain the first temperature collection set.
[0077] Specifically, the first temperature control parameter is a temperature control parameter for reliability testing, which includes parameters of specific ambient temperature, power-on time control parameters, power-on power control parameters, sampling point location parameters, etc. The test environment is set by the first temperature control parameter. After the setting is completed, data is collected by the temperature collection device at the distributed test location, and the first temperature collection set is obtained according to the collection result. Based on the first temperature collection set, a temperature sampling warning is performed before the direct-plug LED lamp beads are shipped out of the factory.
[0078] In summary, the factory quality inspection method and system for direct-plug LED lamp beads provided by this application have the following technical effects:
[0079] 1. The method adopts the method of obtaining the first historical detection statistical information, wherein the first historical detection statistical information is the historical production statistical information of the first company; obtaining the second historical detection statistical information, wherein the second historical detection statistical information is the historical production statistical information of the second company, and performing detection focus distribution of the problems of the company and the common problems of other companies according to the first historical detection statistical information and the second historical detection statistical information, and obtaining a first detection focus distribution list; obtaining a first focus compensation parameter set according to the quality inspection product impact information, and correcting the first detection focus distribution list based on the first focus compensation parameter set to obtain a second detection focus distribution list; performing data acquisition based on the image acquisition device and the temperature acquisition device through the second detection focus distribution list to obtain a first image set and a first temperature acquisition set; performing factory sampling test of direct-plug LED lamp beads based on the first image set and the first temperature acquisition set to obtain a first sampling result; and performing factory warning of direct-plug LED lamp beads according to the first sampling result, so as to achieve the technical effect of combining the production characteristics of direct-plug LED lamp beads, performing intelligent and targeted factory sampling, saving quality inspection workload, and improving quality inspection accuracy.
[0080] 2. Due to the use of multi-angle image acquisition through the image acquisition device and the feature recognition method of the image acquisition results, the random inspection of products is made more intelligent and automated, so as to achieve the technical effect of intelligent product random inspection and thus improve the accuracy and efficiency of product factory inspection.
[0081] 3. By constructing multiple features to identify image features and classifying multiple features, the features in the image recognition process are enriched, and the feature recognition and matching of the image can be made more accurate, achieving the technical effect of improving the accuracy of factory quality inspection.
[0082] 4. Due to the adoption of a method of detailed analysis of the correlation between the matching degree, the matching analysis results of the features are more accurate, which lays a solid foundation for obtaining more accurate factory quality inspection results and provides data support.
[0083] 5. Due to the adoption of a method of detailed analysis of the matching degree, the final matching recognition result is made more intelligent and accurate, thereby achieving the technical effect of improving the accuracy of the early warning of factory quality inspection.
[0084] Embodiment 2
[0085] Based on the same inventive concept as the factory quality inspection method for direct-insertion LED lamp beads in the aforementioned embodiment, the present invention also provides a factory quality inspection system for direct-insertion LED lamp beads, such as Figure 5 As shown, the system comprises:
[0086] A first obtaining unit 11, wherein the first obtaining unit 11 is used to obtain first historical detection statistical information, wherein the first historical detection statistical information is historical production statistical information of the first company;
[0087] A second obtaining unit 12, wherein the second obtaining unit 12 is used to obtain second historical detection statistical information, wherein the second historical detection statistical information is historical production statistical information of the second company, and obtain a first detection focus distribution list according to the first historical detection statistical information and the second historical detection statistical information;
[0088] A third obtaining unit 13, the third obtaining unit 13 is used to obtain a first emphasis compensation parameter set according to the quality inspection product impact information, and to modify the first detection emphasis distribution list based on the first emphasis compensation parameter set to obtain a second detection emphasis distribution list;
[0089] A fourth obtaining unit 14, the fourth obtaining unit 14 is used to perform data acquisition based on the image acquisition device and the temperature acquisition device through the second detection focus distribution list to obtain a first image set and a first temperature acquisition set;
[0090] A fifth obtaining unit 15, wherein the fifth obtaining unit 15 is used to perform a factory sampling test of the direct-plug LED lamp beads based on the first image set and the first temperature acquisition set to obtain a first sampling result;
[0091] The first early warning unit 16 is used for issuing a factory early warning for the direct-plug LED lamp beads according to the first sampling inspection result.
[0092] Furthermore, the system also includes:
[0093] A sixth obtaining unit, the sixth obtaining unit being used to obtain first quantity information of factory-produced direct-plug LED lamp beads;
[0094] A seventh obtaining unit, the seventh obtaining unit being used to obtain first production batch information through production parameters of direct-insertion LED lamp beads;
[0095] A first determining unit, the first determining unit being used to determine a first sample sampling constraint parameter according to the first quantity information and the first production batch information;
[0096] an eighth obtaining unit, the eighth obtaining unit being configured to obtain a first sampling parameter based on the first sample sampling constraint parameter and the second detection emphasis distribution list;
[0097] A ninth obtaining unit, the ninth obtaining unit is used to obtain the first image set and the first temperature acquisition set based on the first sampling parameter.
[0098] Furthermore, the system also includes:
[0099] a tenth obtaining unit, the tenth obtaining unit being configured to obtain a first sampled product according to the first sampling parameter;
[0100] an eleventh obtaining unit, the eleventh obtaining unit being configured to obtain the first image set by performing multi-angle image acquisition of the first sampled product through the image acquisition device;
[0101] A first construction unit, the first construction unit is used to construct an abnormal feature recognition list of direct-plug LED lamp beads;
[0102] a twelfth obtaining unit, the twelfth obtaining unit being used to perform feature matching and recognition on the first image set based on the abnormal feature recognition list to obtain a first matching and recognition result;
[0103] A thirteenth obtaining unit, the thirteenth obtaining unit is used to obtain the first sampling result through the first matching recognition result.
[0104] Furthermore, the system also includes:
[0105] A fourteenth obtaining unit, the fourteenth obtaining unit is used to collect bubble images of the direct-insertion LED lamp beads through big data to obtain a first collection result;
[0106] a fifteenth obtaining unit, the fifteenth obtaining unit being used to perform artificial bubble level identification on the first collection result to obtain a first identification result;
[0107] A sixteenth obtaining unit, the sixteenth obtaining unit is used to collect the sealing glue pictures of the direct-insertion LED lamp beads through big data to obtain a second collection result;
[0108] a seventeenth obtaining unit, the seventeenth obtaining unit being used to perform an artificial sealing grade identification on the second collection result to obtain a second identification result;
[0109] A second construction unit, wherein the second construction unit is used to construct the abnormal feature recognition list through the first identification result and the second identification result.
[0110] Furthermore, the system also includes:
[0111] An eighteenth obtaining unit, the eighteenth obtaining unit being used to perform feature matching and identification on the first image set based on the abnormal feature identification list to obtain a first matching degree list of first matching features;
[0112] a nineteenth obtaining unit, the nineteenth obtaining unit being used to sequentially sort the first matching degree list to obtain a first sorting result;
[0113] a twentieth obtaining unit, configured to perform an association analysis of adjacent matching degrees on the first matching degree in the first sorting result to obtain a first association analysis result;
[0114] A twenty-first obtaining unit is used to distribute the matching degree of the first sorting result based on the first association analysis result, and obtain a first matching recognition result according to the matching degree distribution result.
[0115] Furthermore, the system also includes:
[0116] A twenty-second obtaining unit, the twenty-second obtaining unit is used to obtain a first matching degree associated with a preset threshold;
[0117] A first judgment unit, the first judgment unit is used to judge whether the first matching degree and the second matching degree meet a preset threshold associated with the first matching degree, wherein the second matching degree is an adjacent matching degree of the first matching degree in the first sorting result;
[0118] The twenty-third obtaining unit is used to obtain the first matching recognition result based on the first matching degree and the second matching degree and corresponding matching features when the first matching degree and the second matching degree meet a preset threshold associated with the first matching degree.
[0119] Furthermore, the system also includes:
[0120] A twenty-fourth obtaining unit, the twenty-fourth obtaining unit is used to obtain a first temperature control parameter;
[0121] The twenty-fifth obtaining unit is used to perform a sampling direct-insertion LED lamp bead test through the first temperature control parameter, collect data through the temperature collection device, and obtain the first temperature collection set.
[0122] The foregoing Figure 1 The various variations and specific examples of the factory quality inspection method for direct-plug LED lamp beads in Example 1 are also applicable to the factory quality inspection system for direct-plug LED lamp beads in this embodiment. Through the above detailed description of the factory quality inspection method for direct-plug LED lamp beads, technical personnel in this field can clearly know the implementation method of the factory quality inspection system for direct-plug LED lamp beads in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.
[0123] Exemplary Electronic Devices
[0124] Reference below Figure 6 To describe the electronic device of the present application.
[0125] Figure 6 The figure shows a schematic structural diagram of an electronic device according to the present application.
[0126] Based on the inventive concept of a factory quality inspection method for a direct-insertion LED lamp bead in the aforementioned embodiment, the present invention further provides an electronic device, as shown below. Figure 6 The electronic device according to the present application is described as follows. The electronic device may be the mobile device itself, or a stand-alone device independent of the mobile device, on which a computer program is stored, and when the program is executed by a processor, the steps of any of the methods described above are implemented.
[0127] like Figure 6 As shown, the electronic device 50 includes one or more processors 51 and a memory 52 .
[0128] The processor 51 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 50 to perform desired functions.
[0129] The memory 52 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The non-volatile memory may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 51 may execute the program instructions to implement the methods of the various embodiments of the present application described above and / or other desired functions.
[0130] In one example, the electronic device 50 may further include: an input device 53 and an output device 54, and these components are interconnected via a bus system and / or other forms of connection mechanisms (not shown).
[0131] An embodiment of the present invention provides a factory quality inspection method for direct-plug LED lamp beads, the method is applied to an intelligent factory quality inspection system, the intelligent factory quality inspection system is communicatively connected with an image acquisition device and a temperature acquisition device, the method includes: obtaining first historical detection statistical information, wherein the first historical detection statistical information is the historical production statistical information of a first company; obtaining second historical detection statistical information, wherein the second historical detection statistical information is the historical production statistical information of a second company, and obtaining a first detection focus distribution list according to the first historical detection statistical information and the second historical detection statistical information; obtaining a first focus compensation parameter set according to quality inspection product impact information, and modifying the first detection focus distribution list based on the first focus compensation parameter set to obtain a second detection focus distribution list; performing data acquisition based on the image acquisition device and the temperature acquisition device through the second detection focus distribution list to obtain a first image set and a first temperature acquisition set; performing a factory random inspection test of the direct-plug LED lamp beads based on the first image set and the first temperature acquisition set to obtain a first random inspection result; and performing a factory warning of the direct-plug LED lamp beads according to the first random inspection result. The invention solves the technical problem that the prior art cannot perform accurate factory quality inspection according to the production characteristics of direct-plug LED lamp beads during factory quality inspection of direct-plug LED lamp beads, and achieves the technical effect of combining the production characteristics of direct-plug LED lamp beads to perform intelligent and targeted factory sampling inspection, saving quality inspection workload and improving quality inspection accuracy.
[0132] Through the description of the above implementation methods, the technicians in the relevant field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented with corresponding hardware, and the specific hardware structures used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation method in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, U disk, mobile hard disk, ROM, RAM, disk or optical disk, etc., including a number of instructions to enable a computer device to execute the methods described in each embodiment of the present application.
[0133] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.
[0134] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from a computer-readable storage medium to another computer-readable storage medium, and the available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.
[0135] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present application, the size of the sequence number of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the present application.
[0136] In addition, the terms "system" and "network" are often used interchangeably in this article. The term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.
[0137] It should be understood that in this application, "B corresponding to A" means that B is associated with A, and B can be determined based on A. However, it should also be understood that determining B based on A does not mean determining B only based on A, but B can also be determined based on A and / or other information.
[0138] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0139] In short, the above is only a preferred embodiment of the technical solution of this application, and is not intended to limit the protection scope of this application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application should be included in the protection scope of this application.
Claims
1. A factory quality inspection method for direct-insertion LED lamp beads, characterized in that: The method is applied to an intelligent factory quality inspection system, wherein the intelligent factory quality inspection system is communicatively connected with an image acquisition device and a temperature acquisition device, and the method comprises: Obtaining first historical inspection statistical information, wherein the first historical inspection statistical information is historical production statistical information of the first company, and the first historical inspection statistical information includes problem points, problem quantity, and problem ratio of products sampled by the first company during historical factory inspections, and quality problems reported by the cooperative company after the products were sent to the cooperative company, and the first historical inspection statistical information reflects the focus of the first company's production inspection; Obtaining second historical detection statistical information, wherein the second historical detection statistical information is historical production statistical information of the second company, and the second historical detection statistical information reflects the common quality characteristics of production detection of direct-plug LED lamp beads, and obtaining a first detection focus distribution list according to the first historical detection statistical information and the second historical detection statistical information; Obtain a first set of emphasis compensation parameters according to the quality inspection product impact information, and modify the first detection focus distribution list based on the first set of emphasis compensation parameters to obtain a second detection focus distribution list, wherein the quality inspection product impact information is information on the characteristic quantity distribution of quality problems in the production quality inspection of the first company during the manufacturing process of the direct-plug LED lamp beads; obtain the first set of emphasis compensation parameters according to the frequency of occurrence of each quality feature of the quality inspection product impact information and the influence coefficient of the quality feature itself on the product; Acquire data based on the image acquisition device and the temperature acquisition device through the second detection focus distribution list to obtain a first image set and a first temperature acquisition set; Perform a factory random inspection test on the plug-in LED lamp beads based on the first image set and the first temperature collection set to obtain a first random inspection result; According to the first sampling inspection results, a factory warning of the direct-plug LED lamp beads is issued; Wherein, the method further comprises: Get the first quantity information of factory-made direct-plug LED lamp beads; Obtain the first production batch information through the production parameters of the direct-insertion LED lamp beads; Determine a first sample sampling constraint parameter according to the first quantity information and the first production batch information; Obtaining first sampling parameters based on the first sample sampling constraint parameters and the second detection focus distribution list; Obtaining the first image set and the first temperature acquisition set based on the first sampling parameter; Wherein, the method further comprises: Obtaining a first sampled product according to the first sampling parameter; Capturing multi-angle images of the first sampled product by the image acquisition device to obtain the first image set; Construct an abnormal feature recognition list for direct-plug LED lamp beads; Perform feature matching and recognition on the first image set based on the abnormal feature recognition list to obtain a first matching and recognition result; Obtaining the first sampling result through the first matching recognition result; Wherein, the method further comprises: The bubble images of the plug-in LED lamp beads are collected through big data to obtain the first collection result; Performing artificial bubble level marking on the first collection result to obtain a first marking result; The sealing glue pictures of the plug-in LED lamp beads are collected through big data to obtain the second collection result; Performing an artificial sealing grade marking on the second collection result to obtain a second marking result; Constructing the abnormal feature recognition list through the first identification result and the second identification result; The performing feature matching and recognition on the first image set based on the abnormal feature recognition list further includes: Perform feature matching and recognition on the first image set based on the abnormal feature recognition list to obtain a first matching degree list of first matching features; The first matching degree list is sequentially sorted to obtain a first sorting result, and in the first sorting result, the matching degrees are sorted in descending order; Performing an association analysis of adjacent matching degrees on the first matching degree in the first sorting result to obtain a first association analysis result; Based on the first association analysis result, a matching degree distribution is performed on the first sorting result, and a first matching identification result is obtained according to the matching degree distribution result; The step of allocating the matching degree of the first sorting result based on the first association analysis result and obtaining the first matching recognition result according to the matching degree allocation result includes: Obtaining a first matching degree associated with a preset threshold; Determining whether the association between the first matching degree and the second matching degree satisfies a preset threshold for the association with the first matching degree, wherein the second matching degree is an adjacent matching degree of the first matching degree in the first sorting result; When the correlation between the first matching degree and the second matching degree does not satisfy the preset threshold value of the first matching degree correlation, the judgment is not continued, and the first matching recognition result is determined only according to the feature level and matching degree corresponding to the first matching degree; When the association between the first matching degree and the second matching degree meets the preset threshold of the first matching degree association, it is necessary to continue to determine the association between the second matching degree and the third matching degree, and so on, until it is determined that the matching degree does not meet the preset threshold of the first matching degree association. The first matching identification result is obtained based on the matching degree that meets the preset threshold of the first matching degree association and the corresponding feature level of the match.
2. The method according to claim 1, characterized in that The method further comprises: obtaining a first temperature control parameter; A sampling direct-insertion LED lamp bead test is performed using the first temperature control parameter, and data is collected using the temperature collection device to obtain the first temperature collection set.
3. A factory quality inspection system for direct-insertion LED lamp beads, characterized in that: For executing the method according to any one of claims 1 to 2, the system comprises: A first obtaining unit, the first obtaining unit is used to obtain first historical detection statistical information, wherein the first historical detection statistical information is historical production statistical information of the first company; A second obtaining unit, wherein the second obtaining unit is used to obtain second historical detection statistical information, wherein the second historical detection statistical information is historical production statistical information of the second company, and obtain a first detection focus distribution list according to the first historical detection statistical information and the second historical detection statistical information; a third obtaining unit, the third obtaining unit being used to obtain a first emphasis compensation parameter set according to the quality inspection product impact information, and to modify the first detection emphasis distribution list based on the first emphasis compensation parameter set to obtain a second detection emphasis distribution list; a fourth obtaining unit, configured to obtain a first image set and a first temperature collection set by performing data collection based on an image collection device and a temperature collection device according to the second detection focus distribution list; A fifth obtaining unit, the fifth obtaining unit is used to perform a factory sampling test of the direct-plug LED lamp beads based on the first image set and the first temperature collection set to obtain a first sampling result; The first early warning unit is used to issue a factory early warning for the direct-plug LED lamp beads according to the first sampling inspection result.
4. An electronic device, characterized in that: The method comprises a processor and a memory; the memory is used for storing; and the processor is used for executing the method according to any one of claims 1 to 2 by calling.
5. A computer program product comprising a computer program and / or instructions, characterized in that: When the computer program and / or the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 2 are implemented.
Citation Information
Patent Citations
Wafer test method and system based on tube core parameter display
CN115032493A
LED packaging body detection device
CN217120932U
Process management system and operation method thereof
KR1020030016042A
