Photovoltaic glass detection method, device, equipment and product

Abstract

The invention provides a photovoltaic glass detection method, device, equipment and product, and the method comprises the steps: obtaining the detection information of to-be-detected photovoltaic glass, and the detection information comprises a dimension specification and a detection parameter; obtaining standard parameters corresponding to the photovoltaic glass to be detected according to the dimension specification; and comparing the standard parameters with the detection parameters to obtain a detection result. According to the photovoltaic glass detection method provided by the embodiment of the invention, the standard parameter obtained according to the dimension specification of the photovoltaic glass to be detected is compared with the detection parameter of the photovoltaic glass to be detected, and the detection result is obtained, so that the misjudgment caused by manual input errors when an automatic defective product identification method with a manual preset standard is used is avoided, and the detection efficiency is improved. And a large number of defective products are generated.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic glass detection, and in particular to a photovoltaic glass detection method, device, equipment and product. Background Art

[0002] In the production process of photovoltaic glass panels, in order to ensure the qualification rate of the final product, the photovoltaic glass panels must be strictly inspected for quality. The current technical means is to use photovoltaic glass panel inspection equipment to perform dynamic visual inspections on the various surfaces of photovoltaic glass panels. However, given the high degree of automation of the production line and the large production batches, the visual inspection in the existing technology has problems such as missed inspections and false inspections, and when problems are found, defective products cannot be removed in time and need to be marked and removed from the next process.

[0003] The current detection method, combined with manually preset inspection standard parameters, can initially realize the identification function of defective products, but its application has limitations. The specifications of glass produced on the production line are different every day, which leads to changes in the corresponding inspection standards. Although automatic identification can be achieved through manually preset standards, it will greatly increase the production line changeover time and labor costs. In addition, if there are manual input errors, it may still lead to misjudgment, resulting in a large number of defective products. Summary of the invention

[0004] The purpose of the present invention is to provide a method for automatically identifying defective products with manually preset standards in the prior art, which is used to solve the problem that manual input errors may lead to misjudgment and thus produce a large number of defective products.

[0005] To achieve the above object, an embodiment of the present invention provides a photovoltaic glass detection method, which includes:

[0006] Acquire detection information of the photovoltaic glass to be detected, wherein the detection information includes size specifications and detection parameters;

[0007] Acquire standard parameters corresponding to the photovoltaic glass to be tested according to the size specifications;

[0008] The standard parameters are compared with the detection parameters to obtain the detection results.

[0009] Optionally, the method further comprises:

[0010] When the test result is unqualified, an unqualified signal is sent to a gripping device, wherein the unqualified signal is used by the gripping device to grip and discharge the photovoltaic glass to be tested as an unqualified product; and / or, when the test result is qualified, a qualified test report corresponding to the photovoltaic glass to be tested is obtained.

[0011] Optionally, in the method, wherein the detection information further includes a detection picture of the photovoltaic glass to be detected, the method further includes:

[0012] In the case where the detection result is unqualified, unqualified information is output; wherein the unqualified information includes a marked image on the detection image in which points where the detection parameters are different from the standard parameters are marked.

[0013] Optionally, in the method, the step of obtaining the detection information of the photovoltaic glass to be detected comprises:

[0014] Acquire the detection information sent by the data acquisition gateway; wherein the size specification is acquired by an automatic identification device connected to the data acquisition gateway, and the detection parameter is acquired by an optical detection device connected to the data acquisition gateway.

[0015] Optionally, in the method, the step of obtaining standard parameters corresponding to the photovoltaic glass to be tested according to the size specification includes:

[0016] The size specification is input into the quality inspection model to obtain the standard parameters corresponding to the size specification; wherein the quality inspection model is obtained by training a learning model based on multiple inspection parameters of multiple photovoltaic glasses corresponding to at least one size specification.

[0017] Optionally, in the method, the detection parameter includes at least one of the following:

[0018] bow bend;

[0019] Wave bend;

[0020] Reflectance value;

[0021] Aperture;

[0022] Hole spacing;

[0023] Light transmittance;

[0024] Reflectance value.

[0025] Optionally, the method, wherein the size specification includes at least one of the following:

[0026] length;

[0027] width;

[0028] thickness;

[0029] Roughness.

[0030] In order to achieve the above-mentioned object, an embodiment of the present invention further provides a photovoltaic glass detection device, which includes:

[0031] A first acquisition module is used to acquire detection information of the photovoltaic glass to be detected, wherein the detection information includes size specifications and detection parameters;

[0032] A second acquisition module is used to acquire standard parameters corresponding to the photovoltaic glass to be tested according to the size specifications;

[0033] The third acquisition module is used to compare the standard parameter with the detection parameter to obtain the detection result.

[0034] In order to achieve the above-mentioned purpose, an embodiment of the present invention also provides an electronic device, including: a processor, a memory, and a program or instruction stored in the memory and executable on the processor; wherein, when the processor executes the program or instruction, the photovoltaic glass detection method as described above is implemented.

[0035] In order to achieve the above-mentioned purpose, an embodiment of the present invention further provides a readable storage medium on which a program or instruction is stored, wherein the program or instruction, when executed by a processor, implements the steps in the photovoltaic glass detection method as described above.

[0036] In order to achieve the above-mentioned purpose, an embodiment of the present invention further provides a computer program product, which includes computer instructions, and when the computer instructions are executed by a processor, the steps of the photovoltaic glass detection method as described above are implemented.

[0037] The beneficial effects of the above technical solution of the present invention are as follows:

[0038] The photovoltaic glass detection method of the embodiment of the present invention is to compare the standard parameters obtained according to the size specifications of the photovoltaic glass to be detected with the detection parameters of the photovoltaic glass to be detected to obtain the detection results, thereby avoiding the problem of misjudgment and generation of a large number of defective products due to manual input errors when using an automatic defective product identification method with manually preset standards. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A schematic diagram of a photovoltaic glass detection method according to an embodiment of the present invention;

[0040] Figure 2 This is a flow chart of a photovoltaic glass detection method according to an embodiment of the present invention;

[0041] Figure 3 This is a schematic diagram of the effect of the photovoltaic glass detection method according to an embodiment of the present invention;

[0042] Figure 4 It is a schematic diagram of a detection device for photovoltaic glass according to an embodiment of the present invention. DETAILED DESCRIPTION

[0043] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0044] It should be understood that the references to "one embodiment" or "an embodiment" throughout the specification mean that the specific features, structures, or characteristics associated with the embodiment are included in at least one embodiment of the present invention. Therefore, the references to "in one embodiment" or "in an embodiment" appearing throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0045] In various embodiments of the present invention, it should be understood that the size of the serial numbers of the following 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 embodiments of the present invention.

[0046] Additionally, the terms "system" and "network" are often used interchangeably herein.

[0047] In the embodiments provided in the present application, it should be understood that "B corresponding to A" means that B is associated with A, and B can be determined according to A. However, it should also be understood that determining B according to A does not mean determining B only according to A, and B can also be determined according to A and / or other information.

[0048] For ease of understanding, some contents involved in the embodiments of the present invention are described below:

[0049] like Figure 1 As shown, a photovoltaic glass detection method according to an embodiment of the present invention includes:

[0050] S10, obtaining detection information of the photovoltaic glass to be detected, wherein the detection information includes size specifications and detection parameters;

[0051] S20, obtaining standard parameters corresponding to the photovoltaic glass to be tested according to the size specifications;

[0052] S30, comparing the standard parameter with the detection parameter to obtain a detection result.

[0053] In this embodiment, the standard parameters obtained according to the size specifications of the photovoltaic glass to be inspected are compared with the detection parameters of the photovoltaic glass to be inspected to obtain the detection result, so that the identified size specifications can be automatically matched with the corresponding standard parameters, thereby avoiding the problem of misjudgment and generation of a large number of defective products due to manual input errors when using the automatic defective product identification method with manually preset standards.

[0054] Optionally, the method further comprises:

[0055] When the test result is unqualified, an unqualified signal is sent to a gripping device, wherein the unqualified signal is used by the gripping device to grip and discharge the photovoltaic glass to be tested as an unqualified product; and / or, when the test result is qualified, a qualified test report corresponding to the photovoltaic glass to be tested is obtained.

[0056] In this embodiment, if Figure 2 As shown, an example is now provided. After the test result is recorded in the service area, if the test result is unqualified, it is necessary to send the unqualified signal to the gripping device, so that the suction cup gripping device can accurately grasp the corresponding photovoltaic glass to be tested and discharge it as an unqualified product, that is, Figure 2 If the test result is qualified, the online test report will be displayed on the billboard. Figure 3 The data summary chart shown in the figure enables customers to grasp the product quality status in real time and adjust production plans and quality control strategies in a timely manner. Alternatively, print out a paper version of the test report to put it in the packaging of photovoltaic glass to achieve quality traceability. Finally, the data of qualified and unqualified products are comprehensively analyzed for subsequent quantity improvement work. By analyzing the causes of defective products, targeted improvement measures are formulated to reduce the generation of defective products and improve the overall quality level of products.

[0057] Optionally, in the method, wherein the detection information further includes a detection picture of the photovoltaic glass to be detected, the method further includes:

[0058] In the case where the detection result is unqualified, unqualified information is output; wherein the unqualified information includes a marked image on the detection image in which points where the detection parameters are different from the standard parameters are marked.

[0059] In this embodiment, when the test result is unqualified, the points where the test parameters are different from the standard parameters are marked on the test picture included in the test information, indicating that Figure 2 The "reason for defect" shown in the figure, and the "type of defect" obtained by classifying different points are displayed on the annotated picture.

[0060] Optionally, in the method, step S10 includes:

[0061] Acquire the detection information sent by the data acquisition gateway; wherein the size specification is acquired by an automatic identification device connected to the data acquisition gateway, and the detection parameter is acquired by an optical detection device connected to the data acquisition gateway.

[0062] In this embodiment, Figure 2 In the example shown, the optical inspection device obtains the inspection parameters and image (i.e., the inspection image) of the photovoltaic glass to be inspected, and the automatic identification device obtains the size specifications of the photovoltaic glass to be inspected, which are sent to the data server as actual inspection parameters through the data acquisition gateway. The data server includes the quality inspection model formed by continuous iteration and optimization of the machine learning model, which can directly give whether the inspection result is qualified based on the glass model and real-time inspection parameters known through the size specifications.

[0063] Optionally, in the method, step S20 includes:

[0064] The size specification is input into the quality inspection model to obtain the standard parameters corresponding to the size specification; wherein the quality inspection model is obtained by training a learning model based on multiple inspection parameters of multiple photovoltaic glasses corresponding to at least one size specification.

[0065] In this embodiment, the quality inspection model can obtain the glass model through the size specifications, thereby obtaining the corresponding standard parameters, comparing the inspection parameters with the standard parameters, and directly giving whether the inspection result is qualified. Figure 2 As shown, on the data server, a machine learning model is built, and the Sklearn algorithm library of Python is used to select the Bayesian machine learning algorithm model, and the data of multiple detection parameters of multiple photovoltaic glasses of at least one size specification are imported for periodic training. The data for training in this stage is to collect the size specifications, detection parameters and detection pictures of photovoltaic glass in advance by manual judgment for use in machine learning. The photovoltaic glass used in the model training stage is produced before the photovoltaic glass to be detected. After training, the training results are output as ROC curves to evaluate the performance of the algorithm model and the accuracy of the results. In the subsequent production process, the actual detection parameters of automatic identification are continuously input, and Spark is used for model iterative calculation, and the algorithm model is continuously optimized to improve its accuracy and efficiency, and the quality detection model is formed through iterative optimization. And in the use of the quality detection model, if various changes occur on the production line, including the replacement of raw materials, the adjustment of process parameters, etc., the stability and reliability of the detection results can be ensured through the continuous iteration and optimization of the machine learning model. This not only improves the detection efficiency and reduces labor costs, but also improves the intelligence level of the entire production line, laying a solid foundation for the digital transformation of enterprises.

[0066] Optionally, in the method, the detection parameter includes at least one of the following:

[0067] bow bend;

[0068] Wave bend;

[0069] Reflectance value;

[0070] Aperture;

[0071] Hole spacing;

[0072] Light transmittance;

[0073] Reflectance value.

[0074] In this embodiment, if Figure 3 As shown, taking the bow bend as an example, when the detection parameters include the bow bend, the corresponding bow bend data is displayed on the billboard when the detection result is qualified. Figure 3 The values ​​of bow-length 1 and bow-length 2 of multiple products from 7:35:34 to 7:43:34 are displayed, as well as the maximum and minimum values ​​of the standard parameters. In actual applications, other test parameters are also displayed so that customers can grasp the product quality status in real time and adjust production plans and quality control strategies in a timely manner.

[0075] Optionally, the method, wherein the size specification includes at least one of the following:

[0076] length;

[0077] width;

[0078] thickness;

[0079] Roughness.

[0080] In this embodiment, the automatic identification device identifies the size specifications including length, width, thickness and roughness, thereby determining the model of the photovoltaic glass and matching the corresponding standard parameters.

[0081] Among them, the training logic of the quality detection model is as follows:

[0082] #Assume that there is already a dataset

[0083] data=...#load dataset

[0084] X = data.drop('label',axis = 1) #Feature data

[0085] y=data['label']#label data

[0086] # Divide into training set and test set

[0087] X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=42)

[0088] #Use Sklearn's Bayesian algorithm model

[0089] model = GaussianNB()

[0090] model.fit(X_train,y_train)

[0091] #Predicted probability

[0092] y_scores=model.predict_proba(X_test)

[0093] #Calculate ROC curve

[0094] fpr,tpr,thresholds=roc_curve(y_test,y_scores[:,1])

[0095] roc_auc=auc(fpr,tpr)

[0096] #Draw the ROC curve

[0097] plt.figure()

[0098] plt.plot(fpr,tpr,color='darkorange',lw=2,label='ROC curve(area=%0.2f)'%roc_auc)

[0099] plt.plot([0,1],[0,1],color='navy',lw=2,linestyle='--')

[0100] plt.xlim([0.0,1.0])

[0101] plt.ylim([0.0,1.05])

[0102] plt.xlabel('False Positive Rate')

[0103] plt.ylabel('True Positive Rate')

[0104] plt.title('Receiver Operating Characteristic')

[0105] plt.legend(loc="lower right")

[0106] plt.show()

[0107] #Spark environment initialization

[0108] spark=SparkSession.builder.appName("GlassQualityCheck").getOrCreate()

[0109] #Convert the data into a Spark DataFrame

[0110] spark_data=spark.createDataFrame(data)

[0111] #Create a Bayesian model for Spark ML

[0112] nb=NaiveBayes(smoothing=1.0,modelType="multinomial")

[0113] #Create Pipeline

[0114] pipeline=Pipeline(stages=[nb])

[0115] #Train model

[0116] model_spark=pipeline.fit(spark_data)

[0117] #Continue to introduce actual workshop inspection data for model iterative calculation

[0118] #Assume that new_data is the newly collected data

[0119] new_data=...

[0120] new_spark_data=spark.createDataFrame(new_data)

[0121] # Update the model with new data

[0122] model_spark=model_spark.fit(new_spark_data)

[0123] #Use the model to make predictions

[0124] predictions=model_spark.transform(new_spark_data)

[0125] #Output the type of failure and the reason for failure

[0126] predictions.filter(predictions['prediction']==0).select('glass_type','defect_reason').show()

[0127] #The logic of sending signals to the back-channel suction cup grabbing device depends on the specific hardware interface and communication protocol and needs to be written according to the actual situation.

[0128] like Figure 4 As shown, in order to achieve the above-mentioned purpose, an embodiment of the present invention further provides a photovoltaic glass detection device, which includes:

[0129] A first acquisition module 401 is used to acquire detection information of the photovoltaic glass to be detected, wherein the detection information includes size specifications and detection parameters;

[0130] A second acquisition module 402 is used to acquire standard parameters corresponding to the photovoltaic glass to be tested according to the size specifications;

[0131] The third acquisition module 403 is used to compare the standard parameter with the detection parameter to obtain the detection result.

[0132] Optionally, the device further comprises:

[0133] A first sending module is used to send an unqualified signal to a gripping device when the test result is unqualified, wherein the unqualified signal is used by the gripping device to grip and discharge the photovoltaic glass to be tested as an unqualified product; and / or a fourth acquisition module is used to obtain a qualified test report corresponding to the photovoltaic glass to be tested when the test result is qualified.

[0134] Optionally, in the device, the detection information further includes a detection picture of the photovoltaic glass to be detected, and the device further includes:

[0135] The first output module is used to output unqualified information when the detection result is unqualified; wherein the unqualified information includes a marked image on the detection image in which points where the detection parameters are different from the standard parameters are marked.

[0136] Optionally, in the device, the first acquisition module 401 includes:

[0137] The first acquisition unit is used to acquire the detection information sent by the data acquisition gateway; wherein the size specification is acquired by an automatic recognition device connected to the data acquisition gateway, and the detection parameter is acquired by an optical detection device connected to the data acquisition gateway.

[0138] Optionally, in the device, the second obtaining module 402 includes:

[0139] The second acquisition unit is used to input the size specification into the quality inspection model to obtain the standard parameters corresponding to the size specification; wherein the quality inspection model is obtained by training a learning model based on multiple inspection parameters of multiple photovoltaic glasses corresponding to at least one size specification.

[0140] Optionally, in the device, the detection parameter includes at least one of the following:

[0141] bow bend;

[0142] Wave bend;

[0143] Reflectance value;

[0144] Aperture;

[0145] Hole spacing;

[0146] Light transmittance;

[0147] Reflectance value.

[0148] Optionally, the device, wherein the size specification includes at least one of the following:

[0149] length;

[0150] width;

[0151] thickness;

[0152] Roughness.

[0153] It should be noted here that the above-mentioned device provided in the embodiment of the present invention can implement all the method steps implemented in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects that are the same as the method embodiment in this embodiment will not be described in detail here.

[0154] In order to achieve the above-mentioned purpose, an embodiment of the present invention also provides an electronic device, including: a processor, a memory, and a program or instruction stored in the memory and executable on the processor; wherein, when the processor executes the program or instruction, the photovoltaic glass detection method as described above is implemented.

[0155] In order to achieve the above-mentioned purpose, an embodiment of the present invention further provides a readable storage medium on which a program or instruction is stored, wherein the program or instruction, when executed by a processor, implements the steps in the photovoltaic glass detection method as described above and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0156] It should be further explained that the terminals described in this specification include but are not limited to smart phones, tablet computers, etc., and many of the functional components described are called modules in order to more particularly emphasize the independence of their implementation methods.

[0157] In the embodiment of the present invention, module can be implemented with software so that it can be executed by various types of processors. For example, an executable code module of an identification can include one or more physical or logical blocks of computer instructions, for example, it can be constructed as an object, process or function. Nevertheless, the executable code of the identified module does not need to be physically located together, but can include different instructions stored in different positions, and when these instructions are logically combined together, it constitutes a module and realizes the specified purpose of the module.

[0158] In fact, executable code module can be a single instruction or many instructions, and can even be distributed on a plurality of different code segments, distributed among different programs, and distributed across a plurality of memory devices. Similarly, operating data can be identified in the module, and can be implemented and organized in the data structure of any appropriate type according to any appropriate form. The operating data can be collected as a single data set, or can be distributed in different locations (including on different storage devices), and can only be present on a system or network as an electronic signal at least in part.

[0159] When a module can be implemented by software, considering the level of existing hardware technology, a person skilled in the art can build a corresponding hardware circuit to implement the corresponding function of the module that can be implemented by software without considering the cost. The hardware circuit includes a conventional very large scale integration (VLSI) circuit or gate array and existing semiconductors such as logic chips, transistors, or other discrete components. The module can also be implemented by a programmable hardware device, such as a field programmable gate array, a programmable array logic, a programmable logic device, etc.

[0160] In order to achieve the above-mentioned purpose, an embodiment of the present invention further provides a computer program product, which includes computer instructions, and when the computer instructions are executed by a processor, the steps of the photovoltaic glass detection method as described above are implemented.

[0161] The above exemplary embodiments are described with reference to the accompanying drawings, and many different forms and embodiments are feasible without departing from the spirit and teachings of the present invention. Therefore, the present invention should not be constructed as a limitation of the exemplary embodiments proposed herein. More specifically, these exemplary embodiments are provided so that the present invention will be perfect and complete, and the scope of the present invention will be conveyed to those who are familiar with the technology. In these figures, the component sizes and relative sizes may be exaggerated for clarity. The terms used here are only based on the purpose of describing specific exemplary embodiments and are not intended to be limiting. As used herein, unless the text clearly indicates otherwise, the singular forms "one", "an" and "the" are intended to include these multiple forms. It will be further understood that the terms "including" and / or "comprising" when used in this specification indicate the presence of the features, integers, steps, operations, components and / or components, but do not exclude the presence or increase of one or more other features, integers, steps, operations, components, components and / or their groups. Unless otherwise indicated, when stated, a range of values ​​includes the upper and lower limits of that range and any subranges therebetween.

[0162] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for detecting photovoltaic glass, characterized in that: include: Acquire detection information of the photovoltaic glass to be detected, wherein the detection information includes size specifications and detection parameters; Acquire standard parameters corresponding to the photovoltaic glass to be tested according to the size specifications; The standard parameters are compared with the detection parameters to obtain the detection results.

2. The method according to claim 1, characterized in that The method further comprises: When the test result is unqualified, an unqualified signal is sent to a gripping device, wherein the unqualified signal is used by the gripping device to grip and discharge the photovoltaic glass to be tested as an unqualified product; and / or, when the test result is qualified, a qualified test report corresponding to the photovoltaic glass to be tested is obtained.

3. The method according to claim 1, characterized in that The detection information also includes a detection picture of the photovoltaic glass to be detected, and the method further includes: In the case where the detection result is unqualified, unqualified information is output; wherein the unqualified information includes a marked image on the detection image in which points where the detection parameters are different from the standard parameters are marked.

4. The method according to claim 1, characterized in that: The step of obtaining the detection information of the photovoltaic glass to be detected includes: Acquire the detection information sent by the data acquisition gateway; wherein the size specification is acquired by an automatic identification device connected to the data acquisition gateway, and the detection parameter is acquired by an optical detection device connected to the data acquisition gateway.

5. The method according to claim 1, characterized in that The step of obtaining standard parameters corresponding to the photovoltaic glass to be tested according to the size specifications includes: The size specification is input into the quality inspection model to obtain the standard parameters corresponding to the size specification; wherein the quality inspection model is obtained by training a learning model based on multiple inspection parameters of multiple photovoltaic glasses corresponding to at least one size specification.

6. The method according to claim 1, characterized in that The detection parameters include at least one of the following: bow bend; Wave bend; Reflectance value; Aperture; Hole spacing; Light transmittance; Reflectance value.

7. The method according to claim 1, characterized in that The size specifications include at least one of the following: length; width; thickness; Roughness.

8. A photovoltaic glass detection device, characterized in that: include: A first acquisition module is used to acquire detection information of the photovoltaic glass to be detected, wherein the detection information includes size specifications and detection parameters; A second acquisition module is used to acquire standard parameters corresponding to the photovoltaic glass to be tested according to the size specifications; The third acquisition module is used to compare the standard parameter with the detection parameter to obtain the detection result.

9. An electronic device, comprising: A processor, a memory, and a program or instruction stored in the memory and executable on the processor; characterized in that when the processor executes the program or instruction, the photovoltaic glass detection method as described in any one of claims 1 to 7 is implemented.

10. A readable storage medium having a program or instruction stored thereon, characterized in that: When the program or instruction is executed by the processor, the steps in the photovoltaic glass detection method as described in any one of claims 1 to 7 are implemented.

11. A computer program product, characterized in that The method comprises computer instructions, which, when executed by a processor, implement the steps of the photovoltaic glass detection method as described in any one of claims 1 to 7.

Images