Visual detection method for burrs of automobile injection molded part

Abstract

The invention relates to the technical field of quality detection of injection molded parts, in particular to a visual detection method for burrs of an automobile injection molded part, which is used for analyzing the production state of an injection molding machine during injection molding and the quality of an automobile injection molded part finished product. According to the analysis result, constructing an automobile injection molded part finished product quality prediction model; importing production parameter data during injection molding of an injection molding machine in the current automobile injection molding part production process into the automobile injection molding part finished product quality prediction model to obtain a current automobile injection molding part finished product quality prediction result; and according to the current finished product quality prediction result of the automobile injection molding part, early warning is carried out on the production process when an injection molding machine carries out injection molding in the current production process of the automobile injection molding part. And the production process can be continuously optimized, so that the consistency of product quality is improved, and the production cost is reduced. And through real-time feedback and dynamic analysis of production parameters, different production conditions can be flexibly adapted, and the adaptability and flexibility of production are enhanced.

Description

Technical Field

[0001] The invention relates to the technical field of injection molded part quality inspection, and in particular to a visual inspection method for burrs of automobile injection molded parts. Background Art

[0002] In the automotive manufacturing industry, the burr problem of injection molded parts is an important quality control indicator. Burrs refer to unwanted flakes formed when the material overflows the mold joint during the injection molding process, which may affect the appearance, performance and assembly accuracy of the product. Given the high quality requirements of automotive injection molded parts, how to effectively identify and control burrs has become a challenge that cannot be ignored in the manufacturing process.

[0003] Traditional burr detection methods mainly rely on manual visual inspection. However, this method is not only time-consuming and dependent on the experience of the inspector, but also susceptible to subjective factors, resulting in insufficient consistency and accuracy. Especially in large-scale production, the low efficiency of manual inspection and the human errors that may be introduced are significant bottlenecks. With the development of computer vision technology, automated inspection has gradually been applied to the quality control of injection molded parts. Although the existing burr detection technology has made up for the shortcomings of manual inspection to a certain extent, it also has some shortcomings, such as not considering the influence of the production process and operating conditions of the injection molding machine. These influencing factors include injection temperature, injection pressure, and dry cycle time, which have a direct or indirect effect on the formation of burrs. Ignoring these factors may lead to unstable detection results of burr visual inspection under different process conditions. In addition, current burr detection technologies often lack sufficient flexibility and adaptability when dealing with highly dynamic and complex production environments. These systems are usually based on static, predefined models, have limited responsiveness to process changes, and are difficult to adjust and optimize detection parameters in real time. Therefore, when faced with different batches of production or slight changes in equipment, their detection effect may be significantly reduced.

[0004] In order to solve these problems, the present application designs a visual detection method for burrs of automotive injection molded parts. Summary of the invention

[0005] In order to overcome the defects and shortcomings of the prior art, the present invention provides a visual inspection method for burrs of automotive injection molded parts. By using historical production parameter data and burr visual inspection data, combined with an analysis model, the production status of the injection molding machine and the quality of the finished product are comprehensively analyzed to construct a quality prediction model. The present invention enables continuous optimization of the production process, thereby improving the consistency of product quality and reducing production costs. Through real-time feedback and dynamic analysis of production parameters, it can flexibly adapt to different production conditions and enhance the adaptability and flexibility of production.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, an embodiment of the present invention provides a method for visually inspecting burrs of automotive injection molded parts, comprising the following steps:

[0008] S1. Obtain historical production parameter data of an injection molding machine during injection molding, and obtain historical burr visual inspection data of finished automobile injection molded parts obtained by injection molding of the injection molding machine;

[0009] S2. Importing historical production parameter data into the production status analysis model of the injection molding machine to analyze the production status of the injection molding machine during injection molding;

[0010] S3, importing historical burr visual inspection data into the finished product quality analysis model of automobile injection molded parts to analyze the finished product quality of automobile injection molded parts;

[0011] S4. According to the analysis results of the production status of the injection molded parts during injection molding and the analysis results of the finished product quality of the automobile injection molded parts, a finished product quality prediction model for automobile injection molded parts is constructed; and the production parameter data of the injection molding machine during the injection molding process of the current automobile injection molded parts production process is imported into the finished product quality prediction model for automobile injection molded parts to obtain the current finished product quality prediction results for automobile injection molded parts;

[0012] S5. Based on the current automobile injection molded parts finished product quality prediction results, an early warning is issued for the production process when the injection molding machine is performing injection molding during the current automobile injection molded parts production process.

[0013] In an optional implementation, step S2 includes the following specific steps:

[0014] S21, extracting historical production parameter data of the injection molding machine during the production process of multiple automobile injection molded parts;

[0015] S22, substituting the historical production parameter data into the production parameter variation coefficient calculation formula to calculate the production parameter variation coefficient when the injection molding machine performs injection molding during the production process of the i-th automobile injection molded product in history; the production parameter variation coefficient calculation formula is:

[0016]

[0017] Wherein, SCi is the production parameter abnormality coefficient of the injection molding machine during the production process of the i-th automobile injection molding finished product in history, Ti is the set injection temperature of the injection molding machine during the production process of the i-th automobile injection molding finished product in history in the historical production parameter data, ti is the set injection time of the injection molding machine during the production process of the i-th automobile injection molding finished product in history in the historical production parameter data, tci is the idle cycle time of the injection molding machine used in the production process of the i-th automobile injection molding finished product in history in the historical production parameter data, Pi is the set injection pressure of the injection molding machine during the production process of the i-th automobile injection molding finished product in history in the historical production parameter data, Vi is the injection volume of the injection molding machine during the production process of the i-th automobile injection molding finished product in history in the historical production parameter data, T represents the average set injection temperature of the injection molding machine during the production process of all automobile injection molding finished products in history in the historical production parameter data, They respectively represent the maximum and minimum values ​​of the ratio of the injection time to the idle cycle time set when the injection molding machine performs injection molding in the production process of all the finished automobile injection molded parts in the history of the historical production parameter data, n is the number of finished automobile injection molded parts in the history of the historical production parameter data, and i is any one of 1 to n.

[0018] In an optional implementation manner, step S3 includes the following specific contents:

[0019] S31, extracting historical burr visual inspection data of multiple finished automobile injection molded parts obtained by injection molding by an injection molding machine, wherein the historical burr visual inspection data is obtained by performing image processing on burr inspection images of multiple finished automobile injection molded parts in history using image processing software;

[0020] S32, substituting the historical burr visual inspection data into the automobile injection molded parts finished product quality coefficient calculation formula to calculate the automobile injection molded parts finished product quality coefficient of the i-th automobile injection molded parts finished product obtained by injection molding in history by the injection molding machine; the automobile injection molded parts finished product quality coefficient calculation formula is:

[0021]

[0022] Where, CZi represents the quality coefficient of the finished automobile injection molded part of the i-th automobile injection molded part in history obtained by injection molding by an injection molding machine, Ai represents the number of burr areas in the burr detection image of the i-th automobile injection molded part in history in the historical burr visual inspection data, Si represents the total number of pixels in all burr areas in the burr detection image of the i-th automobile injection molded part in history in the historical burr visual inspection data, σ i It represents the standard deviation of the pixel values ​​of all pixels in the burr area of ​​the i-th automobile injection molded part burr inspection image in the historical burr visual inspection data.

[0023] In an optional embodiment, the construction of the automotive injection molded parts finished product quality prediction model in step S4 includes the following specific contents:

[0024] The finished automobile injection molded parts sample data for training the finished automobile injection molded parts quality prediction model are obtained, wherein the finished automobile injection molded parts sample data include the calculated production parameter abnormality coefficients when the injection molding machine performs injection molding during the production process of multiple finished automobile injection molded parts in history and the finished automobile injection molded parts quality coefficients of multiple finished automobile injection molded parts in history obtained by injection molding by the injection molding machine. The finished automobile injection molded parts sample data for training the finished automobile injection molded parts quality prediction model are divided into a finished automobile injection molded parts sample training set and a finished automobile injection molded parts sample test set, a regression network model is constructed, the production parameter abnormality coefficients when the injection molding machine performs injection molding during the production process of multiple finished automobile injection molded parts in history in the finished automobile injection molded parts sample training set are used as the input of the regression network model, the finished automobile injection molded parts quality coefficients of multiple finished automobile injection molded parts in history obtained by injection molding by the injection molding machine in the finished automobile injection molded parts sample training set are used as the output of the regression network model, the regression network model is trained to obtain an initial regression network model; the initial regression network model is evaluated for model effect by using an average error algorithm, and the corresponding initial regression network model with a value greater than or equal to a preset evaluation value is selected as the finished automobile injection molded parts quality prediction model.

[0025] In an optional implementation manner, step S4 also includes the following specific contents:

[0026] S41, obtaining production parameter data of the injection molding machine during the current automobile injection molding production process;

[0027] S42, substituting the production parameter data of the injection molding machine during the current automobile injection molding production process into the production parameter variation coefficient calculation formula to calculate the production parameter variation coefficient of the injection molding machine during the current automobile injection molding production process;

[0028] S43, importing the calculated production parameter variation coefficient of the injection molding machine during the current automobile injection molding part production process into the automobile injection molding part finished product quality prediction model, and outputting the predicted automobile injection molding part finished product quality coefficient of the current automobile injection molding part finished product.

[0029] In an optional implementation manner, step S5 includes the following specific contents:

[0030] A finished automobile injection molded part quality threshold is preset. When the predicted finished automobile injection molded part quality coefficient of the current finished automobile injection molded part is greater than or equal to the finished automobile injection molded part quality threshold, the production of the current automobile injection molded part continues; when the predicted finished automobile injection molded part quality coefficient of the current finished automobile injection molded part is less than the finished automobile injection molded part quality threshold, an early warning is issued for the production process of the injection molding machine during injection molding in the current automobile injection molded part production process.

[0031] In a second aspect, an embodiment of the present invention provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a visual detection method for burrs of automotive injection molded parts by calling the computer program stored in the memory.

[0032] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium storing instructions, which, when executed on a computer, enables the computer to execute a method for visually inspecting burrs of automotive injection molded parts.

[0033] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0034] The present invention analyzes the production status of an injection molding machine when performing injection molding and the quality of finished automobile injection molding parts; and constructs a quality prediction model for finished automobile injection molding parts according to the analysis results; imports the production parameter data of the injection molding machine during the current automobile injection molding part production process into the quality prediction model for finished automobile injection molding parts to obtain the current quality prediction results for finished automobile injection molding parts; and according to the current quality prediction results for finished automobile injection molding parts, warns the production process of the injection molding machine during the current automobile injection molding part production process when performing injection molding. This allows the production process to be continuously optimized, thereby improving the consistency of product quality and reducing production costs. By providing real-time feedback and dynamically analyzing production parameters, it is possible to flexibly adapt to different production conditions and enhance the adaptability and flexibility of production. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0036] Figure 1 It is a schematic diagram of the overall process of a visual inspection method for burrs of automobile injection molded parts of the present invention;

[0037] Figure 2 A flowchart of constructing a finished product quality prediction model for automobile injection molded parts in a method for visually detecting burrs of automobile injection molded parts of the present invention;

[0038] Figure 3The present invention is a schematic diagram of the structure of an electronic device in a method for visually detecting burrs on automobile injection molded parts. DETAILED DESCRIPTION

[0039] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations on the technical solution of the present invention. The embodiments of the present invention and the technical features in the embodiments may be combined with each other unless there is a conflict.

[0040] Example 1

[0041] like Figure 1 As shown, this embodiment provides a visual detection method for burrs of automotive injection molded parts, which specifically includes the following steps:

[0042] S1. Obtain historical production parameter data of an injection molding machine during injection molding, and obtain historical burr visual inspection data of finished automobile injection molded parts obtained by injection molding of the injection molding machine;

[0043] S2. Importing historical production parameter data into the production status analysis model of the injection molding machine to analyze the production status of the injection molding machine during injection molding;

[0044] S3, importing historical burr visual inspection data into the finished product quality analysis model of automobile injection molded parts to analyze the finished product quality of automobile injection molded parts;

[0045] S4. According to the analysis results of the production status of the injection molded parts during injection molding and the analysis results of the finished product quality of the automobile injection molded parts, a finished product quality prediction model for automobile injection molded parts is constructed; and the production parameter data of the injection molding machine during the injection molding process of the current automobile injection molded parts production process is imported into the finished product quality prediction model for automobile injection molded parts to obtain the current finished product quality prediction results for automobile injection molded parts;

[0046] S5. Based on the current automobile injection molded parts finished product quality prediction results, an early warning is issued for the production process when the injection molding machine is performing injection molding during the current automobile injection molded parts production process.

[0047] In this embodiment, step S2 includes the following specific steps:

[0048] S21, extracting historical production parameter data of the injection molding machine during the production process of multiple automobile injection molded parts;

[0049] S22, substituting the historical production parameter data into the production parameter variation coefficient calculation formula to calculate the production parameter variation coefficient when the injection molding machine performs injection molding during the production process of the i-th automobile injection molded product in history; the production parameter variation coefficient calculation formula is:

[0050]

[0051] Wherein, SCi is the production parameter abnormality coefficient of the injection molding machine during the production process of the i-th automobile injection molding finished product in history, Ti is the set injection temperature of the injection molding machine during the production process of the i-th automobile injection molding finished product in history in the historical production parameter data, ti is the set injection time of the injection molding machine during the production process of the i-th automobile injection molding finished product in history in the historical production parameter data, tci is the idle cycle time of the injection molding machine used in the production process of the i-th automobile injection molding finished product in history in the historical production parameter data, Pi is the set injection pressure of the injection molding machine during the production process of the i-th automobile injection molding finished product in history in the historical production parameter data, Vi is the injection volume of the injection molding machine during the production process of the i-th automobile injection molding finished product in history in the historical production parameter data, T represents the average set injection temperature of the injection molding machine during the production process of all automobile injection molding finished products in history in the historical production parameter data, They respectively represent the maximum and minimum values ​​of the ratio of the injection time to the idle cycle time set when the injection molding machine performs injection molding in the production process of all the finished automobile injection molded parts in the history of the historical production parameter data, n is the number of finished automobile injection molded parts in the history of the historical production parameter data, and i is any one of 1 to n.

[0052] It should be noted that, in this embodiment, the change of the injection molding temperature set by the injection molding machine will directly affect the quality of the automobile injection molding parts, including dimensional accuracy and surface finish. By calculating the logarithmic deviation between the injection molding temperature set by the injection molding machine and the average injection molding temperature, the quality fluctuation of the automobile injection molding parts caused by temperature changes can be identified. In this embodiment, by using the logarithmic function It can compress relatively large temperature changes into a smaller range and is more sensitive to small changes, which helps to identify the subtle effects of temperature on product quality. In this embodiment, the idle cycle time of the injection molding machine not only affects the production efficiency, but also may reflect the stability of the equipment operation. The comparison between the injection time and the idle cycle time can intuitively show the stability of the system operation of the injection molding machine during the injection molding process. In this embodiment, the periodic characteristics of the cosine function are used to make the formula It is particularly suitable for capturing periodic deviations from the average value, thereby revealing whether the injection molding machine's operating rhythm is stable. It can also identify the impact of small fluctuations in time on the quality of the final automotive injection molded parts. Setting the ratio of injection pressure and injection volume directly affects the density and structure of automotive injection molded parts. Exponential function Reflects the nonlinear changes in the ratio of injection pressure to injection volume and its changes relative to the average value of all production. It can capture the complex effects of the interaction between pressure and injection volume on the quality of finished automotive injection molded parts. It can effectively reveal the extreme performance of setting the ratio of injection pressure to injection volume, thereby helping to detect quality defects caused by improper injection pressure and volume ratio. The use of exponential functions can identify complex nonlinear effects and help optimize injection molding process parameters to maintain consistency.

[0053] In this embodiment, step S3 includes the following specific contents:

[0054] S31, extracting historical burr visual inspection data of multiple finished automobile injection molded parts obtained by injection molding by an injection molding machine, wherein the historical burr visual inspection data is obtained by performing image processing on burr inspection images of multiple finished automobile injection molded parts in history using image processing software;

[0055] S32, substituting the historical burr visual inspection data into the automobile injection molded parts finished product quality coefficient calculation formula to calculate the automobile injection molded parts finished product quality coefficient of the i-th automobile injection molded parts finished product obtained by injection molding in history by the injection molding machine; the automobile injection molded parts finished product quality coefficient calculation formula is:

[0056]

[0057] Where, CZi represents the quality coefficient of the finished automobile injection molded part of the i-th automobile injection molded part in history obtained by injection molding by an injection molding machine, Ai represents the number of burr areas in the burr detection image of the i-th automobile injection molded part in history in the historical burr visual inspection data, Si represents the total number of pixels in all burr areas in the burr detection image of the i-th automobile injection molded part in history in the historical burr visual inspection data, σ i It represents the standard deviation of the pixel values ​​of all pixels in the burr area of ​​the i-th automobile injection molded part burr inspection image in the historical burr visual inspection data.

[0058] It should be noted that in this embodiment, the overall burr feature strength of a single injection molded part relative to the historical record is expressed by combining the burr area with the average pixel difference. The use of a logarithmic function can take into account the comprehensive changes brought about by the burr area and the burr texture. This embodiment uses the logarithmic function ln() to compress the large value range and amplify the changes in the small value range. This makes the calculation formula particularly sensitive to subtle but still important changes. Therefore, even if the burr area or pixel difference has only a small fluctuation, It can still be captured and reflected, and can be used to predict product quality changes caused by process changes. In this embodiment, the deviation of the burr area count is measured by a sine function, which can identify the periodic fluctuations in the number of injection molded parts. The sine function has periodic characteristics and can effectively capture the pattern of relative changes in the number of burrs. It can intuitively express the activity and variability of quantity changes within the cycle. For quality prediction, it can indicate the potential impact caused by the micro-imbalance of the mold or process. The calculation formula for the finished quality coefficient of automobile injection molded parts used in this embodiment can track the quality differences caused by changes in materials, molds or processes during the injection molding process in real time by detecting changes in areas, pixel differences and quantities. The processing of sensitive small-range changes in the calculation formula for the finished quality coefficient of automobile injection molded parts can effectively identify potential defects or inconsistencies in the production process of automobile injection molded parts in advance, help engineers discover and deal with problems early, reduce the rate of defective products, and thus ensure the stability and consistency of the finished product.

[0059] In this embodiment, the construction of the automotive injection molded parts finished product quality prediction model in step S4 includes the following specific contents:

[0060] like Figure 2 As shown, sample data of finished automobile injection molded parts for training a quality prediction model for finished automobile injection molded parts are obtained, wherein the sample data of finished automobile injection molded parts include calculated production parameter anomaly coefficients during the production of multiple finished automobile injection molded parts in history when an injection molding machine performs injection molding and finished automobile injection molded parts quality coefficients of multiple finished automobile injection molded parts in history obtained by injection molding by the injection molding machine, the sample data of finished automobile injection molded parts for training a quality prediction model for finished automobile injection molded parts are divided into a training set of finished automobile injection molded parts samples and a test set of finished automobile injection molded parts samples, a regression network model is constructed, and the finished automobile injection molded parts samples are trained. The abnormal coefficients of production parameters during the injection molding process of multiple automobile injection molded parts in the product sample training set are used as the input of the regression network model, and the quality coefficients of multiple automobile injection molded parts in the history obtained by injection molding machines in the automobile injection molded parts product sample training set are used as the output of the regression network model. The regression network model is trained to obtain an initial regression network model. The average error algorithm is used to evaluate the model effect of the initial regression network model, and the corresponding initial regression network model greater than or equal to the preset evaluation value is selected as the automobile injection molded parts product quality prediction model.

[0061] In this embodiment, step S4 also includes the following specific contents:

[0062] S41, obtaining production parameter data of the injection molding machine during the current automobile injection molding production process;

[0063] S42, substituting the production parameter data of the injection molding machine during the current automobile injection molding production process into the production parameter variation coefficient calculation formula to calculate the production parameter variation coefficient of the injection molding machine during the current automobile injection molding production process;

[0064] S43, importing the calculated production parameter variation coefficient of the injection molding machine during the current automobile injection molding part production process into the automobile injection molding part finished product quality prediction model, and outputting the predicted automobile injection molding part finished product quality coefficient of the current automobile injection molding part finished product.

[0065] In this embodiment, step S5 includes the following specific contents:

[0066] A finished automobile injection molded part quality threshold is preset. When the predicted finished automobile injection molded part quality coefficient of the current finished automobile injection molded part is greater than or equal to the finished automobile injection molded part quality threshold, the production of the current automobile injection molded part continues; when the predicted finished automobile injection molded part quality coefficient of the current finished automobile injection molded part is less than the finished automobile injection molded part quality threshold, an early warning is issued for the production process of the injection molding machine during injection molding in the current automobile injection molded part production process. It should be noted that the method for obtaining the value of the quality threshold of automobile injection molded parts is as follows: 5000 sets of production parameter data when the injection molding machine performs injection molding in the production process of automobile injection molded parts are obtained, and the production parameter data when the injection molding machine performs injection molding in the production process of automobile injection molded parts are imported into the production parameter variation coefficient calculation formula to calculate 5000 sets of production parameter variation coefficients when the injection molding machine performs injection molding in the production process of automobile injection molded parts, and the production parameter variation coefficients when the injection molding machine performs injection molding in the production process of automobile injection molded parts are imported into the automobile injection molded parts finished product quality prediction model to predict the automobile injection molded parts finished product quality coefficients of 5000 sets of automobile injection molded parts; 5000 sets of quality judgment results of automobile injection molded parts are obtained, and the automobile injection molded parts finished product quality coefficients and the quality judgment results of automobile injection molded parts are imported into the fitting software to output the value of the automobile injection molded parts finished product quality threshold that meets the highest automobile injection molded parts finished product quality judgment accuracy.

[0067] Example 2

[0068] like Figure 3 As shown, an electronic device according to an embodiment of the present invention includes: a processor and a memory, wherein the memory stores a computer program that can be called by the processor, and the processor executes a visual detection method for burrs of automotive injection molding parts by calling the computer program stored in the memory. It should be noted that all computer programs of the visual detection method for burrs of automotive injection molding parts are implemented using C language.

[0069] Example 3

[0070] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0071] When the computer program is run on a computer device, the computer device is enabled to execute the above-mentioned visual detection method for burrs of automobile injection molded parts.

[0072] Each embodiment of the present invention is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0073] The system and medium provided in the embodiments of the present invention correspond one-to-one to the method, and therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0074] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0075] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0076] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0077] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0078] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0079] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0080] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0081] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A visual inspection method for burrs of automotive injection molded parts, characterized in that: The steps include: S1. Obtain historical production parameter data of an injection molding machine during injection molding, and obtain historical burr visual inspection data of finished automobile injection molded parts obtained by injection molding of the injection molding machine; S2. Importing historical production parameter data into the production status analysis model of the injection molding machine to analyze the production status of the injection molding machine during injection molding; S3, importing historical burr visual inspection data into the finished product quality analysis model of automobile injection molded parts to analyze the finished product quality of automobile injection molded parts; S4. According to the analysis results of the production status of the injection molded parts during injection molding and the analysis results of the finished product quality of the automobile injection molded parts, a finished product quality prediction model for automobile injection molded parts is constructed; and the production parameter data of the injection molding machine during the injection molding process of the current automobile injection molded parts production process is imported into the finished product quality prediction model for automobile injection molded parts to obtain the current finished product quality prediction results for automobile injection molded parts; S5. Based on the current automobile injection molded parts finished product quality prediction results, an early warning is issued for the production process when the injection molding machine is performing injection molding during the current automobile injection molded parts production process.

2. A visual inspection method for burrs of automotive injection molded parts according to claim 1, characterized in that: The step S2 comprises the following specific steps: S21, extracting historical production parameter data of the injection molding machine during the production of multiple automotive injection molded parts in history; S22, substituting the historical production parameter data into the production parameter variation coefficient calculation formula to calculate the production parameter variation coefficient when the injection molding machine performs injection molding during the production process of the i-th automobile injection molded product in history; the production parameter variation coefficient calculation formula is: Wherein, SCi is the production parameter abnormality coefficient of the injection molding machine during the production process of the i-th automobile injection molding finished product in history, Ti is the set injection temperature of the injection molding machine during the production process of the i-th automobile injection molding finished product in history in the historical production parameter data, ti is the set injection time of the injection molding machine during the production process of the i-th automobile injection molding finished product in history in the historical production parameter data, tci is the idle cycle time of the injection molding machine used in the production process of the i-th automobile injection molding finished product in history in the historical production parameter data, Pi is the set injection pressure of the injection molding machine during the production process of the i-th automobile injection molding finished product in history in the historical production parameter data, Vi is the injection volume of the injection molding machine during the production process of the i-th automobile injection molding finished product in history in the historical production parameter data, T represents the average set injection temperature of the injection molding machine during the production process of all automobile injection molding finished products in history in the historical production parameter data, They respectively represent the maximum and minimum values ​​of the ratio of the injection time to the idle cycle time set when the injection molding machine performs injection molding in the production process of all the finished automobile injection molded parts in the history of the historical production parameter data, n is the number of finished automobile injection molded parts in the history of the historical production parameter data, and i is any one of 1 to n.

3. A visual inspection method for burrs of automotive injection molded parts according to claim 2, characterized in that: The step S3 includes the following specific contents: S31, extracting historical burr visual inspection data of multiple finished automobile injection molded parts obtained by injection molding by an injection molding machine, wherein the historical burr visual inspection data is obtained by performing image processing on burr inspection images of multiple finished automobile injection molded parts in history using image processing software; S32, substituting the historical burr visual inspection data into the automobile injection molded parts finished product quality coefficient calculation formula to calculate the automobile injection molded parts finished product quality coefficient of the i-th automobile injection molded parts finished product obtained by injection molding in history by the injection molding machine; the automobile injection molded parts finished product quality coefficient calculation formula is: Where, CZi represents the quality coefficient of the finished automobile injection molded part of the i-th automobile injection molded part in history obtained by injection molding by an injection molding machine, Ai represents the number of burr areas in the burr detection image of the i-th automobile injection molded part in history in the historical burr visual inspection data, Si represents the total number of pixels in all burr areas in the burr detection image of the i-th automobile injection molded part in history in the historical burr visual inspection data, σ i It represents the standard deviation of the pixel values ​​of all pixels in the burr area of ​​the i-th automobile injection molded part burr inspection image in the historical burr visual inspection data.

4. A visual inspection method for burrs of automotive injection molded parts according to claim 3, characterized in that: The step S4 of constructing the automotive injection molded parts finished product quality prediction model includes the following specific contents: The finished automobile injection molded parts sample data for training the finished automobile injection molded parts quality prediction model are obtained, wherein the finished automobile injection molded parts sample data include the calculated production parameter abnormality coefficients when the injection molding machine performs injection molding during the production process of multiple finished automobile injection molded parts in history and the finished automobile injection molded parts quality coefficients of multiple finished automobile injection molded parts in history obtained by injection molding by the injection molding machine. The finished automobile injection molded parts sample data for training the finished automobile injection molded parts quality prediction model are divided into a finished automobile injection molded parts sample training set and a finished automobile injection molded parts sample test set, a regression network model is constructed, the production parameter abnormality coefficients when the injection molding machine performs injection molding during the production process of multiple finished automobile injection molded parts in history in the finished automobile injection molded parts sample training set are used as the input of the regression network model, the finished automobile injection molded parts quality coefficients of multiple finished automobile injection molded parts in history obtained by injection molding by the injection molding machine in the finished automobile injection molded parts sample training set are used as the output of the regression network model, the regression network model is trained to obtain an initial regression network model; the initial regression network model is evaluated for model effect by using an average error algorithm, and the corresponding initial regression network model with a value greater than or equal to a preset evaluation value is selected as the finished automobile injection molded parts quality prediction model.

5. A visual inspection method for burrs of automotive injection molded parts according to claim 4, characterized in that: The step S4 also includes the following specific contents: S41, obtaining production parameter data of the injection molding machine during the current automobile injection molding production process; S42, substituting the production parameter data of the injection molding machine during the current automobile injection molding production process into the production parameter variation coefficient calculation formula to calculate the production parameter variation coefficient of the injection molding machine during the current automobile injection molding production process; S43, importing the calculated production parameter variation coefficient of the injection molding machine during the current automobile injection molding part production process into the automobile injection molding part finished product quality prediction model, and outputting the predicted automobile injection molding part finished product quality coefficient of the current automobile injection molding part finished product.

6. A visual inspection method for burrs of automotive injection molded parts according to claim 5, characterized in that: The step S5 includes the following specific contents: A finished automobile injection molded part quality threshold is preset. When the predicted finished automobile injection molded part quality coefficient of the current finished automobile injection molded part is greater than or equal to the finished automobile injection molded part quality threshold, the production of the current automobile injection molded part continues; when the predicted finished automobile injection molded part quality coefficient of the current finished automobile injection molded part is less than the finished automobile injection molded part quality threshold, an early warning is issued for the production process of the injection molding machine during injection molding in the current automobile injection molded part production process.

7. An electronic device comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; characterized in that the processor executes a visual detection method for burrs of automotive injection molded parts as described in any one of claims 1 to 6 by calling the computer program stored in the memory.

8. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are run on a computer, the computer is caused to execute a visual detection method for burrs of automotive injection molded parts as described in any one of claims 1 to 6.

Images