Quality inspection system and method for melamine tableware

Abstract

The present application relates to the technical field of quality inspection, and provides a quality inspection system and method for melamine tableware. An image acquisition module acquires image data of melamine tableware in a production process through an image acquisition strategy; a defect recognition module automatically recognizes and classifies defects in the image data, generates recognition results, and improves the accuracy of detection; a parameter monitoring module monitors and records whether there are abnormalities in production parameters of defective melamine tableware in the production process, and determines the correlation between abnormal production parameters and defect types, which helps to timely discover problems in the production process and take corresponding measures to adjust them; a dynamic adjustment module dynamically adjusts production parameters according to the correlation between abnormal production parameters and defect types, and continuously monitors the production process to optimize the adjustment of production parameters. The automated adjustment method can reduce human intervention and improve the stability and controllability of the production process.

Description

Technical Field

[0001] The present application relates to the technical field of quality inspection, and in particular to a quality inspection system and method for melamine tableware. Background Art

[0002] Traditional inspection methods include visual inspection, hand feel inspection, and size inspection. The existing inspection system can cover multiple quality indicators of melamine tableware, including appearance quality, physical properties, chemical properties, and safety performance. With the introduction of advanced inspection technologies, such as near-infrared spectroscopy, the inspection efficiency has been significantly improved. Through strict inspection, the safety of melamine tableware can be effectively guaranteed and the risk of migration of harmful substances can be reduced. However, most of them have not solved how to obtain image data of melamine tableware during the production process to identify and classify defects, and at the same time combine monitoring of production parameters to dynamically adjust production parameters for abnormalities.

[0003] For example, the utility model with the publication number CN214334745U discloses a biodegradable tableware detection device, including a detection table, a vertical fixed plate welded to the rear side of the upper surface of the detection table, a support plate a welded to the top of the front side wall of the vertical fixed plate, an electric lifting device fixedly connected to the upper surface of the support plate a, a lifting rod fixedly connected to the output end of the electric lifting device, the bottom end of the lifting rod vertically penetrates the center of the support plate a and is welded with a connecting plate, an electromagnet is fixedly connected to the lower surface of the connecting plate, a support plate b is welded to the middle position of the front side wall of the vertical fixed plate, a connecting hole is provided in the center of the support plate b, a connecting rod penetrates the connecting hole, a hammer is welded to the bottom end of the connecting rod, and an iron plate is welded to the top end of the connecting rod. Strength testing and high temperature resistance testing of biodegradable tableware are conducive to determining the production quality of biodegradable tableware.

[0004] For example, a Chinese patent with authorization announcement number CN108445007B discloses a detection method based on image fusion and a detection device thereof, including using multiple light-emitting modules to illuminate the detection object from different directions and obtain multiple frames of images to be detected, performing image fusion processing on multiple frames of images to be detected, and performing feature screening processing on the obtained texture image or height image. The above method can not only reduce the impact of poor image acquisition quality under low-contrast conditions, but also obtain relatively complete surface feature information, which is conducive to fusing the surface feature information in each frame of the image to be detected into a texture image and a height image, and is conducive to identifying and screening surface defect features from the distinguishing features of these images. The device combined with the above surface defect detection method can eliminate the influence of environmental factors to the greatest extent during the detection of the object to be detected, and can synthesize a feature image including surface defect features from a large number of images, enhance the screening effect of surface defect features, and complete the surface defect detection work under low-contrast conditions.

[0005] The above-mentioned prior art has the problem raised by the background technology: the above-mentioned prior art does not solve the problem of how to obtain image data of melamine tableware during the production process to identify defects and classify them, and at the same time combine monitoring whether there are abnormalities in the production parameters to dynamically adjust the production parameters. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present application provides a quality inspection system and method for melamine tableware.

[0007] In a first aspect, the present application provides a quality inspection system for melamine tableware, the system comprising: an image acquisition module, a defect recognition module, a parameter monitoring module and a dynamic adjustment module;

[0008] The image acquisition module is used to acquire image data of melamine tableware during the production process through an image acquisition strategy;

[0009] The defect recognition module is used to automatically recognize and classify defects in the image data and generate recognition results. The generation strategy of the recognition results includes extracting defect features of melamine tableware in the image data to comprehensively determine the defect type of the melamine tableware;

[0010] The parameter monitoring module is used to monitor and record whether there are abnormalities in the production parameters of defective melamine tableware during the production process, and to determine the correlation between the abnormal production parameters and the defect type. The correlation between the abnormal production parameters and the defect type is obtained by comparing the correlation value and the correlation threshold of the abnormal production parameters and the defect type.

[0011] The dynamic adjustment module is used to dynamically adjust the production parameters according to the correlation between the abnormal production parameters and the defect type, and continuously monitor the production process to optimize the adjustment of the production parameters.

[0012] As an optional implementation, the generation strategy of the recognition result includes:

[0013] Perform image segmentation on the image data of the melamine tableware, configure a defect threshold, and compare the pixel points of the image data of the melamine tableware with the defect threshold to automatically identify whether the image data shows that the melamine tableware has defects;

[0014] When it is identified in the image data that the melamine tableware has defects, the defect features of the melamine tableware in the image data are extracted, the defect features include geometric features, texture features and color features, and the defect type of the melamine tableware is comprehensively judged based on the geometric features, texture features and color features, and the defect types include surface defects, structural defects, functional defects and production defects.

[0015] As an optional implementation, the logic of comprehensively judging the defect type of melamine tableware includes:

[0016] The defect type of the melamine tableware is determined according to the states of the geometric features, texture features and color features of the melamine tableware. If the texture features of the melamine tableware are at the texture extreme value, the defect type of the melamine tableware is a functional defect.

[0017] If the texture feature of the melamine tableware is at the texture base value, the state of the geometric feature of the melamine tableware is judged; if the geometric feature of the melamine tableware is at the geometric extreme value, the defect type of the melamine tableware is a structural defect;

[0018] If the geometric feature of the melamine tableware is at the geometric base value, the state of the color feature of the melamine tableware is determined. If the color feature of the melamine tableware is at the color base value, the defect type of the melamine tableware is a production defect.

[0019] If the color characteristics of the melamine tableware are at the color extremes, the defect type of the melamine tableware is a surface defect.

[0020] As an optional implementation, the judgment logic of the state of the geometric features, texture features and color features of the melamine tableware includes:

[0021] Obtaining values ​​corresponding to geometric features, texture features, and color features of the melamine tableware in the image data, configuring a geometric threshold, a texture threshold, and a color threshold, and obtaining states of the geometric features, texture features, and color features of the melamine tableware according to the values ​​corresponding to the geometric features, texture features, and color features of the melamine tableware in the image data compared with the geometric threshold, the texture threshold, and the color threshold; if the value of the geometric features of the melamine tableware in the image data is less than or equal to the geometric threshold, the geometric features of the melamine tableware are at a geometric base value;

[0022] If the value of the geometric feature of the melamine tableware in the image data is greater than the geometric threshold, the geometric feature of the melamine tableware is at a geometric extreme value;

[0023] If the value of the texture feature of the melamine tableware in the image data is less than or equal to the texture threshold, the texture feature of the melamine tableware is at the texture base value;

[0024] If the value of the texture feature of the melamine tableware in the image data is greater than the texture threshold, the texture feature of the melamine tableware is at a texture extreme value;

[0025] If the value of the color feature of the melamine tableware in the image data is less than or equal to the color threshold, the color feature of the melamine tableware is at the color base value;

[0026] If the value of the color feature of the melamine tableware in the image data is greater than the color threshold, the color feature of the melamine tableware is at a color extreme value.

[0027] As an optional implementation, the logic for determining the correlation between abnormal production parameters and defect types includes:

[0028] Obtain the abnormal production parameters and defect types of defective melamine tableware during the production process, calculate the correlation value between the abnormal production parameters and the defect type, configure the correlation threshold, the correlation threshold includes the correlation basic threshold and the correlation extreme threshold, compare the correlation value between the abnormal production parameters and the defect type with the correlation threshold to obtain the correlation between the abnormal production parameters and the defect type, if the correlation value between the abnormal production parameters and the defect type is less than or equal to the correlation basic threshold, then there is no correlation between the abnormal production parameters and the defect type;

[0029] If the correlation value between the abnormal production parameter and the defect type is greater than the correlation base threshold and the correlation value between the abnormal production parameter and the defect type is less than the correlation extreme threshold, the correlation between the abnormal production parameter and the defect type is a common correlation;

[0030] If the correlation value between the abnormal production parameter and the defect type is greater than or equal to the correlation extreme threshold, the correlation between the abnormal production parameter and the defect type is a single correlation.

[0031] As an optional implementation, the function expression of the association value between the abnormal production parameter and the defect type is as follows:

[0032]

[0033] In the formula, r represents the correlation value between abnormal production parameters and defect types, X i represents the value of the abnormal production parameter for the ith observation, represents the mean of the values ​​of the abnormal production parameter, Y i represents the value of the defect type of the i-th observation, represents the mean of the values ​​for the defect type, and n represents the total number of observations.

[0034] As an optional implementation, the image acquisition strategy includes:

[0035] The sensors are deployed on the production line of melamine tableware, and the synchronous trigger logic is configured to obtain image data of the melamine tableware during the production process, and the sensor parameters are dynamically adjusted according to the quality of the image data.

[0036] As an optional implementation, the synchronization trigger logic includes:

[0037] Configure the target trigger time, determine the sensor trigger time according to the target trigger time, monitor the moving speed of the production line, calculate the sensor trigger frequency according to the moving speed of the production line, and the sensor trigger frequency and the sensor trigger time are reciprocal of each other, and calibrate the sensor regularly.

[0038] In a second aspect, the present application provides a quality detection method for melamine tableware, the method comprising:

[0039] S1. Acquire image data of melamine tableware during the production process through image acquisition strategy;

[0040] S2, automatically identifying and classifying defects in the image data to generate identification results, wherein the generation strategy of the identification results includes extracting defect features of melamine tableware in the image data to comprehensively determine the defect type of the melamine tableware;

[0041] S3. Monitor and record whether there are any abnormalities in the production parameters of defective melamine tableware during the production process, and determine the correlation between the abnormal production parameters and the defect type. The correlation between the abnormal production parameters and the defect type is obtained by comparing the correlation value and the correlation threshold of the abnormal production parameters and the defect type;

[0042] S4. Dynamically adjust production parameters based on the correlation between abnormal production parameters and defect types, and continuously monitor the production process to optimize the adjustment of production parameters.

[0043] Compared with the prior art, the beneficial effects of the present application are as follows: the image acquisition module acquires the image data of melamine tableware in the production process through the image acquisition strategy, which provides a basic data source for subsequent defect identification and parameter monitoring, and greatly improves the detection efficiency compared with the traditional manual detection; the defect recognition module automatically identifies and classifies the defects in the image data, generates recognition results, and can overcome the influence of subjective factors in manual detection and improve the accuracy of detection; the parameter monitoring module monitors and records whether there are abnormalities in the production parameters of defective melamine tableware in the production process, and judges the correlation between abnormal production parameters and defect types, which helps to timely discover problems in the production process and take corresponding measures to adjust them; the dynamic adjustment module dynamically adjusts the production parameters according to the correlation between abnormal production parameters and defect types, and continuously monitors the production process to optimize the adjustment of production parameters. The automated adjustment method can reduce human intervention and improve the stability and controllability of the production process; it helps enterprises to continuously optimize production processes, improve product quality and production efficiency, reduce dependence on manual detection, and thus reduce labor costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0045] Figure 1 A system structure diagram of a quality inspection system for melamine tableware provided in an embodiment of the present application;

[0046] Figure 2A flow chart of a recognition result generation strategy for a quality inspection system for melamine tableware provided in an embodiment of the present application;

[0047] Figure 3 A correlation judgment logic diagram of a quality detection system for melamine tableware provided in an embodiment of the present application;

[0048] Figure 4 This is a flow chart of a method for quality inspection of melamine tableware provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to make the objectives, technical solutions and advantages of the embodiments of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application are clearly and completely described below in conjunction with the drawings in the specification. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.

[0050] Example 1

[0051] like Figure 1 As shown, a system structure diagram of a quality inspection system for melamine tableware is provided for an embodiment of the present application. The system includes an image acquisition module, a defect recognition module, a parameter monitoring module and a dynamic adjustment module.

[0052] The image acquisition module is used to acquire image data of melamine tableware during the production process through an image acquisition strategy. The image acquisition strategy includes a synchronous trigger logic. The synchronous trigger logic includes calculating the trigger frequency of the sensor according to the moving speed of the melamine tableware production line.

[0053] Image acquisition strategies include:

[0054] The sensors are deployed on the production line of melamine tableware, and the synchronous trigger logic is configured to obtain image data of the melamine tableware during the production process, and the sensor parameters are dynamically adjusted according to the quality of the image data.

[0055] The synchronization trigger logic includes:

[0056] Configure the target trigger time, determine the sensor trigger time according to the target trigger time, monitor the moving speed of the production line, calculate the sensor trigger frequency according to the moving speed of the production line, and the sensor trigger frequency and the sensor trigger time are reciprocal of each other, and calibrate the sensor regularly.

[0057] For example, a camera suitable for an industrial production environment is selected, which can maintain stability when the melamine tableware is running on a high-speed production line to ensure that the detailed information of the melamine tableware is captured. At the same time, multiple cameras are installed around the melamine tableware production line so that the melamine tableware can be photographed from different angles at the same time. A surround deployment method can be considered to ensure that the image data of each melamine tableware is captured without omission and that the surface or angle of each melamine tableware can be scanned in all directions. It must also be ensured that all cameras are triggered to shoot at the same time to avoid inconsistent image data due to changes in production line speed or asynchronous camera responses.

[0058] For example, synchronous triggering is not just about time consistency, but also needs to take into account the moving speed of the production line and the spatial distribution between cameras. For example, the moving speed of the production line is monitored in real time, and the field of view size (width of field of view) of each camera is determined, so that the trigger frequency of the camera is the ratio of the moving speed of the production line to the field of view size of each camera. This means that the trigger frequency of the camera must be high enough to capture all melamine tableware passing through the production line per unit time. At this time, the target trigger time is the reciprocal of the trigger frequency of each camera; due to differences in hardware response times of different cameras, slight delays may be introduced, and these delays need to be compensated to ensure that the trigger time remains consistent among all cameras; in long-term operation, the synchronization accuracy of the camera may be affected by temperature, vibration or other environmental factors, so regular calibration is necessary to ensure that the response time and trigger synchronization accuracy of each camera are within the allowable range. Calibration requires real-time monitoring of deviations between cameras and automatic adjustments through special calibration tools.

[0059] It should be understood that each acquired image data needs to be analyzed in a timely manner to ensure that the quality of the image data meets the requirements. If problems such as exposure or focus occur, the camera parameters should be automatically adjusted to adapt to changes in light or environment during the production process of melamine tableware.

[0060] For example, in a dimly lit environment, the exposure time is automatically increased, and in a strong light environment, the exposure time is automatically reduced; a camera with a wide temperature range is selected that can work stably in high or low temperature environments, and a heating plate or air cooling system is used to prevent overheating; the above strategy can effectively obtain efficient and consistent image data to ensure all-round scanning and quality inspection of melamine tableware.

[0061] The defect recognition module is used to automatically identify and classify defects in image data and generate recognition results. The recognition results include whether the image data shows that the melamine tableware has defects and the defect types of the melamine tableware. The defect features of the melamine tableware in the image data are extracted to comprehensively judge the defect types of the melamine tableware. The defect types of melamine tableware include surface defects, structural defects, functional defects and production defects.

[0062] The generation strategy of recognition results is as follows Figure 2 As shown, specifically including:

[0063] The image data of the melamine tableware is segmented, a defect threshold is configured, and the pixel points of the image data of the melamine tableware are compared with the defect threshold to automatically identify whether the image data shows that the melamine tableware has defects.

[0064] When it is identified in the image data that the melamine tableware has defects, the defect features of the melamine tableware in the image data are extracted, the defect features include geometric features, texture features and color features, and the defect type of the melamine tableware is comprehensively judged based on the geometric features, texture features and color features, and the defect types include surface defects, structural defects, functional defects and production defects.

[0065] The logic for comprehensively judging the defect types of melamine tableware includes:

[0066] Obtaining values ​​corresponding to geometric features, texture features, and color features of the melamine tableware in the image data, configuring a geometric threshold, a texture threshold, and a color threshold, and obtaining states of the geometric features, texture features, and color features of the melamine tableware according to the values ​​corresponding to the geometric features, texture features, and color features of the melamine tableware in the image data compared with the geometric threshold, the texture threshold, and the color threshold; if the value of the geometric features of the melamine tableware in the image data is less than or equal to the geometric threshold, the geometric features of the melamine tableware are at a geometric base value;

[0067] If the value of the geometric feature of the melamine tableware in the image data is greater than the geometric threshold, the geometric feature of the melamine tableware is at a geometric extreme value;

[0068] If the value of the texture feature of the melamine tableware in the image data is less than or equal to the texture threshold, the texture feature of the melamine tableware is at the texture base value;

[0069] If the value of the texture feature of the melamine tableware in the image data is greater than the texture threshold, the texture feature of the melamine tableware is at a texture extreme value;

[0070] If the value of the color feature of the melamine tableware in the image data is less than or equal to the color threshold, the color feature of the melamine tableware is at the color base value;

[0071] If the value of the color feature of the melamine tableware in the image data is greater than the color threshold, the color feature of the melamine tableware is at a color extreme value.

[0072] The defect type of the melamine tableware is determined according to the states of the geometric features, texture features and color features of the melamine tableware. If the texture features of the melamine tableware are at the texture extreme value, the defect type of the melamine tableware is a functional defect.

[0073] If the texture feature of the melamine tableware is at the texture base value, the state of the geometric feature of the melamine tableware is judged; if the geometric feature of the melamine tableware is at the geometric extreme value, the defect type of the melamine tableware is a structural defect;

[0074] If the geometric feature of the melamine tableware is at the geometric base value, the state of the color feature of the melamine tableware is determined. If the color feature of the melamine tableware is at the color base value, the defect type of the melamine tableware is a production defect.

[0075] If the color characteristics of the melamine tableware are at the color extremes, the defect type of the melamine tableware is a surface defect.

[0076] It should be understood that before automatically identifying and classifying defects in the image data of melamine tableware, the original image data needs to be enhanced (histogram equalization) and denoised (median filtering) to improve the accuracy of subsequent identification.

[0077] It should be understood that the above-mentioned image segmentation by defect threshold is a conventional method. The principle is to divide the pixels of the image data into two categories by setting a defect threshold: those greater than or equal to the defect threshold are defect areas, and those less than the defect threshold are backgrounds.

[0078] Exemplarily, a defect threshold is configured, and the pixel points of the image data of the melamine tableware are compared with the defect threshold to determine whether the melamine tableware has defects. When the pixel points of the image data of the melamine tableware are greater than or equal to the defect threshold, it means that the image data of the melamine tableware shows that the melamine tableware is defective. At this time, it is necessary to extract the defect features of the melamine tableware in the image data, where the defect features include geometric features, texture features and color features.

[0079] Exemplarily, geometric features are represented by boundary complexity (measured using the ratio of perimeter to area), which is used to reflect the shape complexity of the defect. The higher the boundary complexity, the more complex the shape of the defect area. Texture features are represented by local binary patterns (comparing the grayscale values ​​of the central pixel with the surrounding pixels). The larger the local binary pattern, the more complex the texture. Color features are represented by calculating the standard deviation of the RGB components of the defect area. The standard deviation of the RGB components is used to reflect the degree of color change in the defect area. Areas with larger color changes usually represent uneven color or contaminants.

[0080] It should be understood that there are four types of defects in melamine tableware, including surface defects, structural defects, functional defects and production defects. Surface defects refer to defects on the surface of melamine tableware, usually manifested as surface scratches (shallow and elongated defects on the surface, usually caused by friction or collision), stains (may be due to uneven heating or dye problems during the molding process) and bubbles (usually due to the failure of gas to be discharged during the molding process), etc. Structural defects refer to internal or structural problems of melamine tableware, such as cracks (linear or elongated defects that may penetrate deep into the material, usually caused by stress concentration or external impact), missing corners (a corner or edge part of melamine tableware, etc.). Missing (usually associated with physical damage) and breakage (partial missing or severe damage to the whole, which may affect the function and structural integrity of melamine tableware); functional defects refer to defects that affect the function or performance of melamine tableware, such as insufficient heat resistance (melamine tableware may deform or release harmful substances in high temperature environments) and insufficient chemical resistance (certain detergents or food ingredients may cause material degradation or discoloration); production defects refer to defects that occur during the production process, such as molding defects (defects caused by mold problems or uneven materials during the production process) and poor seams (poor joints of multi-component tableware may cause leakage or structural instability).

[0081] Specifically, when the defect of melamine tableware is a surface defect, the boundary complexity is low (usually indicating that the shape of the defect area is relatively simple), the local binary pattern value is low (usually indicating that the texture is relatively simple), and the standard deviation of the RGB component is large (usually indicating that the color change is significant, such as stains, oil stains or surface scratches); when the defect of melamine tableware is a structural defect, the boundary complexity is high (usually indicating that the shape of the defect is irregular and has a certain geometric complexity), the local binary pattern value is low (usually indicating that the defect surface may be relatively smooth), and the standard deviation of the RGB component is small (usually indicating that the color change is not large); when the defect of melamine tableware is When it is a functional defect, the boundary complexity is high (usually indicating that the defect area has a complex shape or foreign matter is embedded), the local binary pattern value is high (usually indicating that the texture is complex and may affect the normal function of the melamine tableware), and the standard deviation of the RGB component is large (usually indicating that the color variation is large); when the defect of the melamine tableware is a production defect, the boundary complexity is low (usually indicating that the defect shape is regular), the local binary pattern value is low (usually indicating that the texture is simpler), and the standard deviation of the RGB component is small (usually indicating that the color distribution is uniform); the above strategies are used to realize the identification of melamine tableware defects and the fine classification of defect types.

[0082] The parameter monitoring module is used to monitor and record whether there are any abnormalities in the production parameters of defective melamine tableware during the production process, and to determine the correlation between the abnormal production parameters and the defect type. The correlation between the abnormal production parameters and the defect type is obtained by comparing the correlation value and correlation threshold of the abnormal production parameters and the defect type.

[0083] The logic for determining the correlation between abnormal production parameters and defect types is as follows: Figure 3 As shown, specifically including:

[0084] Obtain the abnormal production parameters and defect types of defective melamine tableware during the production process, calculate the correlation value between the abnormal production parameters and the defect type, configure the correlation threshold, the correlation threshold includes the correlation basic threshold and the correlation extreme threshold, compare the correlation value between the abnormal production parameters and the defect type with the correlation threshold to obtain the correlation between the abnormal production parameters and the defect type, if the correlation value between the abnormal production parameters and the defect type is less than or equal to the correlation basic threshold, then there is no correlation between the abnormal production parameters and the defect type;

[0085] If the correlation value between the abnormal production parameter and the defect type is greater than the correlation base threshold and the correlation value between the abnormal production parameter and the defect type is less than the correlation extreme threshold, the correlation between the abnormal production parameter and the defect type is a common correlation;

[0086] If the correlation value between the abnormal production parameter and the defect type is greater than or equal to the correlation extreme threshold, the correlation between the abnormal production parameter and the defect type is a single correlation.

[0087] The function expression of the associated value of abnormal production parameters and defect types is as follows:

[0088]

[0089] In the formula, r represents the correlation value between abnormal production parameters and defect types, X i represents the value of the abnormal production parameter for the ith observation, represents the mean of the values ​​of the abnormal production parameter, Y i represents the value of the defect type of the i-th observation, represents the mean of the values ​​for the defect type, and n represents the total number of observations.

[0090] It should be noted that the correlation value r between the abnormal production parameter and the defect type ranges from -1 to 1. When the correlation value r between the abnormal production parameter and the defect type is closer to 1 or -1, it means that the linear relationship between the abnormal production parameter and the defect type is stronger. When the correlation value r between the abnormal production parameter and the defect type is closer to 0, it means that there is no linear relationship between the abnormal production parameter and the defect type. The above defect types need to be quantified into continuous values ​​for the calculation of the above formula. Each pair of abnormal production parameter values ​​and defect type values ​​is called an observation value.

[0091] Exemplarily, the production parameters include temperature, pressure, humidity, speed, time and equipment status. The temperature includes mold temperature and equipment temperature, the pressure includes injection pressure and mold injection pressure, the speed includes the moving speed of the production line and the material transmission speed, the humidity includes ambient humidity and material humidity, the time includes production cycle, cooling time and heating time, and the equipment status includes fault records and operation stability.

[0092] It should be understood that the production parameters in the normal production process are within the normal range. When the production parameters are not within the normal range, it means that there are abnormalities in the production parameters. For example, if the temperature is too high or too low, it may cause surface defects of the melamine tableware, and may cause cooling too fast or too slow, thereby generating internal stress and causing cracks, and may also affect the physical properties of the melamine tableware; excessive or insufficient pressure may cause the surface to be rough, produce bubbles, etc., may cause structural defects, and may also affect the physical properties of the melamine tableware, resulting in insufficient hardness or decreased strength; excessive humidity may cause uneven materials and surface defects, and may also affect the mechanical strength of the melamine tableware, resulting in decreased functional performance; production speeds that are too fast or too slow may lead to uneven production, thereby affecting the quality of the melamine tableware; and unstable equipment operation or equipment failure may also lead to production defects.

[0093] It should be understood that each production parameter should be checked for abnormalities. If multiple production parameters are abnormal, they need to be monitored and adjusted. In addition, in the actual production process, the combination of multiple production parameters may jointly affect the occurrence of defects. Therefore, it is necessary to determine the correlation between abnormal production parameters and defect types in order to determine how to adjust production parameters to avoid defects in melamine tableware.

[0094] Specifically, the correlation threshold is determined by actual conditions, where the defect type needs to be quantified into a continuous value (for example, 1 represents surface defects, 2 represents structural defects, 3 represents functional defects, and 4 represents production defects). For continuous production parameters (such as temperature and pressure, etc.), the Pearson correlation coefficient is used to calculate the linear correlation between each abnormal production parameter and the occurrence of the defect type. At this time, when the correlation value is close to 1 or -1, it means that the abnormal production parameter has a greater impact on the occurrence of the defect type. When the correlation value is close to 0, it means that the abnormal production parameter has a smaller impact on the occurrence of the defect type. For defect types (at this time, the defect type needs to be converted into a classification label, such as 0 indicates that the defect type occurs, and 1 indicates that the defect type does not occur) and certain production parameters (whether the production parameters exceed the standard), there is a complex nonlinear relationship (for example, too high temperature may cause multiple types of defects). This complex nonlinear relationship is captured using mutual information to determine whether abnormal production parameters will cause a certain type of defect in melamine tableware.

[0095] Exemplarily, if it is obtained that there is no correlation between the abnormal production parameter and the defect type, it means that the abnormal production parameter has little effect on the occurrence of the defect type, may be only a minor factor, or has no obvious relationship with the defect type; if the correlation between the abnormal production parameter and the defect type is a common correlation, it means that the abnormal production parameter has a certain influence on the defect type, but there is a situation where it works together with other abnormal production parameters. It is necessary to further determine which abnormal production parameters jointly cause the occurrence of this type of defect in melamine tableware, and formulate reasonable adjustment measures; if the correlation between the abnormal production parameter and the defect type is a single correlation, it means that there is a strong correlation between the abnormal production parameter and the defect type, that is, the abnormal production parameter is an important factor causing the occurrence of this defect type, and it is necessary to focus on monitoring the abnormal production parameter to reduce the occurrence of this defect type in melamine tableware; through the above logical content, the causes of defects in melamine tableware can be effectively identified, and corresponding adjustments can be made, thereby reducing the occurrence of defects and improving the production efficiency and product quality of melamine tableware.

[0096] The dynamic adjustment module is used to dynamically adjust the production parameters according to the correlation between abnormal production parameters and defect types, and continuously monitor the production process to optimize the adjustment of production parameters.

[0097] For example, in the production process of melamine tableware, the real-time monitored production parameters are compared with the set normal range to obtain abnormal fluctuations in the production parameters; when an abnormal production parameter is detected, the production parameters in the melamine tableware production line equipment are automatically adjusted. For example, if the temperature is too high, the temperature is automatically lowered; if the pressure is too low, the pressure is automatically increased; at the same time, according to the correlation between the abnormal production parameters and the defect type, the production parameters are further adjusted. For example, if a structural defect such as a crack is found, the calculation results of the correlation between the abnormal production parameters and the defect type show that temperature and pressure will cause structural defects, so the temperature and pressure should be controlled together to ensure that the frequency of structural defects is reduced; for another example, the calculation results of the correlation between the abnormal production parameters and the defect type show that the equipment status and the production defects are singly correlated, that is, the equipment status is an important factor leading to production defects, so it is necessary to regularly check the equipment status of the production line to avoid the recurrence of production defects.

[0098] Specifically, after adjusting the production parameters, continuously monitor whether other production parameters in the production process are abnormal and whether there are still defects in the melamine tableware, so as to form a closed-loop feedback mechanism to ensure the effect of the production parameter adjustment; when the frequency of defects in melamine tableware has not decreased significantly, it may be necessary to further optimize how to adjust the production parameters, such as re-determining the correlation between abnormal production parameters and defect types, and further determining which combinations of abnormal production parameters will lead to the occurrence of a certain type of defect through machine learning methods (such as decision trees and logistic regression, etc.); through the above content, dynamic adjustment of production parameters in the production process can be achieved, the production quality of melamine tableware can be ensured and production efficiency can be optimized, and the adjustment of production parameters can be continuously optimized by combining effect feedback with machine learning optimization, thereby realizing refined production management.

[0099] Example 2

[0100] like Figure 4 As shown, a method flow chart of a quality detection method for melamine tableware is provided for an embodiment of the present application, and the method comprises:

[0101] S1. Acquire image data of melamine tableware during the production process through image acquisition strategy;

[0102] S2, automatically identifying and classifying defects in the image data to generate identification results, wherein the generation strategy of the identification results includes extracting defect features of melamine tableware in the image data to comprehensively determine the defect type of the melamine tableware;

[0103] S3. Monitor and record whether there are any abnormalities in the production parameters of defective melamine tableware during the production process, and determine the correlation between the abnormal production parameters and the defect type. The correlation between the abnormal production parameters and the defect type is obtained by comparing the correlation value and the correlation threshold of the abnormal production parameters and the defect type;

[0104] S4. Dynamically adjust production parameters based on the correlation between abnormal production parameters and defect types, and continuously monitor the production process to optimize the adjustment of production parameters.

[0105] Since the principle of solving the problem by the method in the embodiment of the present application is similar to that of the system described above in the embodiment of the present application, the implementation of the method refers to the implementation of the system, and the repeated parts will not be repeated.

[0106] Example 3

[0107] In this embodiment, a computer device is provided, including a memory and a processor, wherein the memory is used to store instructions, and the processor is used to execute the instructions, so that the computer device executes the steps in the above method embodiment.

[0108] Example 4

[0109] In this embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed, the steps in the above method embodiment are implemented.

[0110] The computer-readable storage medium includes: a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, and other media for storing program codes.

[0111] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working process of the method and device described above may refer to the corresponding process in the aforementioned system embodiment, and will not be repeated here.

[0112] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0113] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application, which should be included in the scope of the claims of the present application.

Claims

1. The quality inspection system for melamine tableware is characterized by: include: Image acquisition module, defect recognition module, parameter monitoring module and dynamic adjustment module; The image acquisition module is used to acquire image data of melamine tableware during the production process through an image acquisition strategy; The defect recognition module is used to automatically recognize and classify defects in the image data and generate recognition results. The generation strategy of the recognition results includes extracting defect features of melamine tableware in the image data to comprehensively determine the defect type of the melamine tableware; The parameter monitoring module is used to monitor and record whether there are abnormalities in the production parameters of defective melamine tableware during the production process, and to determine the correlation between the abnormal production parameters and the defect type. The correlation between the abnormal production parameters and the defect type is obtained by comparing the correlation value and the correlation threshold of the abnormal production parameters and the defect type. The dynamic adjustment module is used to dynamically adjust the production parameters according to the correlation between the abnormal production parameters and the defect type, and continuously monitor the production process to optimize the adjustment of the production parameters.

2. The quality inspection system for melamine tableware according to claim 1, characterized in that: The generation strategy of the recognition result includes: Perform image segmentation on the image data of the melamine tableware, configure a defect threshold, and compare the pixel points of the image data of the melamine tableware with the defect threshold to automatically identify whether the image data shows that the melamine tableware has defects; When it is identified in the image data that the melamine tableware has defects, the defect features of the melamine tableware in the image data are extracted, the defect features include geometric features, texture features and color features, and the defect type of the melamine tableware is comprehensively judged based on the geometric features, texture features and color features, and the defect types include surface defects, structural defects, functional defects and production defects.

3. The quality inspection system for melamine tableware according to claim 2, characterized in that: The logic of comprehensively judging the defect types of melamine tableware includes: The defect type of the melamine tableware is determined according to the states of the geometric features, texture features and color features of the melamine tableware. If the texture features of the melamine tableware are at the texture extreme value, the defect type of the melamine tableware is a functional defect. If the texture feature of the melamine tableware is at the texture base value, the state of the geometric feature of the melamine tableware is judged; if the geometric feature of the melamine tableware is at the geometric extreme value, the defect type of the melamine tableware is a structural defect; If the geometric feature of the melamine tableware is at the geometric base value, the state of the color feature of the melamine tableware is determined. If the color feature of the melamine tableware is at the color base value, the defect type of the melamine tableware is a production defect. If the color characteristics of the melamine tableware are at the color extremes, the defect type of the melamine tableware is a surface defect.

4. The quality inspection system for melamine tableware according to claim 3, characterized in that: The judgment logic of the state of the geometric features, texture features and color features of the melamine tableware includes: Obtaining values ​​corresponding to geometric features, texture features, and color features of the melamine tableware in the image data, configuring a geometric threshold, a texture threshold, and a color threshold, and obtaining states of the geometric features, texture features, and color features of the melamine tableware according to the values ​​corresponding to the geometric features, texture features, and color features of the melamine tableware in the image data compared with the geometric threshold, the texture threshold, and the color threshold; if the value of the geometric features of the melamine tableware in the image data is less than or equal to the geometric threshold, the geometric features of the melamine tableware are at a geometric base value; If the value of the geometric feature of the melamine tableware in the image data is greater than the geometric threshold, the geometric feature of the melamine tableware is at a geometric extreme value; If the value of the texture feature of the melamine tableware in the image data is less than or equal to the texture threshold, the texture feature of the melamine tableware is at the texture base value; If the value of the texture feature of the melamine tableware in the image data is greater than the texture threshold, the texture feature of the melamine tableware is at a texture extreme value; If the value of the color feature of the melamine tableware in the image data is less than or equal to the color threshold, the color feature of the melamine tableware is at the color base value; If the value of the color feature of the melamine tableware in the image data is greater than the color threshold, the color feature of the melamine tableware is at a color extreme value.

5. The quality inspection system for melamine tableware according to claim 4, characterized in that: The logic for determining the correlation between abnormal production parameters and defect types includes: Obtain the abnormal production parameters and defect types of defective melamine tableware during the production process, calculate the correlation value between the abnormal production parameters and the defect type, configure the correlation threshold, the correlation threshold includes the correlation basic threshold and the correlation extreme threshold, compare the correlation value between the abnormal production parameters and the defect type with the correlation threshold to obtain the correlation between the abnormal production parameters and the defect type, if the correlation value between the abnormal production parameters and the defect type is less than or equal to the correlation basic threshold, then there is no correlation between the abnormal production parameters and the defect type; If the correlation value between the abnormal production parameter and the defect type is greater than the correlation base threshold and the correlation value between the abnormal production parameter and the defect type is less than the correlation extreme threshold, the correlation between the abnormal production parameter and the defect type is a common correlation; If the correlation value between the abnormal production parameter and the defect type is greater than or equal to the correlation extreme threshold, the correlation between the abnormal production parameter and the defect type is a single correlation.

6. The quality inspection system for melamine tableware according to claim 5, characterized in that: The functional expression of the associated value of the abnormal production parameter and the defect type is as follows: In the formula, r represents the correlation value between abnormal production parameters and defect types, X i represents the value of the abnormal production parameter for the ith observation, represents the mean of the values ​​of the abnormal production parameter, Y i represents the value of the defect type of the i-th observation, represents the mean of the values ​​for the defect type, and n represents the total number of observations.

7. The quality inspection system for melamine tableware according to claim 6, characterized in that: The image acquisition strategy includes: The sensors are deployed on the production line of melamine tableware, and the synchronous trigger logic is configured to obtain image data of the melamine tableware during the production process, and the sensor parameters are dynamically adjusted according to the quality of the image data.

8. The quality inspection system for melamine tableware according to claim 7, characterized in that: The synchronization trigger logic includes: Configure the target trigger time, determine the sensor trigger time according to the target trigger time, monitor the moving speed of the production line, calculate the sensor trigger frequency according to the moving speed of the production line, and the sensor trigger frequency and the sensor trigger time are reciprocal of each other, and calibrate the sensor regularly.

9. A quality inspection method for melamine tableware, implemented based on the quality inspection system for melamine tableware according to any one of claims 1 to 8, characterized in that: include: S1. Acquire image data of melamine tableware during the production process through image acquisition strategy; S2, automatically identifying and classifying defects in the image data to generate identification results, wherein the generation strategy of the identification results includes extracting defect features of melamine tableware in the image data to comprehensively determine the defect type of the melamine tableware; S3. Monitor and record whether there are any abnormalities in the production parameters of defective melamine tableware during the production process, and determine the correlation between the abnormal production parameters and the defect type. The correlation between the abnormal production parameters and the defect type is obtained by comparing the correlation value and the correlation threshold of the abnormal production parameters and the defect type; S4. Dynamically adjust production parameters based on the correlation between abnormal production parameters and defect types, and continuously monitor the production process to optimize the adjustment of production parameters.

Images