Finished glass wine bottle detecting and feeding method and system

Abstract

The invention provides a finished glass wine bottle detecting and feeding method which comprises the following steps: S1, carrying out feeding preparation, namely transferring wine bottles, carrying out automatic feeding, and carrying out automatic correction and guiding; s2, conveying and preliminary arrangement are conducted, specifically, a conveying belt is started, the speed is stabilized, then the wine bottles are guided, and then the wine bottles are preliminarily arranged; s3, carrying out visual and laser detection; s4, carrying out data processing and analysis; s5, sorting is carried out; and S6, carrying out feedback and adjustment. According to the method, the detection precision and efficiency can be remarkably improved, the production process is optimized, the overall quality control level is improved, and the defective rate and the production cost can be reduced.

Description

Technical Field

[0001] The invention specifically relates to a method and system for detecting and feeding finished glass wine bottles. Background Art

[0002] Finished glass wine bottle inspection and loading refers to the process of quality inspection and automatic loading of glass wine bottles manufactured on the production line. At present, there is no efficient way to use advanced sensors and machine vision technology to detect the appearance, size, sealing and other parameters of wine bottles to ensure that each wine bottle meets the quality standards. Therefore, this solution is proposed to solve this problem. Summary of the invention

[0003] The purpose of the present invention is to provide a finished glass wine bottle detection and feeding method in view of the deficiencies in the prior art, and the finished glass wine bottle detection and feeding method can well solve the above problems.

[0004] In order to achieve the above requirements, the technical solution adopted by the present invention is: to provide a finished glass wine bottle detection and feeding method, the finished glass wine bottle detection and feeding method comprises the following steps:

[0005] S1: steps of preparing for loading, including wine bottle transfer, automatic loading, and automatic correction and guidance;

[0006] S2: performing the steps of conveying and preliminary arrangement, including starting the conveyor belt and stabilizing the speed, then guiding the wine bottles, and then preliminary arrangement of the wine bottles;

[0007] S3: Steps for visual and laser inspection;

[0008] S4: Steps for data processing and analysis;

[0009] S5: sorting step;

[0010] S6: Steps for feedback and adjustment.

[0011] The advantages of the finished glass bottle detection and feeding method are as follows:

[0012] This method can significantly improve the accuracy and efficiency of detection, optimize the production process, enhance the overall quality control level and help reduce the defective rate and production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The same reference numerals are used in these drawings to represent the same or similar parts. The exemplary embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0014] Figure 1 The figure schematically shows a flow chart of a method for inspecting and loading finished glass wine bottles according to an embodiment of the present application. DETAILED DESCRIPTION

[0015] In order to make the objectives, technical solutions and advantages of the present application more clear, the present application is further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0016] In the following description, references to "one embodiment", "an embodiment", "an example", "an example", etc. indicate that the embodiment or example described in this way includes specific features, structures, characteristics, properties, elements or limitations, but not every embodiment or example necessarily includes the specific features, structures, characteristics, properties, elements or limitations. In addition, repeated use of the phrase "according to one embodiment of the present application" does not necessarily refer to the same embodiment, although it may refer to the same embodiment.

[0017] For the sake of simplicity, certain technical features well known to those skilled in the art are omitted in the following description.

[0018] According to one embodiment of the present application, a method for detecting and loading finished glass wine bottles is provided, comprising the following steps:

[0019] 1. Loading preparation

[0020] Loading preparation is the starting point of the entire inspection and loading process, ensuring that the glass bottles smoothly enter the automated loading system from the storage area or production line. This step involves the following sub-links:

[0021] (1) Bottle transfer: First, the finished glass bottles are transferred from the production line or storage area to the input end of the automatic feeding system. There is a temporary storage area at the end of the production line to stack the finished glass bottles. These bottles are transported to the input area of ​​the feeding system by manual or automated equipment (such as forklifts or automatic guided vehicles AGV).

[0022] (2) Vibrating plate or automatic loading equipment: To ensure that the bottles can be arranged in an orderly manner on the conveyor belt, a vibrating plate or other automatic loading equipment is used. The vibrating plate moves the bottles through vibration and gradually arranges them into a single row. For large-scale production lines, a multi-layer vibrating plate system is used to increase the loading speed and efficiency. The design of the vibrating plate must ensure that the bottles will not be damaged due to excessive vibration.

[0023] (3) Automatic correction and guidance: Before the wine bottles enter the conveyor belt, an automatic correction and guidance device is required to ensure that each wine bottle enters the conveyor belt in the correct direction and posture. The correction device includes mechanical baffles, conveyor belt guidance systems, etc. to ensure that the wine bottles will not fall over or be misplaced when entering the detection system.

[0024] (4) Safety measures: Safety measures should also be considered during the loading preparation stage to prevent the bottles from being damaged due to collision or other reasons during the transfer process. This includes installing buffer devices at key locations and wrapping the edge of the vibration plate with soft materials.

[0025] Through these preparatory work, it is ensured that the wine bottles are neatly arranged and in the correct direction and position before entering the conveyor belt, avoiding errors or failures in the subsequent inspection process.

[0026] 2. Transportation and preliminary arrangement

[0027] The conveying and preliminary arrangement stage is an important step before the wine bottles enter the inspection station. This process ensures that the wine bottles enter the inspection system at a stable speed and in the correct posture for accurate inspection. The specific description is as follows:

[0028] (1) Start the conveyor belt: After the loading preparation is completed, start the conveyor belt system. The conveyor belt must be designed to ensure smooth operation and adjustable speed. The surface of the conveyor belt will have an anti-slip design to prevent the wine bottles from tipping over or sliding during movement.

[0029] (2) Stable speed: The speed of the conveyor belt needs to be adjusted according to the rhythm of the production line. Too fast speed will cause the bottles to fall over or collide with each other, while too slow speed will reduce production efficiency. Use a frequency converter to control the conveyor belt speed and adjust it flexibly according to actual needs.

[0030] (3) Guide device: During the conveying process, the guide device is set to ensure that the wine bottle always remains in the center of the conveyor belt. The guide device is a fixed mechanical baffle and a dynamically adjusted guide system. The dynamic guide system detects the position of the wine bottle through a sensor and automatically adjusts the angle and position of the guide device to keep the wine bottle on the correct track.

[0031] (4) Preliminary arrangement: If the bottles are not completely aligned during the loading stage, additional arrangement devices are installed on the conveyor belt. For example, multiple transverse baffles are installed to separate the bottles one by one to prevent them from being squeezed or overlapped on the conveyor belt. The arrangement device needs to be customized according to the size and shape of the bottles to ensure that it can accommodate bottles of different specifications.

[0032] (5) Buffer: A buffer is set before the inspection station to regulate the flow of wine bottles on the conveyor belt. The buffer is a short-distance deceleration conveyor belt or a specially designed buffer box to ensure that the wine bottles maintain the appropriate spacing and speed before entering the inspection station.

[0033] (6) Sensor detection: Sensors are installed on the conveyor belt to monitor the position and status of wine bottles in real time. If a wine bottle is detected to have fallen or congestion, the system will automatically sound an alarm and stop the conveyor belt so that the operator can check and handle it.

[0034] These measures ensure that the wine bottles remain stable and in the correct direction during transportation, laying the foundation for subsequent inspection steps.

[0035] 3. Vision and laser inspection

[0036] Vision and laser inspection is the most critical step in the entire inspection and feeding process. Through sophisticated inspection equipment and systems, we ensure that each glass bottle meets the quality standards. The specific description is as follows:

[0037] (1) Visual inspection system: The visual inspection system consists of industrial cameras, lighting equipment, and image processing software. When the wine bottle enters the inspection station, the industrial camera will take a high-resolution image of the wine bottle. To ensure the clarity of the image, the lighting equipment needs to provide uniform and shadow-free lighting, and is selected according to the shape and material of the wine bottle.

[0038] (2) Appearance defect detection: The image processing software will analyze the captured wine bottle images to detect appearance defects of the wine bottles. Appearance defects include cracks, scratches, bubbles and label errors. Based on the preset defect standards, the system quickly identifies and marks unqualified wine bottles.

[0039] (3) Laser measuring equipment: Laser measuring equipment is used to detect the size and shape of wine bottles. Through laser scanning technology, the system obtains the three-dimensional contour data of the wine bottle and compares it with the standard model. The laser measuring equipment includes a laser transmitter, a receiver and a data processing unit, which can accurately measure the height, diameter and thickness parameters of the wine bottle.

[0040] (4) Data processing and analysis: The inspection system sends the data from visual inspection and laser measurement to the central control system. The control system uses a preset algorithm to analyze and process the data to determine whether the wine bottle meets the quality standards. The data analysis process includes image processing, feature extraction, and model matching.

[0041] (5) Real-time feedback: The inspection system will provide real-time feedback on the inspection results and display the inspection status of each bottle on the system interface. If an unqualified bottle is detected, the system will automatically record the defect type and location for subsequent processing. The operator can view detailed inspection reports through the system interface to promptly identify and solve problems in production.

[0042] (6) Multi-angle inspection: To improve the comprehensiveness of inspection, the visual inspection system will capture images of wine bottles from multiple angles. For example, multiple industrial cameras are installed at different positions on the conveyor belt to capture images of the top, side, and bottom of the wine bottle. Through multi-angle image analysis, every detail is ensured to be fully inspected.

[0043] (7) Fault handling: During the inspection process, if the equipment fails or the inspection system is abnormal, the system will automatically sound an alarm and stop the inspection. The operator needs to check and troubleshoot the fault in time to ensure the normal operation of the inspection system. Faults include camera out of focus and laser transmitter failure.

[0044] Through these meticulous testing steps, we ensure that each bottle has undergone a comprehensive quality inspection and meets production standards.

[0045] 4. Data Processing and Analysis

[0046] The data processing and analysis stage is the core of the detection system. By analyzing and processing the collected data, it is determined whether the quality of the wine bottle meets the standards. The specific description is as follows:

[0047] (1) Data acquisition: When a wine bottle passes through the visual inspection system and laser measurement equipment, the system will collect images and 3D contour data in real time. The collected data includes the appearance image, size parameters, shape information, etc. of the wine bottle. This data will be sent to the central control system through a high-speed data transmission interface (such as Ethernet or USB).

[0048] (2) Data preprocessing: The collected raw data needs to be preprocessed to improve the accuracy of the analysis. Image data preprocessing includes denoising, edge detection, and image enhancement. Laser measurement data preprocessing includes coordinate transformation and error correction. Preprocessed data is more suitable for subsequent analysis and processing.

[0049] (3) Image processing: The image processing algorithm will perform detailed analysis on the image data collected by the visual inspection system. Common image processing techniques include template matching, feature extraction, image segmentation, etc. The system will compare the processed image with the preset standard image to identify appearance defects and label errors.

[0050] (4) Dimension and shape analysis: The system will perform dimension and shape analysis on the data collected by the laser measuring device. Through 3D modeling technology, the system reconstructs the 3D contour of the wine bottle and compares it with the standard model. The parameters analyzed include the height, diameter, wall thickness, and bottle mouth shape of the wine bottle. Any parameter that exceeds the tolerance range will be marked as unqualified.

[0051] (5) Defect classification: The inspection system will classify the identified defects according to the preset defect standards. For example, appearance defects such as cracks, scratches, and bubbles are classified according to their severity. Size and shape defects are classified according to the degree to which they exceed the tolerance range. The classification results are helpful for subsequent processing and improvement.

[0052] (6) Qualification judgment: The system will comprehensively analyze the results of image processing and dimensional analysis to determine whether the wine bottle is qualified. The algorithm for qualification judgment needs to consider many factors, including the number, type, location, and severity of defects. Only when all parameters meet the standards will the wine bottle be judged as qualified.

[0053] (7) Data storage: The inspection system will store the inspection data of each wine bottle in the database. The stored data includes the original image, processed image, size parameters, analysis results, etc. Through data storage, the system can achieve long-term preservation and traceability of inspection data.

[0054] (8) Statistical analysis: By performing statistical analysis on the stored data, patterns and problems in production can be discovered. For example, by counting the number and type of unqualified wine bottles, weak links in the production process can be analyzed and improvement measures can be taken. Statistical analysis also generates various reports for production management and quality control.

[0055] (9) Real-time monitoring: The detection system will display the detection status of each wine bottle in real time on the control interface. The operator can view detailed detection reports through the interface to understand the current production status. If the system finds an abnormal situation, it will automatically issue an alarm to remind the operator to check and deal with it.

[0056] Through these meticulous data processing and analysis steps, we ensure that the quality of each wine bottle is fully inspected and evaluated, and the produced wine bottles meet the quality standards.

[0057] 5. Sorting

[0058] The sorting stage is the process of classifying qualified and unqualified wine bottles according to the test results. Through the automated sorting device, qualified wine bottles are ensured to enter the next production link, and unqualified wine bottles are removed from the production line. The specific description is as follows:

[0059] (1) Types of sorting devices: Commonly used sorting devices include pneumatic sorters, electric sorters and robotic arms. Pneumatic sorters push wine bottles to designated locations through airflow, electric sorters move wine bottles to different conveyor belts through electric mechanisms, and robotic arms grab and place wine bottles through programming control.

[0060] (2) Sensor detection: Before the wine bottles enter the sorting device, the system will once again confirm the position and status of the wine bottles through sensors. The sensors detect whether the wine bottles are arranged correctly, whether they have fallen or moved. If an abnormal situation is detected, the system will sound an alarm and suspend the sorting operation to avoid missorting.

[0061] (3) Classification standards: The sorting system will classify the bottles into qualified and unqualified categories based on the test results. Qualified bottles will be sent to the next production link or packaging link, while unqualified bottles will be removed from the production line and placed in a dedicated storage area for processing or scrapping. Classification standards need to be set according to production requirements to ensure accurate classification.

[0062] (4) Automatic sorting operation: The sorting device automatically classifies the bottles through the control system’s instructions. The pneumatic sorter will push the unqualified bottles away from the conveyor belt through airflow according to the test results. The electric sorter will move the bottles to different conveyor belts or storage areas through the electric mechanism. The robotic arm will grab the unqualified bottles and place them in the designated location.

[0063] (5) Classification and storage: Qualified and unqualified wine bottles will enter different conveyor belts or storage areas. Qualified wine bottles will be sent directly to the next production link or packaging line, while unqualified wine bottles will enter a special storage area and wait for further processing. Classification storage areas need to be clearly marked to avoid confusion.

[0064] (6) Recording and tracing: The sorting system will record the classification results of each wine bottle, including the test data and sorting time. Through recording and tracing, production managers can understand the testing and sorting process of each wine bottle, analyze the reasons for unqualified wine bottles, and take corresponding improvement measures.

[0065] (7) Abnormal handling: During the sorting process, if a system failure or abnormal operation is detected, the system will automatically sound an alarm and suspend the sorting operation. The operator needs to check and handle the failure in time to ensure the normal operation of the sorting system. Abnormal conditions include insufficient air pressure in the pneumatic sorter, motor failure in the electric sorter, and position deviation of the robot arm.

[0066] (8) Efficiency optimization: The sorting system needs to be optimized according to the rhythm of the production line to ensure that the sorting speed matches the production speed. By adjusting the speed and parameters of the sorting device, the sorting efficiency can be improved and the downtime of the production line can be reduced. Efficiency optimization also includes regular maintenance and care of the sorting device to avoid production being affected by equipment failure.

[0067] Through these meticulous sorting steps, qualified and unqualified wine bottles are accurately classified to ensure the smooth operation of the production line and product quality.

[0068] 6. Feedback and Adjustment

[0069] Feedback and adjustment are important links in the process of testing and feeding. Through the analysis and summary of the testing and sorting results, the production process can be adjusted and optimized in time to ensure the stability of production and the high quality of products. The specific description is as follows:

[0070] (1) Test result feedback: The test system will record the test data and sorting results of each wine bottle in real time. These data include appearance defects, size parameters, shape information, and whether they are qualified or not. The system will summarize these data to generate a test report and display it in real time on the control interface for operators and production managers to view.

[0071] (2) Abnormal situation alarm: If the detection system finds an abnormal situation, such as an abnormal increase in the number of unqualified wine bottles or frequent occurrence of a certain defect, the system will automatically send out an alarm signal. The alarm signal includes sound and light alarms and interface prompts to remind the operator to check the production line in time to find and eliminate the cause of the abnormality.

[0072] (3) Data analysis and statistics: Through statistical analysis of test data, problems and weak links in the production process are discovered. Analysis methods include trend analysis, defect classification statistics, and process parameter comparison. Through analysis, the root cause of the defects is found and corresponding improvement measures are formulated.

[0073] (4) Process adjustment: Adjust the production process based on the results of data analysis. For example, if a process is found to cause a large number of appearance defects, adjust the operating parameters or equipment settings of the process; if dimensional deviations are found to occur frequently, recalibrate the relevant equipment. Process adjustments need to be made when production is suspended to avoid affecting normal production.

[0074] (5) Equipment maintenance and calibration: In order to ensure the accuracy and stability of the detection system, it is necessary to regularly maintain and calibrate the equipment. Maintenance includes cleaning the lens, checking the sensor, calibrating the laser measurement equipment, etc. The calibration work needs to be carried out in accordance with the requirements of the equipment manufacturer to ensure the accuracy of the test results.

[0075] (6) Operator training: In order to improve the efficiency and accuracy of the detection system, it is also necessary to conduct regular training for operators. The training content includes the operation methods of the detection system, troubleshooting, data analysis skills, etc. Through training, the operator's skill level is improved to ensure the stable operation of the system.

[0076] (7) Implementation of improvement measures: Based on the results of data analysis, formulate and implement improvement measures. Improvement measures include equipment upgrades, process optimization, and adjustment of operating specifications. After the implementation of improvement measures, the improvement effect needs to be verified through the detection system, and corresponding records and evaluations need to be made.

[0077] (8) Continuous improvement: Quality management is a process of continuous improvement. Through continuous feedback and adjustment, production processes and product quality will gradually improve. Regular quality analysis meetings are held to summarize experiences and lessons, share improvement results, form a virtuous cycle, and promote continuous optimization of the entire production line.

[0078] Through these meticulous feedback and adjustment steps, we ensure the stability of the production process and the continuous improvement of product quality, and achieve efficient and high-quality production goals.

[0079] According to an embodiment of the present application, the specific method of data processing and analysis in step 4 of the finished glass wine bottle detection and loading method is as follows:

[0080] 1. Data preprocessing is carried out in the following way:

[0081] The following formula is used to remove noise:

[0082]

[0083]

[0084] P k|k =(IK k H)P k|k-1 ;

[0085] in, is the state estimate at time k, z k is the measurement value, H is the measurement matrix, K k is the Kalman gain, P k|k is the estimation error covariance, and R is the measurement noise covariance matrix.

[0086] The following formula is used for outlier detection:

[0087] D 2 =(x-μ) T ∑ -1 (x-μ);

[0088] Where x is a data point, μ is the mean vector, and ∑ is the covariance matrix.

[0089] 2. The methods for image processing and dimensional analysis are as follows:

[0090] (1) Feature extraction: Use independent component analysis to extract independent features of the image. Independent component analysis separates mixed signals by maximizing independence and is suitable for blind source separation and image feature extraction. X = AS, where X is the observed signal matrix, A is the mixing matrix, and S is the independent component matrix. By solving matrices A and S, the independent features of the image can be obtained.

[0091] (2) Model matching: Generalized maximum likelihood estimation is used to perform model matching. Generalized maximum likelihood estimation estimates parameters by maximizing the likelihood function of the data.

[0092]

[0093] Among them, L(θ|x) is the likelihood function, θ is the parameter to be estimated, and x is the observed data.

[0094] 3. The following methods are used in defect classification:

[0095] During the defect classification stage, statistical methods can be applied to improve the accuracy of classification.

[0096] Classification algorithm: Use support vector machine to classify different types of defects. Support vector machine separates different categories of data points by constructing a hyperplane:

[0097]

[0098] subject to you i (w T φ(x i )+b)≥1-ξ i ,ξ i ≥0;

[0099] Where w is the weight vector, b is the bias, ξ i is the slack variable, C is the penalty parameter, φ(x i ) is the feature mapping function, y i is the category label.

[0100] 4. Statistics in qualification determination

[0101] During the qualification determination stage, statistical methods can be applied to optimize the determination criteria.

[0102] (1) Multivariate statistical process control: Use the Hotelling T^2 control chart to monitor the stability of multiple quality characteristics. The Hotelling T^2 control chart provides more comprehensive process monitoring by considering the correlation between each characteristic.

[0103]

[0104] in, is the sample mean vector, μ is the population mean vector, and ∑ is the sample covariance matrix.

[0105] (2) Bayesian statistical method: Use Bayesian confidence intervals to assess the reliability of parameter estimates.

[0106]

[0107] Among them, P(θ|x) is the posterior distribution, P(x|θ) is the likelihood function, P(θ) is the prior distribution, and P(x) is the marginal likelihood.

[0108] 5. Statistics in Statistical Analysis and Feedback

[0109] In the statistical analysis and feedback stage, statistical methods can be applied to optimize the production process, as follows:

[0110] (1) Multiple regression analysis: Through multiple regression analysis, we can find out the key factors that affect the quality of wine bottles and establish a mathematical model for prediction and optimization.

[0111] y=β0+β1x1+β2x2+…+β n x n +∈;

[0112] Where y represents the response variable, x1, x2, ..., xn represent the predictor variables, β0, β1, ..., βn represent the regression coefficients, and ∈ represents the error term. The regression coefficients are estimated by the least squares method:

[0113]

[0114] (2) Generalized Linear Model: Use generalized linear models to handle data with different distributions and link functions. GLM can handle non-normally distributed data by extending the linear model.

[0115]

[0116] Where g is the link function, μ i is the expectation of the response variable, x i is the vector of predictor variables and β is the regression coefficient.

[0117] (3) Multifactor analysis of variance: Through multifactor analysis of variance, the comprehensive impact of different production processes and conditions on the quality of wine bottles is compared.

[0118]

[0119] Among them, E represents the within-group error matrix and H represents the between-group error matrix.

[0120] The above-mentioned embodiments only represent several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the claims.

Claims

1. A method for testing and feeding finished glass wine bottles, characterized in that: The steps include: S1: steps of preparing for loading, including wine bottle transfer, automatic loading, and automatic correction and guidance; S2: performing the steps of conveying and preliminary arrangement, including starting the conveyor belt and stabilizing the speed, then guiding the wine bottles, and then preliminary arrangement of the wine bottles; S3: Steps for visual and laser inspection; S4: Steps for data processing and analysis; S5: sorting step; S6: Steps for feedback and adjustment.

2. The finished glass wine bottle detection and feeding method according to claim 1, characterized in that: Step S1 specifically includes: The finished glass bottles are transferred from the production line or storage area to the input end of the automatic feeding system. A temporary storage area is set at the end of the production line to stack the produced glass bottles. These bottles are transported to the input area of ​​the feeding system by manual or automatic guided vehicles. After that, the vibrating plate moves the bottles by vibration and gradually arranges them into a single row. Before the bottles enter the conveyor belt, an automatic correction device is set to ensure that each bottle enters the conveyor belt in the correct direction and posture. The correction device is a mechanical baffle. Step S2 specifically includes: After the loading preparation is completed, the conveyor belt system is started. The surface of the conveyor belt is provided with anti-slip patterns to prevent the wine bottles from tipping over or sliding during movement. The conveyor belt speed is controlled by a frequency converter. During the conveying process, a guide device is provided to ensure that the wine bottles always remain in the center of the conveyor belt. An additional arranging device is provided on the conveyor belt. The arranging device is provided with at least two transverse baffles to separate the wine bottles one by one to avoid squeezing or overlapping of the wine bottles on the conveyor belt. A buffer zone is provided in front of the inspection station to adjust the flow of wine bottles on the conveyor belt. The buffer zone is a short-distance deceleration conveyor belt. Sensors are installed on the conveyor belt to monitor the position and status of the wine bottles in real time.

3. The finished glass wine bottle detection and feeding method according to claim 1 is characterized in that: Step S3 specifically includes: Conduct visual inspection. The visual inspection system consists of industrial cameras, lighting equipment, and image processing software. When a wine bottle enters the inspection station, the industrial camera will take a high-resolution image of the wine bottle. To ensure the clarity of the image, the lighting equipment is uniform and shadowless. The image processing software analyzes the captured image of the wine bottle and detects the appearance defects of the wine bottle. Appearance defects include cracks, scratches, bubbles, and label errors. The laser measurement equipment is used to detect the size and shape of the wine bottle. Through laser scanning technology, the three-dimensional contour data of the wine bottle is obtained and compared with the standard model. The inspection system sends the visual inspection and laser measurement data to the central control system. The control system determines whether the wine bottle meets the quality standards. The inspection system feeds back the inspection results in real time and displays the inspection status of each wine bottle on the system interface. If an unqualified wine bottle is detected, the system automatically records the defect type and location; Step S4 specifically includes: When the wine bottle passes through the visual inspection system and laser measuring equipment, the system collects images and three-dimensional contour data in real time. The collected data includes the appearance image, size parameters, and shape information of the wine bottle. These data will be sent to the central control system through a high-speed data transmission interface; the collected raw data is preprocessed to improve the accuracy of the analysis. The preprocessing of laser measurement data includes coordinate conversion and error correction. For the image data collected by the visual inspection system, the image processing algorithm will analyze it, compare the processed image with the preset standard image, identify appearance defects and label errors, and for the data collected by the laser measuring equipment, perform size and shape analysis, reconstruct the three-dimensional contour of the wine bottle, and compare it with the standard model. The inspection system will classify the identified defects according to the preset defect standards, comprehensively analyze the results of image processing and size analysis, and determine whether the wine bottle is qualified. The inspection system will store the inspection data of each wine bottle in the database. The stored data includes the original image, processed image, size parameters, and analysis results.

4. The finished glass wine bottle detection and feeding method according to claim 1, characterized in that: Step S5 specifically includes: A pneumatic sorter is used to push the wine bottles to the designated position through airflow. Before the wine bottles enter the sorting device, the position and status of the wine bottles are confirmed again by sensors. The sensors detect whether the wine bottles are arranged correctly, whether they are tipped over or moved. If an abnormality is detected, an alarm will be issued and the sorting operation will be suspended to avoid missorting. The wine bottles are divided into qualified and unqualified categories according to the test results. Qualified wine bottles will be sent to the next production link, and qualified and unqualified wine bottles will enter different conveyor belts or storage areas respectively. The classification results of each wine bottle, including test data and sorting time, are recorded. If a system failure or abnormal operation is detected, the system will automatically issue an alarm and suspend the sorting operation; Step S6 specifically includes: The detection system records the detection data and sorting results of each wine bottle in real time. These data include appearance defects, size parameters, shape information, and whether it is qualified or not. These data are summarized to generate a detection report and displayed in real time on the control interface for the operator to view. If the detection system finds an abnormal situation, it will automatically send out an alarm signal. Through statistical analysis of the detection data, problems and weak links in the production process are discovered, the root causes of the defects are found, and corresponding improvement measures are formulated; according to the results of data analysis, the production process is adjusted, and the equipment is regularly maintained and calibrated. The maintenance content includes cleaning the lens, checking the sensor, and calibrating the laser measurement equipment.

5. The finished glass wine bottle detection and feeding method according to claim 3 is characterized in that: When performing data processing and analysis, data preprocessing is performed in the following way: The following formula is used to remove noise: P k|k =(I-K k H)P k|k1 ; in, is the state estimate at time k, z k is the measurement value, H is the measurement matrix, K k is the Kalman gain, P k|k is the estimation error covariance, and R is the measurement noise covariance matrix. The following formula is used for outlier detection: D 2 =(x-μ) T ∑ -1 (x-μ); Where x is a data point, μ is the mean vector, and ∑ is the covariance matrix.

6. The finished glass wine bottle detection and feeding method according to claim 3 is characterized by: The methods for image processing and dimensional analysis are as follows: Feature extraction, using independent component analysis to extract independent features of the image. Independent component analysis separates mixed signals by maximizing independence and is suitable for blind source separation and image feature extraction. X = AS, where X is the observed signal matrix, A is the mixing matrix, and S is the independent component matrix. By solving matrices A and S, the independent features of the image can be obtained; Model matching, using generalized maximum likelihood estimation to perform model matching. Generalized maximum likelihood estimation estimates parameters by maximizing the likelihood function of the data; Among them, L(θ|x) is the likelihood function, θ is the parameter to be estimated, and x is the observed data.

7. The finished glass wine bottle detection and feeding method according to claim 3 is characterized in that: The following method is used to classify defects: Use support vector machines to classify different types of defects. Support vector machines separate different categories of data points by constructing hyperplanes: subject to y i (w T φ(x i )+b)≥1-ξ i ,ξ i ≥0; Where w is the weight vector, b is the bias, ξ i is the slack variable, C is the penalty parameter, φ(x i ) is the feature mapping function, y i is the category label.

8. The finished glass wine bottle detection and feeding method according to claim 3 is characterized by: The specific method for making a qualified judgment is as follows: Use the Hotelling T^2 control chart to monitor the stability of multiple quality characteristics. The Hotelling T^2 control chart provides more comprehensive process monitoring by considering the correlation between each characteristic. in, is the sample mean vector, β is the population mean vector, and ∑ is the sample covariance matrix; Use Bayesian confidence intervals to assess the reliability of parameter estimates; Among them, P(θ|x) is the posterior distribution, P(x|θ) is the likelihood function, P(θ) is the prior distribution, and P(x) is the marginal likelihood.

9. The finished glass wine bottle detection and feeding method according to claim 1, characterized in that: The specific methods for statistical analysis and feedback are as follows: Through multiple regression analysis, we can find out the key factors that affect the quality of wine bottles and establish a mathematical model for prediction and optimization; y=β0+β1x1+β2x2+…+β n x n +∈; Where y represents the response variable, x1, x2, ..., xn represent the predictor variables, β0, β1, ..., βn represent the regression coefficients, and ∈ represents the error term. The regression coefficients are estimated by the least squares method: Use generalized linear models to handle data with different distributions and link functions. GLM can handle non-normally distributed data by extending the linear model. Where g is the link function, μ i is the expectation of the response variable, x i is the vector of predictor variables and β is the regression coefficient. Through multi-factor variance analysis, the comprehensive effects of different production processes and conditions on wine bottle quality were compared; Among them, E represents the within-group error matrix and H represents the between-group error matrix.

10. A finished glass wine bottle detection and feeding system, characterized in that: A finished glass wine bottle testing and loading method as claimed in any one of claims 1 to 9.

Images