Wine bottle conveying line for packaging of brewery

Abstract

The invention relates to the technical field of conveyors, in particular to a winebottle conveying line for packaging in a brewery, which comprises a belt conveyor, the top of the belt conveyor is fixedly connected with a fixing plate, the fixing plate is provided with a limiting plate, the outside of the limiting plate is fixedly connected with a connecting plate, and the outside of the connecting plate is fixedly connected with a protective plate. The outer portion of the protection plate is fixedly connected with a hinge seat, the protection plate is pushed through the telescopic adjusting assembly to conduct left-right sliding adjustment, so that distance adjustment is completed, conveying can be conducted according to wine bottles of different sizes, in addition, through arrangement of a wine bottle monitoring system, appearance defects of the wine bottles can be detected, and the practicability is high. And when unqualified wine bottles are encountered, the wine bottles can be moved to the outside of the belt conveyor through the clamping and transferring assembly, and removing is completed.

Description

Technical Field

[0001] The invention relates to the technical field of conveyors, in particular to a conveyor line for packaging wine bottles in a winery. Background Art

[0002] In modern wine production, the wine bottle conveyor line is a key link in the production process. With the continuous expansion of production scale and the increasing demand of consumers for product quality, it is very important to ensure the quality stability of wine bottles during the conveying process.

[0003] Traditional wine bottle conveyor lines have fixed sizes and cannot be adjusted to convey wine bottles of different sizes. They also cannot inspect the wine bottles and cannot remove unqualified wine bottles. Summary of the invention

[0004] In view of the technical problems mentioned in the background technology, the present invention provides a wine bottle conveyor line for packaging in a winery.

[0005] The technical solution adopted by the present invention is: a conveyor line for packaging wine bottles in a winery, comprising a belt conveyor, two top parts of the belt conveyor are fixedly connected with fixed plates, the fixed plates are provided with limit plates, the outside of the limit plates is fixedly connected with a connecting plate, the outside of the connecting plate is fixedly connected with a protective plate, the outside of the protective plate is fixedly connected with a hinge seat, the outside of the hinge seat is rotatably connected with a buffer bar, the outside of the buffer bar is fixedly connected with a buffer plate, a buffer assembly is provided between the annular plate and the fixed plate, a telescopic adjustment assembly is provided between the limit plate and the fixed plate, a fixed frame is provided on the outside of the belt conveyor, a clamping and transferring assembly is provided on the fixed frame, and a wine bottle monitoring system is also provided on the outside of the fixed frame.

[0006] In one embodiment, the buffer component is a first spring disposed between the buffer plate and the protective plate, and two ends of the first spring are respectively connected to the buffer plate and the protective plate.

[0007] In one embodiment, the buffer assembly also includes a second spring, the outside of the fixed plate is fixedly connected to a connecting bar, one end of the second spring is fixedly connected to the connecting bar, one end of the second spring is fixedly connected to a first magnet, and the outside of the protective plate is fixedly connected to a second magnet at a height corresponding to the position of the first magnet, and the first magnet and the second magnet are arranged with the same poles to repel each other.

[0008] In one embodiment, the telescopic adjustment assembly is a plurality of connecting rods arranged between a limit plate and a fixed plate, the connecting rods are hinged to each other to present a scissors-type structure, the connecting rods are rotatably connected to the corresponding limit plate and the fixed plate, the outside of the limit plate and the fixed plate are fixedly connected to a guide rail, a slider is slidably connected in the guide rail, the slider is rotatably connected to the corresponding connecting rod, the outside of the belt conveyor is fixedly connected to a cylinder, the output end of the cylinder is fixedly connected to a connecting frame, one end of the connecting frame extends to one side of the fixed plate and is fixedly connected to the slider.

[0009] In one embodiment, the outside of the fixing frame is rotatably connected to a threaded rod, the outside of the fixing frame is fixedly connected to a motor, the output end of the motor is fixedly connected to the threaded rod, the outside of the threaded rod is threadedly connected to a nut block, the outside of the fixing frame is fixedly connected to a limit rod, and the limit passes through the nut block.

[0010] In one embodiment, the clamping assembly includes a first electric push rod fixedly connected to the bottom of the nut block, a sliding sleeve fixedly connected to the output end of the first electric push rod, and a clamping arm arranged outside the sliding sleeve, the outer sleeve is provided with a slip ring, the bottom of the slip ring is hinged with a hinged rod, one end of the hinged rod is rotatably connected to the clamping arm, the output end of the first electric push rod is fixedly connected to a mounting seat, the clamping arm is rotatably connected to the mounting seat, the outside of the nut block is fixedly connected to a second electric push rod, and the output end of the second electric push rod is fixedly connected to the slip ring.

[0011] In one embodiment, the wine bottle monitoring system is composed of an image acquisition unit, a data processing and analysis unit, a fault diagnosis and early warning unit, and a control and execution unit.

[0012] In one embodiment, the image acquisition unit includes a mounting frame fixedly connected to the outside of the fixing frame and a plurality of industrial cameras fixedly connected to the outside of the mounting frame, and according to the height h and the conveying speed v of the wine bottle, the installation angle θ of the camera and the width w of the shooting area, the following relationship is satisfied:

[0013] w=h×tanθ

[0014] The camera exposure time t exp It should be adjusted according to the conveying speed of the belt conveyor to meet the following requirements:

[0015]

[0016] For the inspection of the mouth and bottom of the wine bottle, an area array camera is fixedly connected to the outside of the fixed plate to shoot the mouth and bottom of the bottle without blind spots. The focal length f of the camera lens is selected according to the size of the shooting area and the working distance d to meet the following requirements:

[0017]

[0018] A fill light is fixedly connected to the outside of the fixing plate;

[0019] Assume the reflectivity of the bottle is R b , the luminous intensity of the light source is I s , the reflectivity at the crack is R c ,

[0020] According to Lambert's cosine law, the reflected light intensity I b and I c They are: I b =I s ×R b ×cos45°

[0021] I c =I s ×R c ×cos45°

[0022] Use a ring light source, the inner diameter of the ring light source is D i n and outer diameter D o ut according to the diameter D of the bottle mouth n Designed to meet:

[0023] D in =D n -ΔD1

[0024] D out =D n +ΔD2

[0025] Where ΔD1 and ΔD2 are appropriate margins.

[0026] In one embodiment, the data processing and analysis unit includes the following:

[0027] Image preprocessing:

[0028] First, the collected wine bottle images are grayed out, the color images are converted into grayscale images, and the weighted average method is used for graying. The formula is:

[0029] Gray(x,y)=0.299×R(x,y)+0.587×G(x,y)+0.114×B(x,y)

[0030] Among them, R(x,y), G(x,y), B(x,y) are the red, green, and blue channel values ​​of the pixel point (x,y) in the color image, and Gray(x,y) is the grayscale value;

[0031] Then, the image is filtered to remove noise interference. The Gaussian filtering algorithm is used, and its filtering kernel function is:

[0032]

[0033] Among them, σ is the standard deviation, and the appropriate σ value is selected according to the characteristics of the noise and the detail requirements of the image;

[0034] Defect feature extraction and identification:

[0035] The object detection algorithm based on deep learning analyzes the preprocessed images and identifies various defect features of the wine bottles. For cracks on the bottle body, the convolutional neural network (CNN) model is trained to automatically learn the texture, shape and grayscale change features of the cracks.

[0036] Assume that the input image of the CNN model is I. After multiple layers of convolution and pooling operations, the feature map F is obtained. Through the fully connected layer and classifier, the output is whether there are cracks in the image and the location and size of the cracks.

[0037] The model training process uses the back propagation algorithm to continuously adjust the weights and biases of the network to minimize the loss function L between the predicted results and the true labels. The commonly used loss function is the cross entropy loss function.

[0038]

[0039] Where N is the number of samples, y i is the true label (0 means no crack, 1 means crack), is the prediction output of the model;

[0040] For the flatness detection of the bottle mouth, the contour information of the bottle mouth edge is extracted to calculate its roundness error ΔC and flatness error ΔP;

[0041] Assume that the actual contour point coordinates of the bottle mouth edge are (x i ,y i ), the ideal circle equation obtained by least squares fitting is (xa) 2 +(yb) 2 =r 2 , then the roundness error ΔC can be calculated by the following formula:

[0042]

[0043] The flatness error ΔP is determined by analyzing the height difference of the bottle mouth edge in the vertical direction. The bottle mouth edge is divided into m equal intervals, and the average height h of each interval is calculated. j , then the flatness error ΔP is:

[0044] ΔP=max(h j )-min(h j)

[0045] According to the preset threshold T C and T P , determine whether the bottle mouth is qualified;

[0046] If ΔC>T C or ΔP>T P , then it is determined that there is a defect in the bottle mouth;

[0047] The fault diagnosis and early warning unit includes the following:

[0048] Fault classification and evaluation:

[0049] For each defect type, a corresponding fault assessment model is established;

[0050] For the cracks on the bottle, let the length of the crack be l, the width be w, and the depth be d. According to the principles of material mechanics and fluid mechanics, the influence of the crack on the strength and sealing of the wine bottle is evaluated. The formula is:

[0051] S=k1×l×w×d+k2×f(l,w,d)

[0052] Among them, k1 and k2 are empirical coefficients, and f(l,w,d) is a function related to the crack shape and distribution, and its specific form is determined by experimental data and simulation analysis;

[0053] According to the value of S, the bottle body crack failure is divided into different levels so that corresponding treatment measures can be taken;

[0054] Early warning mechanism and information transmission:

[0055] When the fault diagnosis unit detects a defect in a wine bottle, the early warning mechanism is immediately activated. Depending on the severity of the fault, the operator is notified through sound and light alarms, display screen prompts, and by sending alarm information to the production management system.

[0056] In one embodiment, the control and execution unit includes the following:

[0057] Belt conveyor speed adjustment:

[0058] According to the working state of the image acquisition unit and the processing speed of the data processing and analysis unit, the speed v of the wine bottle belt conveyor is adjusted in real time;

[0059] Assume that the total time of image acquisition and processing is t total , the safe distance between two adjacent bottles of wine is s safe , the speed of the belt conveyor meets:

[0060]

[0061] By adjusting the frequency converter of the conveying motor of the belt conveyor, the speed of the belt conveyor is controlled to match the working rhythm of the detection system;

[0062] Removal of unqualified wine bottles:

[0063] When the fault diagnosis and early warning unit sends a signal of an unqualified wine bottle, the control and execution unit starts the clamping and transfer component to remove the unqualified wine bottle from the belt conveyor.

[0064] The beneficial effects of the present invention are as follows: compared with the prior art, in the present invention, the protective plate is pushed to slide left and right by the telescopic adjustment component, thereby completing the distance adjustment, so that wine bottles of different sizes can be transported. In addition, through the setting of the wine bottle monitoring system, the appearance defects of the wine bottles can be detected. When encountering unqualified wine bottles, the wine bottles can be moved to the outside of the belt conveyor by the clamping transfer component to complete the removal. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 It is a schematic diagram of the structure of the present invention;

[0066] Figure 2 It is a three-dimensional structural schematic diagram of the present invention;

[0067] Figure 3 It is a schematic diagram of the bottom structure of the present invention;

[0068] Figure 4 It is a schematic diagram of the installation position structure of the cylinder in the present invention;

[0069] Figure 5 It is a side structural schematic diagram of the present invention;

[0070] Figure 6 yes Figure 2 Schematic diagram of the enlarged structure of the A area in the middle;

[0071] Figure 7 yes Figure 2 Schematic diagram of the enlarged structure of the middle B area;

[0072] Figure 8 yes Figure 5 Schematic diagram of the enlarged structure of the C area in the middle.

[0073] The markings in the figure are:

[0074] 100, belt conveyor; 1001, fixed plate; 1002, connecting frame; 1003, guide rail; 1004, connecting rod; 1005, limit plate; 1006, connecting plate; 1007, protective plate; 1008, buffer strip; 1009, buffer plate; 10010, hinge seat; 10011, first spring; 10012, connecting strip; 10013, second spring; 10014, first magnet; 10015, second magnet; 10017, cylinder;

[0075] 200, fixing bracket; 2001, motor; 2002, threaded rod; 2003, mounting bracket; 2004, industrial camera; 2005, nut block; 2006, first electric push rod; 2007, sleeve; 2008, slip ring; 2009, second electric push rod; 20010, articulated rod; 20011, clamping arm; 20012, mounting base. DETAILED DESCRIPTION

[0076] In the description of the present invention, it should be noted that the orientations or positional relationships indicated by terms such as “front”, “up”, “down”, “left”, “right”, “vertical” and “horizontal” are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention.

[0077] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0078] The following is combined with Figure 1-8 The present invention is further described.

[0079] In order to solve the problems existing in the background technology, the present application proposes the following technical solutions: a wine bottle conveyor line 100 for packaging in a winery, comprising a belt conveyor 100, the top of the belt conveyor 100 is fixedly connected with a fixed plate 1001, the fixed plate 1001 is provided with a limit plate 1005, the outside of the limit plate 1005 is fixedly connected with a connecting plate 1006, the outside of the connecting plate 1006 is fixedly connected with a protective plate 1007, the outside of the protective plate 1007 is fixedly connected with a hinge seat 10010, the outside of the hinge seat 10010 is rotatably connected with a buffer bar 1008, the outside of the buffer bar 1008 is fixedly connected with a buffer plate 1009, a buffer assembly is provided between the annular plate and the fixed plate 1001, a telescopic adjustment assembly is provided between the limit plate 1005 and the fixed plate 1001, a fixed frame 200 is provided on the outside of the belt conveyor 100, a clamping and transferring assembly is provided on the fixed frame 200, and a wine bottle monitoring system is also provided on the outside of the fixed frame 200.

[0080] In a further design, the buffer component is a first spring 10011 arranged between the buffer plate 1009 and the protective plate 1007, and the two ends of the first spring 10011 are respectively connected to the buffer plate 1009 and the protective plate 1007. The setting of the first spring 10011 can buffer the impact of the product during the transportation of the wine bottle.

[0081] Among them, the buffer component also includes a second spring 10013, the outside of the fixed plate 1001 is fixedly connected with a connecting strip 10012, one end of the second spring 10013 is fixedly connected to the connecting strip 10012, one end of the second spring 10013 is fixedly connected to the first magnet 10014, and the outside of the protective plate 1007 is fixedly connected to the second magnet 10015 at a height corresponding to the position of the first magnet 10014. The first magnet 10014 and the second magnet 10015 are arranged with the same poles repelling each other. In addition, the second spring 10013 and the first magnet 10014 and the second magnet 10015 are arranged with the same poles repelling each other, which can further buffer the impact of the product during the transportation of the wine bottle, and the larger the distance between the protective plates 1007, the better the buffering effect, because the first magnet 10014 and the second magnet 10015 are closer.

[0082] In a further design, the telescopic adjustment component is a plurality of connecting rods 1004 arranged between the limit plate 1005 and the fixed plate 1001, the connecting rods 1004 are hinged to each other to present a scissor-type structure, the connecting rods 1004 are rotatably connected to the corresponding limit plate 1005 and the fixed plate 1001, the outsides of the limit plate 1005 and the fixed plate 1001 are fixedly connected to the guide rail 1003, the guide rail 1003 is slidably connected to the slider, the slider is rotatably connected to the corresponding connecting rod 1004, and the belt type The outside of the conveyor 100 is fixedly connected to a cylinder 10017, and the output end of the cylinder 10017 is fixedly connected to a connecting frame 1002. One end of the connecting frame 1002 extends to one side of the fixed plate 1001 and is fixedly connected to the slider. The cylinder 10017 drives the connecting frame 1002 to slide, the connecting frame 1002 drives the slider to slide, and the slider drives the connecting rod 1004 to work. The connecting rod 1004 can push the protective plate 1007 to slide left and right, thereby completing the distance adjustment.

[0083] In a further design, the outer part of the fixing frame 200 is rotatably connected with a threaded rod 2002, the outer part of the fixing frame 200 is fixedly connected with a motor 2001, the output end of the motor 2001 is fixedly connected with the threaded rod 2002, the outer part of the threaded rod 2002 is threadedly connected with a nut block 2005, the outer part of the fixing frame 200 is fixedly connected with a limit rod, the limit passes through the nut block 2005, the clamping assembly includes a first electric push rod 2006 fixedly connected to the bottom of the nut block 2005, a sleeve 2007 fixedly connected to the output end of the first electric push rod 2006, and a clamping arm 20011 arranged on the outside of the sleeve 2007, the outer sleeve of the sleeve 2007 is provided with a slip ring 2008, the bottom of the slip ring 2008 is hinged with an articulated rod 20010, one end of the articulated rod 20010 is rotatably connected to the clamping arm 20011, the output end of the first electric push rod 2006 is fixedly connected with a mounting seat 200 12. The clamping arm 20011 is rotatably connected to the mounting seat 20012. The outside of the nut block 2005 is fixedly connected with a second electric push rod 2009. The output end of the second electric push rod 2009 is fixedly connected to the slip ring 2008. When an unqualified wine bottle is encountered, the first electric push rod 2006 pushes the sliding sleeve 2007 to move downward, and the second electric push rod 2009 pushes downward synchronously. When the clamping arm 20011 is located outside the wine bottle, the first electric push rod 2006 stops moving, and the second electric push rod 2009 pushes downward, so that the clamping arm 20011 clamps the outside of the wine bottle under the push of the hinged rod 20010. Subsequently, the first electric push rod 2006 and the second electric push rod 2009 move upward synchronously. After the wine bottle is taken out, the motor 2001 drives the threaded rod 2002 to rotate, and the wine bottle is moved to the outside of the belt conveyor 100 to complete the removal.

[0084] In addition, the second electric push rod 2009 can also be directly fixedly connected to the sliding sleeve 2007.

[0085] As another embodiment, the wine bottle monitoring system includes an image acquisition unit, a data processing and analysis unit, a fault diagnosis and early warning unit, and a control and execution unit.

[0086] In this embodiment, the image acquisition unit includes a mounting frame 2003 fixedly connected to the outside of the fixing frame 200 and a plurality of industrial cameras 2004 fixedly connected to the outside of the mounting frame 2003, and according to the height h and the conveying speed v of the wine bottle, the installation angle θ of the camera and the width w of the shooting area, the following relationship is satisfied:

[0087] w=h×tanθ

[0088] The camera exposure time t exp It should be adjusted according to the conveying speed of the belt conveyor to meet the following requirements:

[0089]

[0090] For the inspection of the mouth and bottom of the wine bottle, an area array camera is fixedly connected to the outside of the fixed plate to shoot the mouth and bottom of the bottle without blind spots. The focal length f of the camera lens is selected according to the size of the shooting area and the working distance d to meet the following requirements:

[0091]

[0092] In this embodiment, a fill light is fixedly connected to the outside of the fixing plate. For bottle body crack detection, a high-brightness strip light source is used to illuminate the bottle body at an angle of 45° to enhance the contrast between the crack and the bottle body surface.

[0093] Assume the reflectivity of the bottle is R b , the luminous intensity of the light source is I s , the reflectivity at the crack is R c ,

[0094] According to Lambert's cosine law, the reflected light intensity I b and I c They are: I b =I s ×R b ×cos45°

[0095] I c =I s ×R c ×cos45°

[0096] In this embodiment, by adjusting the intensity and angle of the light source, I b and I cThe difference is obvious enough to facilitate image acquisition and subsequent defect identification. For the flatness inspection of the bottle mouth, a ring light source is used to provide uniform frontal illumination to avoid the influence of shadows on the inspection results. The inner diameter D of the ring light source i n and outer diameter D o ut according to the diameter D of the bottle mouth n Designed to meet:

[0097] D in =D n -ΔD1

[0098] D out =D n +ΔD2

[0099] ΔD1 and ΔD2 are appropriate margins to ensure that the light source can fully illuminate the bottle mouth area without generating excessive reflected light to interfere with detection.

[0100] In this embodiment, the data processing and analysis unit includes the following:

[0101] Image preprocessing:

[0102] In this embodiment, the collected wine bottle image is first grayed out to convert the color image into a gray image to simplify subsequent calculations and analysis. The weighted average method is used for graying, and the formula is:

[0103] Gray(x,y)=0.299×R(x,y)+0.587×G(x,y)+0.114×B(x,y)

[0104] Among them, R(x,y), G(x,y), B(x,y) are the red, green, and blue channel values ​​of the pixel point (x,y) in the color image, and Gray(x,y) is the grayscale value. ° Then, image filtering is performed to remove noise interference. The Gaussian filtering algorithm is used, and its filtering kernel function is:

[0105]

[0106] Among them, σ is the standard deviation. The appropriate σ value is selected according to the characteristics of the noise and the detail requirements of the image; it is generally between 0.5 and 2. By performing convolution operations on each pixel in the image and the filter kernel, noise smoothing is achieved to improve the quality of the image.

[0107] Defect feature extraction and identification:

[0108] In this embodiment, the preprocessed image is analyzed by a target detection algorithm based on deep learning to identify various defect features of the wine bottle. For cracks on the bottle body, a convolutional neural network (CNN) model is trained to automatically learn the texture, shape and grayscale change features of the cracks.

[0109] Assume that the input image of the CNN model is I. After multiple layers of convolution and pooling operations, the feature map F is obtained. Through the fully connected layer and classifier, the output is whether there are cracks in the image and the location and size of the cracks.

[0110] The model training process uses the back propagation algorithm to continuously adjust the weights and biases of the network to minimize the loss function L between the predicted results and the true labels. The commonly used loss function is the cross entropy loss function.

[0111]

[0112] Where N is the number of samples, y i is the true label (0 means no crack, 1 means crack), is the prediction output of the model;

[0113] For the flatness detection of the bottle mouth, the contour information of the bottle mouth edge is extracted to calculate its roundness error ΔC and flatness error ΔP. Assume that the coordinates of the actual contour point of the bottle mouth edge are (x i ,y i ), the ideal circle equation obtained by least squares fitting is (xa) 2 +(yb) 2 =r 2 , then the roundness error ΔC can be calculated by the following formula:

[0114]

[0115] The flatness error ΔP is determined by analyzing the height difference of the bottle mouth edge in the vertical direction. The bottle mouth edge is divided into m equal intervals, and the average height h of each interval is calculated. j , then the flatness error ΔP is:

[0116] ΔP=max(h j )-min(h j )

[0117] According to the preset threshold T C and T P , judge whether the bottle mouth is qualified. If ΔC>T C or ΔP>T P , then it is determined that there is a defect in the bottle mouth;

[0118] In this embodiment, the fault diagnosis and early warning unit includes the following:

[0119] Fault classification and evaluation:

[0120] Based on the results of defect feature extraction and recognition, the wine bottle faults are classified and evaluated, and the wine bottle defects are divided into serious defects (such as large cracks on the bottle body, serious deformation of the bottle mouth, etc.), moderate defects (such as small cracks on the bottle body, bubbles at the bottom of the bottle, etc.) and minor defects (such as scratches on the bottle surface, uneven labeling, etc.);

[0121] For each defect type, a corresponding fault assessment model is established;

[0122] For the cracks on the bottle, let the length of the crack be l, the width be w, and the depth be d. According to the principles of material mechanics and fluid mechanics, the influence of the crack on the strength and sealing of the wine bottle is evaluated. The formula is:

[0123] S=k1×l×w×d+k2×f(l,w,d)

[0124] Among them, k1 and k2 are empirical coefficients, and f(l,w,d) is a function related to the crack shape and distribution, and its specific form is determined by experimental data and simulation analysis;

[0125] According to the value of S, the bottle body crack failure is divided into different levels so that corresponding treatment measures can be taken;

[0126] Early warning mechanism and information transmission:

[0127] When the fault diagnosis unit detects a defect in a wine bottle, the early warning mechanism is immediately activated. Depending on the severity of the fault, the operator is notified through sound and light alarms, display screen prompts, and by sending alarm information to the production management system.

[0128] In this embodiment, for serious defects, a high-pitched alarm and red flashing light are used, and the position and image information of the defective wine bottle are highlighted on the display screen, and the belt conveyor is stopped at the same time to prevent unqualified products from continuing to flow into the subsequent production links; for moderate defects, a medium-pitched alarm and yellow light are issued to prompt operators to focus on and review; for minor defects, text information is displayed on the display screen, and the type and number of defects are recorded for statistical analysis and quality improvement in the subsequent production process. The early warning information also includes detailed data such as the time of the failure, the batch number of the wine bottle, and the location on the production line, which facilitates enterprises to trace quality and troubleshoot problems.

[0129] Among them, the control and execution unit includes the following:

[0130] Belt conveyor speed adjustment:

[0131] According to the working state of the image acquisition unit and the processing speed of the data processing and analysis unit, the speed v of the wine bottle belt conveyor is adjusted in real time;

[0132] Assume that the total time of image acquisition and processing is ttotal , the safe distance between two adjacent bottles of wine is s safe ,In order to ensure that there will be no missed detection or misjudgment during the detection process, the speed of the belt conveyor meets:

[0133]

[0134] By adjusting the frequency converter of the conveying motor of the belt conveyor, the speed of the belt conveyor is controlled to match the working rhythm of the detection system;

[0135] Removal of unqualified wine bottles:

[0136] When the fault diagnosis and early warning unit sends a signal of an unqualified wine bottle, the control and execution unit starts the clamping and transfer component to remove the unqualified wine bottle from the belt conveyor.

[0137] In summary, the wine bottle monitoring system uses high-resolution industrial cameras, multi-light source combinations and deep learning algorithms to conduct comprehensive and high-precision inspections of the body, mouth and bottom of the wine bottle, and accurately identify various types of defects, including tiny cracks, bubbles, deformations, scratches and label sticking problems. Compared with traditional inspection methods, the inspection accuracy is improved, missed inspections and misjudgments are avoided, and the stability and consistency of product quality are ensured.

[0138] In order for those skilled in the art to fully understand the technical solution, the method of using this embodiment is as follows:

[0139] First, the distance between the two protection plates 1007 is adjusted according to the size of the wine bottle, so that the wine bottle can be stably transported on the belt conveyor 100, as follows:

[0140] The cylinder 10017 drives the connecting frame 1002 to slide, the connecting frame 1002 drives the slider to slide, the slider drives the connecting rod 1004 to work, and the connecting rod 1004 can push the protective plate 1007 to slide left and right to adjust the distance;

[0141] Subsequently, the appearance defects of the wine bottles are inspected through the wine bottle monitoring system. When an unqualified wine bottle is encountered, the first electric push rod 2006 pushes the sliding sleeve 2007 to move downward, and the second electric push rod 2009 pushes downward synchronously. When the clamping arm 20011 is located outside the wine bottle, the first electric push rod 2006 stops moving, and the second electric push rod 2009 pushes downward, so that the clamping arm 20011 clamps the outside of the wine bottle under the push of the hinged rod 20010. Subsequently, the first electric push rod 2006 and the second electric push rod 2009 move upward synchronously. After the wine bottle is taken out, the motor 2001 drives the threaded rod 2002 to rotate, and the wine bottle is moved to the outside of the belt conveyor 100 to complete the removal.

[0142] The standard parts used in the present invention can all be purchased from the market, and special-shaped parts can be customized according to the description in the specification and the drawings. The specific connection methods of each part adopt conventional means such as mature bolts, rivets, welding, etc. in the prior art. Machinery, parts and equipment all adopt conventional models in the prior art, and the circuit connection adopts the conventional connection method in the prior art, which will not be described in detail here. The content not described in detail in this specification belongs to the prior art known to professional and technical personnel in this field.

[0143] While the embodiments of the present invention have been shown and described, it will be apparent to those skilled in the art that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A conveyor line for packaging wine bottles in a winery, comprising a belt conveyor (100), characterized in that: The top of the belt conveyor (100) is fixedly connected to a fixed plate (1001), the fixed plate (1001) is provided with a limit plate (1005), the outside of the limit plate (1005) is fixedly connected to a connecting plate (1006), the outside of the connecting plate (1006) is fixedly connected to a protective plate (1007), the outside of the protective plate (1007) is fixedly connected to a hinge seat (10010), and the outside of the hinge seat (10010) is rotatably connected to A buffer bar (1008) is fixedly connected to the outside of the buffer bar (1008) with a buffer plate (1009), a buffer component is provided between the annular plate and the fixed plate (1001), a telescopic adjustment component is provided between the limit plate (1005) and the fixed plate (1001), a fixed frame (200) is provided on the outside of the belt conveyor (100), a clamping and transporting component is provided on the fixed frame (200), and a wine bottle monitoring system is also provided on the outside of the fixed frame (200).

2. A wine bottle conveyor line for packaging in a winery according to claim 1, characterized in that: The buffer component is a first spring (10011) arranged between the buffer plate (1009) and the protective plate (1007), and two ends of the first spring (10011) are respectively connected to the buffer plate (1009) and the protective plate (1007).

3. The wine bottle conveyor line for packaging in a winery according to claim 2, characterized in that: The buffer component also includes a second spring (10013), the outside of the fixed plate (1001) is fixedly connected to a connecting strip (10012), one end of the second spring (10013) is fixedly connected to the connecting strip (10012), one end of the second spring (10013) is fixedly connected to a first magnet (10014), and the outside of the protective plate (1007) is fixedly connected to a second magnet (10015) at a height corresponding to the position of the first magnet (10014), and the first magnet (10014) and the second magnet (10015) are arranged with the same poles repelling each other.

4. The wine bottle conveyor line for packaging in a winery according to claim 3, characterized in that: The telescopic adjustment assembly is a plurality of connecting rods (1004) arranged between a limit plate (1005) and a fixed plate (1001); the connecting rods (1004) are hinged to each other to present a scissor-type structure; the connecting rods (1004) are rotatably connected to the corresponding limit plate (1005) and the fixed plate (1001); the outsides of the limit plate (1005) and the fixed plate (1001) are fixedly connected to a guide rail (1003); a slider is slidably connected in the guide rail (1003); the slider is rotatably connected to the corresponding connecting rod (1004); the outside of the belt conveyor (100) is fixedly connected to a cylinder (10017); the output end of the cylinder (10017) is fixedly connected to a connecting frame (1002); one end of the connecting frame (1002) extends to one side of the fixed plate (1001) and is fixedly connected to the slider.

5. The wine bottle conveyor line for packaging in a winery according to claim 4, characterized in that: The outside of the fixing frame (200) is rotatably connected to a threaded rod (2002), the outside of the fixing frame (200) is fixedly connected to a motor (2001), the output end of the motor (2001) is fixedly connected to the threaded rod (2002), the outside of the threaded rod (2002) is threadedly connected to a nut block (2005), and the outside of the fixing frame (200) is fixedly connected to a limit rod, and the limit rod passes through the nut block (2005).

6. The wine bottle conveyor line for packaging in a winery according to claim 5, characterized in that: The clamping assembly comprises a first electric push rod (2006) fixedly connected to the bottom of a nut block (2005), a sliding sleeve (2007) fixedly connected to the output end of the first electric push rod (2006), and a clamping arm (20011) arranged outside the sliding sleeve (2007); the sliding sleeve (2007) is sleeved with a slip ring (2008) on the outside; the bottom of the slip ring (2008) is hinged with a hinge rod (20010); one end of the hinge rod (20010) is rotatably connected to the clamping arm (20011); the output end of the first electric push rod (2006) is fixedly connected to a mounting seat (20012); the clamping arm (20011) is rotatably connected to the mounting seat (20012); the outside of the nut block (2005) is fixedly connected to a second electric push rod (2009); the output end of the second electric push rod (2009) is fixedly connected to the slip ring (2008).

7. The wine bottle conveyor line for packaging in a winery according to claim 6, characterized in that: The wine bottle monitoring system consists of an image acquisition unit, a data processing and analysis unit, a fault diagnosis and early warning unit, and a control and execution unit.

8. The wine bottle conveyor line for winery packaging according to claim 7 is characterized in that: The image acquisition unit comprises a mounting frame (2003) fixedly connected to the outside of the fixing frame (200) and a plurality of groups of industrial cameras (2004) fixedly connected to the outside of the mounting frame (2003), and the following relationship is satisfied according to the height h and conveying speed v of the wine bottle, the camera installation angle θ and the shooting area width w: w=h×tanθ The camera exposure time t exp It should be adjusted according to the conveying speed of the belt conveyor to meet the following requirements: For the inspection of the mouth and bottom of the wine bottle, an area array camera is fixedly connected to the outside of the fixed plate to shoot the mouth and bottom of the bottle without blind spots. The focal length f of the camera lens is selected according to the size of the shooting area and the working distance d to meet the following requirements: A fill light is fixedly connected to the outside of the fixing plate; Assume the reflectivity of the bottle is R b , the luminous intensity of the light source is I s , the reflectivity at the crack is R c , According to Lambert's cosine law, the reflected light intensity I b and I c They are: I b =I s ×R b ×cos45° I c =I s ×R c ×cos45° Use a ring light source, the inner diameter of the ring light source is D i n and outer diameter D o ut according to the diameter D of the bottle mouth n Designed to meet: D in =D n -ΔD1 D out =D n +ΔD2 Where ΔD1 and ΔD2 are appropriate margins.

9. The wine bottle conveyor line for packaging in a winery according to claim 8, characterized in that: The data processing and analysis unit includes the following: Image preprocessing: First, the collected wine bottle images are grayed out, the color images are converted into grayscale images, and the weighted average method is used for graying. The formula is: Gray(x,y)=0.299×R(x,y)+0.587×G(x,y)+0.114×B(x,y) Among them, R(x,y), G(x,y), B(x,y) are the red, green, and blue channel values ​​of the pixel point (x,y) in the color image, and Gray(x,y) is the grayscale value; Then, the image is filtered to remove noise interference. The Gaussian filtering algorithm is used, and its filtering kernel function is: Among them, σ is the standard deviation, and the appropriate σ value is selected according to the characteristics of the noise and the detail requirements of the image; Defect feature extraction and identification: The object detection algorithm based on deep learning analyzes the preprocessed images and identifies various defect features of the wine bottles. For cracks on the bottle body, the convolutional neural network (CNN) model is trained to automatically learn the texture, shape and grayscale change features of the cracks. Assume that the input image of the CNN model is I. After multiple layers of convolution and pooling operations, the feature map F is obtained. Through the fully connected layer and classifier, the output is whether there are cracks in the image and the location and size of the cracks. The model training process uses the back propagation algorithm to continuously adjust the weights and biases of the network to minimize the loss function L between the predicted results and the true labels. The commonly used loss function is the cross entropy loss function. Where N is the number of samples, y i is the true label (0 means no crack, 1 means crack), is the prediction output of the model; For the flatness detection of the bottle mouth, the contour information of the bottle mouth edge is extracted to calculate its roundness error ΔC and flatness error ΔP; Assume that the actual contour point coordinates of the bottle mouth edge are (x i ,y i ), the ideal circle equation obtained by least squares fitting is (xa) 2 +(yb) 2 =r 2 , then the roundness error ΔC can be calculated by the following formula: The flatness error ΔP is determined by analyzing the height difference of the bottle mouth edge in the vertical direction. The bottle mouth edge is divided into m equal intervals, and the average height h of each interval is calculated. j , then the flatness error ΔP is: ΔP=max(h j )-bright j ) According to the preset threshold T C and T P , determine whether the bottle mouth is qualified; If ΔC>T C or ΔP>T P , then it is determined that there is a defect in the bottle mouth; The fault diagnosis and early warning unit includes the following: Fault classification and evaluation: For each defect type, a corresponding fault assessment model is established; For the cracks on the bottle, let the length of the crack be l, the width be w, and the depth be d. According to the principles of material mechanics and fluid mechanics, the influence of the crack on the strength and sealing of the wine bottle is evaluated. The formula is: S=k1×l×w×d+k2×f(l,w,d) Among them, k1 and k2 are empirical coefficients, and f(l,w,d) is a function related to the crack shape and distribution, and its specific form is determined by experimental data and simulation analysis; According to the value of S, the bottle body crack failure is divided into different levels so that corresponding treatment measures can be taken; Early warning mechanism and information transmission: When the fault diagnosis unit detects a defect in a wine bottle, the early warning mechanism is immediately activated. Depending on the severity of the fault, the operator is notified through sound and light alarms, display screen prompts, and by sending alarm information to the production management system.

10. A wine bottle conveyor line for packaging in a winery according to claim 9, characterized in that: The control and execution unit includes the following: Belt conveyor speed adjustment: According to the working state of the image acquisition unit and the processing speed of the data processing and analysis unit, the speed v of the wine bottle belt conveyor is adjusted in real time; Assume that the total time of image acquisition and processing is t total , the safe distance between two adjacent bottles of wine is s safe , the speed of the belt conveyor meets: By adjusting the frequency converter of the conveying motor of the belt conveyor, the speed of the belt conveyor is controlled to match the working rhythm of the detection system; Removal of unqualified wine bottles: When the fault diagnosis and early warning unit sends a signal of an unqualified wine bottle, the control and execution unit starts the clamping and transfer component to remove the unqualified wine bottle from the belt conveyor.

Images