A multi-robot collaborative ABS plastic sheet production workstation

Abstract

This invention discloses a multi-robot collaborative ABS plastic sheet production workstation, comprising: an extrusion auxiliary robot for assisting in material loading and mold handling; an extruder for heating and melting ABS plastic granules and extruding them into ABS plastic sheets through a mold; a grinding robot for carrying grinding tools to grind and remove roughness from the surface of the ABS plastic sheets; an inspection robot for detecting defects in the ABS plastic sheets, obtaining defect detection results, and storing the ABS plastic sheets in designated areas based on the defect detection results; and a material conveying module, located between the extrusion auxiliary robot, extruder, grinding robot, and vision inspection robot, for material conveying. This improves the production efficiency and quality of ABS plastic sheets, automatically detects whether the produced ABS plastic sheets are qualified, and stores them in designated areas.

Description

Technical Field

[0001] This invention relates to the field of manufacturing technology, and in particular to a multi-robot collaborative ABS plastic sheet production workstation. Background Technology

[0002] ABS plastic sheets possess excellent mechanical properties, high stability, ease of processing, and superior chemical properties, making them widely used in home appliances, automotive parts, office equipment, machinery, and mold making. Currently, the manufacturing process of ABS plastic sheets faces technical challenges such as low production efficiency and inconsistent product quality, and there is also a lack of automated methods to detect whether the produced ABS plastic sheets are up to standard. Summary of the Invention

[0003] This invention aims to at least partially solve one of the technical problems in the aforementioned technologies. Therefore, the objective of this invention is to propose a multi-robot collaborative ABS plastic sheet production workstation, which improves the production efficiency and quality of ABS plastic sheets, automatically detects whether the produced ABS plastic sheets are qualified, and stores them in designated areas.

[0004] To achieve the above objectives, this invention provides a multi-robot collaborative ABS plastic sheet production workstation, comprising:

[0005] Extrusion assistance robot, used to assist in material loading and mold handling;

[0006] An extruder is used to heat and melt ABS plastic granules and then extrude them into ABS plastic sheets through a mold.

[0007] A sanding robot, equipped with sanding tools, is used to sand and remove roughness from the surface of ABS plastic sheets.

[0008] Inspection robots are used to detect defects in ABS plastic sheets, obtain defect detection results, and store the ABS plastic sheets in different areas based on the defect detection results;

[0009] The material conveying module is installed between the extrusion auxiliary robot, the extruder, the grinding robot, and the vision inspection robot for material conveying.

[0010] According to some embodiments of the present invention, it further includes: a cooling device disposed within a first preset range of the extruder; the cooling device is a cooling water tank or an air-cooled device.

[0011] According to some embodiments of the present invention, it further includes: a dust collection device disposed within a second preset range of the grinding machine for collecting dust generated during grinding.

[0012] According to some embodiments of the present invention, the detection robot includes:

[0013] The first detection module is used to detect the shape, size and surface defects of the ABS plastic sheet and obtain the first detection result;

[0014] The second detection module is used to detect the thickness of the ABS plastic sheet and obtain the second detection result;

[0015] The determination module is used to determine the defect detection result based on the first detection result and the second detection result.

[0016] According to some embodiments of the present invention, the material conveying module includes a conveyor belt or track and a positioning device; wherein the positioning device is used to determine the position information of the ABS plastic sheet in each process.

[0017] According to some embodiments of the present invention, the first detection module includes:

[0018] The first acquisition module is used to acquire a surface image of the ABS plastic sheet;

[0019] The stretching module is used to perform image grayscale processing on the surface image to obtain a grayscale image; it also performs linear expansion on the grayscale image based on a linear function to stretch the grayscale of the pixels in the grayscale image to obtain a stretched image.

[0020] Noise reduction module, used for:

[0021] Obtain the image resolution of the stretched image, and perform image decomposition on the stretched image based on the image resolution to determine multi-level sub-images;

[0022] The texture features of each sub-image are obtained, the corresponding denoising weights are determined based on the texture features, and the corresponding sub-images are denoised based on the denoising weights to obtain the denoised image.

[0023] Edge detection module, used for:

[0024] Edge detection is performed on the denoised image based on the Canny operator edge detection algorithm to generate edge lines, and the first detection information of shape and size is obtained based on the edge lines.

[0025] The comparison module is used to obtain the gray value of each pixel in the denoised image and compare it with the preset gray value. Pixels whose gray values ​​are not within the preset gray value range are identified as defective pixels to obtain the second detection information.

[0026] The first test result is determined based on the first test information and the second test information.

[0027] According to some embodiments of the present invention, the second detection result includes:

[0028] The second acquisition module is used to send a first laser beam to the upper surface of the ABS plastic sheet and acquire the first time after the first laser beam is reflected by the upper surface.

[0029] The third acquisition module is used to send a second laser beam to the lower surface of the ABS plastic sheet and acquire the second time after the second laser beam is reflected by the upper surface.

[0030] The calculation module is used to calculate the thickness of the ABS plastic sheet based on the first time and the second time, and obtain the second detection result;

[0031]

[0032] Where d is the thickness of the ABS plastic sheet; T1 is the first time; T2 is the second time; λ is the refractive index of the ABS plastic sheet; and c is the speed of light.

[0033] According to some embodiments of the present invention, it further includes: a monitoring module, used for:

[0034] Acquire scene images of the area where the workstation is located;

[0035] Based on a pre-trained scene object recognition model, each recognition box is labeled in the scene image, and the scene object corresponding to each recognition box is determined.

[0036] Identify the status information of scene objects and generate monitoring information.

[0037] According to some embodiments of the present invention, the monitoring module identifies the state information of scene objects and generates monitoring information, including:

[0038] Determine the type of scene object, including equipment scene objects and material scene objects;

[0039] The process involves: acquiring a grayscale image of the device scene object and a reference grayscale image; determining the texture feature value of each pixel in the grayscale image; comparing the texture feature value of each pixel in the grayscale image with the texture feature value of the corresponding pixel in the reference grayscale image to obtain a first comparison result; acquiring an HSV space image of the device scene object and a reference HSV space image; for each pixel in the HSV space image, determining the color feature value of the pixel based on its H, S, and V components; comparing the color feature value of the pixel in the HSV space image with the color feature value of the corresponding pixel in the reference HSV space image to obtain a second comparison result; and determining the state information of the device scene object based on the first and second comparison results.

[0040] To obtain video clips of material scene objects, the trajectory of a particle in a video clip W×H×T is represented as follows:

[0041] {(x(t),y(t))∣x∈[1,W],y∈[1,H],t∈[1,T]}

[0042] Where W is the width of the video segment; H is the height of the video segment; T represents the number of consecutive frames of the video segment; and the vector (x(t), y(t)) represents the position of the particle (x, y) at time t.

[0043] Cluster the particle trajectories to obtain regions patch(m) that match the motion characteristics, where m is the region number;

[0044] Determine the status information of the material scene object based on the video clips of the material scene object;

[0045] Based on the status information of equipment scene objects and material scene objects, monitoring information is generated.

[0046] According to some embodiments of the present invention, determining the state information of a material scene object based on a video clip of the material scene object includes:

[0047] Determine the conveying volume and conveying speed of the material scene object;

[0048] numel(m)=U{(x p (t),y p (t))∣(x p ,y p )∈patch(m),t∈[1,T]}

[0049]

[0050] Where numel(m) represents the conveying capacity of the material scene object; U represents the number of elements in the region; (x p ,y p (x) represents the position of the particle in the region; p (t), y p (t) represents the particle (x) in the region. p ,y p The position of (x) at time t; p (1), y p (1) represents the particle (x) in the region. p ,y p The initial position; v is the conveying speed of the material scene object;

[0051] The status information of the material scene object is determined based on the conveying volume and conveying speed of the material scene object.

[0052] This invention proposes a multi-robot collaborative ABS plastic sheet production workstation, which improves the production efficiency and quality of ABS plastic sheets, automatically detects whether the produced ABS plastic sheets are qualified, and stores them in different areas.

[0053] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0054] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0055] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0056] Figure 1 This is a block diagram of a multi-robot collaborative ABS plastic sheet production workstation according to an embodiment of the present invention. Detailed Implementation

[0057] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit the present invention.

[0058] like Figure 1 As shown in the figure, this embodiment of the invention proposes a multi-robot collaborative ABS plastic sheet production workstation, including:

[0059] Extrusion assistance robot, used to assist in material loading and mold handling;

[0060] An extruder is used to heat and melt ABS plastic granules and then extrude them into ABS plastic sheets through a mold.

[0061] A sanding robot, equipped with sanding tools, is used to sand and remove roughness from the surface of ABS plastic sheets.

[0062] Inspection robots are used to detect defects in ABS plastic sheets, obtain defect detection results, and store the ABS plastic sheets in different areas based on the defect detection results;

[0063] The material conveying module is installed between the extrusion auxiliary robot, the extruder, the grinding robot, and the vision inspection robot for material conveying.

[0064] The working principle of the above technical solution is as follows: The extrusion auxiliary robot is mainly responsible for assisting in material loading and mold placement. Its precise operation ensures the accuracy and efficiency of the material loading process, while also enabling quick and accurate mold placement and removal, preparing the material for the extrusion process. Automated operation reduces manual intervention, improving production efficiency and safety. The extrusion auxiliary robot is a six-axis robot with moderate load capacity and high precision.

[0065] An extruder is the core equipment for producing ABS plastic sheets. It heats and melts ABS plastic granules, then extrudes them through a die to form ABS plastic sheets.

[0066] A grinding robot equipped with grinding tools is responsible for grinding and deburring the surface of ABS plastic sheets. This ensures that the surface of the plastic sheet is flat and smooth, meeting the quality requirements for subsequent processing or use. Automated grinding improves production efficiency while ensuring the consistency and stability of grinding quality. Grinding tools include sanding belts and grinding wheels. The grinding robot is selected for its high load capacity and flexibility, adapting to the grinding needs of ABS plastic sheets of different shapes and sizes. It is equipped with a force control system to ensure uniform grinding force and avoid over-grinding or under-grinding.

[0067] The inspection robot detects defects in ABS plastic sheets, such as cracks, bubbles, and impurities. Based on the inspection results, the robot divides the ABS plastic sheets into sections for subsequent processing. The inspection robot is equipped with a high-definition camera and image processing algorithms, enabling it to capture and analyze image information from the plastic sheet surface in real time. Automated inspection improves accuracy and efficiency, reducing the cost and error of manual inspection. The storage area includes acceptable and unacceptable sections.

[0068] The material handling module is positioned between the extrusion auxiliary robot, extruder, grinding robot, and inspection robot, and is responsible for material transport. It ensures smooth connections between each production stage and improves the overall automation level of the production line. Automated material handling reduces the labor intensity of manual handling, increases production efficiency, and ensures accurate and timely material delivery along the production line.

[0069] The beneficial effects of the above technical solution are as follows: The multi-robot collaborative ABS plastic sheet production workstation significantly improves production efficiency and product quality through a highly automated production method. Close collaboration and precise control between the various components ensure the stability and reliability of the entire production process.

[0070] In one embodiment, a central control system is also provided to manage and coordinate all robots and equipment. By programming the parameters and processes of each step, the entire workstation can be automated. A data interaction system enables data exchange between the robots and equipment; for example, the extruder transmits data such as extrusion speed and temperature to the grinding and inspection robots so they can make corresponding adjustments based on actual conditions. A monitoring system, equipped with surveillance cameras and sensors, monitors the workstation's operating status in real time. In case of any abnormality, the system immediately issues an alarm and shuts down the machine, while simultaneously recording relevant data for maintenance personnel to troubleshoot.

[0071] According to some embodiments of the present invention, it further includes: a cooling device disposed within a first preset range of the extruder; the cooling device is a cooling water tank or an air-cooled device.

[0072] The working principle of the above technical solution is as follows: The cooling device is set within the first preset range of the extruder to ensure that the thermoplastic ABS plastic sheet extruded from the extruder can be cooled quickly and evenly. The specific location of the cooling device needs to be determined based on the layout of the production line, the model of the extruder, and the required cooling efficiency.

[0073] The beneficial effects of the above technical solution are: in the multi-robot collaborative ABS plastic sheet production workstation, the installation of the cooling device facilitates the improvement of production efficiency and product quality.

[0074] According to some embodiments of the present invention, it further includes: a dust collection device disposed within a second preset range of the grinding machine for collecting dust generated during grinding.

[0075] The working principle of the above technical solution is as follows: The dust collection device is set within a second preset range of the grinding machine. This range is determined based on the location and diffusion range of dust generated during the grinding process. By precisely setting the position of the dust collection device, it can be ensured that it can effectively remove the dust generated during the grinding process, thereby maintaining a clean production environment.

[0076] The beneficial effects of the above technical solution are: by reasonably setting up and using dust collection devices, the cleanliness of the production environment can be maintained, the health of workers can be protected, and environmental protection requirements can be met.

[0077] According to some embodiments of the present invention, the detection robot includes:

[0078] The first detection module is used to detect the shape, size and surface defects of the ABS plastic sheet and obtain the first detection result;

[0079] The second detection module is used to detect the thickness of the ABS plastic sheet and obtain the second detection result;

[0080] The determination module is used to determine the defect detection result based on the first detection result and the second detection result.

[0081] The working principle of the above technical solution is as follows: The first detection module is responsible for detecting the shape, size, and surface defects of the ABS plastic sheet, and can identify whether the plastic sheet has shape deformation, dimensional deviation, and surface defects such as scratches, cracks, and bubbles. The second detection module generates a second detection result, which records the thickness distribution of the plastic sheet in detail.

[0082] The beneficial effects of the above technical solution are as follows: Through the coordinated work of the first and second detection modules, key parameters such as the shape, size, surface defects, and thickness of the ABS plastic sheet can be comprehensively and accurately detected. Furthermore, the reliable defect detection results generated by the detection module facilitate the assurance of the stability and reliability of the entire production process.

[0083] According to some embodiments of the present invention, the material conveying module includes a conveyor belt or track and a positioning device; wherein the positioning device is used to determine the position information of the ABS plastic sheet in each process.

[0084] The working principle and beneficial effects of the above technical solution are as follows: Through the coordinated operation of conveyor belts or tracks and positioning devices, it ensures the precise and efficient transfer of ABS plastic sheets between various processes. This not only improves the continuity and stability of the production line but also provides strong support for achieving automated and intelligent production.

[0085] According to some embodiments of the present invention, it further includes: a determining module, configured to determine whether defect information is contained based on a first detection result, and to generate a prompt message when the first detection result determines that defect information is contained;

[0086] The determining module includes:

[0087] Build modules are used for:

[0088] Acquire P sample detection images and sample information that have been determined to contain defect information. The sample information includes the detection results of the shape, size, and surface defects of the sample ABS plastic sheet, as well as the determination of whether the sample ABS plastic sheet contains defect information. Form a sample detection result matrix X from the detection results of the P sample detection images. The sample detection result matrix X has P rows and 3 columns. Simultaneously, form a defect result vector Y corresponding to whether the P sample ABS plastic sheets contain defect information. The defect result vector Y has P values. When the sample ABS plastic sheet contains defect information, the defect inspection result corresponding to the sample ABS plastic sheet is 1; when the sample ABS plastic sheet does not contain defect information, the defect inspection result corresponding to the sample ABS plastic sheet is 0.

[0089] Construct a defect learning function for the sample detection result matrix X and the defect result vector Y;

[0090]

[0091] Where f(X) is the constructed defect learning function, and Y i Let X be the i-th value of the defect result vector Y. i,j Let λ be the value in the i-th row and j-th column of the sample detection result matrix X, and let λ0 be the detection constant term to be solved. j Let i be the weight coefficients of the detection items to be solved, i = 1, 2, 3...P, j = 1, 2, 3;

[0092] Determine the detection constant term λ0 and the weighting coefficient λ j ;

[0093]

[0094] in, Take the partial derivative of the defect learning function f(X) with respect to the detection constant term λ0. The defect learning function f(X) is defined with respect to the weight coefficients λ. j Taking partial derivatives, we obtain a system of four equations, which contains a detection constant term λ0 and three weighting coefficients λ. j There are a total of 4 unknowns. By solving the system of equations, the detection constant λ0 and 3 weighting coefficients λ can be obtained. j ;

[0095] Determine whether the test results contain defect information;

[0096]

[0097] Where P is the determined value of the result, and K j This refers to the detection result of the j-th detection item in the first detection result;

[0098] The determined result is compared with a preset threshold. If the determined result is less than the preset threshold, a prompt message is generated.

[0099] The working principle of the above technical solution is as follows: Collect P sample detection images and corresponding sample information, including the detection results of the shape, size, and surface defects of the ABS plastic sheet samples, and the determination of whether the ABS plastic sheet samples contain defect information based on these detection results. The detection results of the P sample detection images are used to form a sample detection result matrix X, which is P rows and 3 columns, where each row represents three detection results (shape, size, and surface defects) for a sample. Simultaneously, a defect result vector Y is formed based on whether the P ABS plastic sheet samples contain defect information. Y has P values, where 1 indicates the presence of defect information and 0 indicates the absence of defect information. A defect learning function f(X) is constructed using a logistic regression model. This function can predict whether a sample contains defect information based on the sample detection result matrix X. The detection constant term λ0 and weight coefficient λ... j The algorithm performs a solution process. For a new first detection result, the trained model is used to calculate a determination value P. This determination value is then compared with a preset threshold. If the determination value is less than the preset threshold, the ABS plastic sheet corresponding to the first detection result is determined to contain defect information, and a warning message is generated. For example, the preset threshold is 0.5.

[0100] The beneficial effects of the above technical solution are as follows: the determination module, by constructing a defect learning function and training it using sample data, achieves accurate judgment on whether ABS plastic sheets contain defect information. This method not only improves the accuracy of detection but also reduces the cost and time of manual intervention.

[0101] According to some embodiments of the present invention, the first detection module includes:

[0102] The first acquisition module is used to acquire a surface image of the ABS plastic sheet;

[0103] The stretching module is used to perform image grayscale processing on the surface image to obtain a grayscale image; it also performs linear expansion on the grayscale image based on a linear function to stretch the grayscale of the pixels in the grayscale image to obtain a stretched image.

[0104] Noise reduction module, used for:

[0105] Obtain the image resolution of the stretched image, and perform image decomposition on the stretched image based on the image resolution to determine multi-level sub-images;

[0106] The texture features of each sub-image are obtained, the corresponding denoising weights are determined based on the texture features, and the corresponding sub-images are denoised based on the denoising weights to obtain the denoised image.

[0107] Edge detection module, used for:

[0108] Edge detection is performed on the denoised image based on the Canny operator edge detection algorithm to generate edge lines, and the first detection information of shape and size is obtained based on the edge lines.

[0109] The comparison module is used to obtain the gray value of each pixel in the denoised image and compare it with the preset gray value. Pixels whose gray values ​​are not within the preset gray value range are identified as defective pixels to obtain the second detection information.

[0110] The first test result is determined based on the first test information and the second test information.

[0111] The working principle of the above technical solution is as follows: The first acquisition module acquires the surface image of the ABS plastic sheet. The stretching module uses a linear function to stretch the pixel values ​​of the grayscale image, enhancing image contrast and making details clearer. The denoising module decomposes the image into multiple sub-images of different orders based on its resolution, allowing for processing of texture features at different scales. For each sub-image, its texture features are extracted, and a preset texture feature-denoising weight data table is consulted to determine the corresponding denoising weights. Then, these weights are used to denoise the sub-images, resulting in a clearer denoised image. The Canny operator is used to perform edge detection on the denoised image, generating edge lines. These edge lines accurately reflect the shape and size information of the ABS plastic sheet. Based on the edge lines, the shape and size features of the ABS plastic sheet are extracted to generate the first detection information. The comparison module acquires the grayscale value of each pixel in the denoised image and compares it with the preset grayscale value. Pixels whose grayscale value is not within the preset grayscale value range are regarded as defective pixels, and the second detection information is obtained. The shape, size and surface defects of the ABS plastic sheet are comprehensively evaluated by combining the first detection information and the second detection information, and the first detection result is finally determined.

[0112] The beneficial effects of the above technical solution are as follows: The first detection module, by integrating multiple image processing modules, achieves accurate detection of the shape, size, and surface defects of ABS plastic sheets. This method not only improves the accuracy and efficiency of detection but also provides reliable data support for subsequent automated processing.

[0113] According to some embodiments of the present invention, the second detection result includes:

[0114] The second acquisition module is used to send a first laser beam to the upper surface of the ABS plastic sheet and acquire the first time after the first laser beam is reflected by the upper surface.

[0115] The third acquisition module is used to send a second laser beam to the lower surface of the ABS plastic sheet and acquire the second time after the second laser beam is reflected by the upper surface.

[0116] The calculation module is used to calculate the thickness of the ABS plastic sheet based on the first time and the second time, and obtain the second detection result;

[0117]

[0118] Where d is the thickness of the ABS plastic sheet; T1 is the first time; T2 is the second time; λ is the refractive index of the ABS plastic sheet; and c is the speed of light.

[0119] The working principle of the above technical solution is as follows: Once the laser beam touches the upper surface of the plastic sheet, it is quickly reflected back. At this time, the second acquisition module accurately captures and records the first time consumed by this reflection process. The laser beam is also reflected after touching the lower surface of the plastic sheet. The third acquisition module is responsible for recording the second time consumed by this reflection process. The calculation module calculates the thickness of the ABS plastic sheet based on the first and second times.

[0120] The beneficial effects of the above technical solution are as follows: the second detection result, by combining laser ranging technology and precise time measurement, provides reliable quantitative information on the thickness of ABS plastic sheets, thereby improving the accuracy of thickness detection.

[0121] According to some embodiments of the present invention, it further includes: a monitoring module, used for:

[0122] Acquire scene images of the area where the workstation is located;

[0123] Based on a pre-trained scene object recognition model, each recognition box is labeled in the scene image, and the scene object corresponding to each recognition box is determined.

[0124] Identify the status information of scene objects and generate monitoring information.

[0125] The working principle of the above technical solution is as follows: The monitoring module first captures real-time scene images of the workstation's location. Using a pre-set and fully trained scene object recognition model, it performs deep analysis on the captured scene images. Each recognition box is precisely labeled in the image, and each box corresponds to a specific object in the image. Based on the model's recognition results, a specific scene object label is assigned to each recognition box. Through image analysis and machine learning algorithms, the object within each recognition box is analyzed in depth to obtain its state information. This state information includes various aspects such as the object's position, size, shape, color, and activity status.

[0126] The beneficial effects of the above technical solution are as follows: It ensures the safe operation of the workstation by monitoring key objects within the workstation in real time, such as equipment and personnel. It enables refined management of the production process and improves production efficiency by monitoring various objects and their status on the production line. When abnormal states or behaviors are detected, the monitoring module can quickly issue early warnings, providing strong support for timely action.

[0127] According to some embodiments of the present invention, the monitoring module identifies the state information of scene objects and generates monitoring information, including:

[0128] Determine the type of scene object, including equipment scene objects and material scene objects;

[0129] The process involves: acquiring a grayscale image of the device scene object and a reference grayscale image; determining the texture feature value of each pixel in the grayscale image; comparing the texture feature value of each pixel in the grayscale image with the texture feature value of the corresponding pixel in the reference grayscale image to obtain a first comparison result; acquiring an HSV space image of the device scene object and a reference HSV space image; for each pixel in the HSV space image, determining the color feature value of the pixel based on its H, S, and V components; comparing the color feature value of the pixel in the HSV space image with the color feature value of the corresponding pixel in the reference HSV space image to obtain a second comparison result; and determining the state information of the device scene object based on the first and second comparison results.

[0130] To obtain video clips of material scene objects, the trajectory of a particle in a video clip W×H×T is represented as follows:

[0131] {(x(t),y(t))∣x∈[1,W],y∈[1,H],t∈[1,T]}

[0132] Where W is the width of the video segment; H is the height of the video segment; T represents the number of consecutive frames of the video segment; and the vector (x(t), y(t)) represents the position of the particle (x, y) at time t.

[0133] Cluster the particle trajectories to obtain regions patch(m) that match the motion characteristics, where m is the region number;

[0134] Determine the status information of the material scene object based on the video clips of the material scene object;

[0135] Based on the status information of equipment scene objects and material scene objects, monitoring information is generated.

[0136] The working principle of the above technical solution is as follows: The monitoring module determines the type of scene object, including equipment scene objects and material scene objects; equipment scene objects include extrusion auxiliary robots, extruders, grinding robots, inspection robots, etc. Material scene objects are the materials conveyed by the material conveying module in the extrusion auxiliary robots, extruders, grinding robots, and vision inspection robots.

[0137] The grayscale image is a real-time image of the device scene object, while the reference grayscale image is a grayscale image of the device scene object under standard conditions. Methods for determining the texture feature value of each pixel in the grayscale image include gray-level co-occurrence matrix, local binary mode, and Gabor filter. The texture feature value of each pixel in the grayscale image is calculated and compared with the texture feature value of the corresponding pixel in the reference grayscale image to obtain the first comparison result. This step helps detect subtle changes on the device surface, such as scratches and wear. The HSV space image of the device scene object and its reference HSV space image are acquired. HSV stands for Hue, Saturation, and Value, respectively. For each pixel in the HSV space image, its color feature value is determined based on the H, S, and V components and compared with the color feature value of the corresponding pixel in the reference image to obtain the second comparison result. This step can detect color changes, reflecting changes in the device's state, such as oxidation and contamination. Combining the first and second comparison results, the monitoring module can determine the specific state information of the device scene object.

[0138] The monitoring module acquires video clips of material scene objects, each with a specific width W, height H, and duration T. Cluster analysis is performed on the motion trajectories of all particles within the video clips to obtain regions (patch(m)) with matching motion characteristics, where m is the region number. This step helps identify material flow patterns, accumulation states, etc. Based on the clustering results and the overall analysis of the video clips, the monitoring module can determine the status information of the material scene objects. The monitoring module integrates the status information of equipment scene objects and material scene objects, reflecting the status of equipment and materials within the scene.

[0139] The beneficial effects of the above technical solution are as follows: By using sophisticated image and video analysis technology, equipment scene objects and material scene objects are monitored separately, achieving comprehensive monitoring of the status of scene objects and ensuring the accuracy and practicality of monitoring information.

[0140] According to some embodiments of the present invention, determining the state information of a material scene object based on a video clip of the material scene object includes:

[0141] Determine the conveying volume and conveying speed of the material scene object;

[0142] numel(m)=U{(xp (t),y p (t))∣(x p ,y p )∈patch(m),t∈[1,T]}

[0143]

[0144] Where numel(m) represents the conveying capacity of the material scene object; U represents the number of elements in the region; (x p ,y p (x) represents the position of the particle in the region; p (t), y p (t) represents the particle (x) in the region. p ,y p The position of (x) at time t; p (1), y p (1) represents the particle (x) in the region. p ,y p The initial position; v is the conveying speed of the material scene object;

[0145] The status information of the material scene object is determined based on the conveying volume and conveying speed of the material scene object.

[0146] The working principle and beneficial effects of the above technical solution are: accurately determining the conveying volume and conveying speed of the material scene object, thereby accurately determining the status information of the material scene object.

[0147] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A multi-robot collaborative ABS plastic sheet production workstation, characterized in that, include: Extrusion assistance robot, used to assist in material loading and mold handling; An extruder is used to heat and melt ABS plastic granules and then extrude them into ABS plastic sheets through a mold. A sanding robot, equipped with sanding tools, is used to sand and remove roughness from the surface of ABS plastic sheets. Inspection robots are used to detect defects in ABS plastic sheets, obtain defect detection results, and store the ABS plastic sheets in different areas based on the defect detection results; The material conveying module is installed between the extrusion auxiliary robot, the extruder, the grinding robot, and the inspection robot, and is used for material conveying. It also includes: a monitoring module, used for: Acquire scene images of the area where the workstation is located; Based on a pre-trained scene object recognition model, each recognition box is labeled in the scene image, and the scene object corresponding to each recognition box is determined. Identify the status information of scene objects and generate monitoring information; The monitoring module identifies the status information of scene objects and generates monitoring information, including: Determine the type of scene object, including equipment scene objects and material scene objects; The process involves: acquiring a grayscale image of the device scene object and a reference grayscale image; determining the texture feature value of each pixel in the grayscale image; comparing the texture feature value of each pixel in the grayscale image with the texture feature value of the corresponding pixel in the reference grayscale image to obtain a first comparison result; acquiring an HSV space image of the device scene object and a reference HSV space image; for each pixel in the HSV space image, determining the color feature value of the pixel based on its H, S, and V components; comparing the color feature value of the pixel in the HSV space image with the color feature value of the corresponding pixel in the reference HSV space image to obtain a second comparison result; and determining the state information of the device scene object based on the first and second comparison results. To obtain video clips of material scene objects, the trajectory of a particle in a video clip W×H×T is represented as follows: Where W is the width of the video segment; H is the height of the video segment; T represents the number of consecutive frames of the video segment; and vector (x(t), y(t)) represents the position of particle (x, y) at time t. Cluster the particle trajectories to obtain regions patch(m) that match the motion characteristics, where m is the region number; Determine the status information of the material scene object based on the video clips of the material scene object; Based on the status information of equipment scene objects and material scene objects, monitoring information is generated.

2. The multi-robot collaborative ABS plastic sheet production workstation as described in claim 1, characterized in that, Also includes: A cooling device is installed within the first preset range of the extruder; the cooling device is a cooling water tank or an air-cooled device.

3. The multi-robot collaborative ABS plastic sheet production workstation as described in claim 1, characterized in that, Also includes: A dust extraction device is installed within the second preset range of the polishing robot to remove dust generated during polishing.

4. The multi-robot collaborative ABS plastic sheet production workstation as described in claim 1, characterized in that, The detection robot includes: The first detection module is used to detect the shape, size and surface defects of the ABS plastic sheet and obtain the first detection result; The second detection module is used to detect the thickness of the ABS plastic sheet and obtain the second detection result; The determination module is used to determine the defect detection result based on the first detection result and the second detection result.

5. The multi-robot collaborative ABS plastic sheet production workstation as described in claim 1, characterized in that, The material conveying module includes a conveyor belt or track and a positioning device; wherein the positioning device is used to determine the position information of the ABS plastic sheet in each process.

6. The multi-robot collaborative ABS plastic sheet production workstation as described in claim 4, characterized in that, The first detection module includes: The first acquisition module is used to acquire a surface image of the ABS plastic sheet; The stretching module is used to perform image grayscale processing on the surface image to obtain a grayscale image; it also performs linear expansion on the grayscale image based on a linear function to stretch the grayscale of the pixels in the grayscale image to obtain a stretched image. Noise reduction module, used for: Obtain the image resolution of the stretched image, and perform image decomposition on the stretched image based on the image resolution to determine multi-level sub-images; The texture features of each sub-image are obtained, the corresponding denoising weights are determined based on the texture features, and the corresponding sub-images are denoised based on the denoising weights to obtain the denoised image. Edge detection module, used for: Edge detection is performed on the denoised image based on the Canny operator edge detection algorithm to generate edge lines, and the first detection information of shape and size is obtained based on the edge lines. The comparison module is used to obtain the gray value of each pixel in the denoised image and compare it with the preset gray value. Pixels whose gray values ​​are not within the preset gray value range are identified as defective pixels to obtain the second detection information. The first test result is determined based on the first test information and the second test information.

7. The multi-robot collaborative ABS plastic sheet production workstation as described in claim 4, characterized in that, The second detection module includes: The second acquisition module is used to send a first laser beam to the upper surface of the ABS plastic sheet and acquire the first time after the first laser beam is reflected by the upper surface. The third acquisition module is used to send a second laser beam to the lower surface of the ABS plastic sheet and acquire the second time after the second laser beam is reflected by the upper surface. The calculation module is used to calculate the thickness of the ABS plastic sheet based on the first time and the second time, and obtain the second detection result; in, The thickness of the ABS plastic sheet; For the first time; For the second time; The refractive index of the ABS plastic sheet; It is the speed of light.

8. The multi-robot collaborative ABS plastic sheet production workstation as described in claim 1, characterized in that, The status information of the material scene object is determined based on the video clips of the material scene object, including: Determine the conveying volume and conveying speed of the material scene object; in, For the conveying volume of material scene objects; The number of elements in the region; The position of the particle in the region; , ) represents particles in the region Position at time t; ) represents particles in the region Position at the initial moment; For the conveying speed of material scene objects; The status information of the material scene object is determined based on the conveying volume and conveying speed of the material scene object.

Images