A blood bag welding thickness intelligent detection system and detection method
Through the intelligent detection system, the welding thickness of blood bags is automatically detected, which solves the problems of low detection efficiency and high personnel requirements in the existing technology, and accurately detects and quality monitoring of different blood bag types is achieved, which improves production efficiency and response speed.
Patent Information
- Application Number
- CN202411230226.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-04
- Publication Date
- 2024-11-19
- Estimated Expiration
- 2044-09-04
AI Technical Summary
The prior art is inefficient in detecting the thickness of blood bag welding, requires different measurement tools, and has high personnel requirements, making it difficult to meet the detection needs of different blood bag types.
An intelligent detection system for blood bag welding thickness is designed, including a data collection unit, a plane frame generation unit, a blood bag overlap unit, a blood bag model filling unit and a detection feedback unit. Through image recognition and three-axis servo drive device, blood is automatically adjusted. Bag position, collect and detect blood bag film thickness, combined with seal defect simulation, realize automated thickness quality detection.
It improves the accuracy and efficiency of detection, can quickly identify and feedback the quality parameters of blood bags, reduce manual intervention, ensure that the quality of the welding area and diaphragm area meets the expected standards, and improves the quality controllability of the production process.
Smart Images

Figure CN118730018B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of automatic detection technology, in particular to an intelligent detection system and a detection method for the welding thickness of a blood bag. Background Art
[0002] Blood bags play an important role in storing, transporting and distributing blood. Therefore, the quality of blood bags is crucial. Whether blood can be stored correctly directly affects the patient's recovery. The sealing of blood bags is key. Blood bag welding is a very important link to ensure the sealing and durability of blood bags.
[0003] At present, the bag body film and the periphery after welding are measured to meet the quality of the product. The traditional measurement method is to use a micrometer to measure the product, but the sizes of different blood bag types are different. At the same time, due to the influence of different measuring parts during the measurement process using the micrometer, different measuring tools need to be used, the detection efficiency is low, and high personnel requirements are required. Therefore, an intelligent detection system and detection method for blood bag welding thickness are proposed. Summary of the invention
[0004] The object of the present invention is to provide a blood bag welding thickness intelligent detection system and detection method thereof to solve the problems raised in the above background technology.
[0005] In order to solve the above technical problems, one of the purposes of the present invention is to provide an intelligent detection system for blood bag welding thickness, including a data collection unit, a plane frame generation unit, a blood bag overlapping unit, a blood bag model filling unit and a detection feedback unit;
[0006] The data collection unit is used to connect to the detection component and simultaneously collect the planar image data and quality requirement conditions of different types of blood bags;
[0007] The plane frame generation unit is used to adjust the image size and position the plane image data according to the detection platform and the camera, and divide the plane image data into a diaphragm area and a welding area, and then input the diaphragm area and the welding area into the detection platform to generate the plane frame;
[0008] The blood bag overlapping unit is used to control the camera to collect images of the blood bags placed on the detection platform, identify the type of the blood bags according to the collected blood bag image data, and then adjust the plane frame according to the identification result, thereby controlling the three-axis servo drive device to adjust the position of the blood bags;
[0009] The blood bag model filling unit is used to establish a blood bag model, collect the blood bag membrane thickness during the process of adjusting the blood bag position, and input the collected blood bag membrane thickness into the blood bag model for filling, and then plan the collection points for the unfilled positions;
[0010] The detection feedback unit is used to simulate the sealing defects of the welding area of the blood bag model in combination with the diaphragm area, and then perform thickness quality detection on the diaphragm area and welding area of the blood bag model according to quality requirements, and then feed back the detection results to the HMI operation panel.
[0011] As a further improvement of the technical solution, the data collection unit is connected to the detection component through PLC, so that the plane frame generation unit, the blood bag overlapping unit, the blood bag model filling unit and the detection feedback unit input data to the detection component through the data collection unit and complete the control;
[0012] The detection assembly includes a detection platform, an HMI operation panel, a three-axis servo drive device, a camera, and a high-precision contact sensor installed on the surface of the axis servo drive device;
[0013] The data collection unit collects plane image data and quality requirements from the inspection management personnel, and establishes a blood bag identification library according to the collected plane image data and quality requirements.
[0014] As a further improvement of the technical solution, the plane frame generation unit includes a point positioning module and a frame generation module;
[0015] The point positioning module is used to obtain the interval distance between the detection platform and the camera, and simulate the blood bag on the detection platform according to the interval distance, so as to adjust the image size of the plane image data, and then divide the adjusted plane image data into the bag body film and the periphery after welding and perform edge point positioning, so that the plane image data is divided into the film area and the welding area;
[0016] The frame generation module is used to input the diaphragm area and the welding area into the detection platform to generate a plane frame, so that a plane frame with the same area and shape as the plane image data is generated at the center of the detection platform.
[0017] As a further improvement of the technical solution, the blood bag overlapping unit includes a blood bag type identification module and a blood bag adjustment module;
[0018] The blood bag type recognition module is used to control the camera to collect images of the detection platform. When a blood bag is recognized in the collected image, the blood bag image data is collected, and then the blood bag type is recognized based on the collected blood bag image data combined with the blood bag recognition library to determine the type of the blood bag in the blood bag image data;
[0019] The blood bag adjustment module is used to extract the corresponding plane image data according to the blood bag type, and send it to the center of the detection platform to adjust the plane frame, and then control the three-axis servo drive device to adjust the position of the blood bag so that the position of the blood bag overlaps with the plane frame.
[0020] As a further improvement of the technical solution, the formula of the blood bag adjustment module is as follows:
[0021]
[0022] in, is the desired blood bag position, is the current blood bag position, is the position error vector.
[0023] As a further improvement of the technical solution, the blood bag model filling unit includes a blood bag filling module and a filling planning module;
[0024] The blood bag filling module is used to establish a blank blood bag model according to the blood bag type, and then collect the blood bag film thickness through a high-precision contact sensor during the process of adjusting the blood bag position, and input the collected blood bag film thickness into the blood bag model for filling;
[0025] The filling planning module is used to perform filling completeness detection on the blood bag model after the blood bag position is adjusted, extract the unfilled positions, and then plan the collection points according to the unfilled positions, and then control the high-precision contact sensor to collect data according to the planned collection points.
[0026] As a further improvement of the technical solution, when the blood bag overlapping unit cannot overlap the blood bag position with the plane frame during the process of adjusting the blood bag position, it is determined that the blood bag is unqualified, otherwise it proceeds to the next step;
[0027] During the detection process, when the sealing defect simulation result shows that there is a sealing defect, the detection feedback unit determines that the blood bag is unqualified, otherwise it proceeds to the next step;
[0028] When the thickness quality test result shows unqualified, the blood bag is judged to be unqualified and the information is fed back to the test management personnel through the HMI operation panel.
[0029] As a further improvement of the present technical solution, the formula of the detection feedback unit is as follows:
[0030]
[0031] Wherein, D(x,y,z) is an image used to simulate the defect location;
[0032] Q membrane (x,y,z)=|h membrane (x,y,z)-h target,membrane |
[0033] Q weld (x,y,z)=|h weld(x,y,z)-h target,weld |
[0034] Where Q is the quality index for the diaphragm area and the welding area, h membrane (x, y, z) is the thickness of the diaphragm area, h weld (x, y, z) is the thickness of the welding area, h target,membrane and h target,weld is the target thickness for the diaphragm area and weld area.
[0035] The second object of the present invention is to provide a blood bag welding thickness intelligent detection method, including any one of the above-mentioned blood bag welding thickness intelligent detection systems, including the following steps:
[0036] S1. Establishing a blood bag identification library through a data collection unit and a plane frame generation unit, and generating a plane frame according to different blood bag types;
[0037] S2, controlling the position of the blood bag and collecting data through the blood bag overlapping unit and the blood bag model filling unit, and filling the blood bag model;
[0038] S3. Testing the filled blood bag model through the testing feedback unit.
[0039] Compared with the prior art, the present invention has the following beneficial effects: by collecting data of different types of blood bags, establishing a blood bag identification library, and then combining images to quickly identify the type of blood bags, targeted detection of blood bags is achieved, and the accuracy of detection is improved; through sealing defect simulation, thickness quality detection and HMI feedback, the key quality parameters of the blood bag model can be fully monitored; through simulated defects and real-time detection, the quality of the welding area and the diaphragm area can be ensured to meet the expected standards, the quality controllability of the production process can be improved, and blood bags that do not meet the requirements can be avoided from entering the market for use; automated thickness quality detection and real-time feedback to the HMI operation panel reduce manual intervention and monitoring costs; detection managers can quickly identify problems on the HMI and take corresponding measures, thereby improving production efficiency and response speed. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Figure 1 This is a structural principle diagram of an intelligent detection system for welding thickness of a blood bag according to the present invention;
[0041] Figure 2 This is a unit operation principle diagram of an intelligent detection system for welding thickness of blood bags according to the present invention.
[0042] The meaning of each number in the figure is:
[0043] 10. Data collection unit; 20. Plane frame generation unit; 30. Blood bag overlapping unit; 40. Blood bag model filling unit; 50. Detection feedback unit. DETAILED DESCRIPTION
[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0045] like Figure 1 As shown, one of the purposes of the present invention is to provide an intelligent detection system for blood bag welding thickness, including a data collection unit 10, a plane frame generation unit 20, a blood bag overlapping unit 30, a blood bag model filling unit 40 and a detection feedback unit 50;
[0046] The data collection unit 10 is used to connect to the detection component and collect the plane image data and quality requirement conditions of different types of blood bags at the same time;
[0047] The data collection unit is connected to the detection component through the PLC, so that the plane frame generation unit, the blood bag overlapping unit, the blood bag model filling unit and the detection feedback unit input data to the detection component through the data collection unit and complete the control;
[0048] The detection components include a detection platform, an HMI operation panel, a three-axis servo drive, a camera, and a high-precision contact sensor mounted on the surface of the axis servo drive;
[0049] The data collection unit collects plane image data and quality requirements from the inspection management personnel, and establishes a blood bag identification library based on the collected plane image data and quality requirements. The specific working steps are as follows:
[0050] Plane image data acquisition: the detection manager inputs the plane image of the blood bag into the data collection unit 10;
[0051] Collection of quality requirements: The inspection management personnel define and collect the conditions and standards for evaluating welding quality, such as minimum and maximum weld widths, weld integrity, defect-free requirements, etc. These conditions can serve as the basis for subsequent evaluations;
[0052] Image preprocessing: preprocess the acquired planar images, including denoising, grayscale, image enhancement, etc., to reduce noise in the image and improve contrast and clarity;
[0053] Feature extraction: Use computer vision technology to extract features that are helpful for identification from the preprocessed images. The features include the shape, edge, grayscale distribution, texture features, etc. of the welding point. These features will be used as the basis for establishing the recognition library.
[0054] Data storage and management: Associate the pre-processed and feature-extracted image data with the corresponding quality requirements and store them in a database or file system to ensure that the data is structured, easy to access and manage.
[0055] The plane frame generation unit 20 is used to adjust the image size and position the plane image data according to the detection platform and the camera, and divide the plane image data into a diaphragm area and a welding area, and then input the diaphragm area and the welding area into the detection platform to generate the plane frame;
[0056] The plane frame generation unit 20 includes a point positioning module and a frame generation module;
[0057] The point positioning module is used to obtain the interval distance between the detection platform and the camera, and simulate the blood bag on the detection platform according to the interval distance, so as to adjust the image size of the plane image data, and then divide the adjusted plane image data into the bag body film and the periphery after welding, and perform edge point positioning, so that the plane image data is divided into the film area and the welding area. The specific working steps are as follows:
[0058] Get the spacing distance: Use sensors or pre-measurement methods to get the exact spacing distance between the detection platform and the camera.
[0059] Simulate the position of the blood bag: according to the measured interval distance, program or set the focus and position of the camera so that the camera can capture the complete plane image of the simulated blood bag, which involves adjusting the focus of the camera or moving the mechanical device to simulate the blood bag at the center of the detection platform;
[0060] Image resizing: Based on the image data captured by the camera and the known separation distance, the image is resized. This usually includes correcting the image size ratio to ensure that subsequent processing is based on the accurate physical size. The formula is as follows:
[0061] Assume that the distance from the detection platform to the camera is , the actual size of the image on the camera is W image ×H image , then the actual physical size W physical ×H physical The calculation formula is as follows:
[0062]
[0063] Where f is the focal length of the camera;
[0064] Diaphragm area and welding area: Use image processing technology, such as edge detection, color segmentation or feature point-based segmentation algorithm to divide the adjusted plane image data into two areas: diaphragm area and welding area. The diaphragm area and welding area are distinguished by shape.
[0065] Edge point positioning: The edge points of the separated diaphragm and welding area are positioned. This can be achieved through edge detection algorithms such as Canny to obtain the contour information and edge points of each area. The calculation formula is as follows:
[0066]
[0067] Among them, G x and G y is the gradient value of each pixel in the image.
[0068] The frame generation module is used to input the diaphragm area and the welding area into the detection platform for plane frame generation, so that a plane frame with the same area and shape as the plane image data is generated at the center of the detection platform. The specific working steps are as follows:
[0069] Calculate the area and shape information of the region: For each region, diaphragm region and welding region, calculate its area A and shape described by boundary points.
[0070] Generate a plane frame: Generate a plane frame with the same area and shape as the plane image data at the center of the detection platform, and use the calculated area A of the diaphragm area and the welding area to determine the size of the frame. Assume that the area of the diaphragm area is A membrane The area of the welding area is A welding , then the area of the frame is A frame Should be A frame =A membrane +A welding ;
[0071] Determine the shape of the frame: Generate a frame of corresponding shape based on the boundary points.
[0072] Generate a frame at the center of the detection platform: Based on the obtained frame size and shape, generate a corresponding plane frame at the center of the detection platform.
[0073] The blood bag overlapping unit 30 is used to control the camera to collect images of the blood bags placed on the detection platform, identify the type of the blood bags according to the collected blood bag image data, and then adjust the plane frame according to the identification result, thereby controlling the three-axis servo drive device to adjust the position of the blood bags;
[0074] The blood bag overlapping unit 30 includes a blood bag type identification module and a blood bag adjustment module;
[0075] The blood bag type recognition module is used to control the camera to collect images of the detection platform. When a blood bag is recognized in the collected image, the blood bag image data is collected, and then the blood bag type is recognized based on the collected blood bag image data combined with the blood bag recognition library to determine the type of blood bag in the blood bag image data. The specific working steps are as follows:
[0076] Image acquisition: Use a camera to acquire real-time images of the detection platform;
[0077] Blood bag detection: Use image processing and computer vision techniques to detect blood bags in images. You can use object detection algorithms such as YOLO, SSD, etc. or feature-based detection methods;
[0078] Blood bag image data acquisition: Once the blood bag is detected, the local image data of the blood bag area is extracted from the original image;
[0079] Blood bag type recognition: Feature extraction is performed on the extracted blood bag image data. Commonly used features include color histogram, texture features, shape features, etc. These features can help describe the appearance and structure of the blood bag.
[0080] Blood bag recognition library: In establishing the blood bag type recognition library, the type of blood bag in the image is determined based on the extracted feature vectors.
[0081] The blood bag adjustment module is used to extract the corresponding plane image data according to the blood bag type, and send it to the center of the detection platform to adjust the plane frame, and then control the three-axis servo drive device to adjust the position of the blood bag so that the position of the blood bag overlaps with the plane frame. The specific working steps are as follows:
[0082] Blood bag image data acquisition and processing: Use a camera to capture the image of the blood bag, and identify and locate the position and bounding box of the blood bag in the image according to a pre-set detection algorithm, and extract the local image data of the blood bag, usually by cropping the area where the blood bag is located;
[0083] Plane frame adjustment and control: The blood bag image data is sent to the detection platform center, which can analyze the image data and adjust the position and posture of the plane frame to overlap with the position of the blood bag. This can be achieved through computer vision algorithms, such as adjusting the position of the plane frame according to the position information of the blood bag;
[0084] Three-axis servo drive control: The three-axis servo drive X, Y, and Z axes are used to mechanically adjust the position of the blood bag. The control system can receive adjustment commands from the detection platform and adjust the position and angle of the servo drive according to the position information of the blood bag and the plane frame to achieve overlapping alignment of the blood bag and the plane frame. The formula is as follows;
[0085]
[0086] in, is the desired blood bag position derived from the image processing and detection platform, The current blood bag position is obtained from the image data collected by the camera. is the position error vector, which represents the difference between the current position and the desired position;
[0087] Then, according to A control algorithm such as a PID controller can be used to calculate the control input of the servo drive so that the blood bag position Gradually approaching , the control input is a command for speed or position adjustment, depending on the control input of the specific servo drive device.
[0088] The blood bag model filling unit 40 is used to establish a blood bag model, collect the blood bag membrane thickness during the blood bag position adjustment process, and input the collected blood bag membrane thickness into the blood bag model for filling, and then plan the collection points for the unfilled positions;
[0089] The blood bag model filling unit 40 includes a blood bag filling module and a filling planning module;
[0090] The blood bag filling module is used to establish a blank blood bag model according to the blood bag type. Then, during the process of adjusting the blood bag position, the blood bag membrane thickness is collected through a high-precision contact sensor, and the collected blood bag membrane thickness is input into the blood bag model for filling. The specific working steps are as follows:
[0091] Blood bag model establishment: Assuming that the shape of the blood bag can be represented by a parametric geometric form, such as a sphere, cylinder, or complex curved surface, set the parameters of the blood bag:
[0092] P=P1,P2,...,P n
[0093] Among them, P i Represents geometric parameters.
[0094] Membrane thickness measured by the sensor: Assume that the blood bag membrane thickness measured by the sensor is h measured (x,y,z), where (x,y,z) are the position coordinates of the sensor in three-dimensional space.
[0095] Blood bag model adjustment: The measured membrane thickness data h measured (x, y, z) is input into the blood bag model, and the parameter P of the blood bag model is adjusted by optimization or numerical fitting method so that the membrane thickness h of the model measured (P,x,y,z) is close to the actual measurement.
[0096] The filling planning module is used to detect the filling completeness of the blood bag model after the blood bag position is adjusted, extract the unfilled positions, and then plan the collection points according to the unfilled positions. After that, the high-precision contact sensor is controlled to collect data according to the planned collection points. The specific working steps are as follows:
[0097] Assume that M(x, y, z) is a binary image or function representing the filling state of the blood bag, where M=1 represents an unfilled position and M=0 represents a filled position. The unfilled position detection can be expressed by the following formula:
[0098]
[0099] According to the unfilled position (x i ,y i ,z i) coordinates, planning the target point where the sensor needs to move to (x i ',y i ',z i '), which can be expressed by the following simplified linear relationship:
[0100] (x i ',y i ',z i ')=(x i ,y i ,z i )
[0101] The sensor is located at each planned point (x i ',y i ',z i The local film thickness h(x i ',y i ',z i ').
[0102] The detection feedback unit 50 is used to simulate the sealing defect of the welding area of the blood bag model in combination with the diaphragm area, and then perform thickness quality detection on the diaphragm area and the welding area of the blood bag model according to the quality requirements, and then feed back the detection results to the HMI operation panel. The specific working steps are as follows:
[0103] Sealing defect simulation: Simulate the sealing defects of the welding area and the diaphragm area of the blood bag model. Assume that the defect can be simulated by an image representing the defect location, denoted as D(x,y,z), where:
[0104]
[0105] The thickness quality test is performed on the membrane area and welding area of the blood bag model. Assume that the thickness of the membrane area and welding area of the blood bag model are represented by hmembrane (x,y,z) and h weld (x, y, z), for the membrane area and welding area, a quality index Q can be defined to evaluate whether the thickness meets the quality requirements. The calculation formula is as follows:
[0106] Q membrane (x,y,z)=|h membrane (x,y,z)-h target,membrane |
[0107] Q weld (x,y,z)=|h weld (x,y,z)-h target,weld |
[0108] Among them, h target,membrane and h target,weld It is the target thickness of the diaphragm area and the welding area, which is set according to the quality requirements.
[0109] The test result Q membrane (x,y,z) and Q weld (x, y, z) are fed back to the HMI operation panel so that the testing manager can monitor and evaluate the quality status of the blood bag model in real time.
[0110] When the blood bag overlapping unit 30 fails to overlap the blood bag position and the plane frame during the process of adjusting the blood bag position, it is determined that the blood bag is unqualified, otherwise it proceeds to the next step;
[0111] During the detection process, when the sealing defect simulation result shows that there is a sealing defect, the detection feedback unit 50 determines that the blood bag is unqualified, otherwise it proceeds to the next step;
[0112] When the thickness quality test result shows unqualified, the blood bag is judged to be unqualified and the information is fed back to the test management personnel through the HMI operation panel.
[0113] The second object of the present invention is to provide a blood bag welding thickness intelligent detection method, including any one of the above blood bag welding thickness intelligent detection systems, comprising the following steps:
[0114] S1, establishing a blood bag identification library through the data collection unit 10 and the plane frame generation unit 20, and generating a plane frame according to different blood bag types;
[0115] S2, controlling the position of the blood bag and collecting data through the blood bag overlapping unit 30 and the blood bag model filling unit 40, and filling the blood bag model;
[0116] S3. The filled blood bag model is tested by the test feedback unit 50.
[0117] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. An intelligent detection system for blood bag welding thickness, characterized by: It comprises a data collection unit (10), a plane frame generation unit (20), a blood bag overlapping unit (30), a blood bag model filling unit (40), and a detection feedback unit (50); The data collection unit (10) is used to connect to the detection component and simultaneously collect the planar image data and quality requirement conditions of different types of blood bags; The plane frame generation unit (20) is used to adjust the image size and position the plane image data according to the detection platform and the camera, and divide the plane image data into a diaphragm area and a welding area, and then input the diaphragm area and the welding area into the detection platform to generate the plane frame; The plane frame generation unit (20) comprises a point positioning module and a frame generation module; The point positioning module is used to obtain the interval distance between the detection platform and the camera, and simulate the blood bag on the detection platform according to the interval distance, so as to adjust the image size of the plane image data, and then divide the adjusted plane image data into the bag body film and the periphery after welding and perform edge point positioning, so that the plane image data is divided into the film area and the welding area; The frame generation module is used to input the diaphragm area and the welding area into the detection platform to generate a plane frame, so that a plane frame with the same area and shape as the plane image data is generated at the center of the detection platform; The blood bag overlapping unit (30) is used to control the camera to collect images of the blood bags placed on the detection platform, identify the type of the blood bags according to the collected blood bag image data, and then adjust the plane frame according to the identification result, thereby controlling the three-axis servo drive device to adjust the position of the blood bags; The blood bag overlapping unit (30) comprises a blood bag type identification module and a blood bag adjustment module; The blood bag type recognition module is used to control the camera to collect images of the detection platform. When a blood bag is recognized in the collected image, the blood bag image data is collected, and then the blood bag type is recognized based on the collected blood bag image data combined with the blood bag recognition library to determine the type of the blood bag in the blood bag image data; The blood bag adjustment module is used to extract the corresponding plane image data according to the blood bag type, and send it to the center of the detection platform to adjust the plane frame, and then control the three-axis servo drive device to adjust the position of the blood bag so that the position of the blood bag overlaps with the plane frame; The blood bag model filling unit (40) is used to establish a blood bag model, collect blood bag membrane thickness during the process of adjusting the blood bag position, input the collected blood bag membrane thickness into the blood bag model for filling, and then plan the collection points for the unfilled positions; The blood bag model filling unit (40) comprises a blood bag filling module and a filling planning module; The blood bag filling module is used to establish a blank blood bag model according to the blood bag type, and then collect the blood bag film thickness through a high-precision contact sensor during the process of adjusting the blood bag position, and input the collected blood bag film thickness into the blood bag model for filling; The filling planning module is used to perform filling completeness detection on the blood bag model after the blood bag position is adjusted, extract the unfilled positions, and then plan the collection points according to the unfilled positions, and then control the high-precision contact sensor to collect data according to the planned collection points; The detection feedback unit (50) is used to simulate the sealing defect of the welding area of the blood bag model in combination with the diaphragm area, and then perform thickness quality detection on the diaphragm area and the welding area of the blood bag model according to the quality requirements, and then feed back the detection results to the HMI operation panel; The data collection unit (10) is connected to the detection component via a PLC, so that the plane frame generation unit (20), the blood bag overlapping unit (30), the blood bag model filling unit (40) and the detection feedback unit (50) input data to the detection component via the data collection unit (10) and complete the control; The detection assembly includes a detection platform, an HMI operation panel, a three-axis servo drive device, a camera, and a high-precision contact sensor installed on the surface of the axis servo drive device; The data collection unit (10) collects plane image data and quality requirements from the inspection management personnel, and establishes a blood bag identification library according to the collected plane image data and quality requirements.
2. The intelligent detection system for blood bag welding thickness according to claim 1 is characterized in that: The formula of the blood bag adjustment module is as follows: in, is the desired blood bag position, is the current blood bag position, is the position error vector.
3. The intelligent detection system for blood bag welding thickness according to claim 1 is characterized in that: When the blood bag overlapping unit (30) fails to overlap the blood bag position and the plane frame during the process of adjusting the blood bag position, it is determined that the blood bag is unqualified, otherwise the next step is entered; During the detection process, when the sealing defect simulation result shows that there is a sealing defect, the detection feedback unit (50) determines that the blood bag is unqualified, otherwise proceeds to the next step; When the thickness quality test result shows unqualified, the blood bag is judged to be unqualified and the information is fed back to the test management personnel through the HMI operation panel.
4. The intelligent detection system for blood bag welding thickness according to claim 1 is characterized in that: The formula of the detection feedback unit (50) is as follows: Wherein, D(x,y,z) is an image used to simulate the defect location; Q membrane (x,y,z)=|h membrane (x,y,z)-h target,membrane | Q weld (x,y,z)=|h weld (x,y,z)-h target,weld | Where Q is the quality index for the diaphragm area and the welding area, h membrane (x, y, z) is the thickness of the diaphragm area, h weld (x, y, z) is the thickness of the welding area, h target,membrane and h target,weld is the target thickness for the diaphragm area and weld area.
5. A blood bag welding thickness intelligent detection method, implemented by using the blood bag welding thickness intelligent detection system according to any one of claims 1 to 4, characterized in that: The steps include: S1, establishing a blood bag identification library through a data collection unit (10) and a plane frame generation unit (20), and generating a plane frame according to different blood bag types; S2, controlling the position of the blood bag and collecting data through the blood bag overlapping unit (30) and the blood bag model filling unit (40), and filling the blood bag model; S3. Testing the filled blood bag model through the testing feedback unit (50).
