Adaptive test tube positioning parameter coordinated control system for labeling machine

Abstract

The present invention discloses an adaptive test tube positioning parameter collaborative control system for a labeling machine, which relates to the field of adaptive control. The system includes: a labeling position information acquisition module for obtaining K labeling position information; a grabbing and labeling simulation module for performing grabbing and labeling simulation; a test tube positioning analysis model acquisition module for obtaining a test tube positioning analysis model; a test tube image acquisition and analysis module for performing image acquisition and analysis on test tubes to be labeled; a collaborative control stability analysis module for performing collaborative control stability analysis; a labeling processing module for generating positioning collaborative control parameters, and running multiple collaborative mechanical arms to grab test tubes to be labeled to the labeling machine for labeling processing. The system solves the technical problem that the accuracy of labeling is difficult to ensure due to the lack of flexibility and adaptability in the existing test tube positioning parameter control, and achieves the technical effect of improving the accuracy of labeling through a highly flexible and adaptable automated labeling system.

Description

Technical Field

[0001] The present application relates to the field of adaptive control, and in particular to an adaptive test tube positioning parameter coordinated control system for a labeling machine. Background Art

[0002] In the fields of modern medicine, scientific research and biotechnology, test tube labeling is an indispensable part of laboratory management and quality control. With the rapid development of automation technology, test tube labeling has gradually shifted from manual operation to automated processing to improve efficiency and accuracy. However, test tubes are of various types and shapes, and the labeling position often varies depending on the experimental requirements, which puts extremely high flexibility and adaptability requirements on automated labeling equipment. Traditional automated labeling machines mostly use fixed robotic arms to label at preset labeling positions and angles. This method is suitable for test tubes with uniform shapes and fixed labeling positions, but it is incapable of handling test tubes of different types and sizes and lacks flexibility. In order to meet the labeling requirements of different test tubes, the operator needs to manually adjust the gripping position and labeling angle of the robotic arm, which is not only time-consuming and labor-intensive, but also prone to inaccurate labeling positions due to human factors, affecting the accuracy of subsequent experiments or test results.

[0003] In the current related technologies, there is a technical problem in the control of test tube positioning parameters due to lack of flexibility and adaptability, which makes it difficult to ensure the accuracy of labeling. Summary of the invention

[0004] The present application provides an adaptive test tube positioning parameter collaborative control system for a labeling machine, acquires labeling position information of a variety of test tubes in an interactive manner, utilizes flexible automated labeling facilities (including a labeling machine and multiple collaborative robotic arms) to perform grasping and labeling simulation, obtains grasping node sets and reset labeling site sets for different test tubes, stores test tube types, grasping node sets and reset labeling site sets based on a knowledge graph, constructs a test tube positioning analysis model, and when a test tube to be labeled enters a labeling control area, an automated image acquisition device acquires and analyzes images, outputs real-time test tube types and positioning analysis images, traverses the test tube positioning analysis model based on the real-time test tube types and positioning analysis images, performs collaborative control stability analysis based on the test tube positioning analysis model, determines the target grasping node set and reset labeling site set, generates positioning collaborative control parameters based on the analysis results, drives multiple collaborative robotic arms to grasp test tubes to the labeling machine to perform labeling processing, and other technical means, thereby achieving a technical effect of improving labeling accuracy through a highly flexible and adaptable automated labeling system.

[0005] The present application provides an adaptive test tube positioning parameter coordinated control system for a labeling machine, including:

[0006] A labeling position information acquisition module, the labeling position information acquisition module is used to interactively obtain K labeling position information of K types of test tubes; a grabbing and labeling simulation module, the grabbing and labeling simulation module is used to use the K labeling position information as constraints, and use flexible automated labeling facilities to perform grabbing and labeling simulation on the K types of test tubes, to obtain K groups of test tube grabbing node sets and K groups of reset labeling site sets, wherein the flexible automated labeling facility is composed of a labeling machine and a plurality of collaborative robotic arms; a test tube positioning analysis model acquisition module, the test tube positioning analysis model acquisition module is used to associate and store the K types of test tubes, K groups of test tube grabbing node sets and K groups of reset labeling site sets based on a knowledge graph to obtain a test tube positioning analysis model; a test tube image acquisition and analysis module, the test tube image acquisition and analysis module is used when the test tubes to be labeled are transported to the flexible automated labeling facility via a conveyor belt. When the labeling control area of ​​the labeling facility is reached, the automated image acquisition device performs image acquisition and analysis on the test tube to be labeled, and outputs a real-time test tube type and a test tube positioning analysis image, wherein the automated image acquisition device is pre-deployed directly above the labeling control area; a collaborative control stability analysis module is used to use the real-time test tube type and the test tube positioning analysis image as constraints, traverse the test tube positioning analysis model to perform collaborative control stability analysis, and obtain a target test tube grabbing node set and a target reset labeling site set; a labeling processing module is used to generate positioning collaborative control parameters according to the target test tube grabbing node set and the target reset labeling site set, and use the positioning collaborative control parameters to operate the multiple collaborative robotic arms to grab the test tube to be labeled to the labeling machine for labeling processing.

[0007] In a possible implementation, the grabbing and labeling simulation module includes:

[0008] A labeling control twin model acquisition module, which is used to interactively obtain the automation equipment information of the flexible automated labeling facility, and construct a labeling control twin model based on the automation equipment information and the labeling control area; a test tube model acquisition module, which is used to interactively obtain K test tube design information of K types of test tubes, and construct K test tube models based on the K test tube design information and K labeling position information; a labeling simulation module, which is used to use the labeling control twin model to perform grasping and labeling simulation on the K test tube models to obtain the K groups of test tube grasping node sets and K groups of reset labeling site sets.

[0009] In a possible implementation, the labeling control twin model acquisition module includes:

[0010] An equipment information acquisition module, the equipment information acquisition module is used to extract the first equipment information of the labeling machine and the multiple second equipment information of the multiple collaborative robotic arms from the automated equipment information; a model construction module, the model construction module is used to use the first equipment information and the multiple second equipment information as modeling data, and adopt the digital twin technology to construct a labeling machine twin model and multiple robotic arm models; a twin space construction module, the twin space construction module is used to pre-construct a twin space with the labeling control area as a constraint; a labeling control twin model generation module, the labeling control twin model generation module is used to extract the equipment layout position information from the automated equipment information, and copy the labeling machine twin model and the multiple robotic arm models to the twin space according to the equipment layout position information to generate the labeling control twin model.

[0011] In a possible implementation, the test tube model acquisition module includes:

[0012] A first test tube design information extraction module, the first test tube design information extraction module is used to extract first test tube design information of a first test tube based on the K test tube design information, wherein the first test tube is any one of the K test tubes; a first basic model construction module, the first basic model construction module is used to construct and obtain a first basic model according to the first test tube design information; a first labeling position information extraction module, the first labeling position information extraction module is used to extract and obtain first labeling position information of the first test tube from the K labeling position information; a first test tube model acquisition module, the first test tube model acquisition module is used to locate and identify a first labeling area in the first basic model according to the first labeling position information to obtain a first test tube model; K test tube model acquisition modules, the K test tube model acquisition modules are used to construct and obtain the K test tube models according to the K test tube design information and the K labeling position information by analogy.

[0013] In a possible implementation, the labeling simulation module includes:

[0014] A first vector model acquisition module, the first vector model acquisition module is used to randomly place the first test tube model in the twin space to obtain a first vector model; a stable grasping simulation module, the stable grasping simulation module is used to use the first labeling area as a grasping taboo, and control the multiple robotic arm models in the labeling control twin model to perform a stable grasping simulation on the first test tube model to obtain a first test tube grasping node set; a spatial position data acquisition module, the spatial position data acquisition module is used to perform labeling alignment of the first test tube model and the labeling machine twin model in the twin space according to the first labeling area, and based on the alignment result, perform spatial position data acquisition on the first test tube grasping node set to obtain a first reset labeling position point set; N random placement and grabbing labeling simulation modules, the N random placement and grabbing labeling simulation modules are used to perform N random placement and grabbing labeling simulations on the first test tube model in the twin space by analogy, to obtain N vector models, N test tube grabbing node sets and N reset labeling site sets; a storage module, the storage module is used to associate and store the N vector models and the N test tube grabbing node sets to obtain a first group of test tube grabbing node sets, store the N reset labeling site sets, and obtain a first group of reset labeling site sets; a test tube grabbing node and reset labeling site set acquisition module, the test tube grabbing node and reset labeling site set acquisition module is used to obtain the K groups of test tube grabbing node sets and K groups of reset labeling site sets by analogy.

[0015] In a possible implementation, the test tube image acquisition and analysis module includes:

[0016] A test tube feature extraction module, the test tube feature extraction module is used to obtain K test tube feature sets by performing test tube feature extraction on the K test tube models; a test tube classification model construction module, the test tube classification model construction module is used to pre-build a test tube classification model, wherein the test tube classification model is generated based on the K test tube feature sets; an automated image acquisition device local update module, the automated image acquisition device local update module is used for the automated image acquisition device including an industrial camera and an edge computing device, and completes the local update of the automated image acquisition device by synchronizing the test tube classification model to the edge computing device.

[0017] In a possible implementation, the test tube image acquisition and analysis module includes:

[0018] An image acquisition module, wherein when the test tube to be labeled is transported to the labeling control area via a conveyor belt, the industrial camera of the automated image acquisition device performs image acquisition on the test tube to be labeled to obtain the test tube positioning analysis image; a real-time test tube type acquisition module, wherein the edge computing device built into the automated image acquisition device analyzes the test tube positioning analysis image through a test tube classification model and outputs the real-time test tube type; and an output module, wherein the automated image acquisition device outputs the real-time test tube type and the test tube positioning analysis image as output results.

[0019] In a possible implementation, the collaborative control stability analysis module includes:

[0020] An alternative data group extraction module, the alternative data group extraction module is used to extract an alternative data group from the test tube positioning analysis model mapping using the real-time test tube type, wherein the alternative data group includes multiple alternative test tube grabbing node sets and multiple alternative reset labeling site sets of associated mappings; an alternative vector model extraction module, the alternative vector model extraction module is used to extract and obtain multiple alternative vector models based on the multiple alternative test tube grabbing node sets; a bird's-eye view image acquisition module, the bird's-eye view image acquisition module is used to perform bird's-eye view image acquisition on the multiple alternative vector models to obtain multiple alternative model analysis images; a similarity calculation module, The similarity calculation module is used to calculate the similarity between the test tube positioning analysis image and multiple alternative model analysis images to obtain multiple similarity coefficients; the target model analysis image acquisition module is used to serialize the multiple similarity coefficients and extract the alternative model analysis images corresponding to the extreme values ​​based on the sorting results to obtain the target model analysis image; the reverse extraction module is used to reversely extract from the multiple alternative test tube grasping node sets and the multiple alternative reset labeling site sets according to the target model analysis image to obtain the target test tube grasping node set and the target reset labeling site set.

[0021] In a possible implementation, the labeling processing module includes:

[0022] A robot grasping trajectory fitting module, the robot grasping trajectory fitting module is used to perform robot grasping trajectory fitting according to the target test tube grasping node set and the target reset labeling site set to obtain multiple operation trajectories of the multiple collaborative robot arms; a positioning collaborative control parameter generation module, the positioning collaborative control parameter generation module is used to generate the positioning collaborative control parameters according to the multiple operation trajectories; a collaborative robot arm operation module, the collaborative robot arm operation module is used to use the positioning collaborative control parameters to operate the multiple collaborative robot arms to grasp the test tube to be labeled to the labeling machine for labeling processing.

[0023] The adaptive test tube positioning parameter collaborative control system for labeling machines proposed in this application is proposed. The labeling position information acquisition module is used to interactively obtain K labeling position information of K test tubes. The grabbing and labeling simulation module is used to take the K labeling position information as constraints. The flexible automated labeling facility is used to perform grabbing and labeling simulation on the K test tubes to obtain K groups of test tube grabbing node sets and K groups of reset labeling site sets. The flexible automated labeling facility is composed of a labeling machine and a plurality of collaborative robotic arms. The test tube positioning analysis model acquisition module is used to associate and store K types of test tubes, K groups of test tube grabbing node sets and K groups of reset labeling site sets based on the knowledge graph to obtain a test tube positioning analysis model. When the test tube to be labeled is transported to the labeling control area of ​​the flexible automated labeling facility through a conveyor belt, The automated image acquisition device performs image acquisition and analysis on the test tube to be labeled, and outputs real-time test tube type and test tube positioning analysis images, wherein the automated image acquisition device is pre-deployed directly above the labeling control area, and through the collaborative control stability analysis module, the real-time test tube type and test tube positioning analysis image are used as constraints, the test tube positioning analysis model is traversed to perform collaborative control stability analysis, and the target test tube grasping node set and the target reset labeling site set are obtained, and the positioning collaborative control parameters are generated according to the target test tube grasping node set and the target reset labeling site set through the labeling processing module, and the positioning collaborative control parameters are used to run multiple collaborative robotic arms to grasp the test tube to be labeled to the labeling machine for labeling processing, thereby achieving the technical effect of improving the accuracy of labeling through a highly flexible and adaptable automated labeling system. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A structural diagram is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or a certain step or several steps of operations can be removed from these processes.

[0025] Figure 1 A schematic diagram of the structure of the adaptive test tube positioning parameter collaborative control system for the labeling machine provided in an embodiment of the present application.

[0026] Figure 2 A schematic diagram of the structure of a collaborative control stability analysis module in the collaborative control system of adaptive test tube positioning parameters for a labeling machine provided in an embodiment of the present application.

[0027] Explanation of the reference numerals: labeling position information acquisition module 10 , grabbing and labeling simulation module 20 , test tube positioning analysis model acquisition module 30 , test tube image acquisition and analysis module 40 , collaborative control stability analysis module 50 , labeling processing module 60 . DETAILED DESCRIPTION

[0028] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0029] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0030] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0031] The embodiment of the present application provides a system for coordinating and controlling adaptive test tube positioning parameters for a labeling machine, such as Figure 1 As shown, the system comprises:

[0032] The labeling position information acquisition module 10 is used to interactively obtain K labeling position information of K test tubes. Specifically, after the system is started, an interactive interface is presented, which is used to input or select the labeling position information of the test tube, that is, the specific position information on the test tube where the label needs to be attached. The user inputs or selects the labeling position information of K test tubes through the interface, including the type, size, and one or more specific labeling positions (such as position coordinates and possible rotation angles) of each test tube. The system receives the information entered by the user and performs a preliminary format check to ensure that the input data format is correct and meets the system requirements. The verified labeling position information is stored in the system database, and each test tube corresponds to a set of labeling position information. At the same time, the system allows the user to update or delete the stored labeling position information. Before or after data storage, the system can perform data verification, such as checking whether the position coordinates are within the reach of the robot arm, whether the rotation angle is reasonable, etc. If a data problem is found, the system will feedback error information to the user through the interface and require the user to re-enter or correct the data.

[0033] The grabbing and labeling simulation module 20 is used to use the K labeling position information as constraints, and use a flexible automated labeling facility to perform a grabbing and labeling simulation on the K types of test tubes, and obtain K groups of test tube grabbing node sets and K groups of reset labeling site sets, wherein the flexible automated labeling facility is composed of a labeling machine and a plurality of collaborative robotic arms. Specifically, the grabbing and labeling simulation module 20 receives the K labeling position information of the K types of test tubes from the labeling position information acquisition module 10, initializes the state of the flexible automated labeling facility, and ensures that the flexible automated labeling facility is in a ready state before the simulation begins. The flexible automated labeling facility is a combination of equipment that can automatically perform labeling tasks, including a labeling machine and a plurality of collaborative robotic arms, which have multiple degrees of freedom and can flexibly move and rotate in three-dimensional space, and are used to grab test tubes and move them to the labeling position for labeling operations. For each test tube, according to its shape, size and placement, multiple effective test tube grasping nodes are planned in three-dimensional space. These nodes should ensure that the robot arm can grasp the test tube stably and will not damage the test tube or the labeling machine. Algorithms (such as path planning algorithms, collision detection algorithms, etc.) are used to optimize the selection of grasping nodes to ensure that the robot arm's motion path is the shortest, most efficient, safe and collision-free. According to the layout and labeling requirements of the labeling machine, corresponding reset nodes are planned for each robot arm. These nodes should ensure that when the robot arm grasps and moves the test tube to these positions, the test tube can be accurately positioned in the labeling area of ​​the labeling machine. Algorithms are also used to optimize the selection of reset nodes to ensure the accuracy of the robot arm's motion path and reset position.

[0034] In the simulation environment, multiple robotic arms are simulated to perform the operation of grabbing test tubes at the same time. The robotic arms move to the top of the test tubes according to the planned test tube grabbing nodes, and adjust their posture to stably grab the test tubes. After the grabbing is successful, the robotic arms move the test tubes to the corresponding robotic arm reset nodes. During the movement process, collisions and interferences are detected in real time, and the motion path of the robotic arms is adjusted to avoid problems. When all the robotic arms are moved to the corresponding reset nodes, the environmental conditions of the labeling operation are simulated to verify the positioning accuracy of the test tubes and the working status of the labeling machine. During each simulation, key data such as the motion path, grabbing time, reset time, and whether collisions or interferences occur are recorded to evaluate the effectiveness and accuracy of the simulation results and check whether there are areas that need to be optimized (such as the selection of grabbing nodes, the layout of reset nodes, the motion parameters of the robotic arms, etc.). Among them, the test tube grabbing nodes are specific positions in three-dimensional space where the robotic arms can stably grab the test tubes. These nodes are planned according to the shape, size and placement of the test tubes to ensure that the robotic arms can accurately and safely grab the test tubes. The robot arm reset nodes are a series of fixed position points that the robot arm needs to return to after successfully grabbing the test tube. These position points are designed to match the relative position of the labeling machine to ensure that the test tube can be accurately positioned in the labeling area for labeling operations.

[0035] In one possible implementation, the grasping and labeling simulation module 20 includes: a labeling control twin model acquisition module, which is used to interactively obtain the automation equipment information of the flexible automated labeling facility, and construct a labeling control twin model based on the automation equipment information and the labeling control area; a test tube model acquisition module, which is used to interactively obtain K test tube design information of K types of test tubes, and construct K test tube models based on the K test tube design information and K labeling position information; a labeling simulation module, which is used to use the labeling control twin model to perform grasping and labeling simulation on the K test tube models to obtain the K groups of test tube grasping node sets and K groups of reset labeling site sets.

[0036] Specifically, the labeling control twin model acquisition module collects detailed information of all automation equipment in the flexible automated labeling facility through an interface or database interaction, including but not limited to the model, specification, range of motion, end effector type, etc. of the robotic arm, as well as the location, size, labeling accuracy, etc. of the labeling machine. Based on the collected automation equipment information, a digital twin model of the labeling control area is constructed using digital modeling technology (such as CAD, 3D modeling, etc.). The labeling control twin model is a virtual mirror image of the actual labeling facility, reflecting the spatial layout, equipment location, and mutual connection relationship of the actual labeling facility, and is used to simulate and predict the behavior and performance of the flexible automated labeling facility in actual operation. In the labeling control twin model, the control parameters of each automation equipment are configured, such as the movement speed, acceleration, force control parameters, etc. of the robotic arm, as well as the labeling speed and accuracy requirements of the labeling machine.

[0037] The test tube model acquisition module obtains detailed design information of K test tubes, including the size, shape, material, weight, etc. of the test tubes, by interacting with the design department or database. Using 3D modeling software or related tools, a 3D model of K test tubes is constructed based on the design information and labeling position information of the test tubes. The test tube model is a 3D virtual model used to simulate and pre-test the behavior and performance of the tubes in the flexible automated labeling facility, which can reflect the appearance, size and physical properties of the test tubes. Relevant attributes such as mass, center of gravity position, grasping difficulty, etc. are configured in the test tube model to more accurately simulate the physical properties and grasping process of the test tubes in subsequent simulations.

[0038] The labeling simulation module imports the labeling control twin model and K test tube models into the labeling simulation module, and sets the initial conditions and parameters of the simulation. Using the path planning algorithm, a suitable grasping path and reset path are planned for each test tube. The simulated robot moves to the top of the test tube according to the planned path and adjusts its posture to stabilize the grasping process of the test tube. During the simulation, the contact force, posture change and other parameters between the robot and the test tube are monitored in real time to ensure the stability and safety of the grasping. The simulated robot moves the grasped test tube to the reset labeling site set. During the movement, the stability and accuracy of the test tube are ensured to avoid collision or interference. On the reset labeling site set, the positioning accuracy of the test tube and the labeling effect of the labeling machine are verified. By simulating the labeling process of the labeling machine, check whether the labeling position of the test tube is accurate and whether the label is flat and wrinkle-free. The K groups of test tube grasping node sets and K groups of reset labeling site sets obtained during the simulation are output to the subsequent modules. This implementation method more accurately simulates the operating status of the actual labeling facilities and the physical properties of the test tube by constructing a labeling control twin model and a test tube model, thereby achieving the technical effect of improving the accuracy and reliability of the simulation results.

[0039] In one possible implementation, the labeling control twin model acquisition module includes: an equipment information acquisition module, which is used to extract the first equipment information of the labeling machine and the multiple second equipment information of the multiple collaborative robotic arms from the automated equipment information; a model construction module, which is used to use the first equipment information and the multiple second equipment information as modeling data, and adopt digital twin technology to construct a labeling machine twin model and multiple robotic arm models; a twin space construction module, which is used to pre-construct a twin space with the labeling control area as a constraint; a labeling control twin model generation module, which is used to extract the equipment layout position information from the automated equipment information, and copy the labeling machine twin model and multiple robotic arm models to the twin space according to the equipment layout position information to generate the labeling control twin model.

[0040] Specifically, the equipment information acquisition module establishes a connection with the automated equipment information system, identifies and extracts key equipment information of the labeling machine, such as model, specifications, performance parameters, etc., from the connected information system as the first equipment information; similarly, the equipment information of multiple robotic arms working in coordination with the labeling machine is extracted, including their respective models, arm lengths, load capacities, etc., as multiple second equipment information.

[0041] The model building module cleans and organizes the acquired first device information and multiple second device information to ensure the accuracy and completeness of the data. According to the requirements of the digital twin technology, the processed device information is converted into the data format and structure required for modeling. Using the digital twin software or platform, a three-dimensional model of the labeling machine is constructed based on the first device information, including its appearance, internal structure, working principle, etc. Similarly, a three-dimensional model is constructed for each collaborative robotic arm based on the second device information to ensure that the model can accurately reflect the actual function and performance of the robotic arm. The twin space construction module defines the boundaries and scope of the twin space according to the actual layout and size of the labeling control area. In the digital twin platform, a virtual three-dimensional environment is created according to the defined twin space range as a container for the subsequent model placement.

[0042] The labeling control twin model generation module extracts the specific layout information of the labeling machine and each robotic arm in the labeling control area from the automation equipment information. According to the extracted location information, the labeling machine twin model and multiple robotic arm models are positioned and placed in the twin space to ensure that the relative position and angle between the models are consistent with the actual layout. After all models are placed, these models are integrated to generate a complete labeling control twin model, which fully reflects the actual situation of the labeling control area. This implementation method accurately captures every detail of the labeling control area, including the precise size of the labeling machine, the range of motion of the robotic arm, the relative position of each device, and the interaction method between the devices, so that the virtual environment is almost consistent with the real environment, achieving the technical effect of realizing refined simulation and highly restoring the real environment.

[0043] In a possible implementation, the test tube model acquisition module includes: a first test tube design information extraction module, the first test tube design information extraction module is used to extract first test tube design information of a first test tube based on the K test tube design information, wherein the first test tube is any one of the K test tubes; a first basic model construction module, the first basic model construction module is used to construct and obtain a first basic model according to the first test tube design information; a first labeling position information extraction module, the first labeling position information extraction module is used to extract and obtain first labeling position information of the first test tube from the K labeling position information; a first test tube model acquisition module, the first test tube model acquisition module is used to locate and identify a first labeling area in the first basic model according to the first labeling position information to obtain a first test tube model; K test tube model acquisition modules, the K test tube model acquisition modules are used to, by analogy, construct and obtain the K test tube models according to the K test tube design information and the K labeling position information.

[0044] Specifically, the first test tube design information extraction module selects the design information of any test tube (i.e., the first test tube) from the K test tube design information, including size, shape, material, etc. The first basic model construction module uses 3D modeling software or algorithm to construct a three-dimensional basic model of the first test tube according to the first test tube design information. The first labeling position information extraction module finds the labeling position information corresponding to the first test tube from the K labeling position information, and the first labeling position information specifies the specific position or area on the first test tube where the label needs to be affixed. The first test tube model acquisition module locates and identifies the labeling area on the first basic model according to the first labeling position information by adding specific marks or colors to the model, and outputs the first test tube model with the labeling area identification. The K test tube model acquisition modules repeat the above steps (from the first test tube design information extraction to the first test tube model acquisition), but each time processes different test tube design information and corresponding labeling position information, and finally constructs K complete test tube models, each of which contains its specific labeling area identification. This implementation method processes the design information and labeling position information of each test tube in steps, ensuring that each test tube model is constructed strictly in accordance with actual needs, avoiding confusion and errors, and achieving the technical effect of improving the accuracy of test tube model construction.

[0045] In one possible implementation, the labeling simulation module includes: a first vector model acquisition module, which is used to randomly place the first test tube model in the twin space to obtain a first vector model; a stable grasping simulation module, which is used to use the first labeling area as a grasping taboo, and control the multiple robotic arm models in the labeling control twin model to perform a stable grasping simulation on the first test tube model to obtain a first test tube grasping node set; a spatial position data acquisition module, which is used to perform labeling alignment of the first test tube model and the labeling machine twin model in the twin space according to the first labeling area, and perform spatial position data acquisition on the first test tube grasping node set based on the alignment result. set, obtain the first reset labeling site set; N random placement and grabbing labeling simulation modules, the N random placement and grabbing labeling simulation modules are used to perform N random placement and grabbing labeling simulations on the first test tube model by analogy in the twin space, to obtain N vector models, N test tube grabbing node sets and N reset labeling site sets; a storage module, the storage module is used to associate the N vector models with the N test tube grabbing node sets to store, obtain the first group of test tube grabbing node sets, store the N reset labeling site sets, and obtain the first group of reset labeling site sets; a test tube grabbing node and reset labeling site set acquisition module, the test tube grabbing node and reset labeling site set acquisition module is used to obtain the K groups of test tube grabbing node sets and K groups of reset labeling site sets by analogy.

[0046] Specifically, the first vector model acquisition module simulates and generates a random position and posture in the twin space, places the first test tube model at this position, records the position and posture of the test tube model at this time, and its relative relationship with other equipment (such as labeling machine, robotic arm), to form a first vector model. The first vector model is a mathematical representation of the position, posture and relationship of the first test tube model with other objects in three-dimensional space. The stable grasping simulation module sets the first labeling area as a grasping taboo area, that is, the robotic arm cannot touch or interfere with this area when grasping the first test tube. The labeling control twin model is used to control multiple robotic arm models to perform stable grasping simulation on the first test tube model, and records the specific position points on the test tube grasped during each successful grasping, to form the first test tube grasping node set.

[0047] The spatial position data acquisition module simulates the labeling alignment process of the first test tube model and the labeling machine twin model according to the position of the first labeling area in the twin space. After the alignment is successful, based on the current alignment result, the spatial position data of each node in the first test tube grabbing node set is collected. The collected data includes the precise position and posture of the test tube relative to the labeling machine, forming the first reset labeling site set. The N-time random placement and grabbing labeling simulation module repeats the steps of first vector model acquisition, stable grabbing simulation and spatial position data acquisition, but randomly changes the position and posture of the test tube model in the twin space in each simulation. Such simulation is performed N times, and each simulation generates a vector model, a test tube grabbing node set and a reset labeling site set.

[0048] The storage module associates and stores the N vector models and the corresponding N test tube grasping node sets to form the first set of test tube grasping node sets. The N reset labeling site sets are stored to form the first set of reset labeling site sets. The test tube grasping node and reset labeling site set acquisition module repeats all the above steps (from the first vector model acquisition to storage) for the remaining K-1 test tube models, and finally obtains K groups of test tube grasping node sets and K groups of reset labeling site sets for subsequent retrieval and use. This implementation method captures the impact of different situations (such as slight changes in the position and posture of the test tube) on the grasping and labeling process through random placement and multiple simulations, achieving the technical effect of comprehensive grasping and labeling simulation and providing rich data support for the test tube positioning analysis model.

[0049] The test tube positioning analysis model acquisition module 30 is used to associate and store the K types of test tubes, K groups of test tube grabbing node sets and K groups of reset labeling site sets based on the knowledge graph to obtain the test tube positioning analysis model. Specifically, K groups of test tube grabbing node sets and K groups of reset labeling site sets of K types of test tubes are received from the grabbing and labeling simulation module 20. Identify all relevant entities, including test tube types, grabbing nodes, reset labeling sites, etc., and define the relationship between these entities, such as "a certain type of test tube corresponds to a set of grabbing node sets" and "a certain type of test tube corresponds to a set of reset labeling site sets". Add necessary attributes to each entity, such as the size, shape, material, etc. of the test tube, as well as the specific coordinates, posture and other information of the grabbing node set and the reset labeling site set. Use a graph database or a relational database to store entities, relationships and attributes in the knowledge graph to ensure that each test tube type can quickly retrieve the corresponding grabbing node set and reset labeling site set through its unique identifier (such as type number). The constructed test tube positioning analysis model can quickly locate the corresponding grasping and labeling positions based on the test tube type.

[0050] The test tube image acquisition and analysis module 40 is used for when the test tube to be labeled is transported to the labeling control area of ​​the flexible automated labeling facility through a conveyor belt, the automated image acquisition device performs image acquisition and analysis on the test tube to be labeled, and outputs a real-time test tube type and test tube positioning analysis image, wherein the automated image acquisition device is pre-deployed directly above the labeling control area. Specifically, when the test tube to be labeled enters the labeling control area of ​​the flexible automated labeling facility through a conveyor belt, the system receives a trigger signal (which may be issued by a sensor or control logic), and the trigger signal activates the automated image acquisition device to prepare to acquire images. The automated image acquisition device (a device that can automatically capture images, such as a high-definition camera or a visual sensor) is pre-deployed directly above the labeling control area to ensure that the top or side of the test tube to be labeled (depending on the labeling requirements, test tube type, and test tube placement posture, etc.) can be clearly photographed. The automated image acquisition device captures images according to preset parameters (such as exposure time, focal length, resolution, etc.) to obtain real-time images of the test tube.

[0051] The collected original image is preprocessed to improve the accuracy and efficiency of subsequent analysis. The preprocessing steps include denoising, contrast enhancement, edge detection, etc. The preprocessed image is clearer, which is conducive to subsequent feature extraction and recognition. Features related to the test tube type and positioning are extracted from the preprocessed image. Including the size, shape, color, texture, label position, etc. of the test tube, the feature extraction method includes image processing technology (such as morphological operation, edge detection, template matching, etc.) and machine learning algorithms (such as feature learning, feature selection, etc.). The extracted features are compared with the features in the pre-stored test tube type template, database or classification model to identify the type of test tube to be labeled. According to the identified test tube type and the extracted features, the precise position and direction of the test tube are further analyzed (i.e., positioning analysis). The real-time test tube type and test tube positioning analysis image are provided as output results to the collaborative control stability analysis module 50 for subsequent processing.

[0052] In one possible implementation, the test tube image acquisition and analysis module 40 includes: a test tube feature extraction module, which is used to obtain K test tube feature sets by performing test tube feature extraction on the K test tube models; a test tube classification model construction module, which is used to pre-build a test tube classification model, wherein the test tube classification model is generated based on the K test tube feature sets; and an automated image acquisition device local update module, which is used for the automated image acquisition device including an industrial camera and an edge computing device, and completes the local update of the automated image acquisition device by synchronizing the test tube classification model to the edge computing device.

[0053] Specifically, the test tube feature extraction module defines the features to be extracted, such as shape, size, color, texture, label position, etc., according to the requirements of test tube labeling. Based on the defined features, an image processing algorithm or machine learning technology is selected to extract these features. For example, an edge detection algorithm is used to extract shape contours, a color histogram is used to extract color features, and a texture analysis algorithm is used to extract texture features. The selected feature extraction algorithm is applied to each test tube model to generate a corresponding feature vector or feature set.

[0054] The test tube classification model construction module selects a classification model based on task requirements and data characteristics, such as support vector machine (SVM), random forest, neural network, etc., and uses the extracted K test tube feature sets as training data to train the selected classification model. During the training process, the model will learn how to map the feature set to the corresponding test tube type. Use an independent test set to evaluate the performance of the model, including indicators such as accuracy, recall rate, F1 score, etc., and adjust the model parameters or select a more appropriate model based on the evaluation results. Optimize model performance through cross-validation, regularization, feature selection and other techniques to ensure that the model has good generalization ability in practical applications. After training, the test tube classification model is obtained, which is used to map the input test tube feature set to the predefined test tube type.

[0055] The local update module of the automated image acquisition device synchronizes the trained test tube classification model from the server or cloud to the edge computing device in the automated image acquisition device, deploys the test tube classification model on the edge computing device, enables it to process image data locally in real time, verifies the running effect of the test tube classification model on the edge computing device, and ensures that the test tube classification model can accurately identify the test tube type. This implementation method can realize real-time processing of local image data by deploying the test tube classification model to the edge computing device, avoiding the delay and bandwidth cost of uploading large amounts of data to the cloud for processing, and achieving the technical effect of improving recognition speed.

[0056] In one possible implementation, the test tube image acquisition and analysis module 40 includes: an image acquisition module, which is used when the test tube to be labeled is transported to the labeling control area through a conveyor belt, and the industrial camera of the automated image acquisition device performs image acquisition on the test tube to be labeled to obtain the test tube positioning analysis image; a real-time test tube type acquisition module, which is used by the edge computing device built into the automated image acquisition device to analyze the test tube positioning analysis image through a test tube classification model and output the real-time test tube type; and an output module, which is used by the automated image acquisition device to output the real-time test tube type and the test tube positioning analysis image as output results.

[0057] Specifically, when the test tube to be labeled enters the labeling control area through the conveyor belt, the image acquisition module receives a trigger signal and starts the industrial camera of the automated image acquisition device, so that the industrial camera captures the image of the test tube to be labeled that enters the labeling control area according to preset parameters, and generates a high-definition test tube positioning analysis image. The real-time test tube type acquisition module transmits the captured test tube positioning analysis image to the edge computing device built into the automated image acquisition device. The edge computing device loads a pre-trained test tube classification model, uses the test tube classification model to analyze the test tube positioning analysis image, and determines the type of the test tube through feature extraction and classification algorithms. After the analysis is completed, the edge computing device outputs real-time test tube type information. The output module integrates the real-time test tube type information and the test tube positioning analysis image to form a complete output result, and the integrated result is transmitted to the subsequent processing module through an appropriate communication interface (such as Ethernet, serial port, etc.). This implementation method extracts the test tube type from the test tube positioning analysis image through the test tube classification model, thereby achieving the technical effect of improving the accuracy and efficiency of test tube type recognition.

[0058] Collaborative control stability analysis module 50, the collaborative control stability analysis module 50 is used to traverse the test tube positioning analysis model to perform collaborative control stability analysis with the real-time test tube type and test tube positioning analysis image as constraints, and obtain the target test tube grabbing node set and the target reset labeling site set. Specifically, the collaborative control stability analysis module 50 receives the real-time test tube type and test tube positioning analysis image from the test tube image acquisition and analysis module 40, and at the same time, also accesses the test tube positioning analysis model stored in the test tube positioning analysis model acquisition module 30, and the test tube positioning analysis model contains the association information of K types of test tubes, K groups of test tube grabbing node sets and K groups of reset labeling site sets. Using the real-time test tube type as the key index, by traversing the nodes and relationships in the model, the grabbing node set and the reset labeling site set of the corresponding test tube are retrieved in the test tube positioning analysis model. The test tube positioning analysis image is further analyzed to verify whether the test tube position in the image is consistent with or close to the retrieved theoretical position. Based on the retrieved test tube grasping node set and reset labeling site set, as well as the actual position of the test tube in the image, the collaborative control stability of multiple collaborative robotic arms when performing grasping and labeling operations is evaluated, including checking whether the motion paths of the robotic arms conflict, whether the kinematic constraints of the robotic arms are satisfied, and whether the operations can be completed within the specified time. If problems are found in the collaborative control stability (such as robotic arm path conflicts, time timeouts, etc.), the target test tube grasping node set and target reset labeling site set are optimized and adjusted to ensure the stability and efficiency of the operation. Finally, the target test tube grasping node set and target reset labeling site set are output.

[0059] like Figure 2As shown, in a possible implementation, the collaborative control stability analysis module 50 includes: an alternative data group extraction module, the alternative data group extraction module is used to extract the alternative data group from the test tube positioning analysis model mapping using the real-time test tube type, wherein the alternative data group includes multiple alternative test tube grasping node sets and multiple alternative reset labeling site sets of associated mappings; an alternative vector model extraction module, the alternative vector model extraction module is used to extract and obtain multiple alternative vector models based on the multiple alternative test tube grasping node sets; a bird's-eye view image acquisition module, the bird's-eye view image acquisition module is used to perform bird's-eye view image acquisition on the multiple alternative vector models to obtain multiple An alternative model analysis image; a similarity calculation module, the similarity calculation module is used to perform similarity calculation on the test tube positioning analysis image and multiple alternative model analysis images to obtain multiple similarity coefficients; a target model analysis image acquisition module, the target model analysis image acquisition module is used to serialize the multiple similarity coefficients and extract the alternative model analysis images corresponding to the extreme values ​​based on the sorting results to obtain the target model analysis image; a reverse extraction module, the reverse extraction module is used to reversely extract from the multiple alternative test tube grasping node sets and the multiple alternative reset labeling site sets according to the target model analysis image to obtain the target test tube grasping node set and the target reset labeling site set.

[0060] Specifically, in the test tube positioning analysis model, the candidate data group extraction module uses the real-time test tube type as an index to retrieve all candidate data groups associated with the type of test tube, and these candidate data groups include multiple possible test tube grabbing node sets and corresponding reset labeling site sets, which are generated based on simulation. The candidate vector model extraction module converts each candidate test tube grabbing node set into a vector model by converting the coordinate points in three-dimensional space, and outputs multiple candidate vector models. The top view image acquisition module simulates the top view processing of multiple candidate vector models, that is, according to the coordinates and orientation of the candidate vector models, the corresponding top view image or simulated view is generated by computer graphics technology, and multiple candidate model analysis images (simulated top view images) are output. The similarity calculation module uses an image similarity algorithm (such as the structural similarity index SSIM, feature matching, etc.) to calculate the similarity between the test tube positioning analysis image and each candidate model analysis image, and outputs multiple similarity coefficients, each of which corresponds to the degree of similarity between an alternative model analysis image and a test tube positioning analysis image. The target model analysis image acquisition module sorts the similarity coefficients and selects the candidate model analysis image with the highest similarity (i.e., corresponding to the extreme value) as the target model analysis image. The reverse extraction module traces back to the candidate test tube grabbing node set and reset labeling site set associated with the target model analysis image, and directly extracts the corresponding target test tube grabbing node set and target reset labeling site set. This implementation method more accurately matches the position of the real-time test tube with the preset candidate data set by simulating overhead image acquisition and similarity calculation, avoiding complex calculations directly based on three-dimensional coordinates, and achieving the technical effect of improving matching efficiency.

[0061] The labeling processing module 60 is used to generate positioning collaborative control parameters according to the target test tube grabbing node set and the target reset labeling site set, and use the positioning collaborative control parameters to operate the multiple collaborative robotic arms to grab the test tube to be labeled to the labeling machine to perform labeling processing. Specifically, the labeling processing module 60 receives the target test tube grabbing node set and the target reset labeling site set from the collaborative control stability analysis module 50. Based on the target test tube grabbing node set and the target reset labeling site set, the positioning collaborative control parameters are generated, including the motion trajectory, speed, acceleration, grasping force, etc. of the robotic arm, to ensure that the robotic arm can accurately and stably grab the test tube to be labeled and move it to the labeling position. The generated positioning collaborative control parameters are verified to ensure that they meet the kinematic constraints and dynamic requirements of the robotic arm, and to check whether there are potential conflicts or errors. The verified positioning collaborative control parameters are converted into control instructions that the robot arm can understand, and sent to multiple collaborative robot arms through the control system. After receiving the control instructions, the multiple collaborative robot arms perform grabbing and moving operations, adjust the posture and position according to the parameters in the instructions, and accurately grab the test tube to be labeled and move it to the labeling position of the labeling machine. When the test tube to be labeled is accurately placed in the labeling position, the labeling machine automatically performs the labeling operation, including steps such as printing, cutting, and pasting the label. After the labeling is completed, the robot arm puts the test tube back to its original position or moves it to the next processing position. The embodiment of the present application adopts an interactive method to obtain the labeling position information of various test tubes, and uses flexible automatic labeling facilities (including a labeling machine and multiple collaborative robotic arms) to perform grasping and labeling simulation, obtain grasping node sets and reset labeling site sets for different test tubes, and store the test tube types, grasping node sets and reset labeling site sets based on the knowledge graph association, and construct a test tube positioning analysis model. When the test tube to be labeled enters the labeling control area, the automated image acquisition device acquires and analyzes the image, and outputs the real-time test tube type and positioning analysis image. According to the real-time test tube type and positioning analysis image, the test tube positioning analysis model is traversed to perform collaborative control stability analysis, and the target grasping node set and reset labeling site set are determined. According to the analysis results, positioning collaborative control parameters are generated, and multiple collaborative robotic arms are driven to grasp the test tubes to the labeling machine to perform labeling processing and other technical means, thereby achieving the technical effect of improving the accuracy of labeling through a highly flexible and adaptable automated labeling system.

[0062] In one possible implementation, the labeling processing module 60 includes: a robot arm grasping trajectory fitting module, which is used to perform robot arm grasping trajectory fitting according to the target test tube grasping node set and the target reset labeling site set to obtain multiple operation trajectories of the multiple collaborative robot arms; a positioning collaborative control parameter generation module, which is used to generate the positioning collaborative control parameters according to the multiple operation trajectories; a collaborative robot arm operation module, which is used to use the positioning collaborative control parameters to operate the multiple collaborative robot arms to grasp the test tubes to be labeled to the labeling machine for labeling processing.

[0063] Specifically, the robot grasping trajectory fitting module analyzes the spatial position relationship between the target test tube grasping node set and the target reset labeling site set, determines the path that the robot needs to move, and combines the physical limitations of the robot (such as joint angle range, end effector reachable space) and dynamic characteristics (such as acceleration, speed limit) to preliminarily optimize the path. Use mathematical methods (such as polynomial interpolation, spline curve, etc.) to fit the optimized path to generate a smooth grasping trajectory that conforms to the robot's motion characteristics. Since multiple collaborative robot arms interact and collaborate, coordinate and optimize the trajectories to ensure that multiple collaborative robot arms do not interfere with each other. The multiple running trajectories of multiple collaborative robot arms obtained by fitting are passed as output to the positioning collaborative control parameter generation module. The positioning collaborative control parameter generation module extracts the key parameters that the robot needs to follow during the movement process from multiple running trajectories, such as starting position, end position, speed, acceleration, time node, etc., and converts these key parameters into a format that the robot control system can understand, such as control instructions, parameter settings, etc. Combined with the collaborative relationship between multiple collaborative robot arms, the generated parameters are further optimized and adjusted to output the positioning collaborative control parameters. The collaborative robot operation module receives the positioning collaborative control parameters and sends them to multiple collaborative robot arms through the control system. After receiving the positioning collaborative control parameters, the multiple collaborative robot arms perform grabbing and moving operations, grab the test tubes to be labeled, and move them to the labeling position of the labeling machine for labeling. This implementation method ensures that multiple collaborative robot arms can accurately and stably complete the grabbing, moving and labeling of the test tubes to be labeled through the collaborative work of the robot arm grabbing trajectory fitting module, the positioning collaborative control parameter generation module and the collaborative robot arm operation module, achieving the technical effect of improving the accuracy and efficiency of labeling and improving the stability and reliability of the entire system.

[0064] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0065] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. An adaptive test tube positioning parameter coordinated control system for labeling machines, characterized in that: The system comprises: A labeling position information acquisition module, wherein the labeling position information acquisition module is used to interactively obtain K labeling position information of K types of test tubes; A grabbing and labeling simulation module, wherein the grabbing and labeling simulation module is used to perform grabbing and labeling simulation on the K types of test tubes using the K labeling position information as constraints, and obtain K groups of test tube grabbing node sets and K groups of reset labeling site sets, wherein the flexible automatic labeling facility is composed of a labeling machine and a plurality of collaborative robotic arms; A test tube positioning analysis model acquisition module, the test tube positioning analysis model acquisition module is used to associate and store the K types of test tubes, K groups of test tube grabbing node sets and K groups of reset labeling site sets based on the knowledge graph to obtain a test tube positioning analysis model; A test tube image acquisition and analysis module, wherein when the test tube to be labeled is transported to the labeling control area of ​​the flexible automated labeling facility through a conveyor belt, an automated image acquisition device performs image acquisition and analysis on the test tube to be labeled, and outputs a real-time test tube type and test tube positioning analysis image, wherein the automated image acquisition device is pre-deployed directly above the labeling control area; A collaborative control stability analysis module, wherein the collaborative control stability analysis module is used to traverse the test tube positioning analysis model to perform collaborative control stability analysis based on the real-time test tube type and the test tube positioning analysis image, and obtain a target test tube grabbing node set and a target reset labeling site set; A labeling processing module, the labeling processing module is used to generate positioning collaborative control parameters according to the target test tube grabbing node set and the target reset labeling site set, and use the positioning collaborative control parameters to operate the multiple collaborative mechanical arms to grab the test tube to be labeled to the labeling machine to perform labeling processing; Wherein, the grabbing and labeling simulation module includes: A labeling control twin model acquisition module, wherein the labeling control twin model acquisition module is used to interactively obtain the automation equipment information of the flexible automated labeling facility, and construct a labeling control twin model according to the automation equipment information and the labeling control area; A test tube model acquisition module, the test tube model acquisition module is used to interactively obtain K test tube design information of K types of test tubes, and construct K test tube models according to the K test tube design information and K labeling position information; A labeling simulation module, wherein the labeling simulation module is used to use the labeling control twin model to perform a grabbing and labeling simulation on the K test tube models to obtain the K groups of test tube grabbing node sets and the K groups of reset labeling site sets; Among them, the labeling control twin model acquisition module includes: A device information acquisition module, the device information acquisition module is used to extract and obtain the first device information of the labeling machine and the plurality of second device information of the plurality of collaborative robot arms from the automation device information; A model building module, wherein the model building module is used to use the first device information and the plurality of second device information as modeling data, and adopt the digital twin technology to construct a labeling machine twin model and a plurality of robotic arm models; A twin space construction module, wherein the twin space construction module is used to pre-construct the twin space with the labeling control area as a constraint; A labeling control twin model generation module, wherein the labeling control twin model generation module is used to extract equipment layout location information from the automation equipment information, and copy the labeling machine twin model and multiple robotic arm models to the twin space according to the equipment layout location information to generate the labeling control twin model.

2. The adaptive test tube positioning parameter coordinated control system for labeling machine according to claim 1, characterized in that: The test tube model acquisition module comprises: A first test tube design information extraction module, the first test tube design information extraction module is used to extract first test tube design information of a first test tube based on the K test tube design information, wherein the first test tube is any one of the K test tubes; A first basic model construction module, the first basic model construction module is used to construct a first basic model according to the first test tube design information; A first labeling position information extraction module, the first labeling position information extraction module is used to extract the first labeling position information of the first test tube from the K labeling position information; A first test tube model acquisition module, the first test tube model acquisition module is used to locate and mark a first labeling area in the first basic model according to the first labeling position information to obtain a first test tube model; K test tube model acquisition modules are used to construct and obtain the K test tube models based on the K test tube design information and the K labeling position information.

3. The adaptive test tube positioning parameter coordinated control system for labeling machine according to claim 2, characterized in that: The labeling simulation module includes: a first vector model acquisition module, wherein the first vector model acquisition module is used to randomly place the first test tube model in the twin space to obtain a first vector model; A stable grasping simulation module, wherein the stable grasping simulation module is used to use the first labeling area as a grasping taboo, and the labeling control twin model controls the multiple robot arm models to perform a stable grasping simulation on the first test tube model to obtain a first test tube grasping node set; A spatial position data acquisition module, wherein the spatial position data acquisition module is used to perform labeling alignment between the first test tube model and the labeling machine twin model in the twin space according to the first labeling area, and to perform spatial position data acquisition on the first test tube grabbing node set based on the alignment result to obtain a first reset labeling site set; N random placement and grabbing labeling simulation modules, wherein the N random placement and grabbing labeling simulation modules are used to perform N random placement and grabbing labeling simulations on the first test tube model in the twin space by analogy, to obtain N vector models, N test tube grabbing node sets and N reset labeling site sets; A storage module, the storage module is used to associate and store the N vector models and the N test tube grabbing node sets to obtain a first set of test tube grabbing node sets, and store the N reset labeling site sets to obtain a first set of reset labeling site sets; The test tube grabbing node and reset labeling site set acquisition module is used to obtain the K groups of test tube grabbing node sets and K groups of reset labeling site sets by analogy.

4. The adaptive test tube positioning parameter coordinated control system for labeling machine according to claim 3, characterized in that: The test tube image acquisition and analysis module comprises: A test tube feature extraction module, the test tube feature extraction module is used to obtain K test tube feature sets by performing test tube feature extraction on the K test tube models; A test tube classification model construction module, wherein the test tube classification model construction module is used to pre-construct a test tube classification model, wherein the test tube classification model is constructed and generated based on the K test tube feature sets; The local update module of the automated image acquisition device is used for the automated image acquisition device including an industrial camera and an edge computing device. The local update of the automated image acquisition device is completed by synchronizing the test tube classification model to the edge computing device.

5. The adaptive test tube positioning parameter coordinated control system for labeling machine according to claim 4, characterized in that: The test tube image acquisition and analysis module comprises: An image acquisition module, wherein when the test tube to be labeled is transported to the labeling control area via a conveyor belt, the industrial camera of the automated image acquisition device performs image acquisition on the test tube to be labeled to obtain the test tube positioning analysis image; A real-time test tube type acquisition module, wherein the real-time test tube type acquisition module is used for the edge computing device built into the automated image acquisition device to analyze the test tube positioning analysis image through a test tube classification model and output the real-time test tube type; An output module is used by the automatic image acquisition device to output the real-time test tube type and test tube positioning analysis image as an output result.

6. The adaptive test tube positioning parameter coordinated control system for labeling machine according to claim 5, characterized in that: The collaborative control stability analysis module includes: An alternative data group extraction module, the alternative data group extraction module is used to extract an alternative data group from the test tube positioning analysis model mapping using the real-time test tube type, wherein the alternative data group includes a plurality of candidate test tube grabbing node sets and a plurality of candidate resetting labeling site sets associated with the mapping; A candidate vector model extraction module, the candidate vector model extraction module is used to extract and obtain multiple candidate vector models based on the multiple candidate test tube grabbing node sets; A bird's-eye view image acquisition module, the bird's-eye view image acquisition module is used to perform bird's-eye view image acquisition on the multiple candidate vector models to obtain multiple candidate model analysis images; A similarity calculation module, the similarity calculation module is used to perform similarity calculation on the test tube positioning analysis image and multiple candidate model analysis images to obtain multiple similarity coefficients; A target model analysis image acquisition module, wherein the target model analysis image acquisition module is used to serialize the multiple similarity coefficients and extract candidate model analysis images corresponding to extreme values ​​based on the sorting results to obtain a target model analysis image; A reverse extraction module is used to reversely extract from the multiple candidate test tube grabbing node sets and the multiple candidate reset labeling site sets according to the target model analysis image to obtain the target test tube grabbing node set and the target reset labeling site set.

7. The adaptive test tube positioning parameter coordinated control system for labeling machine according to claim 1, characterized in that: The labeling processing module includes: A robot arm grasping trajectory fitting module, the robot arm grasping trajectory fitting module is used to perform robot arm grasping trajectory fitting according to the target test tube grasping node set and the target reset labeling site set to obtain multiple operation trajectories of the multiple collaborative robot arms; A positioning collaborative control parameter generation module, the positioning collaborative control parameter generation module is used to generate the positioning collaborative control parameters according to the multiple operation trajectories; A collaborative robot arm operation module is used to use the positioning collaborative control parameters to operate the multiple collaborative robot arms to grab the test tubes to be labeled and bring them to the labeling machine for labeling processing.

Images