Method and system for automated door alignment in vehicle assembly

Abstract

The invention relates to a method for automated door alignment in vehicle assembly, comprising the following method steps: - Acquisition of initial measurement data (250) with positions and distances of reference points of a vehicle assembly (50) consisting of one or more assembled assembly modules (30) using an analysis robot (200) with sensors (220); - Comparing the collected initial measurement data (250) with target values ​​(890) by the evaluation module (800), wherein the evaluation module (800) uses an AI model (850) to calculate the necessary setting values ​​(870) for adjusting the hinges and adjusting the door (10); - Adjusting the door base structure and hinges by the alignment robot (300) based on the calculated setting values ​​(870); - Attaching the door (10) to the hinges and other attachment points by a screw robot (400); - Measuring the position of the built-in door (10) by optical sensors (220) of the analysis robot (200); - Learning the AI ​​model (850) from the first measurement data (250) and the second measurement data (270) to improve the determination of target values ​​(890) for door adjustment and to increase the accuracy and efficiency of future door alignment processes.

Description

[0001] The invention relates to a method, a system, and a computer program product for automated door alignment in vehicle assembly.

[0002] Vehicle production is subject to a continuous modernization process driven by new technological developments. The goal of this process is to increase efficiency. As a result, vehicles are increasingly manufactured in larger modular units to enhance flexibility and efficiency in vehicle production.

[0003] This modularization, however, presents a multitude of challenges. Modular vehicle production utilizes large-format modules that are prefabricated and assembled into a complete unit during final assembly. Modularization necessitates new approaches to manufacturing and assembly, as conventional methods are unsuitable for efficiently assembling the larger and more complex modules. Joining these large modules must be accomplished within the predetermined spatial constraints of the assembly areas, which poses additional challenges due to the modules' size and complexity. Therefore, the development of new joining technologies is required to enable more efficient and safer assembly, particularly in confined spaces within a production hall.In particular, increased automation through the use of robotics and automation systems is being pursued to optimize manufacturing processes.

[0004] Furthermore, the use of cold joining processes instead of welding or bonding processes, which require heat, is planned. These processes are better suited to ensuring the structural integrity of the modules, as they do not introduce additional heat that could lead to deformation or other problems. At the same time, the joining processes must ensure that the joined modules meet the required strength and stiffness standards. This is crucial for the safety and performance of the finished vehicle.

[0005] Furthermore, the tolerances, i.e., the permissible dimensional deviations of the individual components, must be maintained throughout the entire joining process. This is important to ensure the accuracy of fit and functionality of the modules.

[0006] The assembly of vehicle doors presents a particular challenge. The doors must be mounted precisely and securely, which can be difficult with conventional assembly methods. Currently, the doors are mounted to the body and then, due to the lack of accessibility to the door hinges in the closed position, laborious adjustments are made by manually opening and closing the door.

[0007] It is particularly important that the doors are not only installed securely, but also have high-quality joints. High-quality joints in an installed door ensure that the door is not only aesthetically pleasing, but also functional and safe.

[0008] The quality of the door joints in a motor vehicle encompasses various aspects that ensure the door is not only securely and firmly mounted, but also seamlessly and functionally integrated into the vehicle structure. The gaps between the door and the adjacent body panels must be uniform and symmetrical. Uneven gaps can indicate manufacturing defects and detract from the vehicle's aesthetics. These gaps must fall within specified tolerances to guarantee a consistent appearance and proper function. Furthermore, the door surfaces must be flush with the adjacent body panels, eliminating any protruding edges or indentations. A flush fit contributes to the vehicle's visual harmony and improves aerodynamics.

[0009] Furthermore, the door must be firmly and securely attached to the bodywork to prevent vibration and noise during driving and under load. The door itself must also possess high torsional rigidity to prevent deformation when driving over uneven terrain or in an accident.

[0010] Another important aspect concerns water and airtightness. The door must be installed in such a way that no water can penetrate. This requires precise seals and exact fits. A properly installed door also prevents air from entering and the associated noise (wind noise) while driving.

[0011] A built-in door must open and close easily and without resistance. The closing mechanism must function reliably so that the door is securely closed and protected against unintentional opening. For this to happen, the hinges must be precisely aligned to ensure smooth door movement.

[0012] Furthermore, acoustic quality is also of great importance. No unwanted noises (creaking, squeaking) should occur when opening and closing the door. In addition, the door must effectively dampen outside noise to increase driving comfort.

[0013] A built-in door must also offer a high level of crash safety. The door must meet safety standards and provide sufficient protection in the event of an accident. The connection points (hinges, locking mechanisms) must be strong enough to withstand an impact.

[0014] Connections and seals must be corrosion-protected to extend the service life of the door and the vehicle body. For example, a high-quality surface coating protects the seals from environmental influences.

[0015] To ensure all these aspects, precise manufacturing and assembly processes are required.

[0016] US Patent 2010 / 0114525A1 discloses a method for determining the offset and / or play of a motor vehicle door relative to its frame by optically measuring the door during the assembly process.

[0017] DE 10 2017 128 722 A1 discloses a method for positioning at least one attachment part on a motor vehicle body, in which the attachment part is fastened to the motor vehicle body depending on target fastening data and in which actual fastening data is recorded by means of a detection device.

[0018] DE 10 2021 129 359 A1 discloses a device for testing a joint between at least two components, in which a camera captures a joint image of the joint, and the joint image is transformed into a transformed joint image using a joint template that describes a standard joint with a target shape and a target orientation relative to the camera.

[0019] DE 20 2005 019 619 U1 describes a method and a device for attaching at least four side doors to a vehicle body with door openings. Several side doors are mounted together on one side of the vehicle in an assembly station and held, measured, and aligned together by a positioning mechanism that includes a measuring and alignment device. Preferably, the door is attached from the inside of the body by means of a fastening device located on the opposite side of the vehicle.

[0020] EP 2 878 522 A1 relates to a method for mounting an add-on part to a vehicle body. Several body-side hinge halves are positioned and mounted on the vehicle body using a first reference point system that includes body reference points. After mounting, at least one transverse axis coordinate of the body-side hinge halves is recorded. The add-on part-side hinge halves are mounted to the add-on part using both the first reference point system and a second reference point system that includes add-on part reference points. Based on the recorded transverse axis coordinate, at least one correction value is determined to adjust the position of the add-on part-side hinge halves. This correction value is taken into account during their mounting to ensure correct hinge alignment along the vehicle's transverse axis.

[0021] DE 103 47 554 A1 relates to an assembly device for mounting a body part into a car body, which measures gap and drop dimensions between the car body and the body part and is moved until the measured actual values ​​match the target values. The body part is then attached to the car body.

[0022] The invention is based on the objective of developing possibilities for the effective and efficient alignment and assembly of a vehicle door on assembled large-format component modules of a motor vehicle, whereby the assembly takes place taking into account the limited space conditions in an assembly area.

[0023] This problem is solved according to the invention with respect to a method by the features of claim 1, with respect to a system by the features of claim 8, and with respect to a computer program product by the features of claim 14. The further claims relate to preferred embodiments of the invention.

[0024] The inventive method and system for automated door alignment in vehicle assembly integrates various specialized robots and modules that work together to ensure a highly precise, efficient, and optimized adjustment process. The use of high-precision measuring and adjustment systems in the form of an analysis robot, an alignment robot, and a screw-tightening robot guarantees exact door alignment. The automated alignment process reduces manual intervention and increases assembly efficiency. This significantly reduces the number of necessary process steps from body construction to final assembly, thereby increasing overall efficiency.

[0025] The inventive method also compensates for tolerances of the individual components and ensures perfect door alignment. AI-supported data optimization enables continuous process improvement through learning from the collected data. The use of pre-assembled modules and continuous data analysis minimizes process redundancies by eliminating redundant manual rework, thus saving time and costs.

[0026] The AI-supported door alignment adjustment process according to the invention significantly increases efficiency and precision in vehicle assembly. The use of analysis, alignment, and screwing robots in combination with machine learning AI enables optimal adaptation of door assembly processes to the specific requirements of vehicle production. This leads to higher product quality, reduced costs, and overall more efficient production.

[0027] According to a first aspect, the invention provides a method for automated door alignment in vehicle assembly. The method comprises the following process steps: - Acquisition of initial measurement data with positions and distances of reference points of a vehicle assembly consisting of one or more assembled modules, using an analysis robot with sensors; - Transferring the initial measurement data to an evaluation module; - Comparison of the recorded initial measurement data with target values ​​by the evaluation module, whereby the evaluation module uses an AI model to calculate the adjustment values ​​required for setting the hinges and adjusting the door; - Transferring the calculated setting values ​​to an alignment robot for the exact positioning and adjustment of the door base structure at the hinges of the vehicle assembly; - Adjusting the door base structure and hinges by the alignment robot based on the calculated setting values ​​to bring the door into the optimal position; - Attaching the door to the hinges and other fixing points by a screw-driving robot using automated screw systems and torque sensors; - Attaching the outer door panel to the door base structure using an application robot; - Measuring the position of the installed door using optical sensors of the analysis robot and transmitting this second measurement data to the evaluation module; - Learning the AI ​​model from the first measurement data and the second measurement data to improve the determination of target values ​​for door alignment and to increase the accuracy and efficiency of future door alignment processes.

[0028] In a further training course, it is planned that the optical measurement of the door by the analysis robot will be carried out using optical sensors such as cameras, especially 3D cameras, and / or laser sensors.

[0029] In an advantageous embodiment, it is provided that the alignment of the door base structure and the hinges is carried out by the alignment robot using gripping elements and positioning units.

[0030] In another embodiment, it is provided that the process parameters and control commands for the robots are entered and managed via an input module.

[0031] Advantageously, the AI ​​model of the evaluation module continuously learns from the collected data to improve the accuracy of adjustments in future door installations.

[0032] According to a second aspect, the invention provides a system for automated door alignment in vehicle assembly. The system comprises an analysis robot equipped with sensors for measuring the positions and distances of reference points of a vehicle assembly consisting of one or more assembled module units; an alignment robot configured to position and align a door base structure on already mounted hinges of the vehicle assembly, the alignment robot employing precise control mechanisms and positioning units; and a screwing robot configured for fastening the door to the hinges and other fastening points of the module units, and equipped with automated screwing systems and torque sensors.An input module with a graphical user interface (GUI) for inputting and managing configuration parameters and control commands for the robots; an evaluation module with an AI model, wherein the AI ​​model is configured to analyze the data collected by the analysis robot and calculate the necessary setting values, and wherein the AI ​​model is based on neural networks, in particular convolutional neural networks (CNNs); and a database for storing and managing process data such as setpoints, measurement data, calculated setting values, and configuration parameters of the input module, which are used for analysis and calculation by the evaluation module.

[0033] In a further training course, it is planned that the analysis robot will include optical sensors such as cameras, in particular 3D cameras and / or laser sensors and / or tactile sensors.

[0034] In an advantageous embodiment, the alignment robot uses gripping elements and positioning units to handle and precisely position the door base structure.

[0035] In another embodiment, the evaluation module transmits the calculated setting values ​​to the alignment robot and the screwing robot in real time.

[0036] In particular, the evaluation module is integrated into a cloud computing infrastructure.

[0037] Advantageously, the system includes an application robot for applying the door outer panel to the door base structure, the application robot being configured to automatically apply the door outer panel after the door base structure has been aligned by the alignment robot and fastened to the vehicle assembly by the screwing robot, ensuring a uniform distribution and strength of the connection.

[0038] According to a third aspect, the invention provides a computer program product comprising an executable program code configured to perform the method according to the first aspect when executed.

[0039] The invention will now be explained in more detail with reference to exemplary embodiments shown in the drawing.

[0040] This shows: Fig. 1 a block diagram to illustrate an embodiment of a system according to the invention; Fig. 2 a flowchart to explain the individual process steps of a process according to the invention; Fig. 3 a block diagram of a computer program product according to an embodiment of the third aspect of the invention.

[0041] Additional features, aspects and advantages of the invention or its embodiments become apparent from the detailed description in conjunction with the claims.

[0042] Large modules in vehicle manufacturing are large, prefabricated components or assemblies that comprise essential parts of the vehicle structure. These modules include structural elements such as side walls, floor modules, passenger compartments, and front and rear modules. These modules must be designed and manufactured with precision to ensure that the doors can be installed safely and efficiently, especially under the confined space conditions of a modern assembly line.

[0043] A side wall module comprises the entire side structure of the vehicle, including the A, B, and C pillars, as well as adjacent surfaces such as wheel arches and door frames. The vehicle doors are mounted directly to this module. The precise design of the door frames and the associated mounting points for hinges and locking mechanisms is therefore of crucial importance.

[0044] A floor module forms the basic structure of the vehicle, including the underbody, front and rear crossmembers, and side sills. While the floor module itself does not support the doors, it provides the base for mounting the side panels to which the doors are attached. It ensures the structural integrity and rigidity of the vehicle.

[0045] A passenger compartment module comprises the central area of ​​the vehicle where the passengers sit. It includes the pillar structures (A-, B-, and C-pillars) and the roof frame. The vehicle doors are attached to the B-pillars and door frames, which are part of the passenger compartment module. These modules must be manufactured with precision to ensure a perfect fit and proper function of the doors.

[0046] The front and rear modules comprise the front and rear sections of the vehicle, including the hood, trunk, and bumper areas. Although the doors are not directly attached to these modules, they influence the overall structure of the vehicle and must be designed in coordination with the side panels and passenger compartment modules.

[0047] The large-format modules must be manufactured with high precision to ensure the tight tolerances required for installing the vehicle doors. The modules must be sufficiently rigid and strong to hold the doors securely and stably. The modules must feature precisely pre-machined mounting points for hinges, door locks, and other fasteners.

[0048] Furthermore, the large-format modules must be designed and positioned in such a way that they can be efficiently assembled despite the limited space available on the assembly line. Joining methods such as adhesive bonding, riveting, or mechanical fastening techniques are particularly suitable, as these can be used in confined spaces and without much freedom of movement.

[0049] Fig. Figure 1 shows a system 100 according to the invention for automated door alignment in vehicle assembly. The system 100 comprises an analysis robot 200, an alignment robot 300, an application robot 350, a screwing robot 400, an input module 500, a database 700, and an evaluation module 800. The analysis robot 200, the alignment robot 300, the screwing robot 400, the input module 500, the database 700, and the evaluation module 800 can each be equipped with a processor and / or a memory unit.

[0050] In the context of the invention, a "module" is defined as a self-contained, specialized unit of software and / or hardware components. A module is designed to perform a specific function or task and is independent and self-contained; that is, it accepts specific inputs, performs internal processing, and then delivers specific outputs or results. A module can communicate with other modules or components via interfaces. These interfaces determine how data or commands are input into the module and how results or information are output.

[0051] In the context of the invention, a "processor" can be, for example, a machine or an electronic circuit. A processor can, in particular, be a central processing unit (CPU), a microprocessor, or a microcontroller, such as an application-specific integrated circuit or a digital signal processor, optionally in combination with a memory unit for storing program instructions. A processor can also be a virtualized processor, a virtual machine, or a soft CPU. It can, for example, also be a programmable processor equipped with configuration steps for executing the method according to the invention, or configured with configuration steps such that the programmable processor implements the features of the method, the modules, or other aspects and / or partial aspects of the invention.In particular, the processor can contain highly parallel computing units and powerful graphics modules.

[0052] In the context of the invention, a "storage unit" or "storage module" and the like can refer, for example, to volatile memory in the form of random access memory (RAM), permanent storage such as a hard drive or data carrier, or, for example, a replaceable storage module. The storage module can also be a cloud storage solution.

[0053] The term "database" refers to both a storage algorithm and the hardware in the form of a storage unit.

[0054] Furthermore, communication links are provided for the exchange and transmission of data between the individual modules and robots, in particular as wireless communication links, e.g. as mobile communication links (e.g. 4G LTE, 5G, 6G) and / or as near-field communication links, e.g. Bluetooth. ® , Ethernet, NFC (Near Field Communication) or Wi-Fi ® are trained.

[0055] In particular, the Database 700 and the Analysis Module 800 can be integrated into a cloud computing infrastructure. A cloud computing infrastructure offers the ability to scale resources up or down as needed, allowing computing power, storage space, or network resources to be easily adapted to changing requirements. This scalability enables cost optimization and efficient resource allocation without significant hardware investments. Furthermore, users can access applications and data from anywhere with internet access. Cloud computing also offers high flexibility in software deployment, enabling applications to be deployed and updated quickly and without interruption. Cryptographic encryption methods can also be used to protect the connection to the cloud computing infrastructure via a mobile network.Since a rapid calculation result is required to provide the data to the robots 200, 300, 350, and 400 in real time, processing speed is crucial. Therefore, using cloud computing infrastructure is advantageous to enable real-time calculations, as this ensures fast computation.

[0056] The various robots 200, 300, 350, 400 and modules 500, 700, 800 work together to ensure a precise and efficient adjustment process for the doors during vehicle assembly.

[0057] The analysis robot 200 measures the positions and distances of reference points of a vehicle assembly 50, which consists of one or more assembled vehicle modules 30 and into which at least one door 10 is to be installed. These measurements form the basis for the precise alignment of the door 10. The analysis robot 200 incorporates high-precision sensors 220 and measuring devices such as laser rangefinders, 3D cameras, and tactile sensors that acquire precise data about the geometry of the module 30. After the module 30 are assembled to form the vehicle assembly 50, the analysis robot 200 scans the relevant areas of the vehicle assembly 50. The laser rangefinders detect precise distances, while the 3D cameras capture detailed images of the geometry. Tactile sensors can detect the surface texture through physical contact. This initial measurement data 250 is transmitted to the evaluation module 800.

[0058] The alignment robot 300 positions the door base structure on the hinges already attached to the assembly modules 30. This connects the door base structure to the hinges on the assembled assembly modules 300. This is accomplished by the alignment robot, which moves the door 10 into the correct position. These hinges are designed to allow for precise and stable attachment of the door 10 while simultaneously permitting adjustment along various axes to ensure optimal alignment.

[0059] The 300 alignment robot utilizes precise control mechanisms, actuators, and various auxiliary components such as grippers and positioning units to bring the door base structure and hinges into the optimal position. The grippers and positioning units were specifically designed for handling and positioning the door base structure and hinges. The grippers are able to securely grasp and move the door base structure and hinges, while the positioning units ensure precise alignment and fine-tuning.

[0060] Based on the measurement data 250 acquired by the analysis robot 200, the alignment robot 300 adjusts the hinges so that the door 10 can be inserted precisely into the door frame. According to the invention, the measurement data 250 are modified by the evaluation module 800 using a computer-based calculation to ensure optimal adjustment of the door 10.

[0061] After adjusting the door base structure and the hinges, the screw robot 400 takes over the fastening of the door 10 to the hinges and other fastening points.

[0062] Crucially, the door base structure is separated from the subsequent application of the outer door panel. The outer door panel is the visible, external part of the door. This separation allows the alignment robot 300 to precisely align the door hinges without being restricted by the outer panel. This enables precise adjustment of the door's position and orientation, as the alignment robot 300 can focus exclusively on the door base structure. The alignment robot 300 considers not only the position and orientation of the hinges on the door and frame, but also the tolerances and adjustments required for an optimal fit. The precise control mechanisms of the alignment robot 300 enable millimeter-accurate alignment, ensuring perfect integration of the door into the vehicle structure.

[0063] After successful adjustment of the hinges, the door base structure is attached to the hinges and other mounting points of the vehicle unit 50 by the screwing robot 400 using automated screw systems and torque sensors. The screwing robot 400 thus ensures a firm and secure attachment of the door 10 in the adjusted position.

[0064] The outer door panel is then applied to the door base structure. A special application robot 350 is used for the precise positioning and fastening of the outer door panel. The application robot 350 is equipped with tools that can securely grip, position, and fasten the outer door panel. This procedure ensures that the door 10 is optimally adjusted during the adjustment process without the outer door panel affecting the hinge adjustment.

[0065] The application robot 350 comprises a holding unit for gripping and holding the door outer panel during application, a positioning unit for precisely aligning the door outer panel with the door base structure, and a fastening system for securely attaching the door outer panel to the door base structure. The fastening system includes mechanisms for heating, pressing, or gluing to ensure a permanent bond. The application robot 350 is configured to automatically apply the door outer panel after the door base structure has been aligned by the alignment robot 300 and fastened to the vehicle assembly 50 by the screwing robot 400, ensuring uniform distribution and strength of the connection.

[0066] The Input Module 500 is used to input and manage configuration parameters, process parameters, and control commands for the 200, 300, 350, and 400 robots. Equipped with a graphical user interface (GUI), the Input Module 500 enables easy configuration and customization of process sequences. The Input Module 500 can be installed on various platforms such as desktop computers, laptops, tablet PCs, or smartphones. Users can set configuration parameters such as tolerances, screw forces, and positioning specifications via the Input Module 500, which are then transmitted to the respective 200, 300, 350, and 400 robots.

[0067] Database 700 stores all relevant process data, measurements, and configuration parameters. It is a scalable database solution, similar to a cloud computing infrastructure, that ensures secure data storage and rapid access. All data collected during the assembly process is stored in the database and can be retrieved for later analysis and optimization.

[0068] The evaluation module 800 analyzes the collected measurement data 250 and optimizes the adjustment process. For this purpose, the evaluation module 800 contains an AI model 850, which is equipped with advanced AI algorithms. The AI ​​model 850 is based on neural networks, specifically convolutional neural networks (CNNs), which are particularly well-suited for the analysis and processing of image data. These networks are able to recognize patterns and features in the measurement data and derive precise predictions and adjustments from them.

[0069] A neural network consists of neurons arranged in multiple layers and interconnected in various ways. A neuron can receive information at its input from the outside or from another neuron, process it in a specific way, and then pass it on in a modified form to another neuron at its output, or output it as a final result. Between the input and output neurons are the so-called hidden neurons. Depending on the type of network, there can be several layers of hidden neurons. They are responsible for the transmission and processing of information. The output neurons ultimately deliver a result and transmit it to the outside world. The arrangement and interconnection of the neurons give rise to different types of neural networks, such as feed-forward networks, recurrent networks, or convolutional neural networks.The networks can be trained through unsupervised or supervised learning.

[0070] The Convolutional Neural Network (CNN) is a specific type of artificial neural network. It has multiple convolutional layers and is well-suited for machine learning and artificial intelligence (AI) applications in the field of pattern recognition. The individual layers of the CNN are the convolutional layer, the pooling layer, and the fully connected layer. The convolutional layer is the actual convolutional layer and is capable of recognizing and extracting individual features from the input data. In pattern and image recognition, these can be features such as lines, edges, or specific shapes. The input data is processed in the form of tensors, such as a matrix or vectors. The pooling layer, also called the subsampling layer, condenses and reduces the resolution of the recognized features using appropriate filtering functions. The reduced data volume increases the processing speed.Because the CNN is divided into several local, partially interconnected layers, it requires significantly less storage space than fully interconnected neural networks.

[0071] The evaluation module 800 receives the initial measurement data 250 from the analysis robot 200 and compares it with target values ​​890. Based on this comparison, the AI ​​model 850 calculates the necessary settings for adjusting the hinges. These calculated setting values ​​870 are then transmitted to the alignment robot 300.

[0072] After the outer door panel is applied to the door base structure, the position of the installed door is optically measured again by the analysis robot 200. This second optical measurement provides a second set of measurement data 270, which is also transmitted to the evaluation module 800. The AI ​​model 850 analyzes this second set of measurement data 270 together with the first set of measurement data 250 to calculate the optimal hinge setting.

[0073] The AI ​​model 850 continuously learns from the initial measurement data 250 and the results of the second measurement data 270 from the optical measurement of the installed door 10. By comparing this measurement data 250 and 270, the AI ​​model 850 can recognize patterns and make precise predictions to calculate the optimal hinge settings for future door assemblies. Thus, the AI ​​model 850 continuously learns patterns and deviations in the data from numerous door assemblies during the production of a large number of vehicles, identifying inaccuracies in door alignment. Based on the recognized patterns, the AI ​​model 850 adjusts the control parameters of the alignment robot 300 and the screwing robot 400 to precisely position the door 10.With each new assembly and the data collected, the adjustment and fit accuracy improves, as the AI ​​model 850 learns from the initial measurement data (250 reference points) and the second measurement data (270) from the optical measurement of the installed door (10), thus continuously optimizing the efficiency and precision of the entire assembly process. The AI ​​model 850 therefore learns from each assembly operation to improve future settings.

[0074] In Fig. Figure 2 shows the process steps for automated door alignment in vehicle assembly.

[0075] In step S10, initial measurement data 250 with positions and distances of reference points of a vehicle assembly 50, which consists of one or more joined assembly modules 30, are recorded by means of an analysis robot 200 with sensors 220.

[0076] In step S20, the first measurement data 250 are transmitted to an evaluation module 800.

[0077] In step S30, the collected first measurement data 250 are compared with target values ​​890 by the evaluation module 800, whereby the evaluation module 800 uses an AI model 850 to calculate the necessary setting values ​​870 for setting the hinges and adjusting the door 10.

[0078] In step S40, the calculated setting values ​​870 are transmitted to an alignment robot 300 for the precise positioning and adjustment of the door base structure at the hinges of the vehicle assembly 50.

[0079] In step S50, the door base structure at the hinges is adjusted by the alignment robot 300 based on the calculated setting values ​​870 to bring the door 10 into the optimal position.

[0080] In step S60, the door 10 is attached to the hinges and other fastening points by a screw robot 400 using automated screw systems and torque sensors.

[0081] In step S70, the outer door panel is attached to the door base structure by an application robot 350.

[0082] In step S80, the position of the built-in door 10 is measured by optical sensors of the analysis robot 200, and this second measurement data 270 is transmitted to the evaluation module 800.

[0083] In step S90, the AI ​​model 850 learns from the first measurement data 250 and the second measurement data 270 to improve the determination of target values ​​890 for door adjustment and to increase the accuracy and efficiency of future door alignment processes.

[0084] Fig.Figure 3 schematically represents a computer program product 900 comprising an executable program code 950 configured to execute the method according to the first aspect of the present invention.

[0085] The inventive method and system for automated door alignment in vehicle assembly integrates various specialized robots and modules that work together to ensure a highly precise, efficient, and optimized adjustment process. The use of high-precision measuring and adjustment systems in the form of an analysis robot, an alignment robot, and a screw-tightening robot guarantees exact door alignment. The automated alignment process reduces manual intervention and increases assembly efficiency. This significantly reduces the number of necessary process steps from body construction to final assembly, thereby increasing overall efficiency.

[0086] The inventive method also compensates for tolerances of the individual components and ensures perfect door alignment. AI-supported data optimization enables continuous process improvement through learning from the collected data. The use of pre-assembled modules and continuous data analysis minimizes process redundancies by eliminating redundant manual rework, thus saving time and costs.

[0087] The AI-supported door alignment adjustment process according to the invention significantly increases efficiency and precision in vehicle assembly. The use of analysis, alignment, and screwing robots in combination with machine learning AI enables optimal adaptation of door assembly processes to the specific requirements of vehicle production. This leads to higher product quality, reduced costs, and overall more efficient production. Reference sign 10 Door 30 Module 50 Vehicle assembly group 100 System 200 analysis robots 220 sensors 250 first measurement data 270 second measurement data 300 alignment robots 350 application robots 400 screw-driving robots 500 Input module 700 database 800 Evaluation Module 850 AI model 870 settings 890 target values

Claims

[1] Method for automated door alignment in vehicle assembly, comprising the following process steps: - Acquisition (S10) of initial measurement data (250) with positions and distances of reference points of a vehicle assembly (50) consisting of one or more assembled assembly modules (30) by means of an analysis robot (200) with sensors (220); - Transmitting (S20) the first measurement data (250) to an evaluation module (800); - Comparison (S30) of the collected initial measurement data (250) with target values ​​(890) by the evaluation module (800), wherein the evaluation module (800) uses an AI model (850) to calculate the necessary setting values ​​(870) for adjusting the hinges and adjusting the door (10); - Transmitting (S40) the calculated setting values ​​(870) to an alignment robot (300) for precise positioning and adjustment of the door base structure on the hinges of the vehicle assembly (50); - Adjusting (S50) the door base structure and the hinges by the alignment robot (300) based on the calculated setting values ​​(870) to bring the door (10) into the optimal position; - Attaching (S60) the door (10) to the hinges and other fastening points by a screw robot (400) using automated screw systems and torque sensors; - Attaching (S70) the outer door panel to the door base structure by an application robot (350); - Measuring (S80) the position of the built-in door (10) by optical sensors (220) of the analysis robot (200) and transmitting this second measurement data (270) to the evaluation module (800); - Learning (S90) of the AI ​​model (850) from the first measurement data (250) and the second measurement data (270) to improve the determination of target values ​​(890) for door adjustment and to increase the accuracy and efficiency of future door alignment processes. [2] Method according to claim 1, wherein the optical measurement of the door (10) by the analysis robot (200) is carried out using optical sensors such as cameras, in particular 3D cameras and / or laser sensors. [3] Method according to claim 1 or 2, wherein the alignment of the door base structure and the hinges is carried out by the alignment robot (300) using gripping elements and positioning units. [4] Method according to any one of claims 1 to 3, wherein the process parameters and control commands for the robots (200, 300, 350, 400) are entered and managed via an input module (500). [5] Method according to any one of claims 1 to 4, wherein the AI ​​model (850) of the evaluation module (800) continuously learns from the collected data (250, 270) to improve the accuracy of the adjustments in future door installations. [6] Method according to any one of claims 1 to 5, wherein the evaluation module (800) transmits the calculated setting values ​​(870) in real time to the alignment robot (300) and the screwing robot (400). [7] Method according to any one of claims 1 to 6, wherein the evaluation module (800) is integrated into a cloud computing infrastructure. [8] System (100) for automated door alignment in vehicle assembly, comprising an analysis robot (200) equipped with sensors (220) for measuring the positions and distances of reference points of a vehicle assembly (50) consisting of one or more assembled assembly modules (20); an alignment robot (300) configured to position and align a door base structure of a door (10) on already mounted hinges of the vehicle assembly (50), the alignment robot (300) employing precise control mechanisms and positioning units; a screwing robot (400) configured for fastening the door (10) to the hinges and other fastening points of the assembly modules (30) and equipped with automated screwing systems and torque sensors;an input module (500) with a graphical user interface (GUI) for inputting and managing configuration parameters and control commands for the robots (200, 300, 400); an evaluation module (800) with an AI model (850), wherein the AI ​​model (800) is configured to analyze the data (250) collected by the analysis robot (200) and to calculate the necessary setting values ​​(870), wherein the AI ​​model (850) is based on neural networks, in particular convolutional neural networks (CNNs); and a database (700) for storing and managing process data such as setpoints (890), measurement data (250, 270), calculated setting values ​​(870) and configuration parameters of the input module (500), which are used for analysis and calculation by the evaluation module (800), wherein the system (100) is configured to execute the method according to any one of claims 1 to 7. [9] System (100) Method according to claim 8, wherein the analysis robot (200) comprises optical sensors such as cameras, in particular 3D cameras and / or laser sensors and / or tactile sensors. [10] System (100) according to claim 8 or 9, wherein the alignment robot (300) uses gripping elements and positioning units to handle and precisely position the door base structure. [11] System (100) according to one of claims 8 to 10, comprising an application robot (350) for applying the door outer panel to the door base structure, wherein the application robot (350) is configured to automatically apply the door outer panel after the door base structure has been aligned by the alignment robot (300) and fastened to the vehicle assembly (50) by the screwing robot (400), ensuring a uniform distribution and strength of the connection. [12] System (100) according to one of claims 8 to 11, wherein the evaluation module (800) transmits the calculated setting values ​​(870) in real time to the alignment robot (300) and the screwing robot (400). [13] System (100) according to one of claims 8 to 12, wherein the evaluation module (800) is integrated into a cloud computing infrastructure. [14] Computer program product (900) comprising an executable program code (950) configured to perform the method according to any one of claims 1 to 7 when executed.

Images