Big data-based auxiliary assembly device adjustment method and system

Abstract

The application discloses an auxiliary assembly equipment adjustment method and system based on big data, wherein the auxiliary assembly equipment adjustment system based on big data comprises a data collection and processing module, a big data platform module, an assembly operation guiding module, an assembly equipment adjustment module and an application and improvement module; the data collection and processing module collects layout information of an assembly station and process knowledge and operation process related data; the big data platform module establishes a big data platform to store and process assembly station data; the assembly operation guiding module produces operation process animation according to assembly process knowledge and operation process and provides the assembly personnel; and the assembly equipment adjustment module automatically adjusts the layout of assembly equipment based on big data analysis and an assembly station data model; through mutual interaction and connection of various modules, the layout of the assembly station and assembly process data are analyzed based on the big data platform to meet the requirements of different multi-process operation contents and frequent process changes.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of big data analysis, in particular to an auxiliary assembly device adjustment method and system based on big data. BACKGROUND

[0002] Auxiliary assembly refers to the use of auxiliary tools and equipment in the assembly process to improve assembly efficiency and accuracy, auxiliary assembly tools and equipment can provide faster and more convenient assembly methods, reduce manual operation time, thereby improving assembly efficiency and production capacity, auxiliary assembly tools and equipment can also provide accurate positioning, alignment and measurement, help ensure correct installation and accurate alignment of assembly parts, reduce assembly errors and quality problems.

[0003] With the increasing use of auxiliary assembly equipment, abnormal problems in the assembly process also increase, it may be difficult to adjust the parameters of auxiliary assembly equipment, especially for complex equipment or highly accurate adjustment, operators may need to invest more time and effort to adjust and optimize parameters, in the assembly process, there may be problems of incorrect assembly sequence and mismatch, personnel operating and managing auxiliary assembly equipment may lack necessary training and skills, and cannot effectively operate, the layout of assembly stations can also affect the operation of assembly personnel, these problems will make auxiliary assembly not achieve the expected effect. SUMMARY

[0004] The present application provides an auxiliary assembly device adjustment method and system based on big data to solve the above technical problems.

[0005] The technical solution of the present application is as follows:

[0006] The auxiliary assembly device adjustment method based on big data, characterized by comprising the following steps:

[0007] S1: Collecting assembly station layout information including material rack height and equipment placement position;

[0008] S2: Collecting related data of assembly process knowledge and operation process including tooling part model, assembly process knowledge base and operation process animation;

[0009] S3: Analyzing the collected station layout information including material rack height distribution and equipment placement position association;

[0010] S4: Processing the collected assembly process data, extracting assembly sequence, assembly path and reachability and visibility of assembly operation;

[0011] S5: Through big data analysis of the workstation layout data and assembly process data, the best solution for adjusting the height of the material rack is found out to reduce the space interference in the assembly process. Based on feature recognition and matching of workpieces, the placement position of the equipment is adjusted to improve the efficiency and accuracy of assembly operations;

[0012] S6: Design adjustment method, use the collected data to verify in virtual space, simulate the assembly operation process, according to the verification result, adjust and optimize the design adjustment method, to improve the efficiency and accuracy of the assembly process, apply the designed adjustment method to the actual production environment, adjust and optimize the layout of the assembly station;

[0013] S7: In the actual production environment, monitor the use and effect of the assembly station, and optimize the assembly station layout and adjustment method according to the monitoring results to meet the needs of multi-station and multi-process operation.

[0014] The auxiliary assembly equipment adjustment system based on big data includes a data collection and processing module, a big data platform module, an assembly operation guidance module, an assembly equipment adjustment module, and an application and improvement module. The output end of the data collection and processing module is connected to the input end of the big data platform module. The output end of the big data platform module is connected to the input end of the assembly operation guidance module. The output end of the assembly operation guidance module is connected to the input end of the assembly equipment adjustment module. The output end of the assembly equipment adjustment module is connected to the input end of the application and improvement module. Wherein:

[0015] The data collection and processing module collects layout information of assembly stations and related data of assembly process knowledge and operation process;

[0016] The big data platform module establishes a big data platform to store and process assembly station and assembly process and operation process data;

[0017] The assembly operation guidance module produces operation process animation according to assembly process knowledge and operation process data and provides it to assembly personnel;

[0018] The assembly equipment adjustment module automatically adjusts the layout of assembly equipment based on big data analysis and assembly station data model;

[0019] The application and improvement module applies the system to assembly stations in actual production environment, monitors the use and effect, and improves and adjusts the system according to actual needs to continuously optimize the function and performance of the system.

[0020] As a preferred, the data collection and processing module includes a data collection unit, a data arrangement unit, and a data storage management unit, wherein:

[0021] The data collection unit obtains assembly station layout data including material rack height and equipment placement position through cameras and sensors, and obtains relevant data of assembly process data and operation process through communication with process engineers and operators, including tooling part models, assembly process knowledge base and operation process animation;

[0022] The data arrangement unit is connected with the data collection unit to arrange the collected data to conform to a consistent format.

[0023] The data storage management unit is connected with the data arrangement unit, uses a relational database, stores the collected assembly station data in the form of a table in the database, sets access permissions, limits the access range of data, and protects the privacy and confidentiality of data.

[0024] Preferably, the big data platform module includes a data analysis unit and a data visualization unit, wherein:

[0025] The data analysis unit analyzes the assembly station layout data, assembly process data and operation process data arranged by the data collection and processing module, uses a supervised learning algorithm to construct an assembly process model, trains the model to predict the sequence relationship between different operation steps, uses an unsupervised learning algorithm for clustering analysis, and classifies similar assembly process operations into a category, thereby discovering the commonality and difference between different operations;

[0026] The data visualization unit is connected with the data analysis unit, displays the processed assembly station layout data, assembly process data and operation process data in a visual form, uses bar charts, line charts and pie charts in the chart to display the distribution and trend of assembly process data, uses 3D models, schematic diagrams and floor plans to display the layout and operation path of the assembly station, provides interactive operations such as zooming, filtering and searching, so that users can conduct in-depth mining and targeted analysis of the data, and provides linking and linkage functions to enable users to switch and compare between different visualization views.

[0027] Preferably, the assembly operation guidance module includes an operation process animation unit, an AR glasses technology unit, a 3D job guidance unit, and a reachability and visibility verification unit, wherein:

[0028] The operation process animation unit determines the target and content of making operation process animation according to the collected assembly station and assembly process data, determines the key operation steps and processes, makes the script and scene of operation process animation according to the target and content, the script includes text description and action guidance, the scene includes the background of assembly station and the model of related equipment, and Adobe Animate is used to convert the script and scene into animation effects.

[0029] The AR glasses technology unit is connected with the operation flow animation unit, and according to the operation flow animation made by the assembly operation guide module, a virtual assembly step and an actual assembly station and a workpiece are displayed in real time, helping the assembly personnel to accurately assemble according to the operation flow in actual operation. Specifically, by using AR feature recognition technology, each workpiece and equipment in the assembly station is identified and marked, specifically by matching the feature information of the workpiece and the pre-established workpiece model to determine its position and angle in the assembly operation, according to the layout information of the assembly station and the operation flow, the identified and matched workpiece and equipment model are added to the AR scene in a virtual form, when the assembly personnel wear AR glasses and enter the assembly station, the AR glasses acquire real-time video through the camera, and the virtual workpiece and equipment model are superimposed on the actual station, the assembly personnel see the virtual assembly sequence guide and workpiece position indication through the AR glasses;

[0030] The 3D operation guidance unit is connected with the AR glasses technology unit, according to the tooling part 3D model, assembly process, assembly sequence, and relationship between parts in the collected assembly process data, the model of the assembly part and the assembly station is created using SolidWorks, according to the requirements of the assembly process and the assembly sequence, the parts in the 3D model are assembled in the correct order, and the corresponding assembly relationship is created, for each assembly step, according to the operation flow and process requirements, marks, texts and arrow symbols are added on the 3D model to guide the assembly personnel to operate correctly;

[0031] The accessibility and visibility verification unit is connected with the 3D operation guidance unit, according to the simulation of the assembly operation, the accessibility and visibility of each operation step in the assembly process are evaluated, considering the body posture, hand operation space, and workbench height factors, the comfort and convenience of the assembly operation are evaluated, by simulating the position of the assembly personnel, it is determined whether there is a line of sight obstruction and a limited line of sight problem in the assembly process, and whether the assembly personnel can clearly observe and judge in the operation process;

[0032] Preferably, the assembly equipment adjustment module includes an assembly station data analysis unit, an equipment layout adjustment unit, a space interference identification and adjustment unit, wherein:

[0033] The assembly station data analysis unit analyzes and extracts the material shelf height distribution of different regions and the distance relationship data between equipment from the collected assembly station layout data and assembly process data, and presents the obtained data in the form of icons and heat maps;

[0034] The device layout adjustment unit is connected with the assembly station data analysis unit, and based on the collected data, a data model of the assembly station is established using graph theory, vertices are used to represent stations and devices, edges are used to represent the relationship and connection between stations, the data model of the assembly station layout is taken as input, a simulated annealing algorithm is used to calculate the minimum material handling distance, and the device layout on the existing assembly station is adjusted according to the calculated minimum material handling distance.

[0035] The space interference identification and adjustment unit is connected with the device layout adjustment unit, the system analyzes the 3D model of the assembly station, and then judges whether there is space interference through bounding box detection based on the geometric shape of the object, obtains the region and object with interference, determines the cause of the interference, wherein the interference cause includes improper device placement and unsuitable material rack height, analyzes the degree of interference, determines the position of the interference, and adjusts the device position and the material rack height based on the result of the interference analysis.

[0036] As preferred, the application and improvement module comprises a system application unit and an effect evaluation unit, wherein:

[0037] The system application unit deploys the system to the assembly station in the actual production environment and integrates with the existing assembly device and process flow;

[0038] The effect evaluation unit is connected with the system application unit, evaluation indexes including assembly efficiency, accuracy, and simplification degree of the work flow are set according to the target and demand of the system, assembly time, error rate, and output data before and after using the system are collected through sensors in the actual assembly process, the collected data are analyzed using regression analysis, the index changes before and after using the system are compared, the performance and effect of the system are evaluated according to the result of the data analysis, and it is judged whether the improvement of the system achieves the expected target.

[0039] The application has the following beneficial effects:

[0040] The application can automatically adjust the layout of the assembly equipment, including the height of the material rack and the placement position of the equipment, by collecting and analyzing a large amount of assembly station data, thereby optimizing the layout of the assembly station and improving the assembly efficiency; the system provides an assembly process knowledge base and operation process animation, which can be referred to by the assembly personnel for correct operation, thereby reducing the process guidance error and improving the accuracy of the assembly operation; through the feature recognition and workpiece matching technology of the AR glasses, visual operation guidance is realized, and corresponding 3D operation guidance is provided, so that the assembly personnel can intuitively understand the accessibility and visibility of the assembly operation, thereby reducing the occurrence of assembly problems; through simulation and verification of the accessibility and visibility of the assembly operation, the system can discover and solve assembly problems in advance, thereby reducing errors and delays in the assembly process; through verification in the virtual environment, the system can optimize the sequence, path, accessibility and visibility of the assembly operation, thereby improving the efficiency and accuracy of the assembly process and reducing the assembly time and cost. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 A work flow diagram of the application based on big data assisted assembly equipment adjustment method;

[0042] Figure 2 A system block diagram of the application based on big data assisted assembly equipment adjustment system. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the application.

[0044] As shown in Figure 1 The application provides a big data based assisted assembly equipment adjustment method, which comprises the following steps:

[0045] S1: Collecting assembly station layout information including the height of the material rack and the placement position of the equipment;

[0046] S2: Collecting related data of assembly process knowledge and operation process including tooling part models, assembly process knowledge base and operation process animation;

[0047] S3: Analyzing the collected station layout information including the height distribution of the material rack and the placement position of the equipment;

[0048] S4: Processing the collected assembly process data, extracting the assembly sequence, assembly path and accessibility and visibility of the assembly operation;

[0049] S5: Through big data analysis of the workstation layout data and assembly process data, the optimal solution for adjusting the height of the material rack is found out to reduce the space interference in the assembly process, and based on the feature recognition and matching of the workpieces, the placement position of the equipment is adjusted to improve the efficiency and accuracy of the assembly operation;

[0050] S6: The adjustment method is designed, the collected data is used to verify in the virtual space, the assembly operation process is simulated, according to the verification result, the adjustment method is adjusted and optimized, the efficiency and accuracy of the assembly process are improved, the adjustment method is applied to the actual production environment, and the layout adjustment and optimization of the assembly workstation are carried out;

[0051] S7: In the actual production environment, the use and effect of the assembly workstation are monitored, and according to the monitoring result, the assembly workstation layout and adjustment method are optimized to adapt to the needs of multi-station and multi-process operation.

[0052] As shown in Figure 2 The application provides an auxiliary assembly equipment adjustment system based on big data, which comprises a data collection and processing module, a big data platform module, an assembly operation guiding module, an assembly equipment adjustment module and an application and improvement module. The output end of the data collection and processing module is connected to the input end of the big data platform module. The output end of the big data platform module is connected to the input end of the assembly operation guiding module. The output end of the assembly operation guiding module is connected to the input end of the assembly equipment adjustment module. The output end of the assembly equipment adjustment module is connected to the input end of the application and improvement module.

[0053] The data collection and processing module comprises a data collection unit, a data arrangement unit and a data storage management unit. The big data platform module comprises a data analysis unit and a data visualization unit. The assembly operation guiding module comprises an operation flow animation unit, an AR glasses technology unit, a 3D operation guidance unit and a reachability and visibility verification unit. The assembly equipment adjustment module comprises an assembly workstation data analysis unit, an equipment layout adjustment unit and a space interference identification and adjustment unit. The application and improvement module comprises a system application unit and an effect evaluation unit.

[0054] The data collection and processing module collects layout data of assembly stations through sensors, cameras, RFID devices, including material rack height, device placement position, at the same time, collects assembly process data and related data of operation process, including tooling part model, assembly process knowledge base and operation process animation, then stores the collected data in the big data platform, the big data platform uses distributed file system, database or cloud storage technology to store data, ensures the safety and reliability of data, through the use of big data analysis technology, including machine learning and artificial intelligence methods, arranges the collected assembly station and assembly process and operation process data to make it consistent with the format.

[0055] The big data platform module analyzes the assembly station layout data, assembly process data and operation process data arranged by the data collection and processing module, uses supervised learning algorithm to build assembly process model, trains model to predict the sequence relationship between different operation steps, uses unsupervised learning algorithm to carry out clustering analysis, and classifies similar assembly process operations into a class, so as to find the commonness and difference between different operations. The data visualization unit displays the processed assembly station layout data, assembly process data and operation process data in a visual form, wherein the display method includes using bar chart, line chart and pie chart in chart to display the distribution and trend of assembly process data, using 3D model, schematic diagram and plan to display the layout and operation path of assembly station, providing zooming, filtering, searching interactive operation, so that users can deeply mine and analyze the data, at the same time, providing linkage and linkage function, so that users can switch and compare between different visualization views.

[0056] The assembly operation guide module makes operation process animation similar to PPT according to assembly process knowledge and operation process, displays steps, sequence and operation points of assembly process through animation, provides clear operation guide for assembly personnel, determines target and content of operation process animation according to collected assembly station and assembly process data, determines key operation steps and process, according to target and content, makes script and scene of operation process animation, script includes text description and action guidance, scene includes background of assembly station and model of related equipment, uses Adobe Animate to convert script and scene into animation effect.

[0057] Among them:

[0058] The AR glasses technology unit is connected with the operation flow animation unit, and visual operation guidance is realized through AR glasses according to the operation flow animation made by the assembly operation guidance module. The assembly personnel can watch real-time assembly operation guidance through AR glasses, and real-time superimposed display of virtual assembly steps and actual assembly stations and workpieces is realized, so as to help the assembly personnel accurately assemble according to the operation flow in actual operation. Specifically, AR feature recognition algorithm is used to identify and mark each workpiece and equipment in the assembly station, the position and angle of the workpiece in the assembly operation are determined by matching the feature information of the workpiece with the pre-established workpiece model, and the identified and matched workpiece and equipment model are added to the AR scene in a virtual form according to the layout information of the assembly station and the operation flow. When the assembly personnel wears AR glasses and enters the assembly station, the AR glasses acquire real-time video through the camera, and the virtual workpiece and equipment model are superimposed on the actual station, so that the assembly personnel can see virtual assembly sequence guidance and workpiece position indication through the AR glasses;

[0059] The 3D operation guidance unit is connected with the AR glasses technology unit, and the 3D operation guidance unit stores 3D operation guidance. The AR glasses can pull the corresponding 3D operation guidance to realize reachability and visibility verification. Specifically, the assembly personnel can watch the 3D operation guidance on the AR glasses to realize real-time understanding of assembly operation and workpiece position, and verify the reachability and visibility. SolidWorks is used to create models of assembly parts and assembly stations, and the parts in the 3D model are assembled in the correct order according to the requirements of assembly process and assembly sequence, and corresponding assembly relationships are created. For each assembly step, marks, texts and arrow symbols are added to the 3D model according to the operation flow and process requirements to guide the assembly personnel to perform correct operation;

[0060] The reachability and visibility verification unit is connected with the 3D operation guidance unit, and the reachability and visibility of each operation step in the assembly process are evaluated according to the simulation of the assembly operation. The body posture, hand operation space and workbench height factors of the assembly personnel are considered to evaluate the comfort and convenience of the assembly operation. If the workbench is too high, the assembly personnel will have difficulty reaching the assembly position of the workpiece, which will reduce the assembly efficiency. By simulating the position of the assembly personnel, whether there is a line-of-sight obstruction or a limited line-of-sight problem in the assembly process is determined, and whether the assembly personnel can clearly observe and judge in the operation process is evaluated.

[0061] The assembly equipment adjustment module stores and processes the collected data through the big data platform established by the big data platform module, and uses data analysis algorithms and models to extract key information from the data, wherein:

[0062] The assembly station data analysis unit analyzes and extracts the material shelf height distribution of different areas and the distance relationship data between devices from the collected assembly station layout data and assembly process data, and presents the obtained data in the form of icons and heat maps.

[0063] The device layout adjustment unit is connected to the assembly station data analysis unit, and uses graph theory to establish a data model of the assembly station. Specifically, the method of using graph theory to establish a data model of the assembly station is as follows: vertices represent stations and devices, and edges represent the relationship and connection between stations. The data model of the assembly station layout is used as input, and the simulated annealing algorithm is used to calculate the minimum material handling distance. According to the calculated minimum material handling distance, the device layout on the existing assembly station is adjusted.

[0064] The space interference identification and adjustment unit is connected to the device layout adjustment unit. According to the established data model of the assembly station and the collected assembly station layout data, the system judges whether there is a space interference problem by analyzing the layout of the assembly station and the size information of the workpiece. The specific operation of judging space interference is as follows: the system analyzes the 3D model of the assembly station, and then judges whether there is space interference based on bounding box detection based on object geometry. The bounding box detection is as follows: a bounding box is added to the layout of each assembly station, and the overlap between the bounding boxes is detected to determine whether there is space interference. If there is overlap or contact between the bounding boxes, it can be determined that there is space interference. After obtaining the areas and objects that cause interference, the causes of the interference are determined, including improper placement of devices and inappropriate material shelf height. The degree of interference is analyzed, the position of the interference is determined, and the device position and material shelf height are adjusted based on the results of the interference analysis.

[0065] The application and improvement module applies the system to the assembly station in the actual production environment, monitors the usage and effect, and improves and adjusts the system according to actual needs to continuously optimize the function and performance of the system.

[0066] The system application unit deploys the system to the assembly station in the actual production environment and integrates it with the existing assembly devices and process flow.

[0067] The effect evaluation unit is connected with the system application unit, collects data in actual production environment by monitoring the use of the system, such as the use behavior of the operator, the performance index of the system, evaluates the effect and performance of the system through the data, sets evaluation indexes including assembly efficiency, accuracy, simplification degree of work flow according to the target and demand of the system, collects assembly time, error rate, output data before and after using the system through sensors in actual assembly process, analyzes the collected data by using regression analysis, compares the index change before and after using the system, evaluates the performance and effect of the system according to the result of data analysis, and judges whether the improvement of the system reaches the expected target.

[0068] It is apparent for a person skilled in the art that the present application is not limited to the details of the above-described exemplary embodiments, but can be implemented in other concrete forms without departing from the spirit or essential characteristics of the present application. Therefore, the embodiments should be considered in all respects as illustrative and not restrictive, the scope of the present application being defined by the appended claims rather than the above description, and it is intended to embrace all changes and modifications that fall within the meaning and scope of equivalents of the claims.

Claims

1. A method for assisting adjustment of assembly equipment based on big data, characterized in that: It comprises the following steps: S1: Collecting assembly station layout information including material rack height and equipment placement position; S2: Collecting assembly process knowledge and operation process related data including tooling part model, assembly process knowledge base and operation process animation; S3: Analyzing the collected station layout information including material rack height distribution and equipment placement position correlation; S4: Processing the collected assembly process data, extracting assembly sequence, assembly path and assembly operation accessibility and visibility; S5: Through big data analysis of station layout data and assembly process data, finding out the best solution for material rack height adjustment to reduce spatial interference in the assembly process, based on feature recognition and matching of workpieces, adjusting the placement position of equipment to improve the efficiency and accuracy of assembly operation; S6: Designing adjustment method, using collected data to verify in virtual space, simulating assembly operation process, adjusting and optimizing the designed adjustment method according to the verification result to improve the efficiency and accuracy of assembly process, applying the designed adjustment method to actual production environment for layout adjustment and optimization of assembly station; S7: In actual production environment, monitoring the use and effect of assembly station, optimizing assembly station layout and adjustment method according to the monitoring result to adapt to the needs of multi-station and multi-process operation; The auxiliary assembly equipment adjustment method based on big data further comprises an auxiliary assembly equipment adjustment system, including a data collection and processing module, a big data platform module, an assembly operation guidance module, an assembly equipment adjustment module and an application and improvement module; the output end of the data collection and processing module is connected to the input end of the big data platform module, the output end of the big data platform module is connected to the input end of the assembly operation guidance module, the output end of the assembly operation guidance module is connected to the input end of the assembly equipment adjustment module, and the output end of the assembly equipment adjustment module is connected to the input end of the application and improvement module, wherein: The data collection and processing module collects layout information of assembly station and related data of assembly process knowledge and operation process; The big data platform module establishes a big data platform to store and process assembly station and assembly process and operation process data; The assembly operation guidance module produces operation process animation according to assembly process knowledge and operation process data and provides it to assembly personnel; The assembly equipment adjustment module automatically adjusts the layout of assembly equipment based on big data analysis and assembly station data model; The application and improvement module applies the system to assembly station in actual production environment, monitors the use and effect, improves and adjusts the system according to actual needs, and continuously optimizes the function and performance of the system; The assembly equipment adjustment module comprises an assembly station data analysis unit, an equipment layout adjustment unit and a space interference identification and adjustment unit, wherein: The assembly station data analysis unit analyzes and extracts material rack height distribution of different areas and distance relationship data between equipment from the collected assembly station layout data and assembly process data, and presents the obtained data in the form of icons and heat maps; The device layout adjustment unit is connected with the assembly station data analysis unit, and based on the collected data, a data model of the assembly station is established using graph theory, with vertices representing stations and devices and edges representing relationships and connections between stations. The data model of the assembly station layout is input into the system, which uses a simulated annealing algorithm to calculate the minimum material handling distance. Based on the calculated minimum material handling distance, the device layout on the existing assembly station is adjusted. The spatial interference identification and adjustment unit is connected with the device layout adjustment unit. The system analyzes the 3D model of the assembly station and then uses bounding box detection based on object geometry to determine whether there is spatial interference. The areas and objects that cause interference are identified, and the causes of the interference are determined, including improper device placement and inappropriate material rack height. The degree of interference is analyzed, and the location of the interference is determined. Based on the results of the interference analysis, the device position and material rack height are adjusted.

2. A system applied to the big data based assisted assembly device adjustment method according to claim 1, characterized in that: The data collection and processing module includes a data collection unit, a data processing unit, and a data storage management unit. The data collection unit collects data on the layout of the assembly station, including the height of the material rack and the placement of the equipment, through cameras and sensors. The data collection unit also collects data on the assembly process and operation process, including the model of the tooling parts, the assembly process knowledge base, and the operation process animation, by communicating with process engineers and operators. The data processing unit is connected with the data collection unit and processes the collected data to ensure consistency in format. The data storage management unit is connected with the data processing unit and uses a relational database to store the collected assembly station data in table format in the database. Access permissions are set to limit the scope of data access and protect the privacy and confidentiality of the data. The big data platform module includes a data analysis unit and a data visualization unit. The data analysis unit analyzes the assembly station layout data, assembly process data, and operation process data processed by the data collection and processing module. Supervised learning algorithms are used to build an assembly process model and train the model to predict the sequence relationship between different operation steps. Unsupervised learning algorithms are used for clustering analysis to classify similar assembly process operations into one category, thereby discovering the commonalities and differences between different operations.

3. The system of claim 2, wherein: The data visualization unit is connected with the data analysis unit and displays the processed assembly station layout data, assembly process data, and operation process data in a visual form. Bar charts, line charts, and pie charts are used to display the distribution and trends of assembly process data in the charts. 3D models, schematic diagrams, and floor plans are used to display the layout and operation path of the assembly station. Interactive operations such as zooming, filtering, and searching are provided to allow users to conduct in-depth analysis and targeted analysis of the data. Linkage and linkage functions are also provided to allow users to switch between different visualization views and compare them. The assembly operation guidance module includes an operation process animation unit, an AR glasses technology unit, a 3D job guidance unit, and a reachability and visibility verification unit. ​ 4. The system of claim 2, wherein: ​ The operation flow animation unit determines the target and content of making the operation flow animation according to the collected assembly station and assembly process data, determines the key operation steps and flow, makes the script and scene of the operation flow animation according to the target and content, the script includes the text description and action guidance, and the scene includes the background of the assembly station and the model of the related equipment, and the script and scene are converted into the animation effect by using Adobe Animate; The AR glasses technology unit is connected with the operation flow animation unit, the virtual assembly steps and the actual assembly station and workpiece are displayed in real time according to the operation flow animation made by the assembly operation guiding module, and the assembly personnel are helped to accurately assemble according to the operation flow in actual operation; specifically, the AR feature recognition technology is used to identify and mark each workpiece and equipment in the assembly station, the position and angle of the workpiece in the assembly operation are determined by matching the feature information of the workpiece and the pre-established workpiece model, and the identified and matched workpiece and equipment model are added to the AR scene in a virtual form according to the layout information of the assembly station and the operation flow; when the assembly personnel wear the AR glasses and enter the assembly station, the AR glasses acquire real-time video through the camera, and the virtual workpiece and equipment model are superimposed on the actual station, and the assembly personnel see the virtual assembly sequence guidance and workpiece position indication through the AR glasses; The 3D work instruction unit is connected with the AR glasses technology unit, the 3D model of the tooling part, the assembly process, the assembly sequence, and the relationship between the parts in the collected assembly process data are used to create the model of the assembly part and the assembly station by using SolidWorks, the parts in the 3D model are assembled in the correct order according to the requirements of the assembly process and the assembly sequence, and the corresponding assembly relationship is created, and for each assembly step, the mark, text and arrow symbol are added on the 3D model according to the operation flow and the process requirements to guide the assembly personnel to perform the correct operation; The reachability and visibility verification unit is connected with the 3D work instruction unit, the reachability and visibility of each operation step in the assembly process are evaluated according to the simulation of the assembly operation, the body posture, the hand operation space and the workbench height factors are considered to evaluate the comfort and convenience of the assembly operation, the position of the assembly personnel is simulated to determine whether there is a line-of-sight obstruction or a limited line-of-sight problem in the assembly process, and whether the assembly personnel can clearly observe and judge in the operation process is evaluated.

5. The system of claim 2, wherein: The application and improvement module includes a system application unit and an effect evaluation unit, wherein: The system application unit deploys the system to the assembly station in the actual production environment and integrates with the existing assembly equipment and process flow; The effect evaluation unit is connected with the system application unit, sets evaluation indexes including assembly efficiency, accuracy, simplification degree of work flow according to the target and demand of the system, collects assembly time, error rate, output data before and after using the system through the sensor in the actual assembly process, analyzes the collected data using regression analysis, compares the index changes before and after using the system, evaluates the performance and effect of the system according to the result of data analysis, and judges whether the improvement of the system achieves the expected target.

Images