Digital-real collaborative new energy vehicle island-level assembly process optimization method and system

Abstract

The invention discloses a method and a system for optimizing a new energy automobile island-level assembly process based on data-real collaboration, and belongs to the technical field of new energy automobile manufacturing. The method comprises the following steps: (1) deducing a digital space assembly island process, including assembly island process element analysis, assembly island digital twin model construction and assembly island process dynamic deduction; (2) entity space assembly island process test verification, including assembly island process scheme materialization test, assembly process data acquisition, and assembly quality and efficiency verification; and (3) optimizing the assembly island process based on data and real collaboration, including virtual and real data comparison and deviation analysis, process parameter optimization based on data and real feedback, assembly rhythm balance and resource dynamic configuration. By constructing a digital deduction and entity test closed loop, bidirectional mapping and collaborative optimization of the assembly process in a digital space and an entity space are realized, and the accuracy, reliability and overall efficiency of the new energy automobile assembly process can be effectively improved.

Description

Technical Field

[0001] This invention belongs to the field of new energy vehicle manufacturing technology, specifically relating to a method and system for optimizing the island-level assembly process of new energy vehicles through data-driven and real-time collaboration. Background Technology

[0002] With the rapid development of the new energy vehicle industry and the increasingly shorter model iteration cycle, higher demands are being placed on the precision, reliability, and efficiency of assembly processes. For example, new energy vehicle manufacturers have planned island-based manufacturing paradigms, involving island-level precision assembly processes such as body assembly islands, seat assembly islands, window assembly islands, and front and rear windshield assembly islands. These processes involve multi-dimensional parameters including equipment layout, material delivery routes, worker positions, and assembly sequence. Traditional assembly process planning mainly relies on physical trial and error and engineer experience, resulting in long adjustment cycles, high resource consumption, and low optimization efficiency.

[0003] In existing technologies, digital simulation technology has been applied to the assembly process planning stage, using a three-dimensional geometric model of the production line for interference checks and cycle time analysis. However, these purely digital methods have limitations such as insufficient model fidelity and missing physical properties, making it difficult to accurately reflect the dynamic changes in the physical assembly environment. For example, in complex product assembly, the deformation effects of tooling, part contact and springback, and the loads on the assembly can lead to significant deviations between theoretical models and actual results. On the other hand, while sensor network-based physical data acquisition methods can obtain real data from production line operation, they lack deep coupling with digital models and cannot effectively support online optimization and prediction of process parameters.

[0004] Currently, digital twin technology offers new insights for assembly process optimization. Related research has attempted to construct virtual product development management technologies to address data cross-referencing, coupling, and redundancy issues in the development of digital prototypes for mechanical equipment. However, existing digital twin applications largely focus on condition monitoring and fault diagnosis. For example, power grid digital twin fault simulation equipment utilizes historical data for fault reconstruction, or sliding mode reconstruction observers are used in aircraft control for fault diagnosis and fault-tolerant control. However, in the field of assembly processes, a complete technical system for bidirectional mapping and collaborative optimization between digital and physical spaces is still lacking.

[0005] Specifically, in the assembly process of new energy vehicles, the technical challenges include: (1) lagging optimization of process parameters: problems such as unbalanced assembly cycle time and resource waiting time deviation in the physical space cannot be fed back to the digital space for optimization in real time; (2) rigid resource allocation: the allocation of resources such as material distribution and personnel workstations lacks the ability to dynamically adjust based on the assembly status. These problems lead to unstable assembly quality of new energy vehicles and difficulty in further improving production efficiency. Summary of the Invention

[0006] To address the aforementioned technical problems, this invention provides a digital-physical collaborative method and system for optimizing the island-level assembly process of new energy vehicles. This method enables bidirectional mapping and collaborative optimization of the assembly process in both digital and physical spaces, effectively improving the accuracy, reliability, and overall efficiency of the new energy vehicle assembly process.

[0007] To achieve the above objectives, the present invention adopts the following technical solution:

[0008] In a first aspect, the present invention provides a method for optimizing the island-level assembly process of new energy vehicles through data-driven and real-time collaboration, comprising:

[0009] S1. Analyze the process elements of the assembly island in the digital space, construct a digital twin model of the assembly island, and perform dynamic simulation of the assembly island process based on the digital twin model of the assembly island.

[0010] S2. Test the process scheme derived in step S1 on the physical assembly island, collect data on the physical assembly process, and verify the feasibility and effectiveness of the process scheme.

[0011] S3. Based on the verification results of step S2 and the physical assembly process data, iteratively optimize the assembly process parameters and resource configuration in the digital space to form an optimization strategy and feed it back to the physical space for execution.

[0012] Secondly, the present invention provides a data-driven, real-time collaborative system for optimizing the island-level assembly process of new energy vehicles, comprising:

[0013] The digital space assembly process simulation module is used to analyze the process elements of the assembly island in digital space, construct a digital twin model of the assembly island, and perform dynamic simulation of the assembly island process based on the digital twin model of the assembly island.

[0014] The physical space process testing and verification module is used to test the process scheme derived by the digital space assembly process derivation module on the physical assembly island, collect physical assembly process data, and verify the feasibility and effectiveness of the process scheme.

[0015] The assembly island process optimization module is used to iteratively optimize assembly process parameters and resource configuration in the digital space based on the verification results of the physical space process testing and verification module and the physical assembly process data, form an optimization strategy, and feed it back to the physical space for execution.

[0016] Thirdly, the present invention provides an electronic device comprising: one or more processors; a memory for storing one or more programs; wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement the aforementioned method.

[0017] Fourthly, the present invention provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, enable the processor to implement the aforementioned method.

[0018] Fifthly, the present invention provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned method.

[0019] The beneficial effects of this invention are as follows:

[0020] This invention constructs a closed-loop optimization system for digital space simulation and physical space testing of new energy vehicle assembly processes through a data-real collaborative process simulation technology. Based on the analysis of island-level assembly process elements and the construction of a digital twin model, this invention completes dynamic process simulation in digital space, effectively improving the foresight and accuracy of assembly schemes and overcoming, to some extent, the limitations of traditional pure digital simulations due to the lack of physical attributes. Through physical space process testing and verification, and real-time acquisition of multi-source data, dynamic deviations such as assembly cycle time and resource waiting time are fed back to the digital space in real time, solving the problem of lagging process parameter optimization and achieving visualized monitoring and accurate evaluation of the assembly process. The process parameter optimization and dynamic resource allocation strategy based on data-real feedback helps to break through the rigid limitations of traditional resource allocation, enabling dynamic adjustment of resources such as material delivery and personnel positions, and improving the balance and flexibility of the assembly line. This invention provides a complete technical path for island-level assembly processes of new energy vehicles, from digital simulation to physical verification and iterative optimization, helping to improve the accuracy, reliability, and overall production efficiency of the assembly process. Attached Figure Description

[0021] Figure 1 This is a flowchart of the method for optimizing the island-level assembly process of new energy vehicles based on data-real collaboration according to the present invention.

[0022] Figure 2 This is a schematic diagram of the structure of the new energy vehicle island-level assembly process optimization system with digital-real collaboration according to the present invention. Detailed Implementation

[0023] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0024] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0025] The terms “first”, “second”, etc., are used to distinguish similar objects, not to describe or indicate a specific order or sequence.

[0026] The term "comprising" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent in such process, method, article, or apparatus / device.

[0027] Furthermore, to better illustrate the present invention, numerous specific details are provided in the following detailed embodiments. Those skilled in the art should understand that the present invention can be practiced without certain specific details. In some instances, methods, means, elements, and circuits well known to those skilled in the art have not been described in detail in order to highlight the spirit of the invention.

[0028] Figure 1 The flowchart of the present invention, which describes the optimization method for island-level assembly process of new energy vehicles based on data-real collaboration, is shown below. Figure 1 As shown, the method includes:

[0029] S1. Digital Space Assembly Island Process Simulation: Analyze the process elements of the assembly island in digital space, construct a digital twin model of the assembly island, and perform dynamic simulation of the assembly island process based on the digital twin model of the assembly island.

[0030] For example, step S1 may include:

[0031] S1.1 Assembly Island Process Element Analysis: This section analyzes the process elements of the assembly island, including its equipment layout, material delivery paths, robotic arm paths, worker positions, and assembly process sequences. It constructs a set of process elements centered on processes, resources, and timing. ;in, For process sets, For resource collection, This is a combination of timing constraints.

[0032] S1.2 Construction of the Digital Twin Model of the Assembly Island: Based on the three-dimensional geometric model of the assembly island, the physical attributes, behavioral logic, and assembly rules of the assembly island are integrated to construct a digital twin model of the assembly island. , The expression is:

[0033] (1)

[0034] in, The three-dimensional geometric model of the assembly island was obtained by using SolidWorks software and based on the actual equipment layout, tooling fixtures, robotic arms and other physical structures of the assembly island. Physical properties (including assembly force and tolerance); For behavioral logic (including the robot arm's motion trajectory); Assembly rules (including process priority and error prevention logic).

[0035] S1.3, Assembly Island Process Dynamics Simulation: Based on Process Element Sets and assembly island digital twin model A discrete event simulation engine is used to dynamically simulate the assembly island process, and the simulated process scheme is output, including the theoretical assembly cycle time. Theoretical resource waiting time Key equipment utilization rate and material flow status And construct a comprehensive performance index for the simulation system. , The calculation formula is:

[0036] (2)

[0037] in, The minimum assembly cycle time under ideal conditions is determined by the longest single-operation time; The average utilization rate of key equipment is determined by... The average value is used to obtain the result. The cost of material flow congestion is calculated using the following formula: ,in For the quantity of material buffer zone, Let j be the average queue length of the j-th material buffer. Let be the average waiting time of the j-th material buffer; , , Here are the weighting coefficients for each sub-indicator, and .

[0038] This tool is used to quantitatively evaluate the overall performance of a process scheme during the digital twin simulation phase. It comprehensively considers three dimensions: assembly cycle efficiency, key equipment utilization, and material flow smoothness, helping process engineers select the optimal solution from multiple simulation options. In the calculation formula, The larger the value, the closer the actual assembly cycle time is to the ideal assembly cycle time. A higher value indicates a higher equipment utilization rate. The smaller the value, the smoother the material flow. The larger the value, the better the overall efficiency of the process solution.

[0039] S2. Physical assembly island process testing and verification: The process scheme derived in step S1 is tested on the physical assembly island, physical assembly process data is collected, and the feasibility and effectiveness of the process scheme are verified.

[0040] For example, step S2 may include:

[0041] S2.1, Process scheme physicalization test: The process scheme derived in step S1.3 is sent to the control system of the physical assembly island to drive the physical equipment to perform assembly tasks.

[0042] S2.2 Assembly Process Data Acquisition: Through a sensor network deployed on the physical assembly island, real-time data of the physical assembly process is acquired, including time-series data of the assembly process. ,in, For timestamps; This is the device state vector; For assembly quality inspection data; The total number of data points collected, i.e., the total number of time steps recorded by the sensor during assembly; subscript This represents the i-th data point (i.e., the data collected at the i-th time step).

[0043] S2.3, Assembly quality and efficiency verification:

[0044] according to Calculate the assembly cycle time of solids and will The result derived from step S1.3 Compare and calculate the beat matching degree. , The calculation formula is:

[0045] (3)

[0046] The calculation formula is:

[0047] (4)

[0048] in, For the total production time (i.e., the actual total time elapsed from the start to the end of the assembly task), information representing the landmark events of "production start" (such as the first workstation start signal or the first material loading) and "production end" (such as the last workstation completion signal) is encoded in [the relevant data]. of In China, according to It can identify the start and end timestamps of production. and Thus, the calculation is obtained ; The total number of products successfully launched (i.e., in) The number of qualified products that successfully flow through the entire assembly line and finally come off the line within a given time period is a direct measure of output. During the time period, the status vector of the inspection equipment at the end of the assembly line. In this context, a key signal is predefined: "Product successfully rolled off the production line." This signal typically generates a pulse when a single product completes the entire assembly process. In the data sequence, the statistical end-of-line detection device status vector The number of pulses that trigger the "product successfully off the production line" signal can be used to obtain the result. .

[0049] Used to evaluate the consistency between digital twin simulation results and entity execution results, reflecting the prediction accuracy of the digital twin model. The higher the value, the more reliable the digital simulation results are, and the more suitable they are for subsequent optimization decisions. According to formula (3), The closer the value is to 1, the closer the actual assembly cycle time is to the theoretical assembly cycle time, and the more accurate the prediction of the digital twin model.

[0050] At the same time, based on The first pass rate is calculated based on the quality inspection results. And based on predefined assembly quality thresholds judge The pass rate.

[0051] First pass rate This indicates the percentage of products that pass the initial inspection during the assembly process, excluding products that pass after rework. It is a key indicator for measuring the stability of the first-time operation quality and the maturity of the process in the assembly process. The calculation formula is:

[0052] (5)

[0053] in, This refers to the number of products that passed the initial inspection. It is the total number of products produced (i.e., the total number of products submitted to the final inspection station for testing within the statistical period; the data source mainly comes from...). (Number of records at the final inspection station). Used to evaluate the quality stability and process reliability of the assembly process. Low This means more rework and greater quality fluctuations, which will lead to increased hidden costs.

[0054] judge The specific process for achieving the pass rate is as follows:

[0055] (1) Set assembly quality threshold : Set upper and lower limits for different quality indicators (such as adhesive thickness, installation position error, pressing force, etc.);

[0056] (2) Data comparison: Assembly quality inspection data for each product Each one is compared with the threshold of the corresponding indicator;

[0057] (3) Qualification judgment: If all indicators are within the threshold range, the product is qualified; otherwise, it is unqualified.

[0058] (4) Statistical pass rate: Pass rate = Number of qualified products / Total number of inspected products × 100%;

[0059] (5) Output results: Output a pass rate trend chart for quality traceability and process adjustment.

[0060] S3. Assembly Island Process Optimization Based on Digital-Real Collaboration: Based on the verification results of step S2 and the physical assembly process data, the assembly process parameters and resource configuration are iteratively optimized in the digital space to form an optimization strategy and feed it back to the physical space for execution.

[0061] For example, step S3 may include:

[0062] S3.1 Comparison and Deviation Analysis of Virtual and Real Data: The data collected in step S2.2... Compare the data with the theoretical data output from step S1.3 to identify key deviations, including assembly cycle time deviations. Resource waiting time deviation ;in, The actual resource waiting time, based on In and Calculated.

[0063] S3.2 Optimization of process parameters based on numerical and real feedback:

[0064] To minimize and To achieve the goal, an objective function for optimizing the process parameters of the assembly island is established. , The calculation formula is:

[0065] (6)

[0066] in, and These are the weighting coefficients; This represents the total number of resources. This represents the waiting time deviation for the k-th resource; This represents the sum of the waiting time deviations for all resources; It is a minimum value function.

[0067] according to Genetic algorithms are used to optimize process parameters in the digital space (including optimizing process timing and robotic arm movement speed) to generate an optimized set of process parameters. Assembly rhythm with target Among them, the optimized process parameter set This includes key process parameters such as the optimized sequence of operations and the robotic arm's movement speed, and corresponds to an optimized target assembly cycle time. .

[0068] S3.3 Assembly Cycle Balancing and Dynamic Resource Allocation: Based on the optimization results of step S3.2, assembly cycle balancing is performed with the objective of minimizing bottleneck station time. The objective function is... for:

[0069] (7)

[0070] The constraints are:

[0071] (1) The task assignments for each workstation must cover all assembly operations, and there should be no duplication or omission;

[0072] (2) Working time at each workstation Determined by the total time allocated to the tasks;

[0073] (3) The optimized assembly cycle time must meet the following requirements. ;

[0074] in, Let i be the work time for the i-th workstation after reallocation. ; This represents the total number of workstations. It is a function for maximizing the value.

[0075] Based on the balanced assembly cycle time, the operation time of each workstation is redistributed, and the optimal material delivery frequency is calculated. With the number of personnel This is to achieve a balanced production cycle and efficient resource utilization in the assembly island. and The calculation formula is:

[0076] (8)

[0077] (9)

[0078] in, This represents the material consumption rate per unit time at the workstation. For standard delivery container capacity; This represents the total manual operation time for all workstations. This is the preset labor efficiency coefficient. This is the floor function. This represents the ratio of the total manual hours required to complete all manual tasks within an assembly cycle, taking into account labor efficiency, to the hours that a single person can contribute within one assembly cycle. It reflects the theoretically minimum number of personnel required. Since the number of personnel must be an integer and must meet workload requirements, this value needs to be rounded up to obtain the actual number of personnel that should be allocated. .

[0079] This invention proposes a data-driven, real-world collaborative method for optimizing island-level assembly processes in new energy vehicles. Through data-driven, real-world collaborative process simulation technology, it constructs a closed-loop optimization system for digital space simulation and physical space testing of new energy vehicle assembly processes. Based on the analysis of island-level assembly process elements and the construction of a digital twin model, this method performs dynamic process simulation in digital space, effectively improving the foresight and accuracy of assembly schemes and overcoming, to some extent, the limitations of traditional pure digital simulations due to the lack of physical attributes. Through physical space process testing and verification, and real-time acquisition of multi-source data, dynamic deviations such as assembly cycle time and resource waiting time are fed back to the digital space in real time, solving the problem of lagging process parameter optimization and enabling visualized monitoring and accurate evaluation of the assembly process. Based on data-driven, real-world feedback-based process parameter optimization and dynamic resource allocation strategies, this method helps to overcome the rigid limitations of traditional resource allocation, enabling dynamic adjustments to resources such as material delivery and personnel positions, and improving the balance and flexibility of the assembly line.

[0080] The following section uses the front and rear windshield assembly islands as an example to provide a detailed explanation of the data-real synergy optimization method for island-level assembly processes of new energy vehicles according to the present invention.

[0081] In the front and rear windshield assembly islands, the process involves multiple workstations and robotic arms working together, and is subject to strict time constraints, such as requiring installation to be completed within 5 minutes of applying adhesive. The specific process flow is as follows:

[0082] Material delivery: Automated Guided Vehicles (AGVs) transport the front and rear windshields from the warehouse to the designated storage area on the assembly island.

[0083] Loading station (station 1): The loading robot arm picks up glass from the storage area and places it on the positioning fixture at station 1.

[0084] Glue application station (station 2): The glue application robot arm picks up the glass from station 1, applies glue automatically, and then places the glued glass into the buffer zone of station 2.

[0085] Installation station (station 3): The robotic arm picks up the glued glass from station 2, positions it using a vision system, and then installs the glass onto the car body, pressing it together. Installation must be completed within 5 minutes of applying the adhesive to prevent the adhesive from cooling and affecting the bonding quality.

[0086] To verify the effectiveness of the data-real collaboration-based optimization method for island-level assembly processes of new energy vehicles of the present invention, process deduction, testing, and optimization were carried out according to the aforementioned steps. The specific implementation steps are as follows:

[0087] (1) Analysis of process elements of front and rear windshield assembly island: Analyze the process elements of front and rear windshield assembly island, define the process element set E, including the process set P={material loading, glue application, installation}, the resource set R={AGV, material loading robot arm, glue application robot arm, installation robot arm, vision system}, and the time constraint combination T, including the time sequence and dependency relationship of each process.

[0088] (2) Construction of digital twin models of front and rear windshield assembly islands: Based on the three-dimensional geometric models of the front and rear windshield assembly islands, digital twin models of the front and rear windshield assembly islands are constructed. .in:

[0089] The three-dimensional geometric model of the front and rear windshield assembly islands includes, but is not limited to, the loading robot arm, the gluing robot arm, the installation robot arm, the sealant supply equipment, the workstation layout, the robot arm workspace, and the AGV path.

[0090] The physical properties of the front and rear windshield assembly islands include, but are not limited to, glass weight, adhesive width, adhesive height, pressing force, and tolerance range.

[0091] The behavioral logic for assembling the front and rear windshields includes, but is not limited to, the motion trajectory of the robotic arm, the scheduling algorithm of the AGV, and the recognition process of the vision system.

[0092] Assembly rules for the front and rear windshield assembly islands include, but are not limited to, process priorities (material loading → adhesive application → installation), error-proofing logic, and installation time constraints.

[0093] (3) Assembly Island Process Dynamics Simulation: The discrete event simulation engine is used for dynamic process simulation. Input the process element set E and the digital twin model. Simulates the assembly process. Outputs the theoretical assembly cycle time. Equipment utilization rate (e.g., utilization rate of each robotic arm), material flow status (e.g., AGV delivery frequency, buffer queue length). Calculate the comprehensive performance index according to formula (2). ,in Determined by the longest single-process time, Consider buffer waiting time. Through simulation, identify potential bottlenecks, such as excessively long installation time.

[0094] (4) Physicalization test of process scheme: The process scheme determined by digital spatial simulation is sent to the control system of the physical assembly island to drive AGV, robotic arm and other equipment to perform actual assembly tasks.

[0095] (5) Assembly process data acquisition: Time-series data is collected in real time by encoders, vision sensors, radio frequency identification (RFID) and other sensors deployed on the front and rear windshield assembly islands. ,in For timestamps, This is the device state vector (such as the position of the robotic arm and the speed of the AGV). For quality data (such as adhesive thickness, installation position error). This refers to the total number of data points collected, which is the total number of time steps recorded by the sensor during the assembly process.

[0096] (6) Verification of assembly quality and efficiency: Calculate the assembly cycle time of the physical entity. and first-time pass rate .Will and Comparison, the beat matching degree is calculated according to formula (3). Meanwhile, based on predefined quality thresholds Determine the pass rate. If the installation time exceeds 5 minutes, mark it as a quality failure.

[0097] (7) Comparison and deviation analysis of virtual and real data: Compare the physical data Compare with theoretical data to identify key deviations, including beat deviations. Resource waiting time deviation (e.g., AGV waiting time). For example, physical testing may show that installing a robotic arm results in longer cycle times due to visual positioning delays.

[0098] (8) Feedback-based optimization of process parameters: minimizing and To achieve the objective, an objective function is established based on formula (6). A genetic algorithm is used to optimize the process timing and robotic arm movement speed, generating an optimized set of process parameters. Assembly rhythm with target For example, adjusting the speed of the adhesive-applying robotic arm can reduce adhesive application time, or optimizing the vision system's processing algorithm can shorten positioning time.

[0099] (9) Assembly cycle balancing and dynamic resource allocation: With the goal of minimizing bottleneck station time, the operation time of each station is reallocated to ensure... ,in, Let i be the work time for the i-th workstation after reallocation. , Given the total number of workstations. Calculate the optimal material delivery frequency. And staffing plans (such as adjusting maintenance personnel shifts and determining the actual number of personnel that should be allocated), among which This represents the material consumption rate per unit time at the workstation. Standard delivery container capacity. Dynamic configuration ensures installation work is completed within 5 minutes, preventing adhesive from cooling.

[0100] Through the above steps, the data-driven, real-world collaborative method for optimizing the island-level assembly process of new energy vehicles, as described in this invention, achieves rapid iterative optimization of the process scheme in the front and rear windshield assembly islands. Digital simulation identified bottlenecks at the installation stations in advance, physical testing verified the critical points of time constraints, and the optimization module improved cycle time balance and quality stability through parameter adjustment and dynamic resource configuration, verifying the practicality and effectiveness of this method. Subsequent steps are executed based on the matching results, which will not be elaborated further here.

[0101] The present invention also provides a data-driven, real-time collaborative optimization system for island-level assembly processes of new energy vehicles, used to implement the steps of the method of the present invention.

[0102] Figure 2 This diagram illustrates the structure of the new energy vehicle island-level assembly process optimization system based on the digital-real synergy of the present invention. Figure 2 As shown, the system includes the following modules:

[0103] The digital space assembly process simulation module 201 is used to analyze the process elements of the assembly island in the digital space, construct a digital twin model of the assembly island, provide a digital environment for the dynamic simulation of the assembly island process, and perform dynamic simulation of the assembly island process based on the digital twin model of the assembly island.

[0104] The physical space process testing and verification module 202 is used to test the process scheme derived by the digital space assembly process derivation module 201 on the physical assembly island, collect physical assembly process data, and verify the feasibility and effectiveness of the process scheme.

[0105] The assembly island process optimization module 203 is used to iteratively optimize the assembly process parameters and resource configuration in the digital space based on the verification results of the physical space process testing and verification module 202 and the physical assembly process data, form an optimization strategy, and feed it back to the physical space for execution.

[0106] For example, the system also includes a data management and service interface module for storing and managing the assembly island digital twin model, process case library (containing derived process solutions), and generated optimization strategies, and providing a process decision service interface. The process decision service interface serves as a data and functional bridge between the system and external applications (such as Manufacturing Execution System (MES), Enterprise Resource Planning (ERP) systems, and scheduling systems) or user interfaces. Its functions include: providing data querying, receiving instructions and parameters, triggering simulation and optimization, publishing optimization strategies, and service encapsulation.

[0107] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes and related descriptions of each module of the system described above can be found in the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0108] The present invention also provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs; wherein, when the one or more programs are executed by the one or more processors, the one or more processors enable the aforementioned data-real synergy optimization method for island-level assembly processes of new energy vehicles.

[0109] The present invention also provides a computer-readable storage medium storing executable instructions thereon, which, when executed by a processor, enable the processor to implement the aforementioned method for optimizing the island-level assembly process of new energy vehicles through data-real collaboration.

[0110] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the above-mentioned method for optimizing the island-level assembly process of new energy vehicles through data-real collaboration.

[0111] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0112] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0113] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0114] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0115] The contents not described in detail in this specification are existing technologies known to those skilled in the art.

[0116] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the present invention. The above descriptions are exemplary and not exhaustive. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for optimizing the island-level assembly process of new energy vehicles using a data-driven and real-data collaborative approach, characterized in that, include: S1. Analyze the process elements of the assembly island in the digital space, construct a digital twin model of the assembly island, and perform dynamic simulation of the assembly island process based on the digital twin model of the assembly island. S2. Test the process scheme derived in step S1 on the physical assembly island, collect data on the physical assembly process, and verify the feasibility and effectiveness of the process scheme. S3. Based on the verification results of step S2 and the physical assembly process data, iteratively optimize the assembly process parameters and resource configuration in the digital space to form an optimization strategy and feed it back to the physical space for execution.

2. The method according to claim 1, characterized in that, Step S1 includes: S1.1 Analyze the process elements of the assembly island, including the equipment layout, material delivery paths, robotic arm paths, worker positions, and assembly process sequences, and construct a set of process elements centered on processes, resources, and timing. ;in, For process sets, For resource collection, For timing constraint combinations; S1.

2. Based on the three-dimensional geometric model of the assembly island, a digital twin model of the assembly island is constructed by integrating physical attributes, behavioral logic, and assembly rules. , The expression is: (1) in, The three-dimensional geometric model of the assembly island; Physical properties; For behavioral logic; For assembly rules; S1.3, Based on the set of process elements and assembly island digital twin model A discrete event simulation engine is used to dynamically simulate the assembly island process, and the simulated process scheme is output, including the theoretical assembly cycle time. Theoretical resource waiting time Key equipment utilization rate and material flow status And construct a comprehensive performance index for the simulation system. , The calculation formula is: (2) in, The minimum assembly cycle time under ideal conditions is determined by the longest single-operation time; The average utilization rate of key equipment is determined by... The average value is used to obtain the result. The cost of material flow congestion is calculated using the following formula: ,in For the quantity of material buffer zone, Let j be the average queue length of the j-th material buffer. Let be the average waiting time of the j-th material buffer; , , Here are the weight coefficients for each item, and .

3. The method according to claim 2, characterized in that, Step S2 includes: S2.

1. Send the process plan derived in step S1.3 to the control system of the physical assembly island to drive the physical equipment to perform the assembly task. S2.2 Data on the physical assembly process, including time-series data, is collected in real time through a sensor network deployed on the physical assembly island. ,in For timestamps, This is the device state vector. For assembly quality inspection data, This represents the total number of data points collected. S2.3, according to Calculate the assembly cycle time of solids and will The result derived from step S1.3 Compare and calculate the beat matching degree. , The calculation formula is: (3) At the same time, according to Calculate the first pass rate And based on predefined assembly quality thresholds judge The pass rate.

4. The method according to claim 3, characterized in that, Step S3 includes: S3.1, Collect the data from step S2.2 Compare the data with the theoretical data output from step S1.3 to identify key deviations, including assembly cycle time deviations. Resource waiting time deviation ;in, The actual resource waiting time, based on In and Calculated; S3.2, minimizing and To achieve the goal, an objective function for optimizing the process parameters of the assembly island is established. , The calculation formula is: (6) in, and These are the weighting coefficients; This represents the total number of resources. The waiting time deviation for the k-th resource; This is the sum of the waiting time deviations for all resources; according to Genetic algorithms are used to optimize process parameters in the digital space, generating an optimized set of process parameters. Assembly rhythm with target ; S3.

3. Based on the optimization results of step S3.2, the assembly cycle time is balanced with the goal of minimizing the bottleneck station time. The objective function is... for: (7) The constraints are: (1) The task assignments for each workstation must cover all assembly operations, and there should be no duplication or omission; (2) Working time at each workstation Determined by the total time allocated to the tasks; (3) The optimized assembly cycle time must meet the following requirements. ; in, Let i be the work time for the i-th workstation after reallocation. ; This represents the total number of workstations. Based on the balanced assembly cycle time, the operation time of each workstation is redistributed, and the optimal material delivery frequency is calculated. With the number of personnel This is to achieve a balanced production cycle and efficient resource utilization in the assembly island.

5. The method according to claim 4, characterized in that, and The calculation formula is: (8) (9) in, This represents the material consumption rate per unit time at the workstation. For standard delivery container capacity; This represents the total manual operation time for all workstations. This is the preset labor efficiency coefficient. This is the floor function.

6. A data-driven, real-time collaborative optimization system for island-level assembly processes in new energy vehicles, characterized in that: include: The digital space assembly process simulation module is used to analyze the process elements of the assembly island in digital space, construct a digital twin model of the assembly island, and perform dynamic simulation of the assembly island process based on the digital twin model of the assembly island. The physical space process testing and verification module is used to test the process scheme derived by the digital space assembly process derivation module on the physical assembly island, collect physical assembly process data, and verify the feasibility and effectiveness of the process scheme. The assembly island process optimization module is used to iteratively optimize assembly process parameters and resource configuration in the digital space based on the verification results of the physical space process testing and verification module and the physical assembly process data, form an optimization strategy, and feed it back to the physical space for execution.

7. The system according to claim 6, characterized in that, The system also includes a data management and service interface module, which is used to store and manage the assembly island digital twin model, process case library and optimization strategies, and provide a process decision service interface.

8. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; Wherein, when one or more programs are executed by the one or more processors, the one or more processors cause the one or more processors to implement the method according to any one of claims 1-5.

9. A computer-readable storage medium, characterized in that, It stores executable instructions that, when executed by a processor, enable the processor to perform the method described in any one of claims 1-5.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-5.

Images