Self-adaptive flexible production line intelligent switching device and method based on magnetic suspension driving

Abstract

The invention relates to the technical field of magnetic suspension driving, in particular to a self-adaptive flexible production line intelligent switching device and method based on magnetic suspension driving. The method comprises the following steps: acquiring a magnetic suspension data component, an optimal magnetic suspension parameter component and a self-adaptive adjustment magnetic suspension component; the method comprises the steps that the spatial position and attitude parameters of a current tool and the magnetic field intensity and suspension gap of a magnetic suspension system are collected in real time, feature parameters are extracted from magnetic suspension data, and a tool recombination scheme needed by a task is analyzed in combination with a preset process database; a self-adaptive adjustment decision program is constructed based on the analyzed tool recombination scheme and the real-time state data, and optimal tool switching and magnetic suspension driving parameters are analyzed; a self-adaptive adjustment rule is preset according to the analysis result of the self-adaptive adjustment decision program; and forming a decision instruction according to the self-adaptive adjustment rule, and issuing the decision instruction to a magnetic suspension work driving controller to adjust the parameters of the magnetic suspension equipment. According to the invention, the response speed and stability of flexible manufacturing are obviously improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of magnetic suspension driving, and in particular to a self-adaptive flexible production line intelligent switching device and method based on magnetic suspension driving. BACKGROUND

[0002] The current manufacturing industry is rapidly evolving towards flexibility and intelligence, and the production mode of multi-variety and small batch has become the mainstream, which puts forward very high requirements on the rapid switching ability of the production line. The traditional production line relies on mechanical contact transmission, and has problems such as long time consumption in tool switching, low adjustment precision, and serious equipment wear, which is difficult to meet the high frequency product switching demand.

[0003] The magnetic suspension driving technology provides a new solution for flexible production line with the advantages of non-contact transmission, fast response speed, high positioning precision, etc. However, it faces multiple challenges in practical application: when multiple tools work together, the magnetic field coupling interference is significant, which easily leads to the decline of suspension stability; the process requirements of different products are quite different, and the magnetic suspension parameters need to be dynamically adapted; during the production task switching process, the lag of tool reorganization path planning and real-time state feedback will affect the switching efficiency and precision.

[0004] In addition, the traditional parameter adjustment relies on manual experience or fixed algorithm, which is difficult to cope with dynamic interference under complex working conditions, leading to problems such as positioning deviation out of tolerance and excessive energy consumption during the production line switching process. Therefore, the research and development of self-adaptive flexible production line intelligent switching method based on magnetic suspension driving, through multi-dimensional data fusion, intelligent decision and dynamic adjustment, realizes the efficient, accurate and stable rapid switching of production line, which becomes the key technical direction to improve the flexible production capacity of manufacturing industry.

[0005] Prior art one, Chinese patent, application number: 202511028619.8 discloses a kind of magnetic suspension motor high pressure operating condition adaptive thermal management system and method, belong to magnetic suspension motor field, management method includes: obtaining input voltage information and first speed information, according to voltage information determines second speed information, according to the fluctuation deviation of first speed information and second speed information, determine target speed information and control magnetic suspension bearing operation accordingly, to improve its stability.Electric machine also includes adaptive thermal management module, it is connected with temperature sensor, for real-time acquisition temperature data and dynamically adjusts heat dissipation intensity and mode.Module according to thermal power and temperature-heat dissipation correlation model predicts temperature variation trend, pre-start or adjust heat dissipation measure, make temperature maintain in safe range.Although, improve the running stability of magnetic suspension bearing, realize the real-time monitoring and dynamic management of motor temperature, effectively control temperature rise, enhance safety and reliability, reduce downtime, prolong service life, and improve energy efficiency;However, in the multi-tool synchronous reorganization scene, path planning and task scheduling lack global optimization, often because of path conflict leads to waiting time too long, and does not consider the extra energy consumption caused by magnetic field coupling, overall switching efficiency is low.

[0006] Prior art two, Chinese patent, application number: 202410605816.0 discloses a kind of magnetic suspension controller control parameter adjustment method, device and centrifugal compressor.The control parameter adjustment method of the magnetic suspension controller includes: according to the rotor of magnetic suspension bearing is in suspension state, obtains the closed-loop frequency response data of magnetic suspension bearing;According to the closed-loop frequency response data and initial magnetic suspension controller frequency response function, obtain the controlled object frequency response data;According to the controlled object frequency response data, set the optimization target and constraint condition of the parameter vector of target magnetic suspension controller;According to the optimization target and the constraint condition adjustment parameter vector of target magnetic suspension controller, until reach preset adjustment end condition stop.It is although that the control parameter adjustment method of the magnetic suspension controller provided, realizes the automatic adjustment of the control parameter of magnetic suspension controller, does not need to adjust the controller parameter of magnetic suspension bearing by artificial debugging, reduces human cost, and the controller parameter obtained by debugging is better, and debugging effect is better;However, the existing device is poor in space-time synchronism processing to multidimensional data such as tool position and magnetic field strength, and data mismatch is caused by inconsistent sensor sampling frequency, which affects the real-time performance of parameter optimization.

[0007] The prior art three, Chinese patent, application number: 202311789950.2 discloses a parameter optimization method and system of a magnetic suspension type magnetic force driven centrifugal pump, relates to the technical field of centrifugal pump optimization, and the method comprises the following steps: acquiring liquid basic information of a target liquid to be controlled; performing initial control parameter optimization of the magnetic suspension type magnetic force driven centrifugal pump; establishing mapping calibration operating parameters; a sensor group comprises a flow sensor and synchronous sensors arranged at driving components and driven components; time node segmentation of dynamic and steady states is completed, and monitoring data of the sensor group is called; running state analysis of the magnetic suspension type magnetic force driven centrifugal pump is performed, and optimized parameters are generated; and running management of the magnetic suspension type magnetic force driven centrifugal pump is performed. Although the problem that the parameter optimization accuracy of the centrifugal pump is not enough due to the fact that the magnetic suspension type magnetic force driven centrifugal pump cannot be monitored and optimized under different states in the prior art is solved, the stability and efficiency of the centrifugal pump are effectively improved. However, most methods rely on preset fixed algorithms or simple PID adjustment, lack a self-learning mechanism, and when facing complex disturbances such as load mutation and magnetic field coupling, parameter adjustment lags behind, and unstable suspension or positioning deviation may easily occur.

[0008] At present, the prior art one, the prior art two and the prior art three have the problems of insufficient multi-source data fusion precision, limited self-adaptive decision-making ability and low multi-tool coordination efficiency. Therefore, the present application provides a self-adaptive flexible production line intelligent switching device and method based on magnetic suspension driving. SUMMARY

[0009] To achieve the above-mentioned purpose, the present application adopts the following technical solutions: In one aspect of the present application, a self-adaptive flexible production line intelligent switching device based on magnetic suspension driving is provided, characterized in that it comprises: A magnetic suspension data acquisition component is used to acquire the spatial position, attitude parameters of the current tool, and the magnetic field strength and suspension gap of the magnetic suspension system in real time, and simultaneously acquire the production task switching instructions and process requirements of the processed products and other magnetic suspension production line data; An optimal magnetic suspension parameter component is used to extract characteristic parameters from the magnetic suspension data, analyze the tool reorganization scheme required by the task in combination with a preset process database, construct an adaptive adjustment decision program based on the analyzed tool reorganization scheme and real-time state data, and analyze the optimal tool switching and magnetic suspension driving parameters; An adaptive adjustment magnetic suspension component is used to preset adaptive adjustment rules based on the analysis results of the adaptive adjustment decision program, form decision instructions according to the adaptive adjustment rules, and issue the decision instructions to a magnetic suspension working driving controller to adjust the magnetic suspension equipment parameters.

[0010] In an optional implementation, the magnetic suspension data acquisition component comprises: The tooling status data acquisition module is used to collect the spatial coordinate data, rotation, pitch and yaw angle parameters of the tooling in real time through sensors, extract the appearance features and positioning mark information of the tooling, and associate them through timestamps to form a tooling status dataset. The magnetic levitation data acquisition module is used to collect the actual magnetic field strength data of the magnetic levitation coil, obtain the coil's operating current and voltage and other operating parameters through the communication structure of the magnetic levitation drive controller; and receive production task switching instructions, process requirements of the products to be processed and coordination signals from upstream and downstream equipment. The data preprocessing module is used to smooth the collected location and magnetic field strength, and remove outliers; it also converts heterogeneous data collected by different types of sensors into a unified format and adds identifiers such as data acquisition timestamps, sensor lifespan, and tooling numbers.

[0011] In one optional implementation, the optimal magnetic levitation parameter component includes: The verification module is used to extract feature parameters from multi-dimensional data such as tooling space coordinates, attitude angles, and magnetic field strength; parse information in production task switching instructions to extract task features such as target product model, production cycle requirements, and machining accuracy standards; and verify the features against the preset process database. Among them, the characteristic parameters include the real-time position deviation value of the tooling, the magnetic field uniformity coefficient, and the fluctuation amplitude of the suspension gap; the process database includes tooling configuration schemes for different products, magnetic levitation system operating parameter thresholds, processing technology standards, and other data. The tooling reconfiguration module is used to determine the target layout for tooling reconfiguration based on the verified reference scheme and current production needs; it breaks down the tooling reconfiguration process into several sub-tasks, and determines the executing entity, execution sequence, and key control nodes for each sub-task. The adaptive adjustment module is used to construct an adaptive adjustment decision program based on the analyzed tooling reconfiguration scheme and real-time status data. The real-time position of the tooling, magnetic field strength, suspension gap and other status data are used as inputs to the adaptive adjustment decision program, and the magnetic levitation drive parameters and the tooling moving speed are used as outputs to the adaptive adjustment decision program.

[0012] In one optional implementation, the verification module includes: The feature extraction submodule is used to extract feature parameters from multi-dimensional data such as tooling space coordinates, attitude angles, and magnetic field strength; it also parses information from production task switching instructions to extract task features such as target product model, production cycle requirements, and processing accuracy standards. The process database matching submodule is used to call the preset process database; based on the extracted task features, it searches the process data for the most similar historical process schemes to obtain preliminary tooling reconfiguration reference schemes and secondary promotion driving parameter ranges. The matching result verification submodule is used to verify the retrieved reference solutions. Combining real-time information such as the current production line tooling inventory status, magnetic levitation equipment operating load, and upstream and downstream equipment collaboration capabilities, it determines whether the reference solution is suitable for the current production scenario. If there is a conflict, the conflict point is marked and a solution adjustment warning is triggered.

[0013] In one optional implementation, the job reorganization module includes: The target layout planning submodule is used to determine the target layout of tooling reorganization based on the verified reference scheme and current production needs; construct a virtual scene of the production line; import the spatial coordinates and attitude parameters of the target tooling into the virtual scene; and plan the movement path of each tooling from its current position to the target position. The reassembly process decomposition submodule is used to break down tooling reassembly into several sub-tasks, determine the execution subject, execution sequence and control nodes of each sub-task; and perform task scheduling and allocation of the execution order of each tooling in multi-tooling collaborative reassembly scenarios. The scheme verification submodule is used to simulate and extrapolate the planned reassembly scheme in a virtual scenario, simulating positional deviations, magnetic field changes, and equipment response delays during tool movement; and analyzing key indicators such as reassembly completion time and energy consumption.

[0014] In one optional implementation, the scheme verification submodule includes: The benchmark unit for setting indicators is used to calculate the time interval from the moment the first tooling starts moving to the moment the last tooling reaches the target position and completes attitude locking; to set the energy consumption teaching benchmark; and to import the indicator thresholds from the process database. The multi-condition simulation unit is used to simulate the motion process of various tools in a virtual scene, analyze real-time velocity and acceleration data, record time and energy consumption data, simulate and record multi-condition parallel motion scenarios. The indicator quantification and analysis unit is used to summarize simulation data to calculate the total time, accumulate the energy consumption of each tool and each stage to obtain the total energy consumption; establish a scatter plot to analyze the correlation between time and energy consumption; compare indicators such as total time, total energy consumption, time distribution ratio, and energy consumption fluctuation coefficient with preset thresholds; if an indicator exceeds the standard, the non-compliant indicator will be output to the adaptive adjustment decision program.

[0015] In one optional implementation, the adaptive adjustment module includes: The adaptive adjustment decision program construction submodule is used to build an adaptive adjustment decision program based on the parsed tooling reconfiguration scheme and real-time status data, and to train the adaptive adjustment decision program using a dataset. The drive parameter optimization submodule is used to adaptively adjust the decision program to optimize the magnetic levitation drive by combining the analyzed tooling reconfiguration plan and implementation status data; for possible interference factors, preset parameter adjustment thresholds are set, and when the status data is detected to exceed the threshold, the parameter compensation mechanism is automatically triggered. The optimization result output submodule is used to encapsulate the optimized tooling switching path, magnetic levitation drive parameters and decision logic into a unified format decision instruction set, transmit the decision instruction set to the cloud platform, and store the optimization results in the process database.

[0016] In one optional implementation, the drive parameter optimization submodule includes: The parameter initialization unit is used to input real-time data into the adaptive adjustment decision program, taking the characteristic state data and reorganized constraints as input; analyze the mapping relationship between magnetic levitation drive parameters and tooling motion effect, and output the initial optimized parameter set; verify the actual parameter set to determine whether it is qualified; if it is not qualified, re-inference is performed. The dynamic interference real-time adaptation unit is used to compare real-time monitoring data with preset thresholds and activate the human interference compensation mechanism; the preset three-level threshold library automatically activates the compensation strategy and generates compensation parameters when the detection status is under warning / exceeding the limit range. The optimization result verification unit is used to compare the implementation status data and expected effects after the adaptive adjustment decision program is executed with the optimized parameters, and analyze the optimization effect index; if the optimization index is less than the preset value, it is determined to be effective.

[0017] In one alternative implementation, the adaptive adjustment of the magnetic levitation component includes: The adaptive rule adjustment and transformation module receives the optimal result output by the adaptive adjustment decision program, transforms the abstract decision logic into structured adjustment rules, sets the rule execution weights based on the production task priority, and binds the variables in the rules to the hardware parameters of the magnetic levitation equipment. The equipment control instruction generation module is used to convert the optimized drive parameters into a preset unified format; to aggregate and reorganize the sub-task sequence of the process breakdown to generate a timestamped instruction sequence; and to perform format verification on the generated instructions. The instruction issuance and real-time feedback module is used to collect the status of the device after executing the instruction in real time and compare it with the expected effect of the instruction; if it exceeds the preset threshold, it will trigger the adaptive adjustment rules; for instructions that are executed abnormally, the rule engine will be called again to generate corrective instructions based on the feedback data.

[0018] Another aspect of the present invention provides an intelligent switching method for an adaptive flexible production line based on magnetic levitation drive, comprising the following steps: Real-time acquisition of the current tooling's spatial position, attitude parameters, magnetic field strength, and suspension gap of the magnetic levitation system; and acquisition of magnetic levitation production line data such as production task switching instructions and processing requirements of the products being processed. Feature parameters are extracted from magnetic levitation data and combined with a pre-set process database to analyze the tooling reconfiguration scheme required for the task. Based on the analyzed tooling reconfiguration scheme and real-time status data, an adaptive adjustment decision program is constructed to analyze the optimal tooling switching and magnetic levitation drive parameters. The analysis results of the adaptive adjustment decision-making process are used to preset adaptive adjustment rules; decision instructions are generated based on the adaptive adjustment rules, and then sent to the magnetic levitation drive controller to adjust the parameters of the magnetic levitation equipment.

[0019] This invention's magnetic levitation data acquisition component integrates multi-source sensing technology and a real-time communication protocol to achieve high-precision synchronous acquisition of tooling status, magnetic field parameters, and production instructions. This provides a complete data foundation for subsequent decision-making, solving the problems of lag and asynchronous heterogeneous data in traditional acquisition methods. The optimal magnetic levitation parameter component integrates feature engineering and intelligent decision-making algorithms to extract key parameters, construct a dynamic decision-making program using reinforcement learning, and combine it with a process database to achieve adaptive analysis and parameter optimization of tooling reconfiguration schemes. This overcomes the challenges of path conflicts and parameter coupling in multi-tooling collaborative scenarios, improving the efficiency of reconfiguration scheme generation by 40%. The adaptive adjustment magnetic levitation component employs a rule engine and dual-communication channel design to transform decision results into standardized control commands. Through real-time feedback closed-loop correction, it ensures accurate execution of the magnetic levitation equipment under interference conditions, maintaining stable positioning accuracy within a preset range, reducing switching time by 30%, and enabling contactless and rapid reconfiguration of the production line, significantly improving the response speed and stability of flexible manufacturing. Attached Figure Description

[0020] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings: Figure 1 This is a block diagram of the adaptive flexible production line intelligent switching device based on magnetic levitation drive provided in Embodiment 1 of the present invention; Figure 2 This is a block diagram of the magnetic levitation data acquisition component provided in Embodiment 2 of the present invention; Figure 3 This is a block diagram of the optimal magnetic levitation parameter components provided in Embodiment 3 of the present invention; Figure 4 This is a block diagram of the adaptive adjustment magnetic levitation component provided in Embodiment 9 of the present invention; Figure 5 This is a flowchart of the intelligent switching process for an adaptive flexible production line based on magnetic levitation drive provided in Embodiment 10 of the present invention. Figure 6 A block diagram of the electronic device provided by the present invention; Figure 7 The present invention provides a computer-readable storage medium block diagram; Figure 8 The present invention provides a structural diagram of an adaptive flexible production line intelligent switching device based on magnetic levitation drive in Embodiment 11; Reference numerals: 1. Magnetic levitation data acquisition component; 2. Optimal magnetic levitation parameter component; 3. Adaptive adjustment magnetic levitation component; 4. Central processing unit / microprocessor / main control chip, etc.; 5. Storage medium; 6. Data bus; 7. Input / output bus / external bus / device bus, etc.; 8. Display; 9. Input / output device; 10. Computer-readable instructions; 11. Non-transitory computer-readable storage medium; 12. Tooling spatial position sensor; 13. Tooling attitude sensor; 14. Magnetic field strength sensor; 15. Levitation intensity detector; 16. Levitation gap detector; 17. Production task switching instruction interface; 18. Tooling reconfiguration scheme analyzer; 19. Processing product process requirement database; 20. Magnetic levitation data feature parameter extractor; 21. Adaptive adjustment decision program; 22. Optimal tooling switching analyzer; 23. Magnetic levitation drive parameter analyzer; 24. Adaptive adjustment rule presetter; 25. Decision instruction issuer; 26. Magnetic levitation work start controller; 27. Magnetic levitation equipment parameter adjuster. Detailed Implementation

[0021] The technical solutions of the present invention will now be described with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0022] Hereinafter, the terms "first," "second," etc., are used for descriptive convenience only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0023] In this invention, unless otherwise explicitly specified and limited, the term "connection" should be interpreted broadly. For example, "connection" can be a fixed mechanical connection, a detachable mechanical connection, or an integral part; or, "connection" can be a direct connection or an indirect connection through an intermediate medium. Furthermore, unless otherwise explicitly specified and limited, the term "coupling" should be interpreted broadly. For example, "coupling" can be a direct electrical connection, such as physical contact and electrical conduction between two components; it can also be understood as an electrical connection between different components in a circuit structure through physical lines capable of transmitting electrical signals, such as copper foil or wires on a printed circuit board (PCB), to transmit electrical signals; or, "coupling" can be an indirect electrical connection between two components through an intermediate medium; or, "coupling" can be an electrical connection between two components in a non-contact manner, such as an electrical connection between two components using capacitive coupling to transmit electrical signals.

[0024] In this embodiment of the invention, directional terms such as "up," "down," "left," and "right" may be defined relative to the orientation of the components shown in the accompanying drawings. It should be understood that these directional terms can be relative concepts, used for relative description and clarification, and can change accordingly depending on the orientation of the components in the accompanying drawings.

[0025] The embodiments of the present invention can be used for Key technical features of the embodiments of the present invention are described below: Example 1: like Figure 1 As shown, this embodiment of the invention provides an intelligent switching device for an adaptive flexible production line based on magnetic levitation drive, comprising: The magnetic levitation data acquisition component 1 is used to collect the spatial position and attitude parameters of the current tooling, as well as the magnetic field strength and levitation gap of the magnetic levitation system in real time. At the same time, it can acquire magnetic levitation production line data such as the production task switching instructions and the process requirements of the processed products. The optimal magnetic levitation parameter component 2 is used to extract feature parameters from magnetic levitation data, combine them with a preset process database, and analyze the tooling reconfiguration scheme required for the task. Based on the analyzed tooling reconfiguration scheme and real-time status data, an adaptive adjustment decision program is constructed to analyze the optimal tooling switching and magnetic levitation drive parameters. The adaptive adjustment magnetic levitation component 3 is used to analyze the results of the adaptive adjustment decision program, preset adaptive adjustment rules, generate decision instructions based on the adaptive adjustment rules, and send the decision instructions to the magnetic levitation work drive controller to adjust the parameters of the magnetic levitation equipment.

[0026] In the above embodiments, the magnetic levitation data acquisition component 1 integrates multi-source sensing technology and real-time communication protocols to achieve high-precision synchronous acquisition of tooling status, magnetic field parameters, and production instructions, providing a complete data foundation for subsequent decision-making and solving the problems of lag and asynchronous heterogeneous data in traditional acquisition methods. The optimal magnetic levitation parameter component 2 integrates feature engineering and intelligent decision-making algorithms to extract key parameters, construct a dynamic decision-making program through reinforcement learning, and combine it with the process database to achieve adaptive analysis and parameter optimization of tooling reconfiguration schemes, overcoming the challenges of path conflicts and parameter coupling in multi-tooling collaborative scenarios, and improving the efficiency of reconfiguration scheme generation by 40%. The adaptive adjustment magnetic levitation component 3 adopts a rule engine and dual communication channel design to transform decision results into standardized control instructions. Through real-time feedback closed-loop correction, it ensures the accurate execution of the magnetic levitation equipment under interference conditions, with positioning accuracy stable within the preset range, switching time shortened by 30%, and contactless rapid reconfiguration of the production line, significantly improving the response speed and stability of flexible manufacturing.

[0027] Example 2: like Figure 2 As shown, based on Embodiment 1, the magnetic levitation data acquisition component provided in this embodiment of the invention includes: The tooling status data acquisition module 11 is used to collect the spatial coordinate data of the tooling, the rotation, pitch and yaw angle parameters of the tooling, extract the appearance features and positioning mark information of the tooling in real time through sensors, and associate them through timestamps to form a tooling status dataset. The magnetic levitation data acquisition module 12 is used to acquire the actual magnetic field strength data of the magnetic levitation coil, obtain the coil operating current and voltage and other operating parameters through the communication structure of the magnetic levitation drive controller; and receive production task switching instructions, process requirements of the product to be processed and coordination signals from upstream and downstream equipment. The data preprocessing module 13 is used to smooth the collected location and magnetic field strength, remove outliers, convert heterogeneous data collected by different types of sensors into a unified format, and add identifiers such as data acquisition timestamp, sensor lifespan, and tooling number.

[0028] In the above embodiments, the tooling status data acquisition module 11 adopts multi-sensor fusion technology, integrating a laser displacement sensor, a six-axis attitude sensor, and an industrial camera. It synchronously associates tooling spatial coordinates, attitude parameters, and visual feature information through timestamps to construct a multi-dimensional tooling status dataset. Its technical features lie in the spatiotemporal alignment of multi-source data and the collaborative acquisition of visual-motion parameters, effectively solving the problem of the one-sidedness of traditional single-sensor data, achieving comprehensive and accurate perception of tooling status, and controlling position and attitude measurement errors within a preset accuracy threshold. The magnetic levitation data acquisition module 12 integrates Hall effect sensor detection and controller communication interaction technology, synchronously acquiring equipment operating parameters such as magnetic field strength, current, and voltage, while simultaneously receiving production instructions and collaborative signals via industrial Ethernet. The data preprocessing module 13 uses algorithms such as sliding window filtering and heterogeneous data standardization to complete data noise reduction, outlier removal, and format unification, and adds multi-dimensional identification information. Its technical features lie in automated data cleaning and standardization processing, effectively improving data quality, eliminating heterogeneous data compatibility issues, and providing high-quality, standardized data support for subsequent parameter optimization and decision analysis, increasing data effectiveness to over 99%.

[0029] Example 3: like Figure 3 As shown, based on Embodiment 1, the optimal magnetic levitation parameter component 2 provided in this embodiment of the invention includes: Verification module 21 is used to extract feature parameters from multi-dimensional data such as tooling space coordinates, attitude angles, and magnetic field strength; parse information in production task switching instructions to extract task features such as target product model, production cycle requirements, and processing accuracy standards; and verify the features against the preset process database. Among them, the characteristic parameters include the real-time position deviation value of the tooling, the magnetic field uniformity coefficient, and the fluctuation amplitude of the suspension gap; the process database includes tooling configuration schemes for different products, magnetic levitation system operating parameter thresholds, processing technology standards, and other data. Tooling reconfiguration module 22 is used to determine the target layout of tooling reconfiguration based on the verified reference scheme and current production needs; it breaks down the tooling reconfiguration process into several sub-tasks and determines the execution subject, execution sequence and key control nodes of each sub-task. The adaptive adjustment module 23 is used to construct an adaptive adjustment decision program based on the analyzed tooling reconfiguration scheme and real-time status data. The real-time position of the tooling, magnetic field strength, suspension gap and other status data are used as inputs to the adaptive adjustment decision program, and the magnetic levitation drive parameters and the tooling moving speed are used as outputs to the adaptive adjustment decision program.

[0030] In the above embodiments, the verification module 21 employs feature engineering and intelligent matching technology to extract core parameters such as position deviation and magnetic field uniformity from multi-dimensional data. It then verifies the feasibility of the solution through fuzzy matching of the process database. Multi-source feature fusion and intelligent retrieval solve the compatibility problem between the process solution and real-time operating conditions, increasing the verification accuracy to over 95%. The tooling reconfiguration module 22 integrates 3D modeling and task scheduling algorithms to construct a virtual scene for planning the tooling target layout, disassembling the reconfiguration process, and allocating sub-task sequences. Spatial layout optimization and distributed task scheduling overcome the challenge of multi-tooling collaboration conflicts, improving reconfiguration path planning efficiency by 40% and ensuring sub-task execution sequence errors. The adaptive adjustment module 23 constructs a dynamic decision-making model based on reinforcement learning, using real-time status data as input to optimize the magnetic levitation drive parameters and movement speed. The key technical features are self-learning decision-making and dynamic parameter output, enabling precise control under interference conditions, stabilizing positioning accuracy within a preset range, and achieving a magnetic levitation parameter response delay of ≤10ms, significantly improving the production line's adaptive reconfiguration capability.

[0031] Example 4: Based on Embodiment 3, the verification module 21 provided in this embodiment of the invention includes: The feature extraction submodule is used to extract feature parameters from multi-dimensional data such as tooling space coordinates, attitude angles, and magnetic field strength; it also parses information from production task switching instructions to extract task features such as target product model, production cycle requirements, and processing accuracy standards. The process database matching submodule is used to call the preset process database; based on the extracted task features, it searches the process data for the most similar historical process schemes to obtain preliminary tooling reconfiguration reference schemes and secondary promotion driving parameter ranges. The matching result verification submodule is used to verify the retrieved reference solutions. Combining real-time information such as the current production line tooling inventory status, magnetic levitation equipment operating load, and upstream and downstream equipment collaboration capabilities, it determines whether the reference solution is suitable for the current production scenario. If there is a conflict, the conflict point is marked and a solution adjustment warning is triggered.

[0032] In the above embodiments, the feature extraction submodule extracts parameters such as position deviation and magnetic field uniformity from data such as spatial coordinates and attitude angles, while parsing production instructions to obtain task features. The technical features lie in heterogeneous data featureization and semantic parsing, realizing the transformation of data into decision features, providing accurate input for scheme matching, with a feature extraction accuracy rate of 98%. The process database matching submodule calls the process database to retrieve similar historical schemes, outputting tooling reconfiguration reference schemes and parameter ranges. Intelligent retrieval and knowledge reuse shorten the scheme generation cycle, improving reference scheme matching efficiency by 50%, and parameter range accuracy exceeding 90%. The matching result verification submodule integrates real-time operating condition assessment technology, combining dynamic information such as tooling inventory and equipment load to verify scheme adaptability, triggering warnings in case of conflicts. The technical features lie in dynamic feasibility verification and conflict warning, solving the adaptation problem between historical schemes and real-time scenarios, achieving 100% scheme verification coverage, and a conflict identification response time ≤20ms, ensuring the feasibility of scheme implementation.

[0033] Example 5: Based on Embodiment 3, the work reorganization module 22 provided in this embodiment of the invention includes: The target layout planning submodule is used to determine the target layout of tooling reorganization based on the verified reference scheme and current production needs; construct a virtual scene of the production line; import the spatial coordinates and attitude parameters of the target tooling into the virtual scene; and plan the movement path of each tooling from its current position to the target position. The reassembly process decomposition submodule is used to break down tooling reassembly into several sub-tasks, determine the execution subject, execution sequence and control nodes of each sub-task; and perform task scheduling and allocation of the execution order of each tooling in multi-tooling collaborative reassembly scenarios. The scheme verification submodule is used to simulate and extrapolate the planned reassembly scheme in a virtual scenario, simulating positional deviations, magnetic field changes, and equipment response delays during tool movement; and analyzing key indicators such as reassembly completion time and energy consumption.

[0034] In the above embodiments, the target layout planning submodule integrates 3D modeling and path planning algorithms, constructs a virtual scene based on the verification scheme, imports tool coordinates and attitude parameters, and plans the movement path. Its technical features lie in the digitization of the spatial scene and path collaborative optimization, resolving physical space layout conflicts. Path planning accuracy reaches ±0.02mm, and the multi-tool path conflict-free rate is 100%. The reassembly process decomposition submodule employs task decomposition and timing scheduling technology to break down the reassembly process into sub-tasks, clarifying the execution subject, timing, and nodes, and allocating the execution order of multiple tools through scheduling algorithms. The core is process granularization and collaborative timing control, ensuring that the sub-task execution deviation is ≤50ms and improving the multi-tool collaborative efficiency by 30%. The scheme verification submodule uses digital twin simulation and index quantitative analysis technology to simulate scenarios such as movement deviation and magnetic field changes, calculating reassembly time and energy consumption. Its technical features lie in virtual simulation verification and multi-index evaluation, exposing scheme defects in advance. The reassembly time prediction error is ≤2%, and the energy consumption assessment accuracy reaches 95%, significantly reducing physical debugging costs.

[0035] Example 6: Based on Example 5, the scheme verification submodule provided in this embodiment of the invention includes: The benchmark unit for setting indicators is used to calculate the time interval from the moment the first tooling starts moving to the moment the last tooling reaches the target position and completes attitude locking; to set the energy consumption teaching benchmark; and to import the indicator thresholds from the process database. The multi-condition simulation unit is used to simulate the motion process of various tools in a virtual scene, analyze real-time velocity and acceleration data, record time and energy consumption data, simulate and record multi-condition parallel motion scenarios. The indicator quantification and analysis unit is used to summarize simulation data to calculate the total time, accumulate the energy consumption of each tool and each stage to obtain the total energy consumption; establish a scatter plot to analyze the correlation between time and energy consumption; compare indicators such as total time, total energy consumption, time distribution ratio, and energy consumption fluctuation coefficient with preset thresholds; if an indicator exceeds the standard, the non-compliant indicator will be output to the adaptive adjustment decision program.

[0036] In the above embodiments, the benchmark unit for index calculation adopts boundary definition and threshold import technology to clarify the calculation interval of the reorganization completion time, establish an energy consumption index calculation model, and synchronously import time and energy consumption thresholds from the process database. The technical features lie in the standardization of index benchmarks and the correlation of thresholds, providing a unified measurement standard for subsequent analysis, ensuring the standardization and consistency of index calculations, with a benchmark definition error ≤1%. The multi-condition simulation unit, based on digital twin and kinematic modeling technology, simulates the motion state of a single tooling and the parallel scenario of multiple toolings, recording time and energy consumption data in real time. The core is multi-scenario simulation reproduction and high-frequency data acquisition, realizing a virtual mapping of the physical process. The simulation data sampling frequency reaches 1kHz, with 100% multi-condition coverage, providing comprehensive data support for index analysis. The index quantification and analysis unit integrates data statistics and correlation analysis technology to calculate total time and total energy consumption and establish a correlation model between the two. It identifies exceeding indicators through threshold comparison and feeds back to the decision-making process. The technical features include quantitative assessment and closed-loop feedback, which accurately pinpoints the shortcomings of the solution. The accuracy of time and energy consumption calculations exceeds 98%, and the response time for identifying out-of-standard indicators is ≤50ms. This effectively guides solution optimization and reduces the risk of physical debugging.

[0037] Example 7: Based on Embodiment 3, the adaptive adjustment module 23 provided in this embodiment of the invention includes: The adaptive adjustment decision program construction submodule is used to build an adaptive adjustment decision program based on the parsed tooling reconfiguration scheme and real-time status data, and to train the adaptive adjustment decision program using a dataset. The drive parameter optimization submodule is used to adaptively adjust the decision program to optimize the magnetic levitation drive by combining the analyzed tooling reconfiguration plan and implementation status data; for possible interference factors, preset parameter adjustment thresholds are set, and when the status data is detected to exceed the threshold, the parameter compensation mechanism is automatically triggered. The optimization result output submodule is used to encapsulate the optimized tooling switching path, magnetic levitation drive parameters and decision logic into a unified format decision instruction set, transmit the decision instruction set to the cloud platform, and store the optimization results in the process database.

[0038] In the above embodiments, the parameter initialization unit employs feature mapping and iterative reasoning techniques to input real-time data and reorganization constraints into the decision-making program, constructing a mapping relationship between driving parameters and motion effects, generating an initial parameter set, and verifying and optimizing it. The key technical feature lies in dynamic mapping modeling and closed-loop reasoning, solving the problem of initial parameter setting deviations and increasing the parameter verification pass rate to 92%, laying a precise foundation for subsequent optimization. The dynamic interference real-time adaptation unit, based on a three-level threshold mechanism and adaptive compensation algorithm, triggers corresponding compensation strategies through real-time data comparison, generating accurate compensation parameters. The core is hierarchical response and rapid adaptation, effectively addressing interference such as load fluctuations and vibrations, with a compensation response delay ≤5ms, parameter adjustment accuracy reaching ±0.01A, and a 35% improvement in the anti-interference capability of the magnetic levitation system. The optimization result verification unit integrates effect quantification and threshold judgment techniques, comparing the actual state with the expected effect to calculate the optimization index and accurately evaluate the effectiveness of the parameters. Quantitative verification and result feedback ensure that the optimized parameters meet process requirements, providing a reliable basis for the iterative decision-making process.

[0039] Example 8: Based on Example 6, the driving parameter optimization submodule provided in this embodiment of the invention includes: The parameter initialization unit is used to input real-time data into the adaptive adjustment decision program, taking the characteristic state data and reorganized constraints as input; analyze the mapping relationship between magnetic levitation drive parameters and tooling motion effect, and output the initial optimized parameter set; verify the actual parameter set to determine whether it is qualified; if it is not qualified, re-inference is performed. The dynamic interference real-time adaptation unit is used to compare real-time monitoring data with preset thresholds and activate the human interference compensation mechanism; the preset three-level threshold library automatically activates the compensation strategy and generates compensation parameters when the detection status is under warning / exceeding the limit range. The optimization result verification unit is used to compare the implementation status data and expected effects after the adaptive adjustment decision program is executed with the optimized parameters, and analyze the optimization effect index; if the optimization index is less than the preset value, it is determined to be effective.

[0040] In the above embodiments, the parameter initialization unit employs feature mapping and iterative inference techniques to input real-time data and reorganization constraints into the decision-making program, constructing a mapping relationship between driving parameters and motion effects, generating an initial parameter set, and verifying optimization. The key technical feature lies in dynamic mapping modeling and closed-loop inference, solving the problem of initial parameter setting deviations and laying a precise foundation for subsequent optimization. The dynamic interference real-time adaptation unit, based on a three-level threshold mechanism and adaptive compensation algorithm, triggers corresponding compensation strategies through real-time data comparison, generating precise compensation parameters. The core features are graded response and rapid adaptation, effectively addressing interference such as load fluctuations and vibrations, with a compensation response delay ≤5ms, parameter adjustment accuracy reaching ±0.01A, and a 35% improvement in the anti-interference capability of the magnetic levitation system. The optimization result verification unit integrates effect quantification and threshold judgment techniques, comparing the actual state with the expected effect to calculate the optimization index and accurately evaluate the effectiveness of the parameters. The key technical feature lies in quantitative verification and result feedback, ensuring that the optimized parameters meet process requirements and providing a reliable basis for the iterative decision-making process.

[0041] Example 9: like Figure 4 As shown, based on Embodiment 1, the adaptive adjustment magnetic levitation component 3 provided in this embodiment of the invention includes: The adaptive rule adjustment and transformation module 31 is used to receive the optimal result output by the adaptive adjustment decision program, transform the abstract decision logic into structured adjustment rules, set the rule execution weight based on the production task priority, and bind the variables in the rules to the hardware parameters of the magnetic levitation equipment. The equipment control instruction generation module 32 is used to convert the optimized drive parameters into a preset unified format; to aggregate and reorganize the sub-task sequence of the process decomposition to generate an instruction sequence with timestamps; and to perform format verification on the generated instructions. The instruction issuance and real-time feedback module 33 is used to collect the status of the device after executing the instruction in real time and compare it with the expected effect of the instruction; if it exceeds the preset threshold, it triggers the adaptive adjustment rule; for instructions that are executed abnormally, it calls the rule engine again to generate a correction instruction based on the feedback data.

[0042] In the above embodiments, the adaptive rule adjustment and transformation module 31 adopts rule engine and parameter binding technology to transform the decision results into structured rules, set weights based on task priority, and associate them with device hardware parameters. The technical features lie in the visualization of decision logic and hardware adaptation, solving the problem of implementing abstract decisions and ensuring that the adjustment strategy matches the device capabilities. The device control command generation module 32 uses protocol conversion and timing orchestration technology to transform parameters into standardized commands, generate timestamped sequences, and verify the format. The core is command standardization and precise timing control, eliminating device communication barriers, achieving 100% command format compliance, and timing errors ≤10ms, ensuring consistency across multiple devices. The command issuance and real-time feedback module 33 uses closed-loop control and dynamic correction technology to compare the execution effect with expectations. When the performance exceeds the limit, adjustment rules are triggered and correction commands are generated. Real-time verification and rapid iteration improve the system's fault tolerance, with anomaly response latency ≤50ms, ensuring stable operation of the magnetic levitation equipment.

[0043] Example 10: like Figure 5 As shown, based on Examples 1-9, the intelligent switching method for adaptive flexible production lines based on magnetic levitation drive provided by this invention includes the following steps: Step S100: Real-time acquisition of the current tooling's spatial position, attitude parameters, magnetic field strength, and levitation gap of the magnetic levitation system; simultaneously, acquisition of magnetic levitation production line data such as production task switching instructions and processing requirements of the products being processed. Step S200: Extract feature parameters from the magnetic levitation data, combine them with a preset process database, and analyze the tooling reconfiguration scheme required for the task; construct an adaptive adjustment decision program based on the analyzed tooling reconfiguration scheme and real-time status data, and analyze the optimal tooling switching and magnetic levitation drive parameters. Step S300: The analysis results of the adaptive adjustment decision program are used to preset adaptive adjustment rules; a decision instruction is generated according to the adaptive adjustment rules, and the decision instruction is sent to the magnetic levitation work drive controller to adjust the parameters of the magnetic levitation equipment.

[0044] In the above embodiments, step S100 of this embodiment employs multi-source sensor fusion and real-time communication technology to simultaneously collect equipment data such as tooling spatial position, attitude parameters, and magnetic field strength, as well as production instructions, achieving high-precision synchronization of heterogeneous data. The technical feature lies in full-dimensional state perception and real-time data assurance, solving the fragmentation problem of traditional data acquisition and providing a complete data foundation for subsequent decision-making, increasing data efficiency to 99%. Step S200 integrates feature engineering and reinforcement learning technologies to extract key parameters and match them with the process database, constructing an adaptive decision-making program to optimize switching paths and driving parameters. The core is intelligent analysis and dynamic optimization, overcoming the problem of multi-tooling collaboration conflicts, improving the efficiency of reconfiguration scheme generation by 40%, and achieving parameter optimization accuracy of ±0.02mm, meeting the rapid response requirements of flexible production. Step S300 employs a rule engine and closed-loop control technology to convert decision results into standardized instructions and issue them, correcting parameters through real-time feedback. The technical feature lies in decision implementation and dynamic control, ensuring precise equipment execution, with instruction response latency ≤50ms, improving the stability of the magnetic levitation system by 35%, achieving "contactless" rapid reconfiguration of the production line, and significantly improving production flexibility.

[0045] Figure 6 A block diagram of an exemplary electronic device suitable for implementing embodiments of the present invention has been provided.

[0046] The electronic device may include a central processing unit / microprocessor / main control chip, etc. 4; and a storage medium 5, coupled to the central processing unit / microprocessor / main control chip, etc. 4, and storing computer-executable instructions therein for performing the steps of various methods of embodiments of the present invention when executed by the processor.

[0047] The central processing unit / microprocessor / main control chip, etc., can include, but are not limited to, one or more processors or microprocessors.

[0048] Storage medium 5 may include, but is not limited to, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (e.g., hard disk, floppy disk, solid-state drive, removable disk, CD-ROM, DVD-ROM, Blu-ray disc, etc.).

[0049] In addition, the electronic device may also include (but is not limited to) a data bus 6, an input / output bus / external bus / device bus 7, a display 8, and input / output devices 9 (e.g., keyboard, mouse, speaker, etc.).

[0050] The central processing unit / microprocessor / main control chip, etc. 4 can communicate with external devices (8, 9, etc.) via I / O bus 7 through wired or wireless network (not shown).

[0051] The storage medium 5 may also store at least one computer-executable instruction for performing the steps of various functions and / or methods in the embodiments described herein when the central processing unit / microprocessor / main control chip, etc., 4 is running.

[0052] In one embodiment, the at least one computer-executable instruction may also be compiled into or comprise a software product, wherein one or more computer-executable instructions are executed by a processor to perform the steps of the various functions and / or methods in the embodiments described herein.

[0053] Figure 7 A schematic diagram of a computer-readable storage medium according to an embodiment of the present invention.

[0054] like Figure 7 The non-transitory computer-readable storage medium 11 stores instructions, such as computer-readable instructions 10. When the computer-readable instructions 10 are executed by a processor, the various methods described above can be performed. The non-transitory computer-readable storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and / or cache memory. Non-transitory non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. For example, the non-transitory computer-readable storage medium 11 can be connected to a computing device such as a computer, and then, when the computing device executes the computer-readable instructions 10 stored on the computer-readable storage medium 11, the various methods described above can be performed.

[0055] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0056] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0057] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0058] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for executing all or part of the steps of the methods of the various embodiments of this invention through a computer device (which may be a personal computer, server, or network device, etc.). The aforementioned storage medium includes: USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, optical disks, and other media capable of storing program code.

[0059] Example 11: like Figure 8 As shown, based on Embodiments 1-10, the intelligent switching system for adaptive flexible production lines based on magnetic levitation drive provided in this embodiment of the invention includes: a tooling spatial position sensor 12, a tooling attitude sensor 13, a magnetic field strength sensor 14, a suspension strength detector 15, a suspension gap detector 16, a production task switching instruction interface 17, a tooling reconfiguration scheme analyzer 18, a processing product process requirement database 19, a magnetic levitation data feature parameter extractor 20, an adaptive adjustment decision program 21, an optimal tooling switching analyzer 22, a magnetic levitation drive parameter analyzer 23, an adaptive adjustment rule presetter 24, a decision instruction issuer 25, a magnetic levitation work start controller 26, and a magnetic levitation equipment parameter adjuster 27; The left side is divided into a data acquisition layer, which includes a tooling spatial position sensor 1, a tooling attitude sensor 13, a magnetic field strength sensor 14, a suspension strength detector 15, and a suspension gap detector 16. The middle part is divided into a data processing and decision-making layer, which includes a production task switching instruction interface 17, a tooling reconfiguration scheme analyzer 18, a processing product process requirement database 19, a magnetic levitation data feature parameter extractor 20, an adaptive adjustment decision program 21, an optimal tooling switching analyzer 22, a magnetic levitation drive parameter analyzer 23, an adaptive adjustment rule presetter 24, and a decision instruction issuer 25. The right side is divided into an execution drive layer, which includes a magnetic levitation work start controller 26 and a magnetic levitation equipment parameter adjuster 27. The data acquisition layer transmits data to the data processing and decision-making layer through unidirectional signals. The data processing and decision-making layer transmits data to the execution drive layer through unidirectional control instructions.

[0060] Example 12: This embodiment is a specific application process of embodiment 11, and the details are as follows: With the fixture stationary and moving along the X-axis at a speed of 5 mm / s, the ambient temperature is 20±2℃ and the humidity is 40%-60%. The fixture is fixed at a position of 100 mm X-axis, 80 mm Y-axis, and 0° attitude. Data is continuously collected for 10 minutes, recording one set of position, attitude, magnetic field strength, and suspension gap data every 1 second, for a total of 600 sets. The fixture is then controlled to move along the X-axis from 50 mm to 250 mm, with data collected synchronously, repeated 3 times. The industrial control computer loads a preset process database and inputs different production task switching commands. The switching commands "Product A→B", "B→C", "C→D", and "D→E" are input sequentially, with each set of commands repeated 5 times. The time taken for the decision-making process to analyze the solution is recorded. Three random selections are then performed. The system executes a set of instructions, comparing the deviations of the tooling positioning parameters and magnetic levitation drive parameters output by the decision-making program with the preset optimal parameters in the database; it sets the magnetic levitation gap reference value to 0.8mm, the tooling target positioning position to 200mm on the X-axis, 100mm on the Y-axis, and an attitude of 3°; it sends a switching command, records the tooling motion trajectory using a high-speed camera, and monitors the positioning accuracy in real time using a laser displacement sensor, repeating this process 5 times; it adjusts the tooling load and tests the fluctuation range of the magnetic levitation gap; it simulates a multi-product switching scenario on a flexible production line, selecting three typical working conditions: normal switching, variable load switching, and interference switching; and it enables "magnetic levitation drive adaptive" switching. The "intelligent switching device" operates in all modules. In each working condition, the switching task is completed using the experimental group, control group 1, and control group 2, and the switching time for each cycle is recorded. A power analyzer is used to collect the total energy consumption for each working condition, and the unit switching energy consumption is calculated. A laser displacement sensor is used to record the tooling positioning accuracy for each working condition, and the average deviation is calculated. Under interference conditions, the suspension gap fluctuation range and mechanical gap fluctuation of the three devices are recorded to evaluate anti-interference capabilities. Matlab is used to calculate the data variation coefficient to evaluate sensor acquisition stability and suspension gap stability. Positioning accuracy = measured final position - target position; the average and maximum values ​​of each test group are taken. SPSS 26.0 is used to perform an independent samples t-test on the switching time and energy consumption of the experimental and control groups to verify whether the differences are statistically significant.

[0061] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An adaptive flexible production line intelligent switching device based on magnetic suspension driving, characterized in that, Comprise: Magnetic suspension data acquisition component for real-time acquisition of the spatial position, attitude parameters of the current tooling, magnetic field intensity and suspension gap of the magnetic suspension system, and simultaneously obtaining the production task switching instructions and processing product process requirements and other magnetic suspension production line data; Optimal magnetic suspension parameter component for extracting characteristic parameters from the magnetic suspension data, combining the preset process database, and analyzing the tooling reconfiguration scheme required by the task; Based on the analyzed tooling reconfiguration scheme and real-time state data, an adaptive adjustment decision program is constructed to analyze the optimal tooling switching and magnetic suspension driving parameters; The adaptive adjustment magnetic suspension component is used to form a decision instruction according to the adaptive adjustment rule, and the decision instruction is sent to the magnetic suspension working drive controller to adjust the magnetic suspension equipment parameters.

2. The adaptive flexible production line intelligent switching device based on magnetic levitation driving according to claim 1, characterized in that, The magnetic suspension data acquisition component comprises: A tooling state data acquisition module for real-time acquisition of spatial coordinate data of tooling, rotation, pitch and yaw angle parameters of tooling, extraction of tooling appearance features and positioning mark information through sensors, correlation through time stamp, and formation of tooling state data set; A magnetic suspension data acquisition module for acquiring magnetic field intensity data of the magnetic suspension coil, obtaining coil operating current and voltage and other operating parameters through the communication structure of the magnetic suspension drive controller; receiving production task switching instructions, product process requirements to be processed, and coordination signals of upstream and downstream equipment; A data preprocessing module for smoothing the collected position and magnetic field intensity, and eliminating outliers; converting heterogeneous data collected by different types of sensors into a unified format, adding data collection timestamps, sensor names and tooling labels, etc.

3. The adaptive flexible production line intelligent switching device based on magnetic levitation driving according to claim 1, characterized in that, The optimal magnetic suspension parameter component comprises: A verification module for extracting characteristic parameters from tooling spatial coordinates, attitude angles and magnetic field intensity, etc.; analyzing information in the production task switching instructions, extracting target product model, production rhythm requirements, processing precision standards, etc. Task characteristics; verify the characteristics with the preset process database; Wherein, the characteristic parameters include real-time position deviation value of the tooling, magnetic field uniformity coefficient and suspension gap fluctuation amplitude, etc.; the process database includes tooling configuration scheme corresponding to different products, magnetic suspension system operating parameter threshold, processing process standard and other data; A tooling reconfiguration module for determining the target layout of tooling reconfiguration according to the verified reference scheme and current production demand; decomposing the tooling reconfiguration process into several sub-tasks, determining the execution subject, execution timing and key control nodes of each sub-task; An adaptive adjustment module for constructing an adaptive adjustment decision program based on the analyzed tooling reconfiguration scheme and real-time state data; taking tooling real-time position, magnetic field intensity, suspension gap and other state data as inputs of the adaptive adjustment decision program, and taking magnetic suspension driving parameters and tooling moving speed as outputs of the adaptive adjustment decision program.

4. The adaptive flexible production line intelligent switching device based on magnetic levitation driving according to claim 3, characterized in that, The verification module comprises: The feature extraction submodule is configured to extract feature parameters from multi-dimensional data such as tooling space coordinates, attitude angles, and magnetic field strengths; analyze information in the production task switching instruction to extract task features such as target product model, production rhythm requirement, and processing precision standard; The process database matching submodule is configured to call a preset process database; search for the most similar historical process scheme in the process database according to the extracted task features to obtain a preliminary tooling reorganization reference scheme and a secondary process driving parameter range; The matching result verification submodule is configured to verify the reference scheme searched; combine real-time information such as the tooling inventory state of the current production line, the operation load of the magnetic suspension equipment, and the upstream and downstream equipment cooperation capability to determine whether the reference scheme is suitable for the current production scene; if there is a conflict, mark the conflict point and trigger a scheme adjustment warning.

5. The adaptive flexible production line intelligent switching device based on magnetic levitation driving according to claim 3, characterized in that, The work reorganization module includes: The target layout planning submodule is configured to determine a tooling reorganization target layout according to the verified reference scheme and current production demand; construct a production line virtual scene; import the space coordinates and attitude parameters of the target tooling into the virtual scene to plan a moving path of each tooling from the current position to the target position; The reorganization flow disassembly submodule is configured to disassemble the tooling reorganization into a plurality of subtasks, determine an execution subject, an execution time sequence, and a control node of each subtask, and perform task scheduling and distribution of the execution order of each tooling for the multi-tooling cooperative reorganization scene; The scheme verification submodule is configured to simulate position deviation, magnetic field change, and equipment response delay in the tooling movement in the virtual scene to analyze key indicators such as reorganization completion time and energy consumption.

6. The adaptive flexible production line intelligent switching device based on magnetic levitation driving according to claim 5, characterized in that, The scheme verification submodule includes: The index calculation benchmark unit is configured to set an energy consumption index benchmark from the time interval from the time when the first tooling starts to move to the time when the last tooling reaches the target position and completes attitude locking; import the index threshold of the process database; The multi-working-condition simulation unit is configured to simulate the movement process of each tooling in the virtual scene, analyze real-time speed and acceleration data, record time and energy consumption dimensions, simulate a multi-working-condition parallel movement scene, and record the same; The index quantization analysis unit is configured to calculate total time by aggregating simulation data, accumulate total energy consumption by aggregating energy consumption of each tooling at each stage, establish a scatter plot to analyze the correlation between time and energy consumption, compare total time, total energy consumption, time distribution proportion, and energy consumption fluctuation coefficient with preset thresholds, and output an unqualified index to the adaptive adjustment decision program if a certain index exceeds the threshold.

7. The adaptive flexible production line intelligent switching device based on magnetic levitation driving according to claim 3, characterized in that, The adaptive adjustment module includes: The adaptive adjustment decision program construction submodule is configured to construct an adaptive adjustment decision program based on the analyzed tooling reorganization scheme and real-time state data, and train the adaptive adjustment decision program through a data set; The driving parameter optimization submodule is configured to optimize the magnetic suspension driving of the adaptive adjustment decision program in combination with the analyzed tooling reorganization scheme and implementation state data; preset a parameter adjustment threshold for possible interference factors, and automatically trigger a parameter compensation mechanism when detecting that the state data exceeds the threshold. The optimization result output submodule is configured to encapsulate the optimized tool switching path, magnetic suspension driving parameter and decision logic into a decision instruction set in a unified format, and transmit the decision instruction set to a cloud platform; and store the optimization result to a process database. 8.The adaptive flexible production line intelligent switching device based on magnetic levitation driving according to claim 6, wherein, The driving parameter optimization submodule comprises: The parameter initialization unit is configured to input real-time data to the adaptive adjustment decision program, with the featureized state data and recombined constraints as inputs; analyze the mapping relationship of the magnetic suspension driving parameter to the tool movement effect, and output an initial optimization parameter set; verify the initial optimization parameter set, and determine whether it is qualified; if not, re-reasoning is performed; The dynamic interference real-time adaptation unit is configured to compare real-time monitoring data with a preset threshold, and start a human interference compensation mechanism; a three-level threshold library is preset, and when the detection state is in an early warning / over-limit range, a compensation strategy is automatically activated, and compensation parameters are generated; The optimization result verification unit is configured to compare the implementation state data after the execution of the optimization parameter by the adaptive adjustment decision program with the expected effect, and analyze an optimization effect index; if the optimization index is less than a preset value, it is determined to be effective.

9. The adaptive flexible production line intelligent switching device based on magnetic levitation driving according to claim 1, characterized in that, The adaptive adjustment magnetic suspension assembly comprises: The adaptive rule adjustment conversion module is configured to receive the optimal result output by the adaptive adjustment decision program, convert the abstract decision logic into a structured adjustment rule, and set a rule execution weight based on the production task priority; and bind the variables in the rule with the hardware parameters of the magnetic suspension equipment; The device control instruction generation module is configured to convert the optimized driving parameter into a preset unified format, generate a time-stamped instruction sequence by collecting the subtask timing of the disassembled recombination process, and perform format verification on the generated instruction; The instruction issuing and real-time feedback module is configured to compare the state after the execution of the instruction by the equipment with the expected effect of the instruction in real time; if the preset threshold is exceeded, the adaptive adjustment rule is triggered; and for the instruction with execution exception, a correction instruction is generated by re-calling the rule engine according to the feedback data.

10. The adaptive flexible production line intelligent switching method based on magnetic levitation driving according to any one of claims 1 to 9, characterized in that, The adaptive flexible production line intelligent switching method based on magnetic suspension driving comprises the following steps: Real-time acquisition of the spatial position, attitude parameter of the current tool and the magnetic field intensity and suspension gap of the magnetic suspension system, as well as the production task switching instruction issued and the process requirements of the processed product and other magnetic suspension production line data; Feature parameters are extracted from the magnetic suspension data, and a recombination scheme of the tool required by the task is analyzed in combination with a preset process database; based on the analyzed tool recombination scheme and real-time state data, an adaptive adjustment decision program is constructed, and the optimal tool switching and magnetic suspension driving parameter are analyzed; The analysis result of the adaptive adjustment decision program is preset with an adaptive adjustment rule; a decision instruction is formed according to the adaptive adjustment rule, and the decision instruction is issued to a magnetic suspension working driving controller to adjust the magnetic suspension equipment parameters.

Images