A real-time linkage method for digital twin models driven by cyber-physical fusion

Abstract

The present invention discloses a real-time linkage method for digital twin models driven by information-physical fusion, which specifically relates to the technical field of digital twin collaborative control of industrial automation production lines. It is used to solve the problems of instruction conflicts and control failures caused by the mismatch between virtual model parameters and the dynamic capabilities of physical equipment in the existing technology. It collects equipment status and material flow data in real time, extracts equipment dynamic degradation parameters to generate capability attenuation feature vectors, combines implicit process conflict path detection and resource preemption probability simulation, builds a collaborative optimization model of equipment health and process scheduling, and generates a control instruction set containing dynamic capability constraints. After verifying and screening instructions through physical constraint matching, the parameters are closed-loop corrected based on the execution results and the model is iterated to achieve adaptive matching between virtual instructions and physical equipment capabilities. It significantly improves the reliability of digital twin control instructions and the stability of the production line, and avoids the risk of abnormal shutdown caused by over-limit instructions.

Description

Technical Field

[0001] The present invention relates to the technical field of digital twin collaborative control of industrial automation production lines. More specifically, the present invention relates to a real-time linkage method for digital twin models driven by information-physical fusion. Background Art

[0002] In the field of industrial automation, digital twin technology can be used to build virtual mapping models of physical production lines, enabling real-time monitoring and optimization of the production process. In existing technologies, cyber-physical systems (CPS) drive digital twin models by collecting data such as equipment status and material flow, and generate control instructions based on model simulation results to optimize production line operations. However, when implementing closed-loop control between virtual models and physical equipment, one-way or simplified two-way interaction mechanisms are typically relied upon. Specifically, the optimization instructions generated by the virtual model (such as equipment operating parameter adjustments and path planning) are often based on idealized assumptions and do not fully consider the dynamic state changes of the physical equipment (such as mechanical wear and loss of execution accuracy). This leads to a deviation between the control instructions and the actual execution capabilities of the equipment.

[0003] Against this backdrop, existing technologies have the following flaws: when a digital twin model sends optimization instructions to a physical device through closed-loop feedback, the instructions may exceed the device's current physical conditions (such as mechanical structure limits and dynamic response thresholds) due to a dynamic mismatch between the model parameters and the device's actual state, leading to control instruction conflicts. For example, the virtual model requires a robotic arm to perform a task at a specific acceleration, but the actual device cannot respond to the instruction due to aging, resulting in control failure or even abnormal shutdown of the device. Such problems are particularly prominent in bidirectional control scenarios requiring high frequency and strong real-time performance, seriously affecting the reliability and practicality of digital twin technology in industrial control. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a real-time linkage method of a digital twin model driven by information-physical fusion to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A real-time linkage method for digital twin models driven by cyber-physical fusion includes the following steps:

[0007] S1. Real-time collection of equipment status data and material flow data from the physical production line and synchronization to the digital twin model;

[0008] S2. Extracting dynamic degradation parameters of equipment in the physical production line based on equipment status data, and generating equipment capability attenuation feature vectors based on the dynamic degradation parameters;

[0009] S3. Based on dynamic degradation parameters and material flow data, the constraint satisfaction problem model is used to identify implicit process conflict paths, and the Monte Carlo tree search is used to simulate resource preemption probability to generate material scheduling priority coefficients.

[0010] S4. Input the equipment capacity attenuation feature vector and the material scheduling priority coefficient into the digital twin model to generate an optimization control instruction set that includes the equipment dynamic capacity constraints;

[0011] S5. Perform physical constraint matching verification on the optimized control instruction set. If the verification passes, select the valid control instructions and send them to the physical production line.

[0012] S6. Update the dynamic degradation parameters and material scheduling priority coefficients based on the execution results of the effective control instructions by the physical production line.

[0013] In a preferred embodiment, real-time collection of equipment status data and material flow data of the physical production line and synchronization to the digital twin model include:

[0014] Real-time collection of equipment status data on the physical production line, including equipment vibration amplitude, temperature gradient, and operating current parameters;

[0015] Real-time collection of material flow data on the physical production line, including material position coordinates, motion velocity vector, and transmission direction angle;

[0016] Synchronize equipment status data and material flow data to the digital twin model, where the synchronization process includes timestamp alignment of multi-source data and unified spatial coordinate system conversion.

[0017] In a preferred embodiment, extracting dynamic degradation parameters of equipment in a physical production line based on equipment status data and generating equipment capability attenuation feature vectors based on the dynamic degradation parameters include:

[0018] Based on the equipment vibration amplitude, temperature gradient and working current parameters, the equipment vibration time domain characteristic peak, temperature gradient change rate and current fluctuation amplitude-frequency characteristics are extracted as dynamic degradation parameters;

[0019] Calculate the vibration degradation weight coefficient based on the difference between the equipment vibration time domain characteristic peak value and the preset vibration reference value;

[0020] Determine the temperature degradation influencing factor based on the correlation between the temperature gradient change rate and the equipment's heat dissipation efficiency;

[0021] The current load attenuation index is generated by combining the ratio of the current fluctuation amplitude-frequency characteristics and the rated load of the equipment;

[0022] The vibration degradation weight coefficient, temperature degradation influence factor and current load attenuation index are processed by data dimensionality reduction to generate the equipment capacity attenuation feature vector.

[0023] In a preferred embodiment, based on dynamic degradation parameters and material flow data, implicit process conflict paths are identified through a constraint satisfaction problem model, and resource preemption probability is simulated in combination with a Monte Carlo tree search to generate a material scheduling priority coefficient, including:

[0024] Based on dynamic degradation parameters and material flow data, a process conflict detection model that includes equipment health constraints and material spatiotemporal constraints is constructed;

[0025] Traverse the production line process topology network through the constraint satisfaction problem model to identify hidden process conflict paths that violate equipment health constraints or material spatiotemporal constraints;

[0026] Based on Monte Carlo tree search, the resource preemption action is simulated in the implicit process conflict path, and the resource preemption success probability of each implicit process conflict path is calculated;

[0027] The probability of successful resource preemption is weighted and fused with the severity weight of the implicit process conflict path to generate the material scheduling priority coefficient.

[0028] In a preferred embodiment, the severity weight is dynamically adjusted based on the correlation strength between the device capability degradation feature vector and the conflicting path.

[0029] In a preferred embodiment, the equipment capacity decay feature vector and the material scheduling priority coefficient are input into the digital twin model to generate an optimization control instruction set containing the equipment dynamic capacity constraints, including:

[0030] Input the equipment capacity attenuation feature vector and material scheduling priority coefficient into the digital twin model;

[0031] Define the device dynamic capability constraints based on the device capability attenuation feature vector, including the upper limit of the device vibration time domain characteristic peak, the temperature gradient change rate tolerance range, and the current load attenuation index threshold;

[0032] Combining the equipment dynamic capacity constraints and material scheduling priority coefficients, a multi-objective optimization algorithm is used to generate equipment operating parameter adjustment instructions and material path planning instructions;

[0033] Conflict resolution between equipment operating parameter adjustment instructions and material path planning instructions. This includes dynamically adjusting instruction priorities and eliminating instructions that violate material time and space constraints.

[0034] Filter instruction combinations that meet the dynamic capability constraints of the equipment and the synchronization requirements of the production line rhythm to form an optimized control instruction set.

[0035] In a preferred embodiment, the optimized control instruction set is verified for physical constraint matching, and when the verification passes, valid control instructions are screened and sent to the physical production line, including:

[0036] Physical constraint matching verification is performed on the optimized control instruction set, including calculation of trajectory deviation rate under dynamic load sensitivity based on dynamic degradation parameters, and analysis of kinematic chain joint angle safety margins based on production line layout topology.

[0037] When the trajectory deviation rate is lower than the trajectory deviation rate threshold and the safety margin meets the standard, the physical constraint matching verification is determined to have passed, and the valid control instructions are screened and sent to the physical production line;

[0038] During the screening process, instructions with excessive trajectory deviation rates or substandard safety margins are eliminated, and instructions that meet the dynamic capability constraints of the equipment are retained.

[0039] In a preferred embodiment, the trajectory deviation rate under dynamic load sensitivity is calculated by the difference between the real-time device load rate and the command expected load, and the trajectory deviation rate threshold is dynamically adjusted according to the device capacity attenuation characteristic vector.

[0040] In a preferred embodiment, the safety margin of the kinematic chain joint angle is calculated by the difference between the current joint angle and the limit angle of the mechanical structure, and the safety margin is met when the difference is greater than a preset safety threshold.

[0041] In a preferred embodiment, the dynamic degradation parameters and the material scheduling priority coefficients are updated according to the execution results of the effective control instructions by the physical production line, including:

[0042] Obtain the execution result data of the physical production line for effective control instructions, including the actual load rate of the equipment, joint angle deviation value and process beat synchronization error;

[0043] Update dynamic degradation parameters based on execution result data, including correcting the vibration time domain characteristic peak value by the actual load rate of the equipment, correcting the temperature gradient change rate by the joint angle deviation value, and correcting the current load attenuation index by the process beat synchronization error;

[0044] Regenerate the equipment capability degradation feature vector based on the updated dynamic degradation parameters;

[0045] Combining process beat synchronization errors with historical execution results, the material scheduling priority coefficient is updated through a regression model.

[0046] The updated equipment capacity attenuation feature vector and material scheduling priority coefficient are synchronized to the digital twin model to generate the optimization control instruction set for the next cycle.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. Through the deep integration of equipment status and material flow data, a dynamic optimization system for virtual-reality interaction is established to achieve a precise match between production line control instructions and the actual execution capabilities of the equipment. The system deeply couples equipment health degradation parameters with the identification process of process conflict paths to generate an optimized instruction set containing dynamic capability constraints in real time. Through the multi-dimensional representation of the equipment capability degradation feature vector, the combined impact of mechanical wear, heat dissipation degradation, and load attenuation is quantified to ensure that the current performance boundaries of the equipment are fully considered when generating instructions. A two-dimensional verification mechanism combined with physical constraints is used to screen feasible instructions based on dynamic load sensitivity and kinematic safety margins, effectively avoiding the issuance of over-limit instructions due to insufficient equipment capabilities, significantly improving the reliability of virtual-reality interaction and the success rate of instruction execution.

[0049] 2. Through cross-correction of multi-source execution data (such as load deviation and joint angle error), dynamic degradation parameters reflect the evolution trend of equipment performance in real time, and the material scheduling priority coefficient is adaptively optimized based on historical scheduling effects to ensure that the instruction set of the next cycle is deeply aligned with the real-time status of the production line; this enables the system to maintain efficient and stable operation when equipment ages, working conditions fluctuate, or production line layout is adjusted, reducing the frequency of manual intervention and providing a highly robust closed-loop control paradigm for digital twin applications in complex industrial scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a flow chart of a real-time linkage method for digital twin models driven by cyber-physical fusion according to the present invention;

[0051] Figure 2 A flowchart of physical constraint matching verification for optimizing the control instruction set of the present invention. DETAILED DESCRIPTION

[0052] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0053] Example: Figure 1 The present invention provides a real-time linkage method for a digital twin model driven by cyber-physical fusion, comprising the following steps:

[0054] S1. Real-time collection of equipment status data and material flow data from the physical production line and synchronization to the digital twin model;

[0055] S2. Extracting dynamic degradation parameters of equipment in the physical production line based on equipment status data, and generating equipment capability attenuation feature vectors based on the dynamic degradation parameters;

[0056] S3. Based on dynamic degradation parameters and material flow data, the constraint satisfaction problem model is used to identify implicit process conflict paths, and the Monte Carlo tree search is used to simulate resource preemption probability to generate material scheduling priority coefficients.

[0057] S4. Input the equipment capacity attenuation feature vector and the material scheduling priority coefficient into the digital twin model to generate an optimization control instruction set that includes the equipment dynamic capacity constraints;

[0058] S5. Perform physical constraint matching verification on the optimized control instruction set. If the verification passes, select the valid control instructions and send them to the physical production line.

[0059] S6. Update the dynamic degradation parameters and material scheduling priority coefficients based on the execution results of the effective control instructions by the physical production line.

[0060] S1. Real-time collection of equipment status data and material flow data from the physical production line and synchronization to the digital twin model. The specific implementation is as follows:

[0061] Real-time data collection of equipment status on the physical production line, including equipment vibration amplitude, temperature gradient, and operating current parameters. Equipment vibration amplitude is acquired using accelerometers installed on key moving parts of the equipment. For example, a triaxial accelerometer is deployed at the joints of a robotic arm to collect vibration signals at a preset sampling frequency, and the maximum amplitude of the vibration signal is used as the equipment vibration amplitude. The temperature gradient is measured using an array of thermocouples distributed across the surface of the equipment. Specifically, the temperature difference between adjacent thermocouples on the surface of the equipment is calculated. For example, thermocouples are arranged 10 cm apart on the motor housing, and the real-time temperature difference between adjacent thermocouples is used as the local temperature gradient. Operating current parameters are acquired in real time using a current transformer connected in series in the equipment power supply circuit. For example, a Hall effect current sensor is installed on the servo motor power cable to collect the effective current value at a millisecond frequency and record the instantaneous peak current.

[0062] Real-time collection of material flow data from the physical production line, including material position coordinates, motion velocity vectors, and transmission direction angles. Material position coordinates are obtained through the combined positioning of laser rangefinders and RFID tags deployed on both sides of the production line conveyor belt. For example, laser rangefinders are installed at the conveyor belt entrance and exit. Combined with the unique identification of the RFID tag on the material carrier, the real-time position coordinates of the material in the production line plane coordinate system are calculated using triangulation. The motion velocity vector is obtained by dividing the difference between two consecutive frames of material position coordinates by the time interval. For example, if material position coordinates are collected at a frequency of 10 frames per second, the coordinate change between adjacent frames is divided by 0.1 seconds to obtain the plane motion velocity vector. The transmission direction angle is calculated using the tangent direction of the material motion trajectory. For example, three consecutive frames of material position coordinates are fitted to the motion trajectory curve, and the angle between the tangent direction of the current frame position and the production line reference coordinate system is calculated as the transmission direction angle.

[0063] Synchronize device status data and material flow data to the digital twin model. This synchronization process includes timestamp alignment of multi-source data and conversion to a unified spatial coordinate system. Timestamp alignment is achieved through a time synchronization protocol deployed between the sensor nodes and the digital twin model. For example, using the IEEE 1588 Precision Time Protocol (PTP), the local clocks of accelerometers, thermocouples, current transformers, and laser ranging sensors are synchronized with the global clock of the digital twin model server, ensuring that the timestamp deviation of all data is less than 1 millisecond.

[0064] The unified spatial coordinate system conversion is achieved through a pre-calibrated production line reference coordinate system. Specifically, the local coordinate system data collected by each sensor is converted into global coordinate system data with the production line starting point as the origin, the conveyor belt extension direction as the X-axis, and the vertical direction as the Y-axis. For example, the relative relationship between the installation position of the laser ranging sensor and the production line reference coordinate system is calibrated by a laser tracker, and a coordinate transformation matrix is ​​established. The laser ranging data is multiplied by the transformation matrix to obtain the global coordinates.

[0065] During synchronization, the equipment's vibration amplitude, temperature gradient, operating current parameters, material position coordinates, motion velocity vector, and transmission direction angle are unified in data format. For example, the vibration amplitude is converted to millimeters per second squared, the temperature gradient is converted to degrees Celsius per centimeter, the current parameters are converted to amperes, the position coordinates are converted to millimeters, the velocity vector is converted to millimeters per second, and the transmission direction angle is converted to radians. These data are then packaged into structured data frames and transmitted to the digital twin model. The structured data frames contain a data category identifier, a timestamp, a numeric field, and a checksum. For example, using JSON format, the data category identifiers are "vibration," "temperature_gradient," and "current." The checksum is a CRC-32 cyclic redundancy check code, which is used to detect data errors during transmission.

[0066] During the timestamp alignment process, if a sensor node's clock offset exceeds a preset threshold, a clock resynchronization mechanism is triggered. For example, if the clock deviation of a thermocouple node exceeds 5 milliseconds, the digital twin model server sends a clock calibration command to the node, realigning its local clock with the global clock. If a sensor's installation position shifts during spatial coordinate system conversion, the calibration process is re-executed. For example, if a laser ranging sensor's installation angle shifts due to mechanical vibration, the calibration process is manually triggered, and the laser tracker is used to re-measure the transformation matrix parameters relative to the production line's reference coordinate system.

[0067] The collection and synchronization of equipment status and material flow data is performed using real-time stream processing. For example, using Apache Kafka as the data middleware, sensor nodes push data to a Kafka message queue. The digital twin model subscribes to the message queue and processes the data stream according to time windows. The real-time stream processing window is set to 100 milliseconds. Every 100 milliseconds, the received equipment vibration amplitude, temperature gradient, operating current parameters, material position coordinates, motion velocity vector, and transmission direction angle are timestamp aligned and spatial coordinate system transformed. The processed data is then batch-written to the digital twin model's real-time database.

[0068] S2. Extract the dynamic degradation parameters of the equipment in the physical production line based on the equipment status data, and generate the equipment capability attenuation feature vector based on the dynamic degradation parameters. The specific implementation is as follows:

[0069] Based on the equipment vibration amplitude, temperature gradient and working current parameters, the equipment vibration time domain characteristic peak, temperature gradient change rate and current fluctuation amplitude-frequency characteristics are extracted as dynamic degradation parameters. The equipment vibration time domain characteristic peak is obtained by time domain waveform analysis of the equipment vibration amplitude signal. Specifically, the maximum absolute value of the vibration signal is calculated in a continuous time window. The time window length is set according to an integer multiple of the equipment operation cycle. For example, the window length of a rotating equipment is set based on a single-turn cycle. The temperature gradient change rate is calculated by dividing the temperature gradient difference between adjacent time points by the time interval. The time interval is dynamically adjusted according to the production line working conditions. For example, the interval is shortened during the high-load stage of the equipment to increase the monitoring frequency. The current fluctuation amplitude-frequency characteristics are obtained by performing spectral analysis on the current signal to extract the amplitude of the main frequency component. The spectral analysis is implemented using fast Fourier transform. The main frequency component is the frequency component whose energy proportion in the spectrum exceeds the preset threshold.

[0070] The vibration degradation weight coefficient is calculated based on the difference between the equipment's time-domain characteristic vibration peak and a preset vibration baseline value. The preset vibration baseline value is calibrated using vibration data from the equipment's initial healthy state. The calibration process involves collecting and averaging the vibration time-domain characteristic peak values ​​under no-load and rated-load conditions. The vibration degradation weight coefficient is normalized by dividing the difference by the baseline value. This normalization process constrains the weight coefficient to a range between 0 and 1, where 0 indicates no degradation and 1 indicates reaching the preset critical degradation state.

[0071] The temperature degradation impact factor is determined based on the correlation between the temperature gradient change rate and the device's heat dissipation efficiency. The device's heat dissipation efficiency is calculated by multiplying the radiator surface area by the cooling medium flow rate. The radiator surface area is determined based on the device's structural design parameters, and the cooling medium flow rate is monitored in real time using a flow sensor. The temperature degradation impact factor is calculated by taking the ratio of the temperature gradient change rate to the heat dissipation efficiency. Before calculating this ratio, the temperature gradient change rate is filtered using a sliding average filter to eliminate noise.

[0072] The current load attenuation index is generated by combining the ratio of the current fluctuation amplitude-frequency characteristic to the device's rated load. The device's rated load is determined based on the device's nameplate parameters or statistical peak values ​​from historical operating data. For example, the 99th percentile of the current RMS value over 30 consecutive days of operating data is used as the rated load. The current load attenuation index is calculated by dividing the current fluctuation amplitude-frequency characteristic by the rated load and performing a logarithmic transformation. The logarithmic transformation is used to linearize the attenuation trend.

[0073] The vibration degradation weight coefficient, temperature degradation impact factor, and current load attenuation index are processed for data dimensionality reduction to generate a device capacity attenuation feature vector. This data dimensionality reduction utilizes principal component analysis (PCA), which includes the following steps: Normalizing the vibration degradation weight coefficient, temperature degradation impact factor, and current load attenuation index using the standardization formula of subtracting the mean from each parameter and dividing by the standard deviation; Calculating the covariance matrix of the standardized parameters; Extracting the eigenvectors corresponding to the maximum eigenvalues ​​of the covariance matrix as the principal component directions; Projecting the original parameters onto the principal component directions to generate one-dimensional eigenvectors. The PCA direction update cycle is synchronized with the equipment maintenance cycle; for example, the covariance matrix is ​​recalculated quarterly to adapt to changes in equipment degradation trends.

[0074] The mapping relationship between the equipment's capacity degradation eigenvector and dynamic degradation parameters is established through offline calibration. This process involves collecting dynamic degradation parameters under different equipment health states and generating eigenvectors. A regression model is then used to fit the functional relationship between the eigenvectors and the actual load capacity. The regression model is fitted using the least squares method, and robust weighting is applied to abnormal data points during the fitting process to reduce the impact of outliers.

[0075] If inconsistent dimensions or overflow in input parameters are detected during data dimensionality reduction, a data normalization review mechanism is triggered. For example, if the current load attenuation exponent exceeds the valid range of logarithmic transformation, the accuracy of the current fluctuation amplitude-frequency characteristics is recalibrated. The trigger for updating the equipment capacity attenuation feature vector is tied to production line task switching events. For example, when a workpiece is changed or the production cycle is adjusted, the feature vector is immediately updated to ensure model synchronization.

[0076] A fault-tolerance mechanism is incorporated into the calculation of the vibration degradation weight coefficient, temperature degradation impact factor, and current load attenuation index. For example, if the temperature gradient change rate returns an invalid value due to a sensor failure, the historical average value is used instead to calculate the temperature degradation impact factor. The status flags of the fault-tolerance mechanism are linked to the digital twin model to ensure that invalid data does not trigger misjudgments.

[0077] S3. Based on dynamic degradation parameters and material flow data, the constraint satisfaction problem model is used to identify implicit process conflict paths. The Monte Carlo tree search is combined to simulate resource preemption probability to generate material scheduling priority coefficients. The specific implementation is as follows:

[0078] Based on dynamic degradation parameters and material flow data, a process conflict detection model is constructed that incorporates equipment health constraints and material spatiotemporal constraints. Equipment health constraints are defined by dynamic degradation parameters, specifically ensuring that the equipment's vibration time-domain characteristic peak does not exceed a preset vibration threshold, that the temperature gradient change rate does not exceed the allowable range of heat dissipation efficiency, and that the current load attenuation index does not fall below the equipment's minimum load capacity. The preset vibration threshold is dynamically adjusted based on the equipment's factory calibration value, that the allowable range of heat dissipation efficiency is calculated by multiplying the equipment's heat dissipation surface area by the cooling medium flow rate, and that the equipment's minimum load capacity is determined by the statistical quantile of historical operating data.

[0079] Material spatiotemporal constraints are defined using material flow data. These constraints include ensuring that material position coordinates are within the tolerance range of process topology network nodes, and that the velocity vector and transmission direction angle meet the time window requirements for inter-process connection. The node tolerance range is determined by calibrating the physical boundaries of process nodes using laser ranging sensors, and the connection window is calculated by matching the material transmission speed with the process cycle time. The constraint variables in the process conflict detection model include equipment health status variables and material spatiotemporal status variables. Constraints are logically ANDed combinations of equipment health constraints and material spatiotemporal constraints. This logical AND combination indicates that both constraints must be met for verification to pass.

[0080] Using a constraint satisfaction problem model, the production line process topology network is traversed to identify implicit conflicting process paths that violate equipment health constraints or material spatiotemporal constraints. The production line process topology network consists of process nodes and connecting edges. Nodes represent processing steps, and edges represent material flow directions. Node and edge attributes include process duration, equipment load rate, and material buffer capacity. The traversal process begins at the starting process node and searches for paths along the connecting edges in a depth-first manner. Constraint satisfaction is verified for the equipment health state variables and material spatiotemporal state variables along each path. Verification includes checking whether the vibration time-domain characteristic peak exceeds a threshold, whether the temperature gradient change rate is within the allowable heat dissipation range, whether the current load attenuation index exceeds the minimum load capacity, whether the material position coordinates are within the node tolerance range, and whether the velocity vector and direction angle meet the time window. Implicit conflicting process paths are defined as those in which at least one node or edge violates an equipment health constraint or a material spatiotemporal constraint. For example, the vibration time-domain characteristic peak of the robot process node in a path exceeds a preset vibration threshold, or the material transfer direction angle corresponding to an edge exceeds the process connection time window, preventing the material from reaching the next process node on time.

[0081] Based on a Monte Carlo tree search (MCS), resource preemption actions are simulated within implicit conflicting process paths, and the success probability of resource preemption for each implicit conflicting process path is calculated. Resource preemption actions include equipment priority adjustment, material buffer preemption, and process queue reordering. The simulation process is iteratively executed within the digital twin model. The MCS simulation strategy consists of a selection phase, an expansion phase, a simulation phase, and a backtracking phase. The selection phase selects nodes to be explored based on the path conflict severity weights. The expansion phase generates possible resource preemption action combinations. The simulation phase executes the actions and records whether the resource is successfully preempted. The backtracking phase updates node statistics. The resource preemption success probability is the ratio of the number of successful simulations to the total number of simulations. For example, if a certain implicit conflicting process path is simulated 1000 times and 800 of them successfully resolve the conflict by adjusting equipment priority or preempting buffers, the success probability is 0.8. The number of simulations is adaptively adjusted based on the number of conflicting paths. For example, if five conflicting paths are detected, each path is simulated 200 times, and if ten conflicting paths are detected, each path is simulated 100 times. The total number of simulations is kept below 1000 to ensure real-time performance.

[0082] The probability of successful resource preemption is weighted and fused with the severity weight of the implicit process conflict path to generate a material scheduling priority coefficient. The severity weight is dynamically adjusted based on the correlation strength between the equipment capability decay feature vector and the conflict path. This correlation strength is determined by calculating the Pearson correlation coefficient between the equipment capability decay feature vector and the health constraint parameters of the conflict path. For example, if the equipment capability decay feature vector value is 0.65 and the ratio of the vibration time-domain characteristic peak value of a conflict path to the preset vibration threshold is 1.5, the Pearson correlation coefficient is 0.8, and the severity weight is 0.8 × 1.5 = 1.2.

[0083] The material scheduling priority coefficient is equal to the probability of successful resource preemption multiplied by the severity weight. For example, if the probability of successful resource preemption is 0.8 and the severity weight is 1.2, the material scheduling priority coefficient is 0.8 × 1.2 = 0.96. The dynamic adjustment of the severity weight is synchronized with the update cycle of the equipment capacity decay feature vector. For example, the equipment capacity decay feature vector is received every 10 seconds, its correlation strength with each conflicting path is recalculated, and the weight is updated. The weighted fusion weight allocation strategy is dynamically optimized based on the real-time load status of the production line. For example, the weight of the probability of successful resource preemption is increased during peak periods, and the proportion of the severity weight is increased during off-peak periods. The dynamic optimization strategy is trained using historical data. The training process includes collecting material scheduling priority coefficients and actual scheduling performance data under different load conditions, and determining the optimal weight allocation ratio through regression analysis.

[0084] It's worth noting that before calculating the Pearson correlation coefficient between the device capability degradation eigenvector and the conflict path health constraint parameter, both need to be normalized to eliminate dimensional differences. This normalization is achieved through the following steps: collecting the numerical distribution of the device capability degradation eigenvector from historical data and calculating its mean and standard deviation; collecting the numerical distribution of the conflict path health constraint parameter (such as the ratio of the vibration time domain characteristic peak to a preset threshold) from historical data and calculating its mean and standard deviation; subtracting the historical mean from the current device capability degradation eigenvector value and dividing it by the historical standard deviation to obtain the normalized eigenvector value; and subtracting the historical mean from the conflict path health constraint parameter value and dividing it by the historical standard deviation to obtain the normalized parameter value. For example, the historical mean of the equipment capability degradation characteristic vector is 0.5, with a standard deviation of 0.2. When the current value is 0.65, the normalized value is (0.65 - 0.5) / 0.2 = 0.75. The mean of the vibration time-domain characteristic peak ratio of the conflict path is 1.0, with a standard deviation of 0.3. When the current value is 1.5, the normalized value is (1.5 - 1.0) / 0.3 ≈ 1.67. This normalized data is used to calculate the Pearson correlation coefficient to ensure comparability of parameters of different dimensions.

[0085] The constraint update mechanism of the process conflict detection model is linked to the equipment maintenance records. For example, when a key component of the equipment is replaced, the preset vibration threshold is reset according to the health baseline value of the new component. The new baseline value is obtained through no-load and rated load tests. The tolerance range of the material's time and space constraints is dynamically adjusted according to the production line layout. For example, after adding a process node, the tolerance range of the material position coordinates is recalibrated by the laser ranging sensor. The calibration process includes scanning the physical boundaries of the node in the absence of material and calculating the safety margin. The simulation results of the Monte Carlo tree search are stored in the historical database of the digital twin model to optimize subsequent simulation strategies. For example, if the success rate of a resource preemption action in the historical simulation is less than 30%, its selection priority will be reduced in the subsequent simulation. The cleanup cycle of the historical database is synchronized with the production line scheduling cycle. For example, after the end of each day's production, the data of the day is cleared and the weekly statistical average is retained to initialize the simulation of the next day.

[0086] The severity weight anomaly detection mechanism for implicit process conflict paths is implemented by monitoring the weight change rate. For example, when the weight of a path increases by more than 50% within 1 minute, a manual review process is triggered to ensure that the weight mutation is not caused by equipment degradation factors. The anomaly detection results are fed back to the digital twin model, which adjusts the association strength calculation parameters or excludes abnormal data points based on the review results. For example, when the review confirms that the weight mutation is caused by sensor noise, the input value of the equipment capability attenuation feature vector in the association strength calculation is reset. A timeout interrupt mechanism is introduced into the simulation execution process of resource preemption actions. For example, if a single simulation exceeds the preset time threshold, it is forcibly terminated and marked as failed to avoid system resource exhaustion due to deadlock. The timeout threshold is set to 100 milliseconds based on the real-time requirements of the production line.

[0087] The conflict prioritization mechanism for equipment health constraints and material spatiotemporal constraints is implemented through a pre-set rule base. For example, equipment health conflicts are prioritized over material spatiotemporal conflicts. The rule base is customized based on equipment type and production line process requirements. For example, in precision machining scenarios, the weight of equipment health constraints is increased by 50%. The priority classification results are used to optimize the Monte Carlo tree search selection strategy, for example, by increasing the number of simulations for high-priority conflicting paths by 20%. Rule base updates are synchronized with equipment maintenance logs. For example, after each maintenance session, the priority classification ratio is adjusted based on the latest equipment status.

[0088] Step S3 identifies implicit process conflict paths through the constraint satisfaction problem model, combines Monte Carlo tree search to simulate resource preemption probability, and generates material scheduling priority coefficients. Compared with traditional scheduling methods that rely on static rules or single equipment status parameters, it is difficult to dynamically adapt to the coupled conflict between equipment degradation and material flow. This step accurately locates the conflict path through multi-dimensional constraint modeling (equipment health + material time and space), and simulates preemption actions based on Monte Carlo tree search to solve the instruction conflict problem caused by equipment capacity degradation and resource competition; deeply integrates dynamic degradation parameters with material time and space data, and uses dynamic weights (severity weights) to reflect the impact of equipment health on the conflict path in real time, avoiding scheduling deviations caused by static thresholds; when equipment ages or production line load fluctuates, the material scheduling priority coefficient more accurately matches the actual execution capability of the physical equipment, significantly reducing the risk of instruction conflict and improving the reliability and real-time performance of virtual-reality synchronization optimization.

[0089] S4. Input the equipment capacity attenuation feature vector and the material scheduling priority coefficient into the digital twin model to generate an optimization control instruction set containing the equipment dynamic capacity constraints. The specific implementation is as follows:

[0090] Input the equipment capacity degradation feature vector and the material scheduling priority coefficient into the digital twin model. The equipment capacity degradation feature vector, generated in step S2, represents the overall degradation level of the equipment; the material scheduling priority coefficient, generated in step S3, represents the scheduling priority of conflicting process paths. This input process is implemented through the digital twin model's data interface, which maps the feature vector and priority coefficient into model internal optimization variables. For example, the equipment capacity degradation feature vector is mapped into the equipment health status variable, and the material scheduling priority coefficient is mapped into the process node weight parameter.

[0091] Based on the device's capability attenuation eigenvector, dynamic capability constraints are defined for the device, including the upper limit of the device's vibration time-domain characteristic peak value, the tolerance range for the temperature gradient change rate, and the current load attenuation index threshold. The upper limit of the device's vibration time-domain characteristic peak value is dynamically adjusted based on the device's current capability attenuation eigenvector. For example, when the eigenvector value is 0.65, the upper limit is set to 85% of the initial threshold. The tolerance range for the temperature gradient change rate is determined by the difference between the device's heat dissipation efficiency and the current temperature gradient change rate. For example, when the heat dissipation efficiency is 1000 and the current change rate is 2 degrees Celsius per centimeter per minute, the tolerance range is ±10%. The current load attenuation index threshold is set based on the statistical quantiles of the device's rated load and historical operating data. For example, the 95th percentile of the load attenuation index in historical data is used as the threshold.

[0092] Combining the equipment's dynamic capability constraints with the material scheduling priority coefficient, a multi-objective optimization algorithm is used to generate equipment operating parameter adjustment instructions and material path planning instructions. The multi-objective optimization algorithm's optimization objectives include maximizing production line efficiency, minimizing equipment degradation rates, and balancing conflicting process priorities. The optimization variables include equipment processing speed, cooling system power, and material path node selection. For example, the robot's processing speed can be adjusted so that its vibration time-domain characteristic peak does not exceed an upper limit, while allocating shorter material paths to high-priority process nodes. Constraint relaxation strategies are used during the optimization process to address conflicting objectives, such as allowing equipment to temporarily exceed its limit for a certain period of time to ensure the synchronization of critical process beats.

[0093] Conflict resolution is performed between equipment operating parameter adjustment instructions and material path planning instructions. This includes dynamically adjusting instruction priorities and eliminating instructions that violate material spatiotemporal constraints. Dynamically adjusting instruction priorities is updated in real time based on the material scheduling priority coefficient. For example, when the priority coefficient of a process node is 0.96, the corresponding path planning instruction priority is increased by 20%. Instructions that violate material spatiotemporal constraints are eliminated by verifying whether the material position coordinates are within the node tolerance range and whether the transmission direction angle meets the time window. For example, if a instruction causes the material position to exceed the tolerance range by 5 mm or the direction angle deviation exceeds 10 degrees, the instruction is directly eliminated.

[0094] Filter instruction combinations that meet the equipment's dynamic capability constraints and production line tact synchronization requirements to form an optimized control instruction set. Filtering conditions include ensuring that the equipment's vibration time-domain characteristic peak does not exceed the upper limit, the temperature gradient change rate is within the tolerance range, the current load attenuation index is higher than the threshold, and that the material path planning complies with the process tact time window. The generation frequency of the optimized control instruction set is synchronized with the production line tact, for example, generating an instruction set every 5 seconds to adapt to dynamic changes in the production line. The instruction set's encoding format is compatible with the physical equipment control protocol, such as using the Modbus protocol to encapsulate instruction parameters to ensure that they can be directly sent to the PLC for execution.

[0095] The update cycle for equipment dynamic capability constraints is synchronized with the generation cycle of the equipment capability degradation feature vector. For example, feature vectors are received and constraint thresholds are recalculated every 10 seconds. The tolerance range of material spatiotemporal constraints is dynamically adjusted based on the real-time status of the production line. For example, when conveyor speed fluctuations are detected, the tolerance range of material position coordinates is automatically expanded to 8 mm to reduce the false rejection rate. The weight parameters of the multi-objective optimization algorithm are adaptively adjusted based on the production line load status. For example, during peak periods, the focus is on production line efficiency objectives, while during off-peak periods, the focus is on equipment degradation objectives. The weight adjustment rules are implemented through a combination of offline training and online reinforcement learning.

[0096] A command fallback mechanism is introduced during conflict resolution. For example, if three consecutive generated command sets fail to meet constraints, the system automatically switches to a conservative strategy, limiting the equipment load rate to 70% of the rated value and extending the node spacing along the material path. The command fallback mechanism's status marker is linked to the digital twin model's exception log for subsequent maintenance and analysis. Historical data on optimized control command sets is stored in the digital twin database and used to train the weight model for the multi-objective optimization algorithm. For example, the system collects command set and actual execution performance data from the past 24 hours, optimizing the objective weight distribution through regression analysis.

[0097] Step S4 generates an optimized control instruction set by integrating the equipment capability attenuation characteristic vector and the material scheduling priority coefficient. Compared with the traditional instruction generation method that relies on static equipment parameters or a single optimization target, it is difficult to adapt to the coupling requirements of equipment dynamic degradation and real-time scheduling of production lines. The instruction feasible domain is defined based on the equipment dynamic capability constraints (vibration, temperature, current thresholds), and the multi-objective optimization algorithm is combined to balance the production line efficiency, equipment health and process priority to ensure that the instruction set not only meets the current capability limitations of the equipment but also optimizes the material scheduling logic; the equipment health degradation parameters and process conflict priorities are deeply integrated, and the mismatch between instructions and equipment capabilities is solved through dynamic constraints and conflict resolution mechanisms; when the equipment ages or the production line load fluctuates, the generated instruction set accurately matches the execution capability of the physical equipment, avoids the issuance of over-limit instructions, significantly reduces the risk of abnormal downtime, and improves the real-time and reliability of virtual-real linkage.

[0098] Figure 2 A flowchart of the physical constraint matching verification of the optimized control instruction set of the present invention is given. The physical constraint matching verification is performed on the optimized control instruction set. When the verification passes, the valid control instructions are screened and sent to the physical production line. The specific implementation is as follows:

[0099] The optimized control instruction set is verified for physical constraint matching. This includes calculating the trajectory deviation rate under dynamic load sensitivity based on dynamic degradation parameters and analyzing the kinematic chain joint angle safety margins based on the production line layout topology. The dynamic degradation parameters are provided by the equipment capability degradation eigenvector generated in step S2, and the production line layout topology is defined by the process topology network in step S3. The trajectory deviation rate under dynamic load sensitivity is calculated based on the difference between the real-time equipment load rate and the instruction expected load. The real-time equipment load rate is obtained by the effective value of the operating current collected by the current transformer. The instruction expected load is determined by analyzing the equipment operating parameters in the optimized control instruction using the digital twin model. For example, if a command requires the robot arm to operate at 90% of its rated load, but the real-time load rate is only 75% of the rated value due to equipment aging, the trajectory deviation rate is (90% - 75%) = 15%. The trajectory deviation rate threshold is dynamically adjusted based on the equipment capability degradation eigenvector. The adjustment rule is: when the eigenvector value is less than 0.5, the threshold is reduced by 3% for every 0.1 eigenvalue; when the eigenvector value is greater than or equal to 0.5, the threshold is reduced by 6% for every 0.1 eigenvalue. For example, when the eigenvector value is 0.4, the threshold is 22%, and when the eigenvector value is 0.6, the threshold is 14%.

[0100] The safety margin for kinematic chain joint angles is calculated by comparing the current joint angle with the mechanical limit angle. The current joint angle is acquired in real time by an encoder, and the mechanical limit angle is set based on the equipment design parameters. The safety margin is met only when this difference exceeds a preset safety threshold. The preset safety threshold is determined by multiplying the minimum spacing between adjacent process nodes in the production line layout topology by the equipment's mechanical tolerance. For example, if the minimum spacing between adjacent nodes is 500 mm and the equipment's mechanical tolerance is 0.5%, the safety threshold is 500 × 0.5% = 2.5 mm, which translates to a joint angle tolerance of 2 degrees. When calculating the difference, if the current joint angle is 85 degrees and the mechanical limit angle is 90 degrees, the safety margin is 5 degrees. The safety margin is met when the preset safety threshold reaches 2 degrees.

[0101] When the trajectory deviation rate is lower than the trajectory deviation rate threshold and the safety margin meets the standard, the physical constraint matching verification is determined to have passed, and the valid control instructions are screened and sent to the physical production line. During the screening process, instructions with excessive trajectory deviation rates or substandard safety margins are eliminated. For example, when the trajectory deviation rate of a certain instruction is 18% and exceeds the threshold of 15%, or the safety margin of a certain joint is only 1 degree and lower than the threshold of 2 degrees, it is directly eliminated. The retained instructions must also meet the dynamic capability constraints of the equipment, including that the peak value of the equipment vibration time domain characteristic does not exceed the upper limit, the temperature gradient change rate is within the tolerance range, and the current load attenuation index is higher than the threshold. The digital twin model sorts the screened valid control instructions by priority and encapsulates them into instruction frames that can be parsed by the physical device. For example, the instruction parameters are encoded using the Modbus protocol and sent to the PLC controller for execution via industrial Ethernet.

[0102] The dynamic adjustment of the trajectory deviation rate threshold is synchronized with the update cycle of the equipment capability degradation feature vector. For example, the feature vector is received and the threshold is recalculated every 10 seconds. The preset safety margin threshold is dynamically adjusted based on the real-time operating conditions of the production line. For example, when the production line switches to high-precision machining mode, the safety threshold of all process nodes is uniformly reduced by 30%. An instruction priority backtracking mechanism is introduced during the screening process. For example, when a high-priority instruction is eliminated due to insufficient safety margin, the digital twin model is automatically triggered to regenerate an alternative instruction to ensure the continuity of critical processes.

[0103] Intermediate results of physical constraint matching verification are stored in the digital twin database and used to optimize subsequent verification strategies. For example, if the trajectory deviation rate of a certain type of instruction is consistently below a threshold of 50%, the verification frequency can be gradually reduced to once every 30 seconds to reduce the computational load. If sensor data anomalies are detected during verification, such as a sudden change in current transformer readings exceeding the historical fluctuation range, the data review process is triggered, suspending instruction issuance until the anomaly is resolved.

[0104] A redundant check mechanism is introduced to calculate the safety margin of joint angles in the kinematic chain. For example, joint angles and end-effector position coordinates are collected simultaneously, and the angle data consistency is verified through inverse kinematics. If the deviation between the angle and coordinate conversion exceeds the tolerance, the angle data is deemed invalid and re-collected. The redundant check results are fed back to the digital twin model, which adjusts the filter parameters for joint angle collection or triggers the sensor calibration process based on the deviation value.

[0105] Among them, the joint angle tolerance is converted into linear distance according to the arm length of the equipment kinematic chain. For example, if the arm length is 1 meter, the angle tolerance of 2 degrees corresponds to the end linear tolerance of 1×sin(2°)≈34.9 mm, ensuring that the physical meaning of spatial constraint verification is clear.

[0106] Step S5 verifies and filters effective control instructions through physical constraint matching. Compared with traditional instruction verification that relies on fixed thresholds or single equipment parameters, it is difficult to dynamically adapt to execution capability fluctuations caused by equipment degradation and changes in production line layout. This step dynamically adjusts the trajectory deviation rate threshold based on the equipment capability attenuation feature vector, and sets safety margin conditions according to the production line layout topology to achieve collaborative verification of equipment health status and spatial constraints, deeply integrates dynamic degradation parameters with production line spatial topology, and solves the problem of precise matching of instructions and equipment dynamic capabilities through two-dimensional verification (load trajectory + kinematic safety). When equipment performance degrades or production line layout is adjusted, the verification conditions are adapted to the actual capabilities of the physical equipment in real time to avoid control failure caused by the issuance of over-limit instructions, while improving the real-time and reliability of virtual-real linkage, ensuring that the optimized instruction set meets both the current capability limitations of the equipment and the production line space safety requirements.

[0107] S6. Update the dynamic degradation parameters and material scheduling priority coefficients based on the execution results of the effective control instructions by the physical production line. The specific implementation is as follows:

[0108] Obtain the execution result data of the physical production line for valid control instructions, including the actual equipment load rate, joint angle deviation, and process beat synchronization error. The actual equipment load rate is obtained by collecting the real-time effective value of the operating current through the current transformer. For example, if the expected load of a certain instruction is 80% of the rated value and the actual load rate is 75%, the load rate deviation in the execution result data is 5%. The joint angle deviation is calculated by the difference between the actual joint angle recorded by the encoder and the expected angle of the instruction. For example, if the expected angle of the instruction is 90 degrees and the actual angle is 88 degrees, the deviation is 2 degrees. The process beat synchronization error is calculated by the difference between the material arrival timestamp and the planned time of the process node. For example, if a process is scheduled to start at 10:00:00 and the actual material arrival time is 10:00:03, the synchronization error is 3 seconds.

[0109] Dynamic degradation parameters are updated based on execution result data, including correcting the vibration time-domain characteristic peak using the device's actual load rate, correcting the temperature gradient change rate using the joint angle deviation, and correcting the current load attenuation index using the process beat synchronization error. The vibration time-domain characteristic peak is corrected by lowering the vibration peak threshold by the load rate deviation ratio when the actual load rate is lower than the commanded expected load. For example, a 5% deviation corresponds to a 3% reduction in the threshold. The temperature gradient change rate is corrected by adjusting the heat dissipation efficiency calculation weight based on the joint angle deviation. For example, a 2-degree deviation reduces the weight by 0.1, expanding the temperature gradient change rate tolerance range. The current load attenuation index is corrected by converting the process beat synchronization error into a load attenuation compensation coefficient. For example, a 3-second error corresponds to a compensation coefficient of 0.95. The current load attenuation index is adjusted to the original value multiplied by 0.95.

[0110] The equipment capability attenuation eigenvector is regenerated based on the updated dynamic degradation parameters. The regeneration process uses the same data dimensionality reduction method as step S2. For example, the corrected vibration time domain characteristic peak value, temperature gradient change rate, and current load attenuation index are input into the principal component analysis model to calculate a new equipment capability attenuation eigenvector. The covariance matrix of the principal component analysis model is recalculated based on the updated dynamic degradation parameters to ensure that the eigenvector reflects the latest health status of the equipment. For example, when the corrected vibration peak value is 1.0 mm / s2, the temperature gradient change rate is 1.5 degrees Celsius per centimeter per minute, and the current load attenuation index is 0.8, the generated eigenvector value is 0.7, indicating that the overall degradation degree of the equipment is 70%.

[0111] The material scheduling priority coefficient is updated using a regression model, combining process beat synchronization errors with historical execution performance. The regression model uses historical process beat synchronization errors as input variables and priority coefficient adjustments as output variables. The model coefficients are obtained by fitting historical data using the least squares method. For example, if the historical mean synchronization error for a process node is 2 seconds, the regression model outputs an increase of 0.1 in the priority coefficient for that node; if the error is 5 seconds, the coefficient is decreased by 0.2. The model training data includes the execution errors and priority coefficient adjustment records for all process nodes over the past 24 hours, and the model is refitted every 6 hours to adapt to dynamic changes in the production line.

[0112] The updated equipment capacity decay feature vector and material scheduling priority coefficient are synchronized with the digital twin model to generate the next cycle's optimized control instruction set. This synchronization process is implemented through the digital twin model's data interface, for example, by mapping the feature vector to the equipment health status variable and the priority coefficient to the process node weight parameter. Based on the synchronized parameters, the digital twin model immediately initiates instruction generation for the next cycle, for example, updating the instruction set every 10 seconds to ensure real-time matching with the production line's rhythm. The updated instruction set encoding format is compatible with the physical device protocol, for example, using the OPC UA protocol to encapsulate instruction parameters and transmitting them to the PLC controller via Industrial Ethernet for execution.

[0113] The update cycle for dynamic degradation parameters is tied to production line task switching events. For example, when a production line switches workpiece types, a parameter update is immediately triggered to ensure model synchronization. The regression model for the material scheduling priority coefficient initiates an emergency update when an abnormal error is detected. For example, if a synchronization error of more than 10 seconds occurs three times consecutively at a process node, the model is forced to be refitted and the coefficients adjusted. If sensor data anomalies are detected during the update process, such as a sudden change in current transformer readings exceeding the historical fluctuation range, the parameter update is suspended and the data review process is triggered until the anomaly is resolved and execution continues.

[0114] The process of regenerating the feature vectors for equipment capacity degradation incorporates a redundancy check mechanism. For example, principal component analysis and linear discriminant analysis are used simultaneously for dimensionality reduction. If the results differ by more than 5%, manual review is initiated. Redundancy check logs are stored in the digital twin database for subsequent model optimization. Adjustment records for material scheduling priority coefficients are linked to production line maintenance logs. For example, if the priority coefficient of a node is continuously lowered, equipment maintenance recommendations are automatically generated and pushed to the operation and maintenance terminal.

[0115] Step S6 maps the timing error data into a nonlinear adjustment of the priority coefficient through a regression model based on the process beat synchronization error and historical execution results, breaking through the traditional static weight allocation rules. At the same time, the update of the dynamic degradation parameters is not an independent correction, but rather establishes an associated correction model for vibration, temperature, and current parameters through the cross-influence of the joint angle deviation value and the load rate deviation. For example, the joint angle deviation is not only used to adjust the temperature gradient change rate, but also affects the compensation coefficient of the current load attenuation index through spatial tolerance conversion, forming a multi-physics field coupling iterative mechanism for the health status of the equipment. The regeneration of the equipment capacity attenuation feature vector does not simply repeat the initial dimensionality reduction process, but introduces a redundant verification mechanism to compare the consistency of the results of principal component analysis and linear discriminant analysis to ensure that the feature vector after parameter update can not only reflect the real-time degradation degree of the equipment, but also is compatible with the safety margin requirements of the production line topology layout. This collaborative design of multi-algorithm cross-validation and dynamic parameter feedback solves the problem of feature distortion caused by data noise or model drift in traditional methods. In addition, the real-time binding mechanism between priority coefficient updates and production line task switching events enables the model to adaptively adjust parameters without manual intervention when switching processing scenarios. For example, in high-precision processing mode, it automatically reduces the safety threshold and increases the priority weight of key process nodes. Traditional methods usually require presetting multiple working modes and manually switching parameters.

[0116] The solution involved in this embodiment has built a real-time linkage mechanism with deep integration of virtual and real through a complete technical chain of multi-source data collection, dynamic degradation modeling, conflict path identification, instruction generation verification and closed-loop feedback. Traditional digital twin control methods usually rely on one-way instruction issuance or static model parameters, which are difficult to adapt to the coupled changes of dynamic equipment degradation and real-time scheduling of production lines, and lack cross-domain parameter collaborative optimization capabilities. This embodiment is based on the deep fusion of multi-physical field data such as equipment vibration, temperature, and current, and extracts the equipment capacity attenuation feature vector to replace the traditional single health indicator. Through the collaboration of the constraint satisfaction problem model and the Monte Carlo tree search, the equipment health status and material spatiotemporal constraints are embedded in the process conflict detection, realizing the dynamic identification of implicit paths and the accurate simulation of resource preemption probability.

[0117] Furthermore, physical constraint matching verification goes beyond simple threshold determination. Instead, it integrates dynamic load sensitivity and kinematic chain safety margins. The trajectory deviation rate threshold dynamically adjusts with the equipment's health status, and the safety margin condition is deeply linked to the production line layout topology, transcending the limitations of traditional fixed thresholds or empirical rules. The instruction generation and update mechanism integrates equipment dynamic capability constraints, process priorities, and historical execution results into a unified optimization framework, enabling adaptive iteration of the instruction set.

[0118] What is particularly critical is that the update of dynamic degradation parameters and priority coefficients in the closed-loop feedback is not an independent operation. Instead, through the cross-influence of multi-source data such as joint angle deviation and beat synchronization error, a correlation correction model of vibration-temperature-current parameters is established, and the priority weight allocation strategy is optimized based on the historical data of process conflicts, thereby realizing dynamic calibration and adaptive optimization of the execution capabilities of virtual models and physical equipment. For example, when the joint angle deviation exceeds the limit, the vibration threshold is simultaneously lowered and the heat dissipation efficiency weight is increased to avoid system fragmentation caused by independent correction of a single parameter. At the same time, the priority weight allocation strategy constructed based on the historical data of process conflicts analyzes the spatiotemporal characteristics of high-frequency conflict paths, dynamically adjusts the material scheduling rules and equipment load distribution ratio, so that the optimized instruction set can adapt to complex working conditions such as production line processing beat fluctuations and equipment performance degradation. It effectively solves the defect that model parameters in traditional virtual-real linkage lag behind physical state changes, and drives parameter iteration through data closed loop to ensure that the digital twin model always accurately maps the real capability boundaries of the equipment, thereby avoiding execution risks in the control instruction generation stage and realizing the upgrade from a one-way instruction issuance ecosystem to a two-way dynamic collaboration mode.

[0119] The calculations involved in the embodiments are all dimensionless numerical calculations, and the preset parameters and thresholds in the calculations are set by those skilled in the art according to actual conditions.

[0120] It should be noted that the present invention can be deployed on the device itself to implement embedded applications, and can also be run on a PC or other terminal with a user interface, thereby meeting various hardware environments and usage requirements.

[0121] The above embodiments can be implemented in whole or in part via software, hardware, firmware, or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in the embodiments of this application are fully or partially performed. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0122] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0123] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules is only a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0124] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, and may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected to achieve the purpose of this embodiment according to actual needs.

[0125] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0126] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0127] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

[0128] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A real-time linkage method for digital twin models driven by cyber-physical fusion, characterized in that: The steps include: S1. Real-time collection of equipment status data and material flow data from the physical production line and synchronization to the digital twin model; S2. Extracting dynamic degradation parameters of equipment in the physical production line based on equipment status data, and generating equipment capability attenuation feature vectors based on the dynamic degradation parameters; S3. Based on dynamic degradation parameters and material flow data, the constraint satisfaction problem model is used to identify implicit process conflict paths, and the Monte Carlo tree search is used to simulate resource preemption probability to generate material scheduling priority coefficients. S4. Input the equipment capacity attenuation feature vector and the material scheduling priority coefficient into the digital twin model to generate an optimization control instruction set that includes the equipment dynamic capacity constraints; S5. Perform physical constraint matching verification on the optimized control instruction set. If the verification passes, select the valid control instructions and send them to the physical production line. S6. Update the dynamic degradation parameters and material scheduling priority coefficients based on the execution results of the effective control instructions by the physical production line; The dynamic degradation parameters of the equipment in the physical production line are extracted based on the equipment status data, and the equipment capability attenuation feature vector is generated based on the dynamic degradation parameters, including: Based on the equipment vibration amplitude, temperature gradient and working current parameters, the equipment vibration time domain characteristic peak, temperature gradient change rate and current fluctuation amplitude-frequency characteristics are extracted as dynamic degradation parameters; Calculate the vibration degradation weight coefficient based on the difference between the equipment vibration time domain characteristic peak value and the preset vibration reference value; Determine the temperature degradation influencing factor based on the correlation between the temperature gradient change rate and the equipment's heat dissipation efficiency; The current load attenuation index is generated by combining the ratio of the current fluctuation amplitude-frequency characteristics and the rated load of the equipment; The vibration degradation weight coefficient, temperature degradation impact factor and current load attenuation index are processed for data dimension reduction to generate the equipment capacity attenuation feature vector; Among them, based on dynamic degradation parameters and material flow data, the implicit process conflict path is identified through the constraint satisfaction problem model, and the resource preemption probability is simulated by Monte Carlo tree search to generate the material scheduling priority coefficient, including: Based on dynamic degradation parameters and material flow data, a process conflict detection model that includes equipment health constraints and material spatiotemporal constraints is constructed; Traverse the production line process topology network through the constraint satisfaction problem model to identify hidden process conflict paths that violate equipment health constraints or material spatiotemporal constraints; Based on Monte Carlo tree search, the resource preemption action is simulated in the implicit process conflict path, and the resource preemption success probability of each implicit process conflict path is calculated; The probability of successful resource preemption is weighted and fused with the severity weight of the implicit process conflict path to generate the material scheduling priority coefficient.

2. The real-time linkage method of digital twin models driven by information-physical fusion according to claim 1 is characterized in that: Real-time collection of equipment status data and material flow data from the physical production line and synchronization to the digital twin model, including: Real-time collection of equipment status data on the physical production line, including equipment vibration amplitude, temperature gradient, and operating current parameters; Real-time collection of material flow data on the physical production line, including material position coordinates, motion velocity vector, and transmission direction angle; Synchronize equipment status data and material flow data to the digital twin model, where the synchronization process includes timestamp alignment of multi-source data and unified spatial coordinate system conversion.

3. The real-time linkage method of digital twin models driven by information-physical fusion according to claim 2 is characterized in that: The severity weight is dynamically adjusted based on the correlation strength between the device capability attenuation feature vector and the conflict path.

4. The real-time linkage method of digital twin models driven by information-physical fusion according to claim 1 is characterized in that: The equipment capacity decay feature vector and material scheduling priority coefficient are input into the digital twin model to generate an optimized control instruction set that contains the equipment dynamic capacity constraints, including: Input the equipment capacity attenuation feature vector and material scheduling priority coefficient into the digital twin model; Define the device dynamic capability constraints based on the device capability attenuation feature vector, including the upper limit of the device vibration time domain characteristic peak, the temperature gradient change rate tolerance range, and the current load attenuation index threshold; Combining the equipment dynamic capacity constraints and material scheduling priority coefficients, a multi-objective optimization algorithm is used to generate equipment operating parameter adjustment instructions and material path planning instructions; Conflict resolution between equipment operating parameter adjustment instructions and material path planning instructions. This includes dynamically adjusting instruction priorities and eliminating instructions that violate material time and space constraints. Filter instruction combinations that meet the dynamic capability constraints of the equipment and the synchronization requirements of the production line rhythm to form an optimized control instruction set.

5. The real-time linkage method of digital twin models driven by information-physical fusion according to claim 1 is characterized in that: Perform physical constraint matching verification on the optimized control instruction set. If the verification passes, filter the valid control instructions and send them to the physical production line, including: Physical constraint matching verification is performed on the optimized control instruction set, including calculation of trajectory deviation rate under dynamic load sensitivity based on dynamic degradation parameters, and analysis of kinematic chain joint angle safety margins based on production line layout topology. When the trajectory deviation rate is lower than the trajectory deviation rate threshold and the safety margin meets the standard, the physical constraint matching verification is determined to have passed, and the valid control instructions are screened and sent to the physical production line; During the screening process, instructions with excessive trajectory deviation rates or substandard safety margins are eliminated, and instructions that meet the dynamic capability constraints of the equipment are retained.

6. The real-time linkage method of digital twin models driven by information-physical fusion according to claim 5 is characterized in that: The trajectory deviation rate under dynamic load sensitivity is calculated by the difference between the real-time device load rate and the command expected load, and the trajectory deviation rate threshold is dynamically adjusted according to the device capacity attenuation feature vector.

7. The real-time linkage method of digital twin models driven by cyber-physical fusion according to claim 6 is characterized in that: The safety margin of the kinematic chain joint angle is calculated by the difference between the current joint angle and the limit angle of the mechanical structure. The safety margin is met when the difference is greater than the preset safety threshold.

8. The real-time linkage method of digital twin models driven by information-physical fusion according to claim 1 is characterized in that: Based on the results of the physical production line's execution of effective control instructions, the dynamic degradation parameters and material scheduling priority coefficients are updated, including: Obtain the execution result data of the physical production line for effective control instructions, including the actual load rate of the equipment, joint angle deviation value and process beat synchronization error; Update dynamic degradation parameters based on execution result data, including correcting the vibration time domain characteristic peak value by the actual load rate of the equipment, correcting the temperature gradient change rate by the joint angle deviation value, and correcting the current load attenuation index by the process beat synchronization error; Regenerate the equipment capability degradation feature vector based on the updated dynamic degradation parameters; Combining process beat synchronization errors with historical execution results, the material scheduling priority coefficient is updated through a regression model. The updated equipment capacity attenuation feature vector and material scheduling priority coefficient are synchronized to the digital twin model to generate the optimization control instruction set for the next cycle.

Images