Digital-twin-based device operation state monitoring method and device

Abstract

The application discloses a device running state monitoring method and device based on digital twinning, and relates to the technical field of device running state monitoring. The method comprises the following steps: constructing a digital twinning model of a device in a virtual space based on device parameters; calculating a twinning synchronization state of the digital twinning model of the device at a current time; performing state deduction according to the twinning synchronization state to obtain virtual running data corresponding to each time node in a first future preset time period; calculating a state deviation between current running data of each time node and corresponding virtual running data; constructing a virtual response feature library according to the state deviation; searching for virtual response data matched with a current working condition feature in the virtual response feature library, and obtaining a state evolution trend of the device according to the virtual response data and a virtual evolution state; and calculating an evaluation result according to the state evolution trend and the current running data of the device. The technical scheme provided by the application can improve the reliability of device running state evaluation.

Description

Technical Field

[0001] This application relates to the technical field of equipment operation status monitoring, specifically to a method and device for equipment operation status monitoring based on digital twins. Background Technology

[0002] With the increasing intelligence of industrial equipment, equipment operation status monitoring technology is playing an increasingly important role in ensuring safe equipment operation and preventing failures. Especially in power systems, the operating status of key equipment such as integrated primary and secondary ring main units directly affects power supply reliability, thus requiring real-time and accurate status monitoring and assessment.

[0003] Existing equipment operation status monitoring methods primarily analyze and predict equipment status by collecting equipment operation data and combining it with theoretical or empirical models. These methods can establish simulation models based on design parameters in the early stages of equipment commissioning, and predict the future operating status of the equipment through model extrapolation, thereby achieving early warning.

[0004] However, as equipment continues to operate, its actual physical characteristics change due to factors such as aging, wear, and environmental variations, while the initially established model parameters remain unchanged. This leads to a gradual deviation between the model's predictions and the actual operating state of the equipment. This deviation accumulates and increases with the extension of operating time, causing a continuous decline in the accuracy of model-based state predictions and affecting the reliability of equipment operating state assessments. Summary of the Invention

[0005] This application provides a method and device for monitoring equipment operating status based on digital twins, which can improve the reliability of equipment operating status assessment.

[0006] The first aspect of this application provides a method for monitoring the operating status of equipment based on digital twins, specifically including: Obtain the device parameters and construct a digital twin model of the device in virtual space based on the device parameters; The current operating data of the device is acquired in real time, and the current operating data is mapped to the digital twin model to obtain the twin synchronization state of the digital twin model at the current moment. Based on the twin synchronization state, the state of the digital twin model is extrapolated in the first future preset time period to obtain the virtual operation data corresponding to each time node in the first future preset time period. When time progresses to the first future preset time period, calculate the state deviation between the current running data and the corresponding virtual running data at each time node; The digital twin model is corrected based on the state deviation, and a virtual response feature library is constructed based on the corrected digital twin model; The current operating condition characteristics of the device are obtained, virtual response data matching the current operating condition characteristics are searched in the virtual response feature library, and the state evolution trend of the device in a second future preset time period is obtained based on the virtual response data and the virtual evolution state. The current operating status assessment result of the device is calculated based on the state evolution trend and the current operating data of the device.

[0007] By employing the above technical solution, a digital twin model of the equipment is constructed in virtual space, and the current operating data of the equipment is mapped to the digital twin model in real time, achieving synchronization between the physical equipment and the digital model. This allows the digital twin model to accurately reflect the real-time operating status of the equipment. Through state evolution projection of the digital twin model, virtual operating data for a first preset future time period is obtained. This data is compared with the actual operating data of the equipment as time progresses, calculating the state deviation and promptly identifying differences between the model and the actual operating state. Based on the state deviation, the digital twin model is corrected, enabling the model parameters to dynamically adapt to changes in the physical characteristics of the equipment during long-term operation, thereby maintaining the model's predictive accuracy. By constructing a virtual response feature library and combining it with the current operating characteristics of the equipment, the accumulation and rapid matching of equipment performance degradation patterns under different operating conditions are achieved, thus obtaining the state evolution trend for a second preset future time period. Finally, based on the state evolution trend and the current operating data of the equipment, an accurate assessment of the equipment's operating status is achieved, effectively solving the problem of accumulated deviations between model predictions and actual operating states in existing technologies, and improving the reliability of long-term equipment status monitoring.

[0008] Optionally, the step of performing state extrapolation on the digital twin model based on the twin synchronization state in a first future preset time period to obtain virtual operation data corresponding to each time node in the first future preset time period includes: Extract the current state parameters from the twin synchronization state, and establish a state evolution equation based on the digital twin model and the current state parameters; Obtain the preset operating boundary conditions within the first future preset time period, and divide the first future preset time period into multiple time nodes according to the preset time step; Using the current state parameters as initial conditions and the running boundary conditions as constraints, the state evolution equation is iteratively solved at each of the time nodes to obtain the virtual running data corresponding to each time node in the first future preset time period.

[0009] By employing the aforementioned technical solution, current state parameters are extracted from the digital twin synchronization state, and a state evolution equation is established in conjunction with the digital twin model, providing a mathematical foundation for state prediction. A discretized state prediction framework is established by setting operational boundary conditions and dividing the first preset future time period into multiple time nodes. Using the current state parameters as initial conditions and the operational boundary conditions as constraints, the state evolution equation is iteratively solved, enabling quantitative prediction of the future operating state of the equipment. This gives the state prediction results clear physical meaning and mathematical basis, thereby improving the accuracy and reliability of state prediction.

[0010] Optionally, the step of correcting the digital twin model based on the state deviation includes: Determine whether the state deviation exceeds a preset deviation threshold; When the state deviation exceeds the preset deviation threshold, the correlation between the state deviation and each model parameter in the digital twin model is analyzed to determine the target model parameter that has the greatest impact on the state deviation. Based on the magnitude and direction of the state deviation, calculate the correction amount for the target model parameters; The target model parameters in the digital twin model are adjusted according to the correction amount to obtain the corrected digital twin model.

[0011] By adopting the above technical solution, a triggering mechanism for model correction is established based on a preset deviation threshold to judge state deviations. By analyzing the correlation between state deviations and various model parameters in the digital twin model, the target model parameter with the greatest impact on state deviations is identified, avoiding blind correction of all model parameters. The correction amount of the target model parameter is calculated based on the magnitude and direction of the state deviation, and targeted parameter adjustments are made to the digital twin model, achieving accuracy and efficiency in model correction and ensuring that the corrected digital twin model can better adapt to changes in the actual operating state of the equipment.

[0012] Optionally, obtaining the state evolution trend of the device within a second future preset time period based on the virtual response data and the virtual evolution state includes: Extract the equipment performance degradation pattern corresponding to the current operating condition characteristics from the virtual response data; The virtual operation data of each time node within the second future preset time period is extracted from the virtual operation data as the basic evolution data, and the first future preset time period includes the second future preset time period; Calculate the performance degradation amount at each time node within the second future predetermined time period based on the device performance degradation law; The performance degradation at each time point is superimposed onto the basic evolution data at the corresponding time point to obtain the corrected evolution data; Arrange the corrected evolution data of each time point within the second future predetermined time period in a time sequence to form the state evolution trend of the equipment within the second future predetermined time period under the current operating condition.

[0013] By employing the above technical solution, the performance degradation law corresponding to the current operating condition characteristics is extracted from the virtual response data, realizing a quantitative characterization of the performance change characteristics of the equipment under specific operating conditions. A baseline reference for state evolution is established by extracting basic evolution data within a second preset future time period from the virtual operation data. The performance degradation amount at each time node is calculated by combining the performance degradation law, and then superimposed on the basic evolution data to obtain corrected evolution data, thus considering factors contributing to equipment performance degradation. Finally, the corrected evolution data is arranged in a time series to form a state evolution trend, which not only reflects the operating trajectory of the equipment under ideal conditions but also considers the performance degradation impact during actual operation. This makes the state evolution prediction closer to the actual operating characteristics of the equipment, improving the accuracy and reliability of state prediction.

[0014] Optionally, calculating the current operating status assessment result of the device based on the state evolution trend and the device's operating data includes: The evolution trajectory of key state indicators is extracted from the state evolution trend, and the key state indicators in the current running data are compared with the corresponding evolution trajectory to determine the position of each key state indicator in the evolution trajectory. Based on the position of each key status indicator in the evolution trajectory, the remaining margin of each key status indicator from the preset warning threshold is calculated, and the remaining margins of each key status indicator are weighted and combined to obtain the overall health score of the equipment. Based on the comprehensive health score and the state evolution trend, the current operating status assessment result of the equipment is determined.

[0015] By employing the aforementioned technical solution, the evolution trajectory of key state indicators is extracted from the state evolution trend. Comparing the key state indicators in the current operating data with the evolution trajectory enables precise positioning of the equipment's current operating state within the predicted trajectory. By calculating and weighting the remaining margins of each key state indicator from the preset warning threshold, a comprehensive health score reflecting the overall operating status of the equipment is obtained. This score considers both the relative importance of each indicator and quantifies the overall safe operating margin of the equipment. Combining the comprehensive health score and the state evolution trend to determine the current operating status assessment result not only reflects the current health level of the equipment but also includes trend information on future state changes. This provides a reliable basis for a comprehensive assessment of the equipment's operating status, helping to promptly identify potential failure risks and take preventative measures.

[0016] Optionally, calculating the remaining margin of each key state indicator from the preset warning threshold based on the position of each key state indicator in the evolution trajectory includes: On each of the aforementioned evolution trajectories, determine the current position point corresponding to the key state indicators in the current operating data, and the warning position point corresponding to the preset warning threshold; The path integral is performed from the current position point to the warning position point along the evolution trajectory to obtain the arc length of the target evolution trajectory curve; Based on the local curvature of the evolution trajectory at the current position, the arc length of the curve is weighted and corrected to obtain the remaining margin of each key state indicator from the preset warning threshold.

[0017] By employing the above technical solution, the current position and warning position are determined on the evolution trajectory, establishing a spatial reference benchmark for assessing the remaining margin. Calculating the curve arc length by performing path integration along the evolution trajectory not only considers the straight-line distance between the state index and the warning threshold but also reflects the nonlinear changes during the state evolution process. Weighted correction of the curve arc length is applied by incorporating the local curvature of the evolution trajectory at the current position, fully considering the acceleration characteristics of state changes. This makes the calculation of the remaining margin more accurately reflect the dynamic characteristics of equipment state evolution, providing a more scientific quantitative basis for assessing the safe operating margin of the equipment.

[0018] Optionally, determining the current operating status assessment result of the device based on the comprehensive health score and the state evolution trend includes: Extract the average rate of change of the key state indicators within the second future preset time period from the state evolution trend, and sum the weighted average rates of change of each key state indicator to obtain the comprehensive rate of change. The current operating status evaluation index is calculated based on the preset operating status evaluation index formula; The preset operating status evaluation index formula is as follows: ; Where R is the current operating status assessment index, H is the comprehensive health score, v is the comprehensive change rate, and Δt is the length of the second future preset time period; The current operating status assessment result of the device is generated based on the current operating status assessment index.

[0019] By employing the aforementioned technical solution, the average rate of change of key state indicators is extracted from the state evolution trend and weighted summed to obtain the comprehensive rate of change, thus achieving a quantitative characterization of the speed of equipment state changes. Through a pre-defined operational status assessment index formula, the comprehensive health score and the comprehensive rate of change are organically combined. The exponential term reflects the non-linear impact of state changes on health, while the linear term reflects the trend direction of state changes. This mathematical model considers both the current health status of the equipment and the future development trend of state changes, enabling the operational status assessment results to more comprehensively reflect the operational risks of the equipment and provide a more reliable basis for equipment maintenance decisions.

[0020] In a second aspect, this application provides a device operation status monitoring device based on digital twins, the device operation status monitoring device based on digital twins includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the device operation status monitoring device based on digital twins to perform the method described in the first aspect and any possible implementation thereof.

[0021] Thirdly, this application provides a computer program product containing instructions that, when the computer program product is run on a digital twin-based device operation status monitoring device, causes the digital twin-based device operation status monitoring device to perform the method described in the first aspect and any possible implementation thereof.

[0022] Fourthly, this application provides a computer-readable storage medium including instructions that, when executed on a digital twin-based device operation status monitoring device, cause the digital twin-based device operation status monitoring device to perform the method described in the first aspect and any possible implementation thereof. Attached Figure Description

[0023] Figure 1 This is a schematic flowchart of a device operation status monitoring method based on digital twin provided in an embodiment of this application; Figure 2This is an exemplary hardware structure diagram of a device operation status monitoring device based on digital twin provided in an embodiment of this application. Detailed Implementation

[0024] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0025] In the description of the embodiments of this application, the words "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design that is described as "for example" or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design options. Rather, the use of the words "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0026] In the description of the embodiments of this application, the term "multiple" means two or more. For example, multiple systems means two or more systems, and multiple screen terminals means two or more screen terminals. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0027] This application provides a method for monitoring equipment operating status based on digital twins, referencing... Figure 1 , Figure 1 This is a flowchart illustrating a device operation status monitoring method based on digital twins provided in an embodiment of this application, including steps S101 to S107, as follows: S101: Obtain the device parameters and construct a digital twin model of the device in the virtual space based on the device parameters.

[0028] In this embodiment of the application, a digital twin model refers to a digital simulation model constructed in virtual space that completely corresponds to a physical device. This model can reflect the structural features, operating status, and behavioral characteristics of the physical device in real time.

[0029] Specifically, the process begins by acquiring comprehensive equipment parameters through various data collection methods. These parameters include static parameters such as geometric dimensions, material properties, rated power, operating pressure, and temperature range, as well as dynamic parameters such as operating speed, flow rate, vibration frequency, and temperature distribution. The acquired parameters are then preprocessed, including data cleaning, format standardization, and parameter classification. Next, a geometric model framework for the equipment is established in virtual space, constructing its three-dimensional geometry based on the geometric dimensions and structural information from the parameters. Subsequently, the equipment's physical property parameters are mapped onto the geometric model, including the assignment of values ​​for physical properties such as material density, elastic modulus, and thermal conductivity. Further, a mathematical model is established based on the equipment's working principle and control logic, transforming the equipment's dynamic operating characteristics into a system of mathematical equations and control algorithms. Finally, the completed digital twin model undergoes parameter verification and simulation testing to ensure that it accurately reflects the real behavioral characteristics of the physical equipment, thus completing the construction of the digital twin model.

[0030] S102: Obtain the current operating data of the device in real time, map the current operating data to the digital twin model, and obtain the twin synchronization state of the digital twin model at the current moment.

[0031] In this embodiment, the twin synchronization state refers to the digital twin model and the physical device maintaining a completely consistent operating state at the current moment. This state is achieved by mapping the real-time operating data of the physical device into the virtual model, ensuring that the virtual model can accurately reflect the real-time operating conditions of the physical device. For example, when the real-time speed of the industrial pump is 1450 rpm, the outlet pressure is 0.6 MPa, and the flow rate is 150 m³ / h, the corresponding virtual pump in the digital twin model will also synchronously display the same operating parameters and state.

[0032] Specifically, the system first collects real-time operational data from various sensors deployed on the equipment. This includes temperature values ​​from different parts of the equipment collected by temperature sensors, system pressure parameters acquired by pressure sensors, vibration amplitude and frequency monitored by vibration sensors, and medium flow rate data measured by flow meters. Then, the collected real-time operational data is timestamped and its format converted to ensure timeliness and compatibility. Next, a parameter mapping relationship is established between the physical equipment and the digital twin model, mapping each piece of real-time operational data to a corresponding state variable in the model. Subsequently, the processed current operational data is transmitted to the digital twin model in virtual space via a data transmission interface, updating the model's state parameters. Further, the digital twin model is driven to perform corresponding simulation calculations based on the input operational data, updating all relevant state variables and output parameters within the model. Finally, the consistency between the mapped digital twin model state and the actual state of the physical equipment is verified, completing the establishment of the digital twin model's synchronized state at the current moment.

[0033] S103: Based on the twin synchronization state, perform state deduction on the digital twin model in the first future preset time period to obtain the virtual operation data corresponding to each time node in the first future preset time period.

[0034] In this embodiment, state simulation refers to predicting the changes in the operating state of a device over a future time period based on the current synchronized state of a digital twin model, using mathematical modeling and numerical calculation methods, thereby obtaining virtual operating data at various future time points. For example, for a centrifugal pump, state simulation can predict the device's operating trajectory and the changing trends of various parameters over the next 24 hours based on current state parameters such as speed, pressure, and temperature.

[0035] Specifically, firstly, all state parameters of the device, including operating parameters, environmental parameters, and control parameters, are extracted from the current twin synchronization state, and these parameters are used as the starting conditions for state evolution. Then, based on the physical mechanism and mathematical description of the digital twin model, a set of state evolution equations describing the changing patterns of the device state is established using the extracted current state parameters. This set of equations describes the functional relationship between the rate of change of state variables over time and the current state, input conditions, and time. Next, the operating boundary conditions within a first preset future time period are obtained, including constraints such as expected load changes, ambient temperature changes, and control strategy adjustments. This first preset future time period is divided into multiple discrete time nodes according to a preset time step. Subsequently, using the current state parameters as initial conditions and the operating boundary conditions as constraints, the state evolution equations are iteratively solved at each time node using a numerical integration method. The system state is updated by progressively calculating the increment of state variables within each time step. Finally, the state vectors obtained at each time node are converted into the corresponding virtual operating data format, including the values, units, and timestamps of each operating parameter, completing the acquisition of virtual operating data for each time node within the first preset future time period.

[0036] S104: When time progresses to the first future preset time period, calculate the state deviation between the current running data and the corresponding virtual running data at each time node.

[0037] In this embodiment, the state deviation refers to the difference between the actual operating data of the device and the virtual operating data predicted by the digital twin model at the same time point. This deviation reflects the degree of conformity between the prediction accuracy of the digital twin model and the actual operating condition of the device. For example, when the actual rotational speed of the device at a certain moment is 1480 rpm, while the virtual rotational speed predicted by the digital twin model is 1450 rpm, the state deviation of the rotational speed parameter at that moment is 30 rpm.

[0038] Specifically, the process begins by executing the state deviation calculation procedure when the actual time progresses to the start of the first preset future time period. Then, for each time node within the first preset future time period, the actual operating data of the equipment at that time node is acquired synchronously, including operating parameters such as temperature, pressure, vibration, and flow rate collected in real time by various sensors. Next, virtual operating data for the corresponding time node is extracted from the prediction results obtained in the previous state extrapolation steps, ensuring a complete correspondence between the virtual and actual data at each time node. Subsequently, the state deviation is calculated for each operating parameter using methods such as absolute deviation, relative deviation, or weighted deviation to obtain the deviation value for each parameter. Further, the calculated parameter deviations are organized, categorized, and stored, establishing a correspondence between the deviation data and time nodes. Finally, the state deviation data for all time nodes is aggregated to form a deviation dataset, providing fundamental data support for subsequent model optimization and state assessment, thus completing the state deviation calculation between the current operating data and the corresponding virtual operating data at each time node.

[0039] S105: Correct the digital twin model based on the state deviation, and construct a virtual response feature library based on the corrected digital twin model.

[0040] In this embodiment of the application, the virtual response feature library refers to a database that contains the response features of the device under different operating conditions, which is built based on the modified digital twin model. The feature library stores the output response patterns and characteristic parameters of the device under various input stimuli.

[0041] Specifically, the process begins by determining whether the calculated state deviation exceeds a preset deviation threshold. A set deviation tolerance range is then used to determine if the digital twin model needs correction. When the state deviation exceeds the preset threshold, the correlation between the state deviation and the parameters of each model in the digital twin is analyzed. Sensitivity analysis and parameter influence assessment methods are used to identify the target model parameters that have the greatest impact on the state deviation. Then, the correction amount for the target model parameters is calculated based on the magnitude and direction of the state deviation. Mathematical optimization methods such as gradient descent, least squares, or Kalman filtering are used to determine the magnitude and direction of the parameter adjustment. Next, the target model parameters in the digital twin are adjusted according to the calculated correction amount, updating the model's internal parameter settings to obtain the corrected digital twin model. Subsequently, multi-condition simulation calculations are performed based on the corrected digital twin model. By changing different input and boundary conditions, virtual response data of the equipment under various operating scenarios is obtained. Furthermore, feature extraction and pattern recognition are performed on the obtained virtual response data to extract key response feature parameters and their changing patterns. Finally, the extracted response features are classified and stored according to operating condition type, parameter category and time series to establish a structured virtual response feature library, thus completing the construction of the virtual response feature library based on the modified digital twin model.

[0042] S106: Obtain the current operating condition characteristics of the equipment, search for virtual response data that matches the current operating condition characteristics in the virtual response feature library, and obtain the state evolution trend of the equipment in the second future preset time period based on the virtual response data and the virtual evolution state.

[0043] In this embodiment, the state evolution trend refers to the change pattern and development trajectory of various operating state parameters of the equipment in a future time period under specific operating conditions. This trend comprehensively considers the normal operation evolution and performance degradation of the equipment.

[0044] Specifically, the current operating characteristics of the equipment are first obtained, including key operating parameters such as current load level, operating mode, environmental conditions, and control strategies. Then, a feature matching algorithm is used in the virtual response feature library to find virtual response data that matches the current operating characteristics. The best-matching response feature data is determined through similarity calculation and pattern recognition methods. Next, the equipment performance degradation patterns corresponding to the current operating characteristics are extracted from the matched virtual response data, including degradation characteristic parameters such as wear rates of key components, efficiency degradation curves, and fault development modes. Subsequently, virtual operating data for each time node within a second future preset time period is extracted from the previously obtained virtual operating data as basic evolution data, where the first future preset time period includes the second future preset time period. Then, the performance degradation amount at each time node within the second future preset time period is calculated based on the extracted equipment performance degradation patterns. The degree of equipment performance degradation at each time node is determined using a degradation model and time integration methods. Furthermore, the performance degradation amounts at each time node are superimposed onto the basic evolution data for the corresponding time node, considering the cumulative impact of degradation on equipment operating parameters, to obtain corrected evolution data reflecting the actual equipment state. Finally, the corrected evolution data at each time point within the second future preset time period are arranged in a time series to form a continuous state change curve and trend chart, thus completing the construction of the state evolution trend of the equipment under the current working condition within the second future preset time period.

[0045] S107: Calculate the current operating status assessment result of the equipment based on the state evolution trend and the current operating data of the equipment.

[0046] In this embodiment, the current operating status assessment result refers to a quantitative assessment conclusion on the health level and safety degree of the equipment at the current moment, based on a comprehensive analysis of the equipment's current operating data and future state evolution trends. This assessment result typically includes key indicators such as the equipment's health level, risk level, and expected availability.

[0047] Specifically, the process begins by extracting the evolution trajectories of key state indicators from the state evolution trend. This includes the change curves and development paths of core equipment performance parameters such as efficiency, vibration, temperature, and pressure over time. Next, the key state indicators in the current operating data are compared and analyzed with their corresponding evolution trajectories. Time positioning and numerical matching methods are used to determine the specific position of each key state indicator within its evolution trajectory. Then, based on the position of each key state indicator within its evolution trajectory, and combined with preset equipment safety operation boundaries and warning thresholds, the remaining margin of each key state indicator from the preset warning threshold is calculated, assessing the equipment's safety reserve space in various dimensions. Subsequently, considering the varying importance of different key state indicators to the overall health of the equipment, the remaining margins of each key state indicator are weighted and comprehensively calculated. The analytic hierarchy process (AHP) or expert scoring method is used to determine the weighting coefficients, resulting in a comprehensive health score reflecting the overall condition of the equipment. Finally, based on the comprehensive health score, the development direction and rate of change of the state evolution trend, and combined with historical operating experience and industry standards, the operational risk level and health status classification of the equipment are comprehensively judged to determine the current operating status assessment result.

[0048] Based on the above embodiments, as an optional embodiment, S103: the step of performing state deduction on the digital twin model according to the twin synchronization state in a first future preset time period to obtain the virtual operation data corresponding to each time node in the first future preset time period may specifically include the following steps: S201: Extract the current state parameters from the twin synchronization state, and establish the state evolution equation based on the digital twin model and the current state parameters.

[0049] In the embodiments of this application, the state evolution equation refers to a set of mathematical equations that describe the changes of equipment state parameters over time. This set of equations is established based on physical laws and system dynamics principles, and can quantitatively express the interrelationships between various state variables of the equipment and their evolution process over time.

[0050] Specifically, firstly, the current state parameters of the equipment are extracted from the digital twin synchronization state, including multi-dimensional data such as the equipment's operating parameters, control parameters, environmental parameters, and internal state variables. These parameters are categorized and organized according to their physical meaning and mathematical properties to form a state vector. Then, based on the equipment's physical mechanism, mathematical model, and control logic contained in the digital twin model, the key physical processes and constraints affecting the equipment's state evolution are determined, and an input vector is established. Next, the extracted current state parameters are used as the model's input variables. Combining the physical equations and mathematical relationships in the digital twin model, the general form of the state evolution equation is established: dx / dt = f(x(t), u(t), t), where f is the state transition function vector. Subsequently, the established equation system is mathematically normalized, discretizing the continuous-time equation into a recursive form. Furthermore, the initial conditions required for solving the equations are set. The current state parameters are substituted as initial values ​​into the equation system to determine the parameter matrix A and the input matrix B, so that the equation is expressed in the state-space form of dx / dt = Ax(t) + Bu(t) + w(t), where w(t) is the process noise term. Finally, the completeness and solvability of the established state evolution equations are verified to ensure that the equation set can accurately reflect the dynamic characteristics and evolution law of the equipment. For example, for the evolution of the contact resistance of the switch contacts in the primary and secondary integrated ring network box, the established state evolution equation is: dR(t) / dt = α·R(t) + β·I²(t) + γ·T(t) + ω(t), where R(t) is the contact resistance value, α is the basic aging coefficient, I(t) is the load current, β is the current influence factor, T(t) is the ambient temperature, γ is the temperature influence coefficient, and ω(t) is the random disturbance term, thus completing the establishment of the state evolution equation based on the digital twin model and the current state parameters.

[0051] S202: Obtain the preset operating boundary conditions within the first future preset time period, and divide the first future preset time period into multiple time nodes according to the preset time step.

[0052] In this embodiment, operational boundary conditions refer to the constraints and limiting parameters that the equipment needs to meet during operation within a preset future time period, including boundary constraints such as the equipment's safe operating range, environmental condition limitations, and control strategy constraints. The first preset future time period refers to a specific time interval extending into the future from the current moment, used for equipment state evolution analysis and prediction calculations. The preset time step refers to the time discretization interval used in numerically solving the state evolution equation; the selection of this step size needs to balance the requirements of computational accuracy and computational efficiency. A time node refers to a discrete time point obtained by equally dividing the time period according to the preset time step; each node corresponds to a specific moment for the calculation and storage of state parameters.

[0053] Specifically, the process begins by obtaining the preset operational boundary conditions for the first future preset time period. This involves extracting the safe operating parameter ranges for the equipment from its technical specifications, operation manual, and control system, including constraint information such as the maximum and minimum values ​​and allowable variation ranges of each state parameter. Next, the start and end times of the first future preset time period are determined, and the total time span is calculated. Then, a preset time step is determined based on numerical solution accuracy requirements and computational resource limitations, and an appropriate step size is selected through stability analysis and error estimation methods. Subsequently, the first future preset time period is divided into equal intervals according to the preset time step, and the total number of time nodes is calculated by dividing the total time span by the preset time step. Further, a discrete time node sequence arranged chronologically is generated, with the specific time of each node determined by adding the node number to the product of the start time and the time step. Finally, the rationality of the time node division is verified, ensuring that the last time node does not exceed the end time of the preset time period, thus completing the acquisition of the operational boundary conditions and the setting of the time node division within the first future preset time period.

[0054] S203: Using the current state parameters as initial conditions and the running boundary conditions as constraints, iteratively solve the state evolution equation at each time node to obtain the virtual running data corresponding to each time node in the first future preset time period.

[0055] In this embodiment of the application, virtual operation data refers to the simulated operation status data of the primary and secondary fusion ring network equipment in the future time period calculated by digital twin model and state evolution equation. Specifically, it includes the predicted values ​​and trends of key parameters such as switch contact resistance value, insulation resistance value, protection action time, load current, and equipment temperature at various time nodes in the future.

[0056] Specifically, the current state parameters are first set as the initial conditions for the state evolution equation, and the values ​​of various key state variables measured at the current moment are input into the evolution equation as the starting values ​​for iterative calculation. Then, the operating boundary conditions are set as constraints in the iterative solution process, including the upper and lower limits of safe operation for each key parameter, such as the maximum allowable value of contact resistance, the minimum allowable value of insulation resistance, and the maximum operating temperature of the equipment. Next, the total duration and time step of the first future preset time period are set, and several equally spaced time nodes are established. The state evolution equation is solved step by step using a numerical integration method, and the predicted state value for the next time node is calculated based on the state value of the current time node and the external input conditions. Subsequently, in each iteration step, the calculation results are checked to see if they meet the operating boundary condition constraints. If the predicted value exceeds the safe operating range, corresponding corrections are made or an early warning mechanism is triggered. Further, the predicted values ​​of multiple key state parameters for each time node are calculated sequentially using the same iterative solution method, forming a virtual operating data matrix containing multiple time nodes and multi-dimensional state parameters. Finally, the numerical stability and convergence of the entire iterative solution process are verified to ensure that the prediction error at each time node is controlled within a reasonable range. For example, for the evolution of switch contact resistance, the future prediction period is set to 30 days, the time step is 1 day, the current initial contact resistance value is 50 milliohms, the boundary constraint is 200 milliohms, the fourth-order Runge-Kutta method is used to solve the contact resistance evolution equation, and the increase and cumulative value of contact resistance are calculated daily according to the daily load current and ambient temperature conditions. Finally, the contact resistance prediction data sequence corresponding to 30 time nodes is obtained, and the virtual operation data is generated.

[0057] Based on the above embodiments, as an optional embodiment, S105: the step of correcting the digital twin model according to the state deviation may specifically include the following steps: S301: Determine whether the state deviation exceeds the preset deviation threshold; when the state deviation exceeds the preset deviation threshold, analyze the correlation between the state deviation and the model parameters in the digital twin model, and determine the target model parameter that has the greatest impact on the state deviation.

[0058] Specifically, the process begins by calculating the state deviation between the virtual and actual operating data of the integrated primary and secondary ring main unit (RMU) equipment. This is achieved by comparing the predicted and measured values ​​of various state variables, such as switch position, voltage and current values, equipment temperature, and insulation status, to obtain the deviation values. The calculated state deviation is then compared with a preset deviation threshold to determine if it exceeds the acceptable range for safe operation of the RMU equipment. If the deviation is within the threshold, normal monitoring continues; otherwise, the model parameter analysis process is initiated. Next, when the state deviation exceeds the preset threshold, all model parameters in the digital twin model of the integrated primary and secondary RMU equipment are extracted. These parameters include electrical, mechanical, and insulation parameters of the primary equipment, as well as control, protection, and measurement parameters of the secondary equipment. Sensitivity analysis is then used to analyze the impact of each model parameter on the state deviation of the RMU equipment. Correlation relationships are established by perturbing each model parameter and observing its contribution to changes in switch action characteristics, electrical performance, and protection functions. Furthermore, the sensitivity coefficients and influence weights of each model parameter are calculated to quantify the contribution of each parameter change to the overall state deviation of the ring network equipment, and a ranking list of parameter influence is established. Finally, based on the sensitivity analysis results and influence weight ranking, several model parameters with the greatest impact on the state deviation of the primary and secondary fusion ring network equipment are selected as target model parameters, thus completing the identification and determination of key model parameters.

[0059] S302: Calculate the correction amount of the target model parameters based on the magnitude and direction of the state deviation; adjust the target model parameters in the digital twin model according to the correction amount to obtain the corrected digital twin model.

[0060] In this embodiment, the modified digital twin model refers to the updated model obtained by adjusting and optimizing the key parameters of the original digital twin model based on the state deviation analysis results. This model can more accurately reflect the actual operating characteristics and state change patterns of the primary and secondary integrated ring main unit equipment. For example, for primary and secondary integrated ring main unit equipment, the modified digital twin model may include calibrated switch mechanical characteristic parameters, optimized transformer equivalent circuit parameters, updated insulation aging model parameters, and recalibrated protection device parameters, thereby significantly improving the matching degree between the model output and the actual operating data of the equipment.

[0061] Specifically, the process begins by analyzing the magnitude of the state deviations to determine the absolute values ​​of deviations in various state variables of the primary and secondary integrated ring main unit equipment, such as switch action time, voltage and current amplitudes, and equipment temperature, and to assess the severity and scope of the deviations. Next, the directional characteristics of the state deviations are determined, identifying whether each state variable exhibits positive or negative deviations, and determining whether the model's predicted values ​​are higher or lower than the actual values, providing a basis for parameter adjustment. Then, based on the magnitude and direction of the deviations, a method for calculating the correction amount of the target model parameters is established. First, a sensitivity matrix between the state deviation vector and the model parameters is constructed. By performing parameter perturbation analysis on the digital twin model, the influence coefficients of each model parameter on each state variable are obtained. Then, the least squares method is used to solve for the parameter correction amount, establishing a linear equation system in the form that the sensitivity matrix multiplied by the parameter correction vector equals the state deviation vector. The parameter correction amount that minimizes the state deviation is obtained through matrix inversion or pseudo-inversion. For nonlinear cases, the gradient descent method is used iteratively, with the sum of squares of the state deviations as the objective function. The gradient of the objective function with respect to each model parameter is calculated, and the parameters are updated according to the negative gradient direction until convergence. Subsequently, the target model parameters in the digital twin model of the integrated primary and secondary ring main unit were adjusted item by item, with parameters for switchgear, transformer, and protection control being increased or decreased according to the calculated correction amounts. Furthermore, the rationality and effectiveness of the adjusted parameters were verified to ensure that the corrected parameter values ​​remained within the physically feasible range and met the equipment technical specifications. Finally, the mathematical description and simulation algorithm of the digital twin model were reconstructed, integrating all the corrected target model parameters to form a corrected digital twin model capable of more accurately predicting the operating status of the integrated primary and secondary ring main unit.

[0062] For example, parameter correction is performed to address the deviation in switch action time. Assume the model predicts a switch opening time of 45ms, the actual measured value is 48ms, and the state deviation is 3ms; the model predicts a closing time of 42ms, the actual measured value is 40ms, and the state deviation is -2ms. A state deviation vector Δy = [3, -2]T is constructed. Through parameter perturbation analysis, a sensitivity matrix S = [[0.5, 0.3], [0.2, 0.8]] is obtained, where the first row represents the influence of the mechanical spring stiffness coefficient and damping coefficient on the opening time, and the second row represents the influence on the closing time. The parameter correction amount was solved using the least squares method: Δp = (STS)⁻¹STΔy. STS = [[0.29, 0.31], [0.31, 0.73]] was calculated, and its inverse matrix is ​​[[4.85, -2.06], [-2.06, 1.93]]. The final parameter correction amount Δp = [8.26, -7.74]T indicates that the mechanical spring stiffness coefficient needs to be increased by 8.26%, and the damping coefficient needs to be decreased by 7.74%. The original parameter values ​​of the spring stiffness coefficient (1200 N / m) were adjusted to 1299 N / m, and the damping coefficient (0.85) was adjusted to 0.78, completing the parameter correction of the digital twin model.

[0063] Based on the above embodiments, as an optional embodiment, S106: the step of obtaining the state evolution trend of the device within a second future preset time period based on virtual response data and virtual evolution state may specifically include the following steps: S401: Extract the equipment performance degradation law corresponding to the current operating condition characteristics from the virtual response data; extract the virtual operation data of each time node within the second future preset time period from the virtual operation data as the basic evolution data, wherein the first future preset time period includes the second future preset time period.

[0064] In the embodiments of this application, the equipment performance degradation law refers to the evolution pattern and trend characteristics of the gradual decrease of key performance indicators of primary and secondary integrated ring main unit equipment over time under specific operating conditions, including the rate, magnitude, influencing factors, and mathematical representation of the degradation process. For example, for primary and secondary integrated ring main unit equipment, the equipment performance degradation law may include the increasing contact resistance caused by wear of switchgear contacts, the decreasing insulation performance caused by aging of transformer insulation materials, the attenuation characteristics of response accuracy caused by aging of electronic components of protection devices, and the long-term impact mode of environmental factors on the overall reliability of the equipment.

[0065] Specifically, the virtual response data is first analyzed and processed to identify the historical performance change trajectory of the primary and secondary integrated ring main unit equipment under current operating conditions. Time series analysis is used to segment the virtual response data according to time windows, calculating the rate of change and cumulative change of equipment performance indicators within each time period. A functional relationship between performance indicators and time is established, and the mathematical expression and characteristic parameters of performance degradation, such as the decay constant and decay exponent, are determined through polynomial fitting or exponential decay models. Then, a mapping relationship between current operating conditions and equipment performance degradation patterns is established. A multiple regression model is constructed, using operating condition variables such as load level, ambient temperature and humidity, and operation frequency as independent variables, and performance degradation characteristic parameters as dependent variables. The regression coefficients are solved using least squares or support vector regression algorithms to quantify the contribution weight of each operating condition factor to the performance degradation rate, establishing a linear or nonlinear mapping function in the form that the degradation rate equals the sum of the products of each operating condition factor and its corresponding coefficient. Next, the start and end times of a second future preset time period are determined from the virtual operation data. This time period is a subset of the first future preset time period and is used for the key predictive analysis interval. Subsequently, virtual operational data corresponding to each time node within the second future preset time period are extracted in chronological order, including the predicted value sequence of each state variable of the ring network equipment within that time period, forming a basic evolution data set. For example, by analyzing the virtual response data, it was found that the switch contact resistance follows an exponential decay model. The changes are defined as follows: the attenuation constant α = 2.5 milliohms and the attenuation exponent β = 0.003 / day; the working condition mapping relationship is established as attenuation rate = 0.15 × load current + 0.08 × ambient temperature + 0.02 × operating frequency - 5.2; the 15th to 30th days are extracted from the first future preset time period of 30 days as the second future preset time period, and the virtual operation data of 15 time nodes are obtained as the basic evolution data.

[0066] S402: Calculate the performance degradation amount at each time node within the second future predetermined time period based on the equipment performance degradation law; superimpose the performance degradation amount at each time node onto the basic evolution data of the corresponding time node to obtain the corrected evolution data; arrange the corrected evolution data of each time point within the second future predetermined time period in a time series to form the state evolution trend of the equipment within the second future predetermined time period under the current operating condition.

[0067] In this embodiment, the state evolution trend refers to the trajectory and direction of change of key state parameters of the primary and secondary integrated ring main unit equipment under current operating conditions within a predetermined future time period, comprehensively considering the combined effects of changes in normal operating conditions and performance degradation. For example, for the primary and secondary integrated ring main unit equipment, the state evolution trend may include the trend of gradually increasing contact resistance of switchgear over time, the trend of slowly decreasing insulation resistance of transformers due to aging, the trend of prolonged response time of protection devices due to component aging, and the expected degradation trajectory of overall equipment reliability indicators under current operating conditions.

[0068] Specifically, firstly, a mathematical calculation model is established based on the performance degradation law of the equipment. For key performance indicators of the integrated primary and secondary ring main unit equipment, such as switch operation characteristics, electrical parameter stability, and insulation performance, the cumulative performance degradation of each time node relative to the current time within the second predetermined future time period is calculated. Then, the specific performance degradation values ​​for each time node are calculated, including the degradation magnitude of key parameters such as contact resistance increment, insulation resistance decrease, and protection accuracy offset, forming a correspondence table between time nodes and performance degradation amounts. Next, the calculated performance degradation amounts for each time node are superimposed onto the basic evolution data of the corresponding time node according to their corresponding physical meaning and mathematical relationships. Data fusion of the degradation effect is achieved through addition, multiplication correction, or function transformation. Subsequently, the superimposed data undergoes a rationality check and boundary condition constraint to ensure that the corrected evolution data conforms to the physical characteristics and safe operation requirements of the integrated primary and secondary ring main unit equipment, avoiding unreasonable values ​​or states. Furthermore, the corrected evolution data for each time node within the second predetermined future time period are arranged and organized in chronological order to establish a time-series data structure, forming a continuous trajectory of equipment state changes over time. Finally, trend analysis and feature extraction are performed on the time series data to identify the state evolution law, change rate and development direction of the primary and secondary integrated ring network equipment under the current working conditions, forming a complete state evolution trend of the equipment in the second future predetermined time period.

[0069] Based on the above embodiments, as an optional embodiment, S107: the step of calculating the current operating status evaluation result of the device based on the state evolution trend and the current operating data of the device may specifically include the following steps: S501: Extract the evolution trajectory of key state indicators from the state evolution trend, compare the key state indicators in the current running data with the corresponding evolution trajectory, and determine the position of each key state indicator in the evolution trajectory.

[0070] In this embodiment, the evolution trajectory refers to the change path and development curve of a single key state indicator in the primary and secondary integrated ring main unit equipment over time. Each key state indicator corresponds to an independent evolution trajectory. For example, for the primary and secondary integrated ring main unit equipment, the contact resistance indicator of the switchgear corresponds to a contact resistance evolution trajectory, the insulation resistance indicator of the transformer corresponds to an insulation resistance evolution trajectory, and the response time indicator of the protection device corresponds to a response time evolution trajectory. Each trajectory describes the expected change process and numerical distribution of the specific indicator from the current moment to a predetermined future time period.

[0071] Specifically, firstly, the dedicated evolution trajectories of each key state indicator of the primary and secondary integrated ring main unit equipment are extracted one by one from the state evolution trend, establishing multiple independent state evolution paths such as switch action time trajectory, contact resistance trajectory, transformer loss trajectory, insulation resistance trajectory, and protection accuracy trajectory. Then, the real-time measured values ​​of each key state indicator in the current operating data of the equipment are obtained, including the measured values ​​of switch action time, contact resistance, transformer loss, and insulation resistance at the current moment. Next, the current measured value of each key state indicator is matched one-to-one with its corresponding evolution trajectory, and the trajectory position point closest to the current measured value is located on the corresponding evolution trajectory through numerical search and interpolation calculation methods. Subsequently, the specific position coordinates of the current measured value of each key state indicator in its corresponding evolution trajectory are determined, including the corresponding time on the trajectory time axis and the corresponding value on the numerical axis. Furthermore, the relative relationship between the current position point of each key state indicator and the starting point of the evolution trajectory is analyzed to assess the current degree of decay and development stage of each performance indicator of the equipment. Finally, by combining the positional distribution of all key status indicators in their respective evolution trajectories, an overall positioning result of the current operating status of the primary and secondary integrated ring network equipment in the multi-dimensional evolution space is formed.

[0072] S502: Based on the position of each key status indicator in the evolution trajectory, calculate the remaining margin of each key status indicator from the preset warning threshold, and weight and combine the remaining margins of each key status indicator to obtain the overall health score of the equipment.

[0073] In this embodiment, the margin refers to the attenuation space and safety margin that each key state indicator of the primary and secondary integrated ring main unit can withstand from the current operating state to the preset warning threshold state, comprehensively considering the influence of evolution path length and local change rate. For example, for the primary and secondary integrated ring main unit, the margin of switch contact resistance represents the weighted path length from the current resistance value along the evolution trajectory to the warning resistance threshold; the margin of transformer insulation resistance represents the corrected evolution distance from the current insulation state to the insulation warning state; and the margin of protection response time represents the curve weighted length from the current response accuracy to the accuracy warning line.

[0074] Specifically, firstly, the current position and warning position are precisely located on the evolution trajectory of each key status indicator. Using numerical matching methods, coordinate points corresponding to the measured values ​​of the current operating data are found on various evolution curves, such as the switch action time trajectory, contact resistance trajectory, and insulation resistance trajectory. Simultaneously, the position points corresponding to the warning states are determined on the corresponding trajectories based on preset warning thresholds. Then, path integration is performed along each evolution trajectory from the current position to the warning position. Numerical integration methods, such as Simpson's integral or trapezoidal integral, are used to calculate the arc length of the evolution path of each key indicator of the primary and secondary integrated ring network equipment, obtaining the arc length values ​​of each target evolution trajectory. Next, the local curvature parameters of each evolution trajectory at the current position are calculated. The degree of curvature and steepness of change of the trajectory at the current state point are determined using first-order and second-order derivative calculation methods, reflecting the attenuation acceleration characteristics of the status indicator at the current stage. Subsequently, the arc lengths of each curve are weighted and corrected based on local curvature values. Higher risk weights are assigned to trajectory segments with greater curvature, while relatively lower weights are assigned to smoother segments with less curvature, thus forming a corrected margin for each key status indicator from the preset warning threshold. Further, importance weight coefficients for each key status indicator are established, assigning corresponding weight values ​​to different indicators based on the criticality and fault impact of the primary and secondary integrated ring main unit. Finally, the margins of each key status indicator are weighted and averaged according to their importance weights. Taking into account the safety margin status of all key indicators, a comprehensive health score for the primary and secondary integrated ring main unit is obtained.

[0075] S503: Determine the current operating status assessment result of the equipment based on the comprehensive health score and the status evolution trend.

[0076] Specifically, firstly, the average rate of change of each key state indicator within a second preset time period is extracted from the state evolution trend. The average decay or improvement rate of key parameters such as the switching action time change rate, contact resistance change rate, insulation resistance change rate, and protection response accuracy change rate of the primary and secondary integrated ring main unit equipment within the preset time period is calculated. Then, corresponding weight coefficients are assigned according to the importance of each key state indicator, and the average rate of change of each key state indicator is weighted and summed to obtain the comprehensive rate of change v reflecting the overall performance change trend of the equipment. Next, a preset operating state evaluation index formula is applied for calculation. This formula is... Where R is the current operating status assessment index, H is the comprehensive health score, v is the comprehensive rate of change, and Δt is the length of the second preset future time period. The formula consists of three core parts: the basic health term H serves as the assessment benchmark, reflecting the current static health level of the equipment; a linear correction term... The impact of equipment performance change trends on the current state is considered, where v·Δt represents the total change over the time period Δt. Normalization by dividing by H ensures comparability between equipment at different health levels; the exponential decay term... Excessive rate of change is suppressed using a Gaussian decay function to prevent short-term drastic changes from unduly impacting long-term assessments. Parameter H is derived from the comprehensive health score calculated in the preceding steps, parameter v is obtained by weighting the average rate of change of each key status indicator, and parameter Δt is the pre-set length of a second future time period. The advantage of this formula is that it accurately reflects the current health status while reasonably incorporating predictive information about future evolution trends. The exponential decay term effectively balances the impact of changing trends, avoiding overly optimistic or pessimistic assessment biases. Finally, based on the calculated current operating status assessment index R, combined with preset status rating standards and threshold ranges, the current operating status assessment result of the primary and secondary integrated ring main unit is generated, including different status levels such as excellent, normal, attention, and alert.

[0077] Based on the above embodiments, as an optional embodiment, S502: the step of calculating the remaining margin of each key state indicator from the preset warning threshold according to the position of each key state indicator in the evolution trajectory may specifically include the following steps: S601: Determine the current position point on each evolution trajectory that corresponds to the key status indicators in the current operating data, as well as the warning position point that corresponds to the preset warning threshold.

[0078] In this embodiment, a warning location point refers to a specific coordinate position on the evolution trajectory of a key status indicator of a primary and secondary integrated ring main unit (RMU) equipment, corresponding to a preset warning threshold value. These points mark the critical node where the equipment's performance indicator transitions from a normal operating state to an abnormal or faulty state. For example, for an MNU integrated ring main unit, a warning location point on the evolution trajectory of switch contact resistance corresponds to the trajectory coordinates when the contact resistance reaches the preset warning threshold; a warning location point on the evolution trajectory of transformer insulation resistance corresponds to the trajectory position when the insulation performance decreases to a warning level; and a warning location point on the evolution trajectory of protection device response time corresponds to the trajectory node when the response delay exceeds the safety limit. These warning location points constitute important reference benchmarks for equipment status monitoring and early warning.

[0079] Specifically, the process begins by acquiring the current operational data of key status indicators for the primary and secondary integrated ring main unit equipment, including real-time values ​​of key measurement parameters such as switch action time, contact resistance, transformer loss parameters, insulation resistance, and protection response accuracy. Then, the current position point is located on the evolution trajectory corresponding to each key status indicator. Through numerical matching and interpolation methods, the trajectory coordinates that are closest to or completely correspond to the measured values ​​of the current operational data are found on various curves, such as the switch action time evolution trajectory, contact resistance evolution trajectory, and insulation resistance evolution trajectory. Next, based on pre-set warning threshold standards for each key status indicator, the precise coordinates of the warning position points are determined on the corresponding evolution trajectories. By calculating the intersection of the threshold values ​​and the trajectory function, or by searching and matching discrete trajectory points, the specific position on the evolution trajectory when each indicator reaches the warning state is located. Finally, the relative positional relationship between the current position point and the warning position point on each evolution trajectory is verified to ensure that the current position point is before the warning position point, meaning the current state of the equipment has not yet reached the warning level, providing an effective path interval for subsequent remaining margin calculations.

[0080] S602: Perform path integration along the evolution trajectory from the current position to the warning position to obtain the arc length of the target evolution trajectory curve.

[0081] In this embodiment, path integral refers to the mathematical integration process of accumulating arc length infinitesimal elements from the current position point to the warning position point along a continuous path of the evolution trajectory of key state indicators of primary and secondary integrated ring main unit equipment. This process is used to accurately measure the actual geometric length of the trajectory curve. For example, for primary and secondary integrated ring main unit equipment, the path integral of the switch contact resistance evolution trajectory calculates the arc length from the current resistance state point along the predicted resistance decay curve to the warning resistance threshold point; the path integral of the transformer insulation resistance evolution trajectory measures the curve path length from the current insulation level point to the insulation warning point; and the path integral of the protection response time evolution trajectory calculates the trajectory arc length from the current response accuracy point to the accuracy warning point. This integration method can accurately reflect the true change distance of the state indicators along the nonlinear evolution path.

[0082] Specifically, firstly, mathematical function expressions or discretized data point sequences of the evolution trajectories of each key state indicator are established. The switching action time trajectory, contact resistance trajectory, and insulation resistance trajectory of the primary and secondary integrated ring network equipment are represented as continuous functions or discrete point sets with respect to time parameters. Then, the integration interval and integration variables of the path integral are determined, using the time parameters corresponding to the current position point and the time parameters corresponding to the warning position point as the upper and lower limits of integration, establishing a clear integration calculation range. Next, the arc length integral formula is applied to calculate the path integral. For the evolution trajectory in the form of a continuous function, the standard arc length integral formula is used, calculating the arc length by calculating the first derivative of the trajectory function and combining it with the integration interval. For the discretized trajectory data, a piecewise linear approximation method is used to calculate the arc length between adjacent points and then sum them. Subsequently, an appropriate numerical integration algorithm is selected for accurate calculation. Numerical methods such as Simpson's integral method, trapezoidal integral method, or Gaussian integral method are used to discretize the arc length integral. Through multi-step iteration and precision control, the accuracy requirements of the integration calculation results are ensured to meet the requirements of engineering applications. Furthermore, numerical errors in the calculation process are controlled and corrected. Adaptive step size adjustment and error estimation methods are used to improve the accuracy of path integral calculations. In particular, denser calculations are performed in areas with drastic changes in trajectory curvature to avoid the accumulation of integration errors. Finally, the arc length of the curve from the current position to the warning position point is output for each key state indicator's evolution trajectory.

[0083] S603: Based on the local curvature of the evolution trajectory at the current position, the arc length of the curve is weighted and corrected to obtain the remaining margin of each key state indicator from the preset warning threshold.

[0084] In this embodiment, local curvature refers to a quantitative indicator of the instantaneous bending degree and steepness of the evolution trajectory of key state indicators of primary and secondary integrated ring main unit equipment at the current location point. It reflects the attenuation acceleration characteristics and the degree of swiftness of the evolution trend of the state indicator at the current stage. For example, for primary and secondary integrated ring main unit equipment, the local curvature of the switch contact resistance evolution trajectory at the current location point reflects whether there is an accelerating trend in the resistance deterioration rate; the local curvature of the transformer insulation resistance evolution trajectory characterizes the rapid and slow changes in insulation performance degradation; and the local curvature of the protection device response accuracy evolution trajectory shows whether the accuracy degradation shows an accelerated deterioration trend. The larger the local curvature value, the more drastic the change in the state indicator near that location, which means a higher risk of equipment performance degradation.

[0085] Specifically, firstly, the local curvature values ​​of the evolution trajectories of each key state indicator at the current position are calculated. The curvature parameters at the current position are calculated using the first and second derivatives of the trajectory function using curve differential geometry. For discretized trajectory data, the local curvature value is approximated by the difference between adjacent data points. Then, a risk weighting coefficient calculation model based on local curvature is established. Appropriate weighting correction coefficients are set according to the curvature magnitude. Higher risk weight coefficients are assigned to trajectory segments with larger local curvature to reflect the danger of accelerated deterioration, while relatively lower weight coefficients are assigned to smoother segments with smaller local curvature to reflect the relative safety of gradual changes. Next, the local curvature weighting coefficients are applied to the previously calculated curve arc lengths for correction calculations. The arc length values ​​are combined with the corresponding curvature weighting coefficients through multiplication operations to weight the original geometric arc lengths based on risk characteristics, obtaining the remaining margin of each key state indicator from the preset warning threshold.

[0086] The following describes an exemplary device for monitoring the operational status of a device based on a digital twin, provided by an embodiment of this application. Figure 2 This is an exemplary hardware structure diagram of a device operation status monitoring device based on digital twin provided in an embodiment of this application.

[0087] In some embodiments, the device operation status monitoring device based on digital twins is a computer device or includes a computer device. The computer device includes a processor, memory, and a network interface connected via a system bus. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device stores data. The network interface of the computer device is used to communicate with other external terminals or servers via a network connection. In some embodiments, the network interface can be a wired network interface; in some embodiments, the network interface can also be a wireless network interface. When the computer program is executed by the processor, it implements the methods in the embodiments of this application.

[0088] Those skilled in the art will understand that Figure 2 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0089] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application 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 scope of the technical solutions of the embodiments of this application.

[0090] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as meaning "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0091] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. 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 (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive), etc.

[0092] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for monitoring equipment operating status based on digital twins, characterized in that, The method includes: Obtain the device parameters and construct a digital twin model of the device in virtual space based on the device parameters; The current operating data of the device is acquired in real time, and the current operating data is mapped to the digital twin model to obtain the twin synchronization state of the digital twin model at the current moment. Based on the twin synchronization state, the state of the digital twin model is extrapolated in the first future preset time period to obtain the virtual operation data corresponding to each time node in the first future preset time period. When time progresses to the first future preset time period, calculate the state deviation between the current running data and the corresponding virtual running data at each time node; The digital twin model is corrected based on the state deviation, and a virtual response feature library is constructed based on the corrected digital twin model. The current operating condition characteristics of the device are obtained, virtual response data matching the current operating condition characteristics are searched in the virtual response feature library, and the state evolution trend of the device in a second future preset time period is obtained based on the virtual response data and the virtual evolution state. The current operating status assessment result of the device is calculated based on the state evolution trend and the current operating data of the device.

2. The equipment operation status monitoring method based on digital twin according to claim 1, characterized in that, The step of performing state deduction on the digital twin model based on the twin synchronization state in a first future preset time period to obtain virtual operation data corresponding to each time node in the first future preset time period includes: Extract the current state parameters from the twin synchronization state, and establish a state evolution equation based on the digital twin model and the current state parameters; Obtain the preset operating boundary conditions within the first future preset time period, and divide the first future preset time period into multiple time nodes according to the preset time step; Using the current state parameters as initial conditions and the running boundary conditions as constraints, the state evolution equation is iteratively solved at each of the time nodes to obtain the virtual running data corresponding to each time node in the first future preset time period.

3. The equipment operation status monitoring method based on digital twin according to claim 1, characterized in that, The step of correcting the digital twin model based on the state deviation includes: Determine whether the state deviation exceeds a preset deviation threshold; When the state deviation exceeds the preset deviation threshold, the correlation between the state deviation and each model parameter in the digital twin model is analyzed to determine the target model parameter that has the greatest impact on the state deviation. Based on the magnitude and direction of the state deviation, calculate the correction amount for the target model parameters; The target model parameters in the digital twin model are adjusted according to the correction amount to obtain the corrected digital twin model.

4. The equipment operation status monitoring method based on digital twin according to claim 1, characterized in that, The step of obtaining the state evolution trend of the device within a second future preset time period based on the virtual response data and the virtual evolution state includes: Extract the equipment performance degradation pattern corresponding to the current operating condition characteristics from the virtual response data; The virtual operation data of each time node within the second future preset time period is extracted from the virtual operation data as the basic evolution data, and the first future preset time period includes the second future preset time period; Calculate the performance degradation amount at each time node within the second future predetermined time period based on the device performance degradation law; The performance degradation at each time point is superimposed onto the basic evolution data at the corresponding time point to obtain the corrected evolution data; Arrange the corrected evolution data of each time point within the second future predetermined time period in a time sequence to form the state evolution trend of the equipment within the second future predetermined time period under the current operating condition.

5. The equipment operation status monitoring method based on digital twin according to claim 1, characterized in that, The step of calculating the current operating status assessment result of the device based on the state evolution trend and the current operating data of the device includes: The evolution trajectory of key state indicators is extracted from the state evolution trend, and the key state indicators in the current running data are compared with the corresponding evolution trajectory to determine the position of each key state indicator in the evolution trajectory. Based on the position of each key status indicator in the evolution trajectory, the remaining margin of each key status indicator from the preset warning threshold is calculated, and the remaining margins of each key status indicator are weighted and combined to obtain the overall health score of the equipment. Based on the comprehensive health score and the state evolution trend, the current operating status assessment result of the equipment is determined.

6. The equipment operation status monitoring method based on digital twin according to claim 5, characterized in that, The step of calculating the remaining margin of each key state indicator from the preset warning threshold based on the position of each key state indicator in the evolution trajectory includes: On each of the aforementioned evolution trajectories, determine the current position point corresponding to the key state indicators in the current operating data, and the warning position point corresponding to the preset warning threshold; The path integral is performed from the current position point to the warning position point along the evolution trajectory to obtain the arc length of the target evolution trajectory curve; Based on the local curvature of the evolution trajectory at the current position, the arc length of the curve is weighted and corrected to obtain the remaining margin of each key state indicator from the preset warning threshold.

7. The equipment operation status monitoring method based on digital twin according to claim 5, characterized in that, The step of determining the current operating status assessment result of the equipment based on the comprehensive health score and the state evolution trend includes: Extract the average rate of change of the key state indicators within the second future preset time period from the state evolution trend, and sum the weighted average rates of change of each key state indicator to obtain the comprehensive rate of change. The current operating status evaluation index is calculated based on the preset operating status evaluation index formula; The preset operating status evaluation index formula is as follows: ; Where R is the current operating status assessment index, H is the comprehensive health score, v is the comprehensive change rate, and Δt is the length of the second future preset time period; The current operating status assessment result of the device is generated based on the current operating status assessment index.

8. A device for monitoring equipment operation status based on digital twins, characterized in that, The digital twin-based device operation status monitoring device includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the digital twin-based device operation status monitoring device to perform the method as described in any one of claims 1-7.

9. A computer program product containing instructions, characterized in that, When the computer program product is run on a digital twin-based device operation status monitoring device, the digital twin-based device operation status monitoring device performs the method as described in any one of claims 1-7.

10. A computer-readable storage medium comprising instructions, characterized in that, When the instructions are executed on a digital twin-based device operation status monitoring device, the digital twin-based device operation status monitoring device performs the method as described in any one of claims 1-7.

Images