A method for dynamic correction of parameters of a line device digital twin model of an MPC

Abstract

The application discloses a kind of MPC's line equipment digital twin model parameter dynamic correction method, belong to the technical field of power system automation, including through distributed edge node acquisition original working condition data, extract load fluctuation, environmental disturbance and mechanical spectrum key features, form chaotic feature vector, the application quantifies this complex interaction by multi-physics field coupling entropy source formula, can more accurately describe equipment state evolution process, the introduction of Lyapunov index further assesses the sensitivity of system to initial disturbance, to early warning potential instability risk, in power transformer overheating fault prediction, can detect thermal-electric coupling anomaly in advance hours, avoid sudden stop, significantly improve the safety and reliability of equipment operation, through double channel parallel computing, realize the real-time adaptive correction of parameter, significantly improve the adaptability to complex working condition.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of power system automation, and particularly relates to a line equipment digital twin model parameter dynamic correction method of MPC. BACKGROUND

[0002] With the development of smart grids, the operation environment of power line equipment is increasingly complex, and is faced with challenges such as multi-source disturbance, nonlinear coupling and parameter time variation. Although the traditional model predictive control has the ability of feedforward control and constraint processing.

[0003] However, the existing line equipment digital twin model parameter dynamic correction method still has certain defects. In the MPC framework, the model is usually assumed to be a single physical field, which leads to incomplete description of the system state evolution. The unmodeled dynamic behavior and parameter drift in the actual equipment will cause the state of the model to be unmatched with the real system. The single-channel linear filtering or fixed threshold strategy is used to process the working condition disturbance, which lacks real-time identification ability for high-frequency chaotic disturbance. The trend signal is extracted by relying on a low-pass filter, which cannot capture instantaneous impact or high-frequency resonance modulation signals, resulting in lag in adjusting the correction parameters and failing to dynamically adapt to complex working conditions. In the parameter correction, experience rules or static thresholds are often relied on, and there is a lack of quantitative mechanism for dynamically matching historical parameters with the current working conditions. Therefore, the line equipment digital twin model parameter dynamic correction method of MPC is proposed. SUMMARY

[0004] The purpose of the present application is to provide a line equipment digital twin model parameter dynamic correction method of MPC to solve the problems raised in the background.

[0005] To achieve the above purpose, the present application provides the following technical solution: a line equipment digital twin model parameter dynamic correction method of MPC, comprising the following steps:

[0006] S1, collecting original working condition data through a distributed edge node, extracting load fluctuation, environmental disturbance and mechanical spectrum key features to form a chaotic feature vector;

[0007] S2, calculating the entropy rate in real time according to the output chaotic feature vector through multi-physical field partial differential coupling and Lyapunov index evaluation;

[0008] S3, generating chaotic quantization factors and pre-correction parameters through double-channel parallel calculation based on the generated entropy rate;

[0009] S4, integrating the output pre-correction parameters and historical parameters, evaluating the fitness through Cauchy-Schwarz inequality, and outputting the optimal parameters;

[0010] S5, map the optimized optimal parameters to a nanosecond-level pulse sequence, and perform FPGA device parameter dynamic compensation correction through the quantum pulse sequence;

[0011] S6, monitor the executed twin entity device mutual information, trigger entropy model reconstruction when the credibility is lower than the threshold, and form a closed loop optimization.

[0012] Preferably, S1, a plurality of node edge sensors are deployed around the key equipment to collect vibration, temperature, current, speed and other raw working condition data in real time. The multi-node data is aligned by timestamp, noise and invalid signals are removed, and the peak value, RMS, kurtosis and other indicators of the signal are calculated.

[0013] It is understood that the instantaneous impact and long-term trend of the quantized load fluctuation are combined with temperature, humidity and other external parameters to extract the environmental interference mode related to the equipment operating state. The frequency spectrum peak value and harmonic component are extracted by Fourier transform, the high-frequency resonance modulation signal is captured by envelope spectrum analysis, and local mechanical damage is identified.

[0014] Based on phase space reconstruction, Lyapunov exponent, fractal dimension and other chaotic characteristic quantities are calculated, time domain and frequency domain features are spliced into high-dimensional feature vectors, and chaotic feature vectors containing linear and nonlinear information are formed.

[0015] Preferably, S2, the multi-physical field partial differential coupling step includes: obtaining the chaotic characteristic vector, constructing a physical field partial differential coupling equation model according to the actual equipment physical characteristics, the single physical field includes a mechanical field and an electrical field, the mechanical parameter is defined as , the gradient of the electrical parameter to the thermal parameter is , indicating the sensitivity of the electrical change to the mechanical state;

[0016] The electrical parameter is , the gradient of the thermal parameter to the electrical state is , the multi-physical field partial differential coupling entropy source implementation formula is:

[0017] ,

[0018] In the formula, represents the multi-physical field partial differential coupling entropy source, represents the coupling weight coefficient of the i-th physical field, represents the electrical parameter, represents the thermal parameter, represents the gradient of the mechanical parameter to the electrical parameter, represents the gradient of the electrical parameter to the thermal parameter, represents the vector module length, represents the weighted sum of coupling terms of all n physical fields, represents the amplification coefficient of chaotic characteristics to coupling entropy, represents the chaotic characteristic vector.

[0019] Preferably, the S2, Lyapunov exponent step includes: perturbing the initial state of the multi-physical field partial differential coupling entropy source to generate two adjacent orbits, a main orbit and a perturbed orbit, and the specific steps include:

[0020] Obtain the current stable running state of the multi-physical field partial differential coupling entropy source as the initial state of the main orbit. The stable running state contains the parameter values of all physical fields. In each parameter dimension of the initial state, a very small perturbation value (perturbation amount) is added to ensure that the system after perturbation is still in the linear response region and will not cause fundamental changes in system behavior.

[0021] The perturbation amount is added to each parameter of the initial state to form a new initial state point. The new initial state point is very close to the original initial point but not exactly the same, which constitutes the starting point of the perturbed orbit.

[0022] Record the state difference of the two orbits at the initial time, and set the time step and the number of iterations.

[0023] Simulate the evolution process of the multi-physical field partial differential coupling entropy source by numerical integration, track the state changes of the main orbit and the perturbed orbit in real time, calculate the distance changes of the two orbits within the time step, and evaluate the divergence speed.

[0024] According to the logarithmic average growth rate of the orbit divergence, the Lyapunov exponent is calculated, and the formula is:

[0025] ,

[0026] In the formula, represents the Lyapunov exponent, represents the time step, represents the system state perturbation vector length at time t, represents the perturbation vector length at the initial time, represents the natural logarithm, represents the correction coefficient of the multi-physical field partial differential coupling entropy source to the Lyapunov exponent, reflecting the enhancement effect of the multi-physical field partial differential coupling entropy source on chaotic behavior.

[0027] Preferably, the S2, real-time entropy change rate step includes: calculating the entropy change rate in real time according to the multi-physical field partial differential coupling entropy source and the Lyapunov exponent, and the formula is:

[0028] ,

[0029] In the formula, represents the entropy rate, represents the entropy rate reference coefficient, represents the exponential function, which amplifies the influence of the Lyapunov exponent on the entropy rate, represents the amplification coefficient of the multi-physical field partial differential coupling entropy source on the entropy rate, reflecting the nonlinear enhancement effect of the multi-physical field partial differential coupling entropy source on the entropy.

[0030] Preferably, the S3, the chaotic quantization factor generation step includes: obtaining the entropy rate, splitting the entropy rate into channel A and channel B according to the time sequence, performing chaotic quantization factor calculation on channel A, and performing pre-correction parameter calculation on channel B; extracting high-frequency components of the entropy rate in channel A through nonlinear filtering, generating a chaotic intensity index through dynamic threshold comparison, and mapping the chaotic intensity index to a chaotic quantization factor according to the chaotic intensity index , the implementation formula is:

[0031] ,

[0032] In the formula, represents the moving average value of the entropy rate in the time window , represents the nonlinear amplification coefficient, which controls the sensitivity of the entropy rate to the CQF, represents the dynamic threshold offset, which adjusts the reference line of the chaotic determination.

[0033] Preferably, the S3, the pre-correction parameter generation step in channel B includes: generating a pre-correction parameter according to the chaotic quantization factor in channel A , the implementation formula is:

[0034] ,

[0035] In the formula, represents the reference correction coefficient, represents the enhancement coefficient of the entropy rate to the correction parameter, aligning of channel A with of channel B in the time dimension, weighting and fusing PCP, taking as the weight factor, dynamically adjusting the correction amplitude of the pre-correction parameter: the higher the CQF value, the larger the correction amplitude; the lower the CQF value, the smaller the correction amplitude, and outputting the final chaotic quantization factor and the pre-correction parameter .

[0036] Preferably, the S4, the optimal parameter step includes: obtaining the pre-correction parameter and the historical parameter sequence, aligning the pre-correction parameter and the historical parameter sequence according to the time stamp, normalizing the parameter vector, and constructing the parameter vector pair , j represents the index of the history parameter.

[0037] The inner product of each pair of parameter vectors is calculated by quantifying the pre-correction parameter and the history parameter sequence with Cauchy-Schwarz inequality The norm of the pre-correction parameter and the history parameter sequence is calculated respectively and The Cauchy-Schwarz inequality quantification value is , The closer to 1, the more similar the current pre-correction parameter and the history parameter are, The smaller, the greater the deviation.

[0038] According to the Cauchy-Schwarz inequality quantification value, the optimal parameter combination is screened: if the goal is stability, the largest parameter pair is selected; if the goal is exploration, the smallest parameter pair is selected, and the results of multiple history parameters are weighted and averaged to obtain a comprehensive fitness value, and if the comprehensive fitness is lower than a preset threshold, a parameter correction mechanism is triggered, and the optimal parameter combination is selected according to the fitness result.

[0039] The target refers to the optimization direction of the system running strategy: stability target and exploration target;

[0040] Stability target: the system is currently running smoothly (such as key indicators such as equipment temperature, vibration, etc. are within the safe range), and the history strategy that has been verified to be effective is retained to avoid adjusting the parameters greatly;

[0041] Exploration target: when the system performance is declining (such as equipment efficiency is decreasing, failure rate is rising), facing new working conditions or needing to break through the current performance bottleneck, new strategies are tried.

[0042] The steps to determine whether to choose the stability target or the exploration target include:

[0043] System running state evaluation: monitor whether the equipment running parameters are within the safe range, if the fluctuation is small and the state is stable, select the stability target; if the fluctuation is large and close to the critical value, select the exploration target.

[0044] Comprehensive fitness value judgment: if the comprehensive fitness value is high, it means that the current parameter combination is good, then select the stability target; if the comprehensive fitness value is low, it means that the current parameter combination is not good, then select the exploration target.

[0045] Preferably, the S5 acquires the optimal parameters, maps the numerical range of the optimal parameters to the coding range of the pulse sequence, converts the quantized parameter values to pulse sequences of corresponding frequencies through Poisson pulse coding, and divides the pulse sequence into fixed-length nanosecond-level time windows.

[0046] By calling the pulse generation module inside the FPGA, nanosecond-level pulses are generated according to the encoded parameters, the optimized pulse parameters are loaded into the memory of the FPGA in real time through the external interface, and the generated nanosecond-level pulse sequence is injected into the target device through the quantum control interface.

[0047] According to the feedback signal of the quantum pulse, the pulse parameters are dynamically adjusted to compensate for the device drift, and the parameter adaptive correction is realized through the real-time feedback of the FPGA.

[0048] Preferably, in the deployment of the line equipment digital twin, an initial digital twin model is constructed based on the equipment design drawings, historical operation data and physical models, real-time operation data of the twin entity equipment are obtained, the physical equipment data and the digital twin model output data are aligned according to the time stamp to form a time sequence pair, and the mutual information value is dynamically calculated through a sliding window statistical method.

[0049] The mutual information is compared with the preset credibility threshold, if the mutual information is lower than the threshold for continuous N time windows, it is determined that the model credibility is insufficient, and the reconstructed model is deployed to the digital twin system to replace the original model.

[0050] Compared with the prior art, the beneficial effects of the present application are:

[0051] 1、The present application can more accurately describe the evolution process of the equipment state by quantifying the multi-physical field coupling entropy source formula, and the introduction of the Lyapunov index further evaluates the sensitivity of the system to the initial disturbance, thereby early warning the potential instability risk, in the prediction of the overheat fault of the power transformer, the thermal-electric coupling abnormality can be detected hours in advance to avoid sudden shutdown, and the safety and reliability of the equipment operation are significantly improved;

[0052] 2、The present application realizes real-time adaptive correction of parameters through double-channel parallel calculation, in the power grid frequency fluctuation correction, channel A quickly identifies high-frequency chaotic disturbance through nonlinear filtering and dynamic threshold comparison, and maps it to a chaotic quantization factor, while channel B dynamically adjusts the pre-correction parameter according to the chaotic quantization factor, realizes real-time adaptive correction of parameters, and significantly improves the adaptability to complex working conditions;

[0053] 3、The present application quantifies the similarity of the pre-correction parameter and the historical parameter through Cauchy-Schwarz inequality, dynamically calculates the inner product and the norm, and selects the parameter combination most matched with the current working condition, so as to avoid over-correction or insufficient correction, if the target is stability, the parameter pair with high similarity is selected, if the target is exploratory, the parameter pair with large difference is selected, supporting flexible strategy switching in different scenes, and significantly improving the stability of long-term operation of the equipment;

[0054] 4、The application maps the optimal parameters into nanosecond-level pulse sequences through Poisson pulse coding, realizes real-time correction at the hardware level through FPGA, completes pulse generation and injection at the nanosecond level through the parallel computing capability of FPGA, ensures accurate control of equipment parameters, dynamically adjusts parameters according to the feedback signal of the quantum pulse through the real-time feedback mechanism of FPGA, forms a closed-loop compensation, effectively deals with equipment drift, and significantly improves dynamic performance. BRIEF DESCRIPTION OF DRAWINGS

[0055] Figure 1 The running process of the MPC line equipment digital twin model parameter dynamic correction method Figure One ;

[0056] Figure 2 The running process of the MPC line equipment digital twin model parameter dynamic correction method Figure Two ;

[0057] Figure 3 The running process of the MPC line equipment digital twin model parameter dynamic correction method Figure Three ;

[0058] Figure 4 The running process of the MPC line equipment digital twin model parameter dynamic correction method Figure Four . DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the application will be described clearly and completely below with reference to the drawings in the embodiments of the application. Obviously, the described embodiments are only part of the embodiments of the application, rather than all the embodiments of the application. Based on the embodiments in the application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the application.

[0060] Embodiment:

[0061] Please refer to Figures 1-4 , the application provides a technical solution: comprising the following steps:

[0062] S1, collect original working condition data through a distributed edge node, extract load fluctuation, environmental disturbance and mechanical spectrum key features, and form a chaotic feature vector;

[0063] S2, according to the output chaotic feature vector, through multi-physical field partial differential coupling and Lyapunov index evaluation, real-time calculation of entropy change rate;

[0064] S3, based on the generated entropy change rate, generate chaotic quantization factors and pre-correction parameters through double-channel parallel computing;

[0065] S4, integrate the pre-corrected parameters and historical parameters, evaluate the fitness through Cauchy-Schwarz inequality, and output the optimal parameters;

[0066] S5, map the optimized optimal parameters to a nanosecond-level pulse sequence, and perform FPGA device parameter dynamic compensation correction through the quantum pulse sequence;

[0067] S6, monitor the mutual information of the executed twin entity device, trigger entropy model reconstruction when the credibility is lower than the threshold, and form a closed-loop optimization.

[0068] In this embodiment, S1, a plurality of node edge sensors are deployed around the key equipment, including but not limited to transformers, circuit breakers, transmission lines, current transformers, voltage transformers, power electronic devices, etc. Real-time collection of vibration, temperature, current, speed and other original working condition data, aligning multi-node data through time stamp, removing noise and invalid signals, calculating signal peak value, RMS, kurtosis and other indicators.

[0069] It is understood that the instantaneous impact and long-term trend of the quantized load fluctuation are combined with temperature, humidity and other external parameters to extract the environmental interference mode related to the device operating state, extract the frequency spectrum peak value and harmonic component through Fourier transform, capture the high-frequency resonance modulation signal through envelope spectrum analysis, and identify local mechanical damage.

[0070] Based on phase space reconstruction, calculate Lyapunov exponent, fractal dimension and other chaotic characteristic quantities, splice time domain, frequency domain features and chaotic features into a high-dimensional feature vector, and form a chaotic feature vector containing linear and nonlinear information.

[0071] In this embodiment, S2, the multi-physical field partial differential coupling step includes: obtaining a chaotic characteristic vector, constructing a physical field partial differential coupling equation model according to the actual device physical characteristics, a single physical field includes a mechanical field and an electrical field, the mechanical parameter is defined as , the gradient of the electrical parameter to the thermal parameter is , which represents the sensitivity of the electrical change to the mechanical state;

[0072] The electrical parameter is , the gradient of the thermal parameter to the electrical state is , which represents the sensitivity of the thermal change to the electrical state, and the multi-physical field partial differential coupling entropy source implementation formula is:

[0073] ,

[0074] In the formula, represents the multi-physical field partial differential coupling entropy source, represents the coupling weight coefficient of the i-th physical field, represents an electrical parameter, represents a thermal parameter, represents a gradient of a mechanical parameter to an electrical parameter, represents a gradient of an electrical parameter to a thermal parameter, represents a vector norm, represents a weighted sum of coupling terms of all n physical fields, represents an amplification coefficient of chaotic features to coupling entropy, represents a chaotic feature vector.

[0075] In this embodiment, the S2, Lyapunov exponent step includes: perturbing the initial state of the multi-physical field partial differential coupling entropy source to generate two adjacent orbits, a main orbit and a perturbed orbit, and the specific steps include:

[0076] Obtain the current stable running state of the multi-physical field partial differential coupling entropy source as the initial state of the main orbit. The stable running state contains the parameter values of all physical fields. In each parameter dimension of the initial state, a very small perturbation value (perturbation amount) is added, which is usually to orders of magnitude, to ensure that the system after perturbation is still in the linear response region and will not cause fundamental changes in system behavior.

[0077] Add the perturbation amount to each parameter of the initial state to form a new initial state point. The new initial state point is very close to the original initial point but not exactly the same, which constitutes the starting point of the perturbed orbit.

[0078] Record the state difference of the two orbits at the initial time, and set the time step and the number of iterations.

[0079] In this embodiment, the evolution process of the multi-physical field partial differential coupling entropy source is simulated by numerical integration, the state changes of the main orbit and the perturbed orbit are tracked in real time, the distance changes of the two orbits within the time step are calculated, and the divergence speed is evaluated.

[0080] According to the logarithmic average growth rate of the orbit divergence, the Lyapunov exponent is calculated, and the formula is:

[0081] ,

[0082] In the formula, represents the Lyapunov exponent, represents the time step, represents the system state perturbation vector norm at time t, represents the perturbation vector norm at the initial time, represents the natural logarithm, This represents the correction coefficient of the multiphysics partial differential coupling entropy source to the Lyapunov exponent, reflecting the enhancing effect of the multiphysics partial differential coupling entropy source on chaotic behavior.

[0083] In this embodiment, step S2, the real-time entropy rate change step, includes: calculating the entropy rate change in real time based on the multiphysics partial differential coupling entropy source and the Lyapunov exponent, with the formula as follows:

[0084] ,

[0085] In the formula, Represents the rate of entropy change. Represents the base coefficient for entropy rate of change. This represents an exponential function, used to amplify the effect of the Lyapunov exponent on the rate of entropy change. It represents the amplification factor of the entropy rate of the multiphysics partial differential coupling entropy source, reflecting the nonlinear enhancement effect of the entropy rate on the entropy change by the multiphysics partial differential coupling entropy source.

[0086] In this embodiment, step S3, the chaotic quantization factor generation step, includes: obtaining the entropy change rate, splitting the entropy change rate into channel A and channel B according to the time series, calculating the chaotic quantization factor for channel A, and calculating the pre-correction parameter for channel B; and extracting high-frequency components from the entropy change rate in channel A through nonlinear filtering.

[0087] In this embodiment, a chaos intensity index is generated through dynamic threshold comparison, and then mapped to a chaos quantization factor. The formula is as follows:

[0088] ,

[0089] In the formula, This indicates the rate of entropy change within a time window. The moving average within, This represents the nonlinear amplification factor, controlling the sensitivity of the entropy rate of change to the CQF. This represents the dynamic threshold offset, which adjusts the baseline for chaos determination.

[0090] In this embodiment, step S3, generating pre-correction parameters in channel B, includes: generating pre-correction parameters based on the chaotic quantization factor in channel A. The formula is as follows:

[0091] ,

[0092] In the formula, Indicates the reference correction factor. This represents the enhancement factor of the entropy change rate on the correction parameter, which will affect channel A. With channel B Aligning in time dimension, weighted fusion of PCP to As a weight factor, dynamically adjust the correction amplitude of pre-correction parameter: the higher the CQF value, the larger the correction amplitude; the lower the CQF value, the smaller the correction amplitude, and output the final chaotic quantization factor And the pre-correction parameter When , that is, the current entropy rate is equal to the moving average value of the entropy rate in the time window , indicating that the system is in a stable state without abnormal fluctuations, when , the correction amplitude increases; when , the correction amplitude decreases.

[0093] In this embodiment, the S4, optimal parameter step includes: obtaining a pre-correction parameter and a historical parameter sequence, aligning the pre-correction parameter and the historical parameter sequence according to time stamps, normalizing the parameter vector, and constructing a parameter vector pair , j represents a historical parameter index.

[0094] The pre-correction parameter and the historical parameter sequence are quantified by the Cauchy-Schwarz inequality, and for each parameter vector pair, the inner product is calculated, the norms and of the pre-correction parameter and the historical parameter sequence are calculated respectively, and the Cauchy-Schwarz inequality quantification value is , The closer to 1, the more similar the current pre-correction parameter and the historical parameter, The smaller, the greater the deviation.

[0095] In this embodiment, the optimal parameter combination is selected according to the Cauchy-Schwarz inequality quantification value: if the target is stability, the parameter pair with the largest value is selected; if the target is exploratory, the parameter pair with the smallest value is selected, and the results of multiple historical parameters are weighted and averaged to obtain a comprehensive fitness value, if the comprehensive fitness is lower than a preset threshold, a parameter correction mechanism is triggered, and the optimal parameter combination is selected according to the fitness result.

[0096] The target indicates the optimization direction of the system running strategy: stability target and exploratory target.

[0097] Stability target: the system is currently running smoothly (such as key indicators such as device temperature, vibration, etc. are within the safe range), the historical strategy that has been verified to be effective is retained, and the parameters are not adjusted significantly.

[0098] Exploratory target: when the system performance decreases (such as device efficiency decreases, failure rate rises), faces new working conditions or needs to break through the current performance bottleneck, new strategies are tried. ​​​

[0099] determining whether to select a stability target or an exploratory target, the steps comprising:

[0100] System running state evaluation: Monitor whether the equipment running parameters are within the safe range. If the fluctuation is small and the state is stable, select the stability target; if the fluctuation is large and close to the critical value, select the exploratory target.

[0101] Comprehensive fitness value judgment: If the comprehensive fitness value is high, it indicates that the current parameter combination is effective, and the stability target is selected; if the comprehensive fitness value is low, it indicates that the current parameter combination is not effective, and the exploratory target is selected.

[0102] In this embodiment, S5, the optimal parameters are obtained, the numerical range of the optimal parameters is mapped to the encoding range of the pulse sequence, the quantized parameter value is converted into a pulse sequence of corresponding frequency through Poisson pulse encoding, and the pulse sequence is divided into fixed-length nanosecond-level time windows.

[0103] In this embodiment, by calling the pulse generation module inside the FPGA, nanosecond-level pulses are generated according to the encoded parameters, the optimized pulse parameters are loaded into the memory of the FPGA in real time through the external interface, and the generated nanosecond-level pulse sequence is injected into the target device through the quantum control interface.

[0104] According to the feedback signal of the quantum pulse, the pulse parameters are dynamically adjusted to compensate for the equipment drift, and the parameter adaptive correction is realized through the real-time feedback of the FPGA.

[0105] In this embodiment, S6, when deploying the line equipment digital twin, an initial digital twin model is constructed based on the equipment design drawings, historical operation data and physical models, real-time operation data of the twin entity equipment are obtained, the physical equipment data and the digital twin model output data are aligned according to the time stamp to form a time sequence pair, and the mutual information value is dynamically calculated through the sliding window statistical method.

[0106] The mutual information is compared with the preset credibility threshold value. If the mutual information is continuously lower than the threshold value in N time windows, it is determined that the model credibility is insufficient, and the reconstruction is triggered. The reconstructed model is deployed to the digital twin system to replace the original model.

[0107] Working principle: By deploying multiple node edge sensors around the key equipment, real-time collection of vibration, temperature, current, speed and other original working condition data is realized, and the time deviation of multi-source data is eliminated through time stamp alignment. Key features of load fluctuation, environmental disturbance and mechanical spectrum are extracted using signal processing technology to quantify the change trend of equipment running state. On this basis, Lyapunov index, fractal dimension and other chaotic characteristic quantities are calculated through phase space reconstruction and nonlinear dynamics analysis, and time domain, frequency domain and nonlinear features are fused into high-dimensional chaotic feature vectors.

[0108] Based on the physical characteristics of the device, a multi-physical field partial differential coupling equation model is constructed, the interaction effect between each physical field is quantified, the chaos characteristic vector is introduced as the input, the multi-physical field coupling entropy source is calculated, the nonlinear change of the energy distribution of the system is reflected, further, the evolution process of the entropy source is simulated by numerical integration, the sensitivity of the system to the initial disturbance is evaluated, and the entropy change rate is calculated in real time combined with the nonlinear enhancement effect of the entropy source; the entropy change rate calculated in real time is divided into two channels and processed in parallel, channel A extracts high-frequency chaotic components through nonlinear filtering, generates a chaos intensity index combined with dynamic threshold comparison, and maps it into a chaos quantization factor; Channel B allocates pre-correction parameters according to the chaos quantization factor, dynamically adjusts the weight of the pre-correction parameter through time dimension alignment and weighted fusion, standardizes the pre-correction parameter after aligning with the historical parameter sequence, quantifies the similarity of the two by using Cauchy-Schwarz inequality, selects the parameter combination with the highest or lowest similarity according to the target demand, and generates a comprehensive fitness value through weighted average, if the fitness is lower than the threshold, the parameter correction mechanism is triggered, and the correction strategy is dynamically adjusted; The optimal parameters optimized are mapped into a nanosecond pulse sequence, the parameter values are converted into pulse signals of corresponding frequency through Poisson pulse coding, the FPGA hardware module generates control signals in real time according to the coded pulse sequence, and injects the target device through the quantum control interface, dynamically compensates the device drift, and dynamically calculates the mutual information between the physical device and the digital twin model through the sliding window statistical method, evaluates the data consistency of the two, when the mutual information is continuously lower than the preset threshold, it is determined that the model credibility is insufficient, the model reconstruction mechanism is triggered, and the digital twin model is updated based on the latest working condition data and chaos characteristic vector, and is redeployed to the system.

[0109] Although embodiments of the present application have been shown and described, it will be understood by those having ordinary skill in the art that various changes, modifications, alternatives, and variations can be made thereto without departing from the principles and spirit of the application, and the scope of the present application is defined by the appended claims and their equivalents.

[0110] The above describes the present application and its embodiments, which are not restrictive, and the embodiments shown in the drawings are only one of the embodiments of the present application, and the actual structure is not limited thereto. In summary, if a person skilled in the art is inspired by it, without departing from the purpose of the present application, without creative design, similar structure and embodiments of the technical solution can be designed, which shall belong to the protection scope of the present application.

Claims

1. A method for dynamic correction of parameters in a digital twin model of MPC line equipment, characterized in that, Includes the following steps: S1. Collect raw operating condition data through distributed edge nodes, extract key features of load fluctuation, environmental disturbance and mechanical spectrum, and form a chaotic feature vector; S2. Based on the output chaotic feature vector, the entropy rate is calculated in real time through multi-physics partial differential coupling and Lyapunov exponent evaluation. S3. Based on the generated entropy change rate, the chaotic quantization factor and pre-correction parameters are generated through dual-channel parallel computation. S4. Integrate the pre-corrected parameters and historical parameters, evaluate the fitness using the Cauchy-Schwarz inequality, and output the optimal parameters; S5. Map the optimized parameters to nanosecond-level pulse sequences, and use quantum pulse sequences to perform dynamic compensation and correction of FPGA device parameters; S6. Monitor the mutual information of the twin entity devices being executed. When the credibility is lower than the threshold, trigger the entropy model reconstruction to form a closed-loop optimization. The S2 step, the real-time entropy rate change step, includes: calculating the entropy rate change in real time based on the multi-physics partial differential coupled entropy source and the Lyapunov exponent, with the formula as follows: ， In the formula, Represents the rate of entropy change. Represents the base coefficient for entropy rate of change. Represents an exponential function. The Lyapunov index represents the Lyapunov index. Indicates the time step. This represents the amplification factor of the entropy rate by the multiphysics partial differential coupling entropy source. This represents a multiphysics partial differential coupling entropy source; The S3 step of generating the chaos quantization factor includes: obtaining the entropy change rate; splitting the entropy change rate into channel A and channel B according to the time series; extracting high-frequency components from the entropy change rate in channel A through nonlinear filtering; generating a chaos intensity index through dynamic threshold comparison; and mapping the chaos intensity index to a chaos quantization factor. .

2. The method for dynamic correction of parameters of a digital twin model of MPC line equipment according to claim 1, characterized in that: The S2 step, multi-physics partial differential coupling, includes: obtaining chaotic feature vectors; constructing a physical field partial differential coupling equation model based on the actual physical characteristics of the equipment; where a single physical field includes a mechanical field and an electrical field; and the mechanical parameters are defined as follows: Electrical parameters are The formula for realizing the entropy source of multiphysics partial differential coupling is: ， In the formula, This represents a multiphysics partial differential coupling entropy source. This represents the coupling weight coefficient of the i-th physical field. Indicates electrical parameters, Represents thermodynamic parameters, This represents the gradient of mechanical parameters with respect to electrical parameters. This represents the gradient of electrical parameters with respect to thermodynamic parameters. Represents the magnitude of the vector. This represents a weighted summation of the coupling terms over all n physical fields. This represents the amplification factor of chaotic features on coupling entropy. This represents the chaotic eigenvector.

3. The method for dynamic correction of parameters of a digital twin model of MPC line equipment according to claim 2, characterized in that: The S2 step, the Lyapunov exponent step, includes: perturbing the initial state of the multiphysics partial differential coupled entropy source to generate two adjacent orbits, recording the state difference between the two orbits at the initial moment, setting the time step and the number of iterations, and calculating the Lyapunov exponent, with the formula as follows: ， In the formula, The Lyapunov index represents the Lyapunov index. Indicates the time step. Let represent the magnitude of the system state perturbation vector at time t. This represents the magnitude of the perturbation vector at the initial moment. Represents the natural logarithm. This represents the correction coefficient of the Lyapunov exponent to the multiphysics partial differential coupling entropy source.

4. The method for dynamic correction of parameters of a digital twin model of MPC line equipment according to claim 1, characterized in that: The step S3, generating pre-calibration parameters in channel B, includes: generating pre-calibration parameters based on the chaotic quantization factor in channel A. The formula is as follows: ， In the formula, Indicates the reference correction factor. Represents the chaos quantization factor. This represents the enhancement factor of the entropy change rate on the correction parameter. Represents the rate of entropy change. This indicates the rate of entropy change within a time window. The moving average within.

5. The method for dynamic correction of parameters of a digital twin model of MPC line equipment according to claim 1, characterized in that: The optimal parameter step in S4 includes: obtaining the pre-correction parameters and historical parameter sequences, constructing parameter vector pairs, quantizing the pre-correction parameters and historical parameter sequences using the Cauchy-Schwarz inequality, and calculating the inner product for each parameter vector pair. The norms of the pre-correction parameter and historical parameter sequences are calculated separately, and the Cauchy-Schwarz inequality quantization value is... ; The optimal parameter combination is selected based on the quantized values ​​of the Cauchy-Schwarz inequality: if the objective is stability, then choose... The largest parameter pair; if the goal is exploratory, then choose... The smallest parameter pair, for multiple historical parameters The results are weighted and averaged to obtain the overall fitness value. If the overall fitness is lower than the preset threshold, the parameter correction mechanism is triggered, and the optimal parameter combination is selected based on the fitness results.

6. The method for dynamic correction of parameters of a digital twin model of MPC line equipment according to claim 1, characterized in that: In step S5, the optimal parameters are obtained, and the numerical range of the optimal parameters is mapped to the encoding range of the pulse sequence. Through Poisson pulse coding, the quantized parameter values ​​are converted into pulse sequences of corresponding frequencies. The pulse sequence is divided into fixed-length nanosecond-level time windows. By calling the pulse generation module inside the FPGA, nanosecond-level pulses are generated according to the encoded parameters. The optimized pulse parameters are loaded into the FPGA's memory in real time through an external interface. The generated nanosecond-level pulse sequence is injected into the target device through a quantum control interface. Based on the feedback signal of the quantum pulse, the pulse parameters are dynamically adjusted to compensate for device drift. Parameter adaptive correction is achieved through real-time feedback from the FPGA.

7. The method for dynamic correction of parameters of a digital twin model of MPC line equipment according to claim 1, characterized in that: In step S6, real-time operating data of the twin physical device is acquired, and the physical device data and the output data of the digital twin model are aligned by timestamp to form a time series pair. The mutual information value is dynamically calculated by the sliding window statistical method, and the mutual information value is compared with the preset credibility threshold. If the mutual information value is lower than the threshold for N consecutive time windows, it is determined that the model credibility is insufficient, and reconstruction is triggered. The reconstructed model is deployed to the digital twin system for updating.

Images