AI-based fault analogue simulation test digital electric energy meter calibration method

Abstract

The invention discloses an AI-based fault analogue simulation test digital electric energy meter calibration method, which comprises the following steps: acquiring historical operation data of an electric energy meter, and generating a fault mode by analyzing the historical operation data of the electric energy meter by using an artificial intelligence-based multi-mode fault simulation algorithm; based on the strength of the fault mode, analyzing the influence of the fault mode on the performance of the electric energy meter through an electric energy meter performance degradation prediction algorithm based on the fault mode, and calculating to obtain a response value of performance parameters of the electric energy meter; based on the performance parameter response value of the electric energy meter, a verification error of each performance parameter is calculated through a digital electric energy meter performance verification algorithm; and according to the performance parameter verification error, parameters are optimized through a self-adaptive parameter updating algorithm. The method has the advantages of being good in fault simulation comprehensiveness, accurate in performance degradation prediction, high in verification error sensitivity, good in adaptability, fast in parameter convergence and the like.

Description

Technical Field

[0001] The invention belongs to the technical field of electric energy meter testing and calibration, and particularly relates to a digital electric energy meter calibration method. Background Art

[0002] With the rapid development of smart grids and digital power metering technologies, digital energy meters, as core devices for power metering, monitoring, and management, have become an essential component of modern power systems. Compared to traditional mechanical energy meters, digital energy meters offer higher measurement accuracy, more powerful data processing capabilities, more stable communication performance, and a wider range of applications. They play a key role in ensuring the stable operation of power systems, guaranteeing the accuracy of metering data, and safeguarding the rights and interests of power users. However, traditional energy meter calibration methods are often time-consuming and labor-intensive. In particular, on-site calibration processes are subject to inefficiency, susceptibility to human error or improper equipment commissioning, and may not accurately reflect the actual operating status of the energy meter due to environmental interference.

[0003] To this end, technical personnel in this field usually use a verification method based on fault simulation testing to test and calibrate electricity meters. By simulating different fault scenarios in a simulation environment, the performance of the electricity meter under various working conditions is evaluated, and its measurement accuracy is verified, thereby comprehensively improving the efficiency and accuracy of the electricity meter calibration work.

[0004] However, the existing verification methods still have the following problems: 1. The complexity and diversity of failure modes are difficult to fully simulate: Existing methods rely on a single manually preset failure mode and cannot fully cover the complex and diverse failure scenarios that electricity meters may encounter in actual operation.

[0005] 2. Insufficient accuracy in performance degradation prediction: Existing methods use linear models, which are difficult to accurately reflect the complex relationship between fault intensity and performance degradation.

[0006] 3. Insufficient sensitivity and adaptability of performance verification errors: Existing methods use a fixed threshold to compare the predicted value with the standard value to calculate the static error, ignoring the impact of fault severity and performance degradation on the error.

[0007] 4. Insufficient convergence and stability during parameter optimization: Parameter adjustment (such as fault amplitude) relies on manual trial and error or simple gradient descent, which has slow convergence and is prone to falling into local extremes or oscillations. Especially under complex fault modes, parameter optimization is inefficient and difficult to quickly adapt to diverse operating conditions, resulting in a balance between prediction accuracy and test efficiency. Summary of the Invention

[0008] The present invention proposes an AI-based fault simulation test digital electricity meter calibration method, the purpose of which is to solve the problems existing in existing calibration methods, such as the complexity and diversity of fault modes that are difficult to fully simulate, the insufficient accuracy of performance degradation prediction, the insufficient sensitivity and adaptability of performance calibration errors, and the insufficient convergence and stability during parameter optimization.

[0009] The technical solutions of the present invention are as follows: A digital energy meter calibration method based on AI fault simulation test includes the following steps: Step S1: Obtain historical operating data of the electric energy meter, and use a multi-modal fault simulation algorithm based on artificial intelligence to generate a fault mode by analyzing the historical operating data of the electric energy meter; Step S2: Based on the fault mode intensity, the impact of the fault mode on the performance of the electric energy meter is analyzed by using a fault mode-based electric energy meter performance degradation prediction algorithm, and a response value of the electric energy meter performance parameter is calculated; Step S3: Based on the performance parameter response value of the electric energy meter, a calibration error of each performance parameter is calculated using a digital electric energy meter performance calibration algorithm; Step S4: check the error according to the performance parameters and optimize the parameters through the adaptive parameter update algorithm.

[0010] As a further improvement of the AI-based fault simulation test digital energy meter calibration method, step S1 specifically includes: Step S1-1: Acquire historical operating data of the electric energy meter, wherein the historical operating data includes operating records of the electric energy meter under various environmental conditions, and divide the historical operating data of the electric energy meter into a training set and a validation set. The training set is used to train the artificial intelligence model, and the validation set is used to evaluate the accuracy of the fault mode generated by the artificial intelligence model; Step S1-2: Use a multi-modal fault simulation algorithm based on artificial intelligence to generate multiple fault modes by analyzing the historical operating data of the electricity meter.

[0011] As a further improvement to the AI-based fault simulation test digital energy meter calibration method, the AI-based multimodal fault simulation algorithm generates fault modes by analyzing the historical operating data of the energy meter, combining three fault influencing factors: periodic, transient, and sudden. It also introduces random noise to enhance authenticity, simulating complex fault scenarios that digital energy meters may encounter in actual operation. Periodic faults appear as disturbances that fluctuate regularly over time and are used to simulate a sine wave-like fluctuation pattern; Transient faults are simulated by exponential decay functions, which cause rapid changes in a short period of time. The duration and impact range of transient faults are controlled by adjusting the decay rate. Mutational faults are used to simulate emergencies; Random noise is generated according to a normal distribution, and the fluctuation range is controlled by a standard deviation parameter.

[0012] As a further improvement of the AI-based fault simulation test digital electricity meter calibration method: in step S2, the fault mode-based electricity meter performance degradation prediction algorithm calculates the direct impact on the specific performance parameters of the electricity meter for each fault mode, introduces a sensitivity coefficient, and measures the sensitivity of a specific fault to a specific performance.

[0013] As a further improvement of the AI-based fault simulation test digital electricity meter calibration method: in step S2, the fault mode-based electricity meter performance degradation prediction algorithm performs nonlinear processing on the fault mode intensity to reflect the nonlinear response differences of different individual electricity meters to faults.

[0014] As a further improvement of the AI-based fault simulation test digital electricity meter calibration method: in step S2, the fault mode-based electricity meter performance degradation prediction algorithm reflects the fault resistance of performance parameters through a dynamic resistance factor. The resistance baseline under fault-free conditions is used as the initial value. As the fault mode intensity increases, the dynamic resistance factor gradually decreases, reflecting the performance degradation of the electricity meter under continuous faults; the attenuation rate of the dynamic resistance factor is controlled by the degradation coefficient.

[0015] As a further improvement of the AI-based fault simulation test digital energy meter calibration method: in step S3, the digital energy meter performance calibration algorithm processes each performance parameter one by one in the following manner: Extract the energy meter performance parameter response value and the corresponding standard threshold, calculate the relative deviation between the two, introduce a pre-set weighting factor to reflect the importance of different performance parameters in the overall performance of the energy meter, and eliminate the influence of positive and negative signs by squaring to reflect the absolute magnitude of the deviation; Based on the accumulated information of fault mode intensity, a dynamic severity factor is calculated to enhance the sensitivity of the error to severe faults; A dynamic adjustment term is introduced to adjust the calibration error based on fault severity and performance degradation. Specifically, the inverse of the sum of the meter's performance parameter response value and a smoothing constant is multiplied by the dynamic severity factor to create an amplification term. This amplifies the calibration error, making it more sensitive to the negative impact of severe faults on performance. Perform square root processing on the above calculation results to obtain the final calibration error value of each performance parameter.

[0016] As a further improvement of the AI-based fault simulation test digital electricity meter calibration method: when calculating the dynamic severity factor, an initial severity coefficient is used as a benchmark value, and then dynamically adjusted according to the ratio of the total intensity of all current fault modes to the preset maximum fault mode intensity.

[0017] As a further improvement to the AI-based fault simulation test digital energy meter calibration method: in step S4, before adjusting the parameters, the direction and degree of influence of the parameter change on the calibration error are determined, that is, the sensitivity of the parameters is calculated: the sensitivity of the calibration error to the fault mode and the sensitivity of the fault mode to the target parameter are analyzed, and combined through the chain method to obtain the overall influence of the parameters on the calibration error; an exponential decay factor is introduced. When the error is large, the value of the exponential decay factor is small, and the influence of the sensitivity is amplified, thereby accelerating the adjustment. When the error is small, the exponential decay factor is close to 1, and the influence of the sensitivity is moderately weakened; A momentum term is introduced to smooth the parameter update process and reduce the oscillation during adjustment. The momentum term is calculated based on the difference between the current parameter value and the previous parameter value, multiplied by a momentum coefficient.

[0018] As a further improvement of the AI-based fault simulation test digital electricity meter calibration method: in step S4, in order to ensure the physical rationality of the parameters, range constraints are set to prevent the parameters from exceeding the actual acceptable range.

[0019] Compared with the prior art, the present invention has the following positive effects: 1. This invention automatically generates composite fault modes encompassing periodic, transient, and sudden faults by acquiring historical operating data from electricity meters (such as voltage fluctuations, temperature changes, humidity effects, and external interference) and combining it with an AI-based multimodal fault simulation algorithm. This AI-based learning method adaptively generates fault modes and dynamically adjusts them based on the historical operating data of different electricity meters. This avoids the limitations of traditional methods based on artificial assumptions, significantly improves the authenticity and intelligence of the test, and comprehensively enhances the coverage of fault modes.

[0020] 2. The electric energy meter performance degradation prediction algorithm of the present invention uses fault mode intensity as input and incorporates sensitivity coefficients, nonlinear transformations, and dynamic resistance factors to calculate the response values of electric energy meter performance parameters (such as metering accuracy). This method intuitively reflects the performance of electric energy meters under different fault intensities, accurately capturing the cumulative effects of faults on performance and individual differences. It can accurately quantify the impact of faults on electric energy meter performance, providing a reliable basis for performance degradation analysis. Furthermore, due to the use of nonlinear processing and resistance factor adjustment, this method is applicable to electric energy meters of different types and states, providing greater adaptability and significantly reducing the need for individual testing of large numbers of samples in traditional manual testing.

[0021] 3. The digital energy meter performance verification algorithm of this invention comprehensively considers the impact of faults and the importance of performance. By introducing dynamic adjustment terms and dynamic severity factors, it amplifies the impact of severe faults on errors, facilitating timely detection of potential meter failure risks and demonstrating good sensitivity and adaptability. Furthermore, the error magnitude is processed through square root processing, resulting in intuitive and reasonable values, facilitating subsequent parameter adjustments and performance improvements, ensuring that the verification results are more closely aligned with practical application requirements.

[0022] 4. To address the issues of insufficient convergence and stability during parameter optimization, this invention optimizes parameters (such as fault amplitude) using an adaptive parameter update algorithm based on performance parameter verification errors. This brings the fault mode and performance prediction results closer to the standard value, improving the reliability of the test system. The introduction of a momentum term and an exponential decay factor significantly accelerates iterative convergence, reduces computational resource consumption, and avoids potential oscillation during the optimization process. Furthermore, by setting range constraints to ensure the physical rationality of the parameters, the optimization results are applicable to real-world electricity meter testing scenarios, improving the reliability and stability of the test system. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 Flowchart of the method of the present invention. DETAILED DESCRIPTION

[0024] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0025] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0026] like Figure 1 , a digital energy meter calibration method based on AI fault simulation test, comprising the following steps: Step S1: Obtain historical operating data of the electric energy meter, use a multi-modal fault simulation algorithm based on artificial intelligence, and generate multiple fault modes by analyzing the historical operating data of the electric energy meter.

[0027] The specific process is: Step S1-1: Obtain historical operating data of the electricity meter, including operating records of the electricity meter under various environmental conditions, such as voltage fluctuations, temperature changes, humidity effects, and external interference (such as electromagnetic interference or power outages). After processing, the historical operating data of the electricity meter is divided into a training set and a validation set. The training set is used to train the artificial intelligence model, and the validation set is used to evaluate the accuracy of the failure patterns generated by the artificial intelligence model.

[0028] Step S1-2: Use a multi-modal fault simulation algorithm based on artificial intelligence to generate multiple fault modes by analyzing the historical operating data of the electricity meter.

[0029] The core of the algorithm lies in combining periodic, transient and sudden faults, while introducing random noise to enhance authenticity, aiming to simulate the complex fault scenarios that digital electricity meters may encounter in actual operation.

[0030] The failure mode includes three failure influencing factors: periodic failure, transient failure and sudden failure.

[0031] The periodic fault is manifested as a disturbance that fluctuates regularly over time, simulating a sine wave-like fluctuation pattern, such as a periodic spike in voltage, with a starting point and fluctuation speed defined by an oscillation frequency and phase shift.

[0032] Transient faults are superimposed on periodic faults. These faults simulate rapid changes occurring within a short period of time using an exponential decay function. The duration and impact of transient faults are controlled by adjusting the decay rate. When the decay rate is fast, the impact of the fault disappears quickly, while when the decay rate is slow, the impact persists for a longer period. This, combined with the decay mechanism of periodic faults, forms a composite pattern that combines volatility with short-term impacts.

[0033] The sudden fault simulates an emergency, such as a momentary power outage, and uses a step change to indicate that the fault suddenly occurs and persists at a certain moment. Specifically, when the time reaches a preset starting point, the fault intensity will suddenly increase to a fixed value and remain unchanged thereafter. If the current time is less than the starting point, the jump effect is zero. Once the time exceeds the starting point, the jump effect takes effect immediately.

[0034] In order to enhance the authenticity and unpredictability of the failure mode, random noise is further introduced. The random noise is generated according to the normal distribution, and the fluctuation range is controlled by a standard deviation parameter to ensure that the generated failure mode is both diverse and close to the actual scenario.

[0035] The calculation formula for the failure mode intensity generated by the multimodal fault simulation algorithm based on artificial intelligence is: ; in, Indicates the the intensity of each failure mode; express The factors affecting the failure are superimposed. ; Indicates the The fault magnitude of each fault influencing factor is used to measure the impact of the fault influencing factor on the electric energy meter failure, and is learned from historical operation data through an artificial intelligence model; The exponential decay function is used to simulate the short-term nature of transient faults, ensuring that the fault impact does not last indefinitely but gradually weakens over time; Indicates the The decay rate of each fault influencing factor controls the decay speed and reflects the duration of transient faults. It is learned from historical operation data through artificial intelligence models; Represents the square of the time difference, that is, the current time Relative to the fault start time The offset of is used to calculate the change of fault intensity over time, and the square form ensures that the attenuation is symmetrical; Indicates the oscillation characteristics of periodic faults simulated by a sine function, and the frequency is given by The phase is determined by Adjustment; Indicates the The oscillation frequency of each fault influencing factor controls the frequency of sinusoidal fluctuations, reflecting the oscillation speed of periodic faults, and is learned from historical operation data through artificial intelligence models; Indicates the The phase shift of each fault influencing factor is adjusted to adjust the starting phase of the sinusoidal fluctuation, determine the initial state of the periodic fault, and avoid complete synchronization of all fault modes. This is learned from historical operation data through artificial intelligence models; Indicates the mutation intensity coefficient, which controls the intensity of mutation faults and is learned from historical operation data through artificial intelligence models; Indicates when When the value is 0, The time value is 1, simulating the switching characteristics of sudden faults to ensure that the fault Moments occur suddenly and persist; Represents the Gaussian noise term, which is a random variable and obeys the normal distribution ,randomness is introduced to simulate unpredictable interference in real environments, making the failure mode closer to the actual operating conditions, generated by the artificial intelligence model.

[0036] This step uses artificial intelligence models to learn fault characteristics from historical operating data, eliminating the need for manual pre-set fault modes and significantly improving the intelligence level of the testing process.

[0037] Step S2: Based on the fault mode intensity, the impact of the fault mode on the performance of the electric energy meter is analyzed by using a fault mode-based electric energy meter performance degradation prediction algorithm, and a response value of the electric energy meter performance parameter is calculated.

[0038] Specifically include: (1) The fault mode-based energy meter performance degradation prediction algorithm introduces a sensitivity coefficient to measure the sensitivity of a specific fault to a specific performance, such as a voltage spike may have a greater impact on metering accuracy.

[0039] (2) The energy meter performance degradation prediction algorithm based on the fault mode also performs nonlinear processing on the fault mode intensity. The index can amplify or weaken the impact of the fault, reflecting the difference in nonlinear response of different energy meters to the fault.

[0040] (3) The performance degradation prediction algorithm of the electric energy meter based on the fault mode reflects the fault resistance of the performance parameters through the dynamic resistance factor. The resistance baseline under the fault-free condition is used as the initial value. As the intensity of the fault mode increases, the dynamic resistance factor will gradually decrease, reflecting the performance degradation of the electric energy meter under continuous faults. The decay rate of the dynamic resistance factor is controlled by a degradation coefficient to ensure that the resistance will not drop rapidly due to minor faults. It will also comprehensively consider the total intensity of all fault modes to ensure that the dynamic adjustment can reflect the superposition effect of multiple faults.

[0041] The calculation formula for the response value of the electric energy meter performance parameter is: ; in, Indicates the The response value of a performance parameter measures the performance of the energy meter under fault conditions, with a value range of 0 to 1, where 1 indicates no degradation and 0 indicates complete failure; Indicates the cumulative impact of all failure modes on the performance of the energy meter; Indicates the sensitivity coefficient, reflecting the The failure mode The degree of influence of a performance parameter measures the sensitivity of a specific fault to a specific performance. It can be set according to the specific implementation scenario and is not limited here. Indicates the The nonlinear transformation of the intensity of each fault mode reflects the nonlinear characteristics of the impact of fault intensity on performance. For example, a small fault may have a small impact, while a large fault may cause rapid degradation. Indicates the The failure mode The nonlinear influence index of each performance parameter adjusts the influence degree of the fault mode intensity and reflects the difference in nonlinear response of different electric energy meters to faults. It can be set according to the specific implementation scenario and is not limited here. Represents the resistance attenuation effect. The exponential function is used to simulate the weakening of the fault resistance of the electric energy meter as the fault intensity increases. The exponential form ensures a smooth transition. Avoid zero denominator; represents the dynamic resistance factor, i.e. The fault resistance capability of each performance parameter is calculated as follows: ; in, Indicates the The resistance baseline of each performance parameter under fault-free conditions serves as the initial value of the resistance, reflecting the fault resistance capability of the electric energy meter under ideal conditions. It can be set according to the specific implementation scenario and is not limited here. represents the degradation coefficient, controlling the The coefficient of the resistance attenuation rate of a performance parameter adjusts the sensitivity of the resistance to the intensity of the failure mode; Represents the sum of the intensities of all failure modes.

[0042] This step uses the fault mode as input to quickly calculate the degree of performance degradation and generate an intuitive response vector. The automated process reduces the time and cost of manual testing and is particularly efficient when testing a large number of electricity meters or simulating complex fault scenarios.

[0043] Step S3: Based on the performance parameter response value of the electric energy meter, a calibration error of each performance parameter is calculated using a digital electric energy meter performance calibration algorithm.

[0044] The digital energy meter performance verification algorithm processes each performance parameter one by one. The specific method is: (1) The response value of the performance parameter of the electric energy meter and the corresponding standard threshold are extracted, the relative deviation between the two is calculated, and a pre-set weighting factor is introduced to reflect the importance of different performance parameters in the overall performance of the electric energy meter. The influence of the positive and negative signs is eliminated by squaring to reflect the absolute size of the deviation.

[0045] (2) Based on the accumulated information of fault mode intensity, a dynamic severity factor is calculated to enhance the sensitivity of the error to severe faults. Specifically, an initial severity coefficient is used as a baseline value, and then dynamically adjusted based on the ratio of the total intensity of all current fault modes to the preset maximum fault mode intensity.

[0046] (3) A dynamic adjustment term is introduced to adjust the calibration error based on the severity of the fault and the degree of performance degradation. Specifically, the reciprocal of the performance parameter response value of the energy meter is taken. To avoid calculation problems caused by the zero performance parameter response value of the energy meter, a small smoothing constant is added to the performance parameter response value of the energy meter. This constant is then multiplied by the dynamic severity factor to obtain an amplification term. When the performance prediction value is lower (i.e., the more severe the degradation), the larger the reciprocal, and when combined with the dynamic severity factor, the calibration error will be significantly amplified, making it more sensitive to capture the negative impact of severe faults on performance.

[0047] (4) In order to make the magnitude of the calibration error consistent with intuitive understanding and facilitate subsequent analysis, a square root operation is performed to obtain the final calibration error value of each performance parameter. The square root operation retains the positive value characteristic of the error and adjusts the value to a more reasonable range, ensuring that the error is neither exaggerated nor distorted.

[0048] The calculation formula for performance parameter calibration error is: ; in, Indicates the The calibration error of each performance parameter reflects the degree of deviation between the predicted performance value and the standard value; The square term of the relative error includes a weighting factor. It calculates the relative deviation between the predicted performance value and the standard value, eliminates the influence of the positive and negative signs by squaring, and introduces a weighting factor to highlight the importance of performance. Indicates the Standard thresholds for performance parameters; Indicates the The weighting factors of the performance parameters are used to reflect the importance of different performance parameters. They can be set according to the specific implementation scenario and are not limited here. represents a dynamic adjustment term, which is used to adjust the error according to the severity of the fault and the degree of performance degradation; Indicates the reciprocal form of the performance degradation sensitive item; represents a smoothing constant, used to avoid the denominator being zero; Indicates the The dynamic severity factor of each performance parameter dynamically adjusts the sensitivity of the error according to the intensity of the failure mode. The calculation formula is: ; in, Indicates the initial severity coefficient, which serves as the benchmark value of the dynamic severity factor; represents the normalized total fault intensity; Indicates the preset upper limit of the fault mode intensity, which is used to standardize the fault impact. It can be set according to the specific implementation scenario and is not limited here.

[0049] This step adjusts the calibration error calculation according to the importance of performance parameters and the severity of the fault by designing weighting factors and dynamic severity factors, making the calibration results more in line with actual application requirements.

[0050] Step S4: check the error according to the performance parameters and optimize the parameters through the adaptive parameter update algorithm.

[0051] Before adjusting parameters, it's necessary to determine the direction and extent of the impact of parameter changes on calibration error—that is, to calculate the parameter sensitivity. Specifically, it's necessary to analyze the sensitivity of the calibration error to the failure mode and the sensitivity of the failure mode to the target parameter. These two factors are then combined using the chain method to determine the overall impact of the parameters on the calibration error. To speed convergence, this step introduces an exponential decay factor. When the error is large, the exponential decay factor is small, amplifying the sensitivity impact and accelerating adjustment. When the error is small, the exponential decay factor approaches 1, moderately reducing the sensitivity impact and avoiding over-adjustment.

[0052] Furthermore, to avoid oscillations during the optimization process, a momentum term is introduced to smooth the parameter update process and reduce oscillations during adjustments. The momentum term is calculated based on the difference between the current parameter value and the previous parameter value, multiplied by a momentum coefficient. This helps the adaptive parameter update algorithm find the optimization direction more quickly in the parameter space, especially when the error surface is relatively flat or has multiple local extremes. During the first iteration, since there are no values from the previous round, the momentum term is set to zero. Starting from the second round, it gradually takes effect.

[0053] The parameter update formula is as follows: ; in, Indicates in In the iteration The failure amplitude of each failure mode; Indicates in In the iteration The failure magnitude of each failure mode; Indicates the In the iteration The failure amplitude of each failure mode; represents the momentum term, which is used to reduce the oscillation during the parameter update process and ensure the smoothness of the update process; Represents the momentum coefficient, which is used to accelerate the optimization process and reduce the oscillation of parameter updates. It can be set according to the specific implementation scenario and is not limited here; The gradient of the fault amplitude is the sensitivity of the calibration error to the fault amplitude in the current iteration. The calculation formula is: ; in, Indicates the The performance parameters of Sensitivity to each failure mode; Indicates the The fault amplitude of the first fault mode has an impact on the The impact of each failure mode; Indicates the convergence coefficient, which is used to accelerate convergence. It can be set according to the specific implementation scenario and is not limited here; It represents the norm of the error, reflecting the size of the overall error. The calculation formula is: .

[0054] In order to ensure the physical rationality of the parameters, a range constraint is set to prevent it from exceeding the actual acceptable range. Specifically, a minimum and maximum range is set, which is determined by the working characteristics or test standards of the energy meter: ; in, and These are the minimum and maximum values of the fault amplitude, which can be set according to the specific implementation scenario and are not limited here; Indicates taking the maximum value; Indicates taking the minimum value.

[0055] The parameters of the new iteration reflect the optimization requirements while maintaining practical feasibility. By adjusting the parameters, the error is gradually reduced, so that the performance prediction results of the electricity meter are as close to the standard value as possible. Iterations will continue until the error converges to a preset threshold or the maximum number of iterations is reached.

[0056] The above steps complete an AI-based fault simulation test digital electricity meter calibration method.

[0057] It should be noted that it is obvious to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention. The scope of the present invention is defined by the claims rather than the foregoing description.

Claims

1. A digital energy meter calibration method for fault simulation testing based on AI, characterized by: The following steps are involved: Step S1: Obtain historical operating data of the electric energy meter, and use a multi-modal fault simulation algorithm based on artificial intelligence to generate a fault mode by analyzing the historical operating data of the electric energy meter; Step S2: Based on the fault mode intensity, the impact of the fault mode on the performance of the electric energy meter is analyzed by using a fault mode-based electric energy meter performance degradation prediction algorithm, and a response value of the electric energy meter performance parameter is calculated; Step S3: Based on the performance parameter response value of the electric energy meter, a calibration error of each performance parameter is calculated using a digital electric energy meter performance calibration algorithm; Step S4: Check the error according to the performance parameters and optimize the parameters through the adaptive parameter update algorithm.

2. The AI-based fault simulation test digital energy meter calibration method according to claim 1, characterized in that: The step S1 specifically includes: Step S1-1: Acquire historical operating data of the electric energy meter, wherein the historical operating data includes operating records of the electric energy meter under various environmental conditions, and divide the historical operating data of the electric energy meter into a training set and a validation set. The training set is used to train the artificial intelligence model, and the validation set is used to evaluate the accuracy of the fault mode generated by the artificial intelligence model; Step S1-2: Use a multi-modal fault simulation algorithm based on artificial intelligence to generate multiple fault modes by analyzing the historical operating data of the electricity meter.

3. The AI-based fault simulation test digital energy meter calibration method according to claim 2, characterized in that: The AI-based multimodal fault simulation algorithm generates fault modes by analyzing the historical operating data of the electricity meter. It combines three fault influencing factors: periodic, transient, and sudden. It also introduces random noise to enhance authenticity and simulates the complex fault scenarios that digital electricity meters may encounter in actual operation. Periodic faults appear as disturbances that fluctuate regularly over time and are used to simulate a sine wave-like fluctuation pattern; Transient faults are simulated by exponential decay functions, which cause rapid changes in a short period of time. The duration and impact range of transient faults are controlled by adjusting the decay rate. Mutational faults are used to simulate emergencies; Random noise is generated according to a normal distribution, and the fluctuation range is controlled by a standard deviation parameter.

4. The AI-based fault simulation test digital energy meter calibration method according to claim 1, characterized in that: In step S2, the electric energy meter performance degradation prediction algorithm based on the fault mode calculates the direct impact on the specific performance parameters of the electric energy meter for each fault mode, introduces a sensitivity coefficient, and measures the sensitivity of a specific fault to a specific performance.

5. The AI-based fault simulation test digital energy meter calibration method according to claim 4 is characterized in that: In step S2, the electric energy meter performance degradation prediction algorithm based on the fault mode performs nonlinear processing on the fault mode intensity to reflect the nonlinear response differences of different electric energy meters to the fault.

6. The AI-based fault simulation test digital energy meter calibration method according to claim 5, characterized in that: In step S2, the fault mode-based electricity meter performance degradation prediction algorithm reflects the fault resistance of performance parameters through a dynamic resistance factor. The resistance baseline under fault-free conditions is used as the initial value. As the fault mode intensity increases, the dynamic resistance factor gradually decreases, reflecting the performance degradation of the electricity meter under continuous faults; the attenuation rate of the dynamic resistance factor is controlled by the degradation coefficient.

7. The AI-based fault simulation test digital energy meter calibration method according to claim 1, characterized in that: In step S3, the digital electric energy meter performance verification algorithm processes each performance parameter one by one in the following manner: Extract the energy meter performance parameter response value and the corresponding standard threshold, calculate the relative deviation between the two, introduce a pre-set weighting factor to reflect the importance of different performance parameters in the overall performance of the energy meter, and eliminate the influence of positive and negative signs by squaring to reflect the absolute magnitude of the deviation; Based on the accumulated information of fault mode intensity, a dynamic severity factor is calculated to enhance the sensitivity of the error to severe faults; A dynamic adjustment term is introduced to adjust the calibration error based on fault severity and performance degradation. Specifically, the inverse of the sum of the meter's performance parameter response value and a smoothing constant is multiplied by the dynamic severity factor to create an amplification term. This amplifies the calibration error, making it more sensitive to the negative impact of severe faults on performance. Perform square root processing on the above calculation results to obtain the final calibration error value of each performance parameter.

8. The AI-based fault simulation test digital energy meter calibration method according to claim 7, characterized in that: When calculating the dynamic severity factor, an initial severity coefficient is used as a baseline value, and then dynamically adjusted according to the ratio of the total intensity of all current failure modes to the preset maximum failure mode intensity.

9. The AI-based fault simulation test digital electric energy meter calibration method according to claim 1, characterized in that: In step S4, before adjusting the parameters, the direction and degree of the impact of the parameter changes on the calibration error are determined, that is, the sensitivity of the parameters is calculated: the sensitivity of the calibration error to the fault mode and the sensitivity of the fault mode to the target parameter are analyzed and combined through the chain method to obtain the overall impact of the parameters on the calibration error; an exponential decay factor is introduced. When the error is large, the value of the exponential decay factor is small, and the impact of the sensitivity is amplified, thereby accelerating the adjustment. When the error is small, the exponential decay factor is close to 1, and the impact of the sensitivity is moderately weakened; A momentum term is introduced to smooth the parameter update process and reduce the oscillation during adjustment. The momentum term is calculated based on the difference between the current parameter value and the previous parameter value, multiplied by a momentum coefficient.

10. The AI-based fault simulation test digital energy meter calibration method according to claim 9, characterized in that: In step S4, in order to ensure the physical rationality of the parameters, range constraints are set to prevent the parameters from exceeding the actual acceptable range.

Images