Transformer substation intelligent monitoring system based on digital twinborn technology

Abstract

The invention discloses a transformer substation intelligent monitoring system based on a digital twinborn technology, and relates to the technical field of intelligent monitoring, which comprises the steps of collecting and preprocessing operation data, constructing a digital twinborn model, simulating and generating twinborn data, counting the probability density of the operation data and the twinborn data, and calculating information entropy by using an information entropy formula. Calculating mutual information by using a mutual information formula; calculating entropy change of the information entropy, calculating a dynamic entropy adjustment coefficient by using a Sigmoid function, calculating an abnormal index by using a weighted fusion method and combining the dynamic entropy adjustment coefficient, performing state monitoring on the transformer substation, and dividing early warning grades based on a monitoring result. According to the method, through multi-scale coupling modeling of information entropy analysis and mutual information estimation, the precision and the real-time performance of transformer substation operation state monitoring are improved, a Sigmoid function dynamic adjustment mechanism and a weighted fusion algorithm are introduced, classification judgment is carried out on the abnormal state from the angle of entropy change response, and the monitoring sensitivity and the response accuracy are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent monitoring technology, and in particular to an intelligent monitoring system for a substation based on digital twin technology. Background Art

[0002] With the continuous development of smart grid and Internet of Things technologies, substations, as key nodes in the power system, real-time monitoring and intelligent management of their operating status have become important means to ensure the safe and stable operation of the power grid. Traditional substation monitoring systems mostly use parameter monitoring methods based on fixed thresholds, and mainly rely on SCADA systems and manual inspections to complete status collection and analysis. With the development of sensor networks, edge computing and data-driven analysis methods, substation intelligent monitoring has gradually evolved towards data fusion, model simulation and predictive maintenance. Digital twin technology, as an advanced means of integrating physical modeling and data-driven simulation, has demonstrated strong engineering value in multiple industrial fields such as manufacturing, aviation, and power.

[0003] The existing technology for intelligent monitoring of substations still has obvious shortcomings. The current status assessment mechanisms mostly rely on traditional statistical threshold judgment or rule reasoning, lacking in-depth measurement and dynamic adjustment mechanisms for the internal correlation of operating data, and unable to achieve refined identification of equipment status and early warning. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides an intelligent monitoring system for substations based on digital twin technology to solve the problem that the current status assessment mechanism mostly relies on traditional statistical threshold judgment or rule reasoning, lacks in-depth measurement and dynamic adjustment mechanism of the internal correlation of operating data, and cannot achieve refined identification and early warning of equipment status.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a substation intelligent monitoring system based on digital twin technology, which includes:

[0008] The information collection module is used to collect and preprocess operating data, build a digital twin model, simulate and generate twin data, calculate the probability density of operating data and twin data, calculate information entropy using the information entropy formula, and calculate mutual information using the mutual information formula;

[0009] The monitoring level module is used to calculate the entropy change of information entropy, use the Sigmoid function to calculate the dynamic entropy adjustment coefficient, use the weighted fusion method and the dynamic entropy adjustment coefficient to calculate the anomaly index, perform status monitoring on the substation, and divide the warning level based on the monitoring results.

[0010] As a preferred solution of the substation intelligent monitoring system based on digital twin technology described in the present invention, the collection of operating data and pre-processing thereof include:

[0011] The intelligent sensors include current, voltage, temperature, humidity and wind speed sensors

[0012] The operating data includes current, voltage, temperature, humidity and wind speed data;

[0013] The preprocessing includes realigning the running data according to timestamps using a linear interpolation method, performing denoising using a low-pass filter, identifying and deleting outliers using an interquartile range method, filling missing data using the median, and normalizing the filled running data.

[0014] As a preferred solution of the substation intelligent monitoring system based on digital twin technology described in the present invention, the steps of constructing a digital twin model and calculating information entropy and mutual information include:

[0015] Use ANSYS to build a digital twin model, calibrate the digital twin model parameters using the Monte Carlo method based on operational data, simulate and generate twin data, and perform preprocessing;

[0016] Use the PTP protocol to synchronize the time between running data and twin data;

[0017] Use a sliding window to set the time window, use the histogram method to divide the running data and twin data into K discrete intervals, count the probability density of the running data and twin data, use the information entropy formula to calculate the information entropy, and use the mutual information formula to calculate the mutual information.

[0018] As a preferred solution of the substation intelligent monitoring system based on digital twin technology described in the present invention, the method of using the Sigmoid function to calculate the dynamic entropy adjustment coefficient includes:

[0019] Use the difference method to calculate the entropy change of information entropy, collect historical entropy change data, and calculate the standard deviation of entropy change;

[0020] Use the Sigmoid function to calculate the dynamic entropy adjustment coefficient.

[0021] As a preferred solution of the substation intelligent monitoring system based on digital twin technology described in the present invention, the method of using the weighted fusion method to calculate the abnormality index and perform status monitoring on the substation includes:

[0022] The anomaly index is calculated using the weighted fusion method combined with the dynamic entropy adjustment coefficient;

[0023] Use statistical analysis to set the monitoring threshold, and compare the abnormal index with the monitoring threshold. If the abnormal index is greater than the monitoring threshold, it is judged as an abnormal state, otherwise it is judged as a normal state.

[0024] As a preferred solution of the substation intelligent monitoring system based on digital twin technology described in the present invention, the division of warning levels based on monitoring results includes:

[0025] Based on the monitoring results, the abnormal state is classified into grades using the classification rules, the mean of the abnormal index is calculated as a scalar, and the abnormal deviation of the abnormal index is calculated;

[0026] Use the percentile method to set the classification threshold and compare the abnormal deviation with the classification threshold. If the abnormal deviation is greater than the classification threshold, it is judged as a serious abnormality and the maintenance personnel are notified to perform repairs. Otherwise, it is judged as a minor abnormality and an early warning is issued and recorded.

[0027] In a second aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the substation intelligent monitoring system based on digital twin technology as described in the first aspect of the present invention is implemented.

[0028] The beneficial effects of the present invention are as follows: the present invention improves the accuracy and real-time performance of substation operation status monitoring through multi-scale coupling modeling of information entropy analysis and mutual information estimation, introduces the dynamic adjustment mechanism of Sigmoid function and weighted fusion algorithm, and makes hierarchical judgments on abnormal states from the perspective of entropy change response, thereby improving the monitoring sensitivity and response accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0030] Figure 1 This is a structural diagram of the substation intelligent monitoring system based on digital twin technology in Example 1.

[0031] Figure 2 This is an operation flow chart of the substation intelligent monitoring system based on digital twin technology in Example 1. DETAILED DESCRIPTION

[0032] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0033] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0034] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0035] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a substation intelligent monitoring system based on digital twin technology, including:

[0036] The information collection module is used to collect and preprocess operating data, build a digital twin model, simulate and generate twin data, calculate the probability density of operating data and twin data, calculate information entropy using the information entropy formula, and calculate mutual information using the mutual information formula;

[0037] Specifically, collect and pre-process operational data, including:

[0038] Use smart sensors to collect and pre-process substation operation data;

[0039] The intelligent sensors include current, voltage, temperature, humidity and wind speed sensors

[0040] The operating data includes current, voltage, temperature, humidity and wind speed data;

[0041] The preprocessing includes realigning the running data according to timestamps using a linear interpolation method, performing denoising using a low-pass filter, identifying and deleting outliers using an interquartile range method, filling missing data using the median, and normalizing the filled running data.

[0042] The integrated collection of electrical parameters and environmental parameters ensures that the mutual information of subsequent calculations is not limited to the analysis between similar variables. The integration of high sampling frequency and multi-dimensional information helps to carry out refined modeling of key operating nodes and improve the credibility of model simulation. Low-pass filtering suppresses high-frequency interference and prevents false trends from being misidentified as anomalies. IQR is based on a non-parametric method and is not affected by extreme values. Outlier identification is more robust. The median is not affected by local fluctuations and maintains the overall trend of the data set stable. Normalization processing provides a basis for comparison on the same scale for subsequent modeling, effectively preventing a certain variable from dominating the information entropy value.

[0043] Next, we build a digital twin model and calculate information entropy and mutual information, including:

[0044] Use ANSYS to build a digital twin model, use the Monte Carlo method to calibrate the digital twin model parameters based on the operating data, simulate and generate twin data, and perform preprocessing. The twin data corresponds to the operating data.

[0045] Use the PTP protocol to synchronize the time between running data and twin data;

[0046] Use a sliding window to set the time window, use the histogram method to divide the running data and twin data into K discrete intervals, count the probability density of the running data and twin data, and use the information entropy formula to calculate the information entropy. The formula is:

[0047]

[0048] Where H(X i ) is the information entropy of the i-th data, X i is the i-th running data and twin data, K is the number of discrete intervals, p(x ik ) is the value x of the i-th data in window T ik The probability that p(x ik )=0, then it is defined as p(x ik )logp(x ik )=0,x ik is the discretized value of the i-th data in the k-th interval, where k is the index of the histogram interval;

[0049] Mutual information is calculated using the mutual information formula, which is:

[0050]

[0051] Where I(X i ;X j ) is the mutual information between the i-th and j-th data, p(x i ,x j ) is the value of the i-th and j-th data in the window T at the same time (x i ,x j ), p(x i ) and p(x j ) are the marginal probabilities of the i-th and j-th data, respectively, x i and x j are the discretized values ​​of the i-th and j-th data respectively.

[0052] ANSYS supports electric-thermal-fluid three-field coupled modeling, which is suitable for restoring the physical mechanism level of the operating status of equipment in substations. Through the Monte Carlo method, random sampling is performed in the parameter space, giving the model probabilistic response capabilities. It can effectively model input disturbances, measurement errors, etc., and the simulation data is matched one-to-one with the actual operation data to form twin data pairs, enhancing the monitoring model's ability to respond to the dynamic behavior of the system. The introduction of information entropy and mutual information as monitoring indicators enables the system to evolve from static threshold judgment to dynamic multi-dimensional trend perception.

[0053] The monitoring level module is used to calculate the entropy change of information entropy, use the Sigmoid function to calculate the dynamic entropy adjustment coefficient, use the weighted fusion method and the dynamic entropy adjustment coefficient to calculate the abnormality index, perform status monitoring on the substation, and divide the warning level based on the monitoring results;

[0054] Specifically, the Sigmoid function is used to calculate the dynamic entropy adjustment coefficient, including:

[0055] The entropy change of information entropy is calculated using the difference method. The formula is:

[0056] ΔH(X i )=H(X i (t))-H(X i (tT)),

[0057] Where ΔH(X i ) is the entropy change of the i-th data, information entropy, H(X i (t)) is the information entropy of the i-th data at time t, and T is the time window;

[0058] Collect historical entropy change data and calculate the standard deviation of entropy change. The formula is:

[0059]

[0060] where σ H is the standard deviation of entropy change, M is the number of historical windows, μ ΔH is the mean value of historical entropy change, mT is the relative time offset of the historical time window, which is expressed as the start time of the mth historical time window relative to the current time t, m is the index of the historical time window, and (t-mT) is the start time of m historical time windows;

[0061] The dynamic entropy adjustment coefficient is calculated using the Sigmoid function. The formula is:

[0062]

[0063] where λ T (t) is the dynamic entropy adjustment coefficient at time t.

[0064] The difference method highlights the rate of change of data uncertainty and is suitable for judging the speed of device status change. Many device operating parameters show periodic or slight changes under continuous conditions. The introduction of entropy difference helps to filter background noise, respond only to significant fluctuations, and effectively suppress the interference of normal fluctuations. The change in information entropy as a state indicator can reflect the abnormal trend of the system in advance. The standard deviation represents the common fluctuations under the influence of the system's own noise and the environment. Sigmoid can map the entropy change to (0,1) to avoid jumps.

[0065] Furthermore, a weighted fusion method is used to calculate the anomaly index and perform condition monitoring on the substation, including:

[0066] The weighted fusion method is used to calculate the anomaly index in combination with the dynamic entropy adjustment coefficient. The formula is:

[0067]

[0068] Where S(t) is the abnormal index at time t, Q is the number of collected data, α i is the importance weight of the i-th data, set using the empirical rule, β ij is the coupling weight between the i-th and j-th data, set using the empirical rule;

[0069] Use statistical analysis to set the monitoring threshold, and compare the abnormal index with the monitoring threshold. If the abnormal index is greater than the monitoring threshold, it is judged as an abnormal state, otherwise it is judged as a normal state.

[0070] The importance weights and coupling weights of the variables ensure that the system warning focuses on electrical and environmental coupling anomalies. Combined with actual system operation statistics, the threshold can be automatically adjusted as the equipment life cycle progresses, improving the efficiency of alarm warnings. The dynamic threshold is adaptable to production environment drift, thereby keeping the false alarm rate within a controllable range and improving the reliability of the monitoring system.

[0071] Furthermore, the warning levels are divided based on the monitoring results, including:

[0072] Based on the monitoring results, the abnormal state is classified into different levels using the classification rules. The mean of the abnormal index is defined as a scalar, and the abnormal deviation of the abnormal index is calculated using the formula:

[0073] D(t)=S(t)-S th (t),

[0074] Where D(t) is the abnormal deviation at time t, S th (t) is the scalar of time t;

[0075] Use the percentile method to set the classification threshold and compare the abnormal deviation with the classification threshold. If the abnormal deviation is greater than the classification threshold, it is judged as a serious abnormality and the maintenance personnel are notified to perform repairs. Otherwise, it is judged as a minor abnormality and an early warning is issued and recorded.

[0076] Differentiate operation and maintenance response measures and priorities based on the severity of the anomaly to achieve rational allocation of resources. Minor alarms will not disrupt normal operation and maintenance, while severe alarms provide strong response signals to reduce operating cost waste. Information such as alarm level, time point, deviation amplitude, etc. forms a historical record to provide a basis for analyzing equipment status changes.

[0077] This embodiment also provides a computer device, which is suitable for the case of a substation intelligent monitoring system based on digital twin technology, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute computer-executable instructions to implement the substation intelligent monitoring system based on digital twin technology proposed in the above embodiment.

[0078] The computer device may be a terminal, comprising a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device comprises a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse.

[0079] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A substation intelligent monitoring system based on digital twin technology, characterized by: include: The information collection module is used to collect and preprocess operating data, build a digital twin model, simulate and generate twin data, calculate the probability density of operating data and twin data, calculate information entropy using the information entropy formula, and calculate mutual information using the mutual information formula; The monitoring level module is used to calculate the entropy change of information entropy, use the Sigmoid function to calculate the dynamic entropy adjustment coefficient, use the weighted fusion method and the dynamic entropy adjustment coefficient to calculate the anomaly index, perform status monitoring on the substation, and divide the warning level based on the monitoring results.

2. The intelligent monitoring system for substations based on digital twin technology according to claim 1, characterized in that: The collecting and pre-processing of the operating data includes: The intelligent sensors include current, voltage, temperature, humidity and wind speed sensors The operating data includes current, voltage, temperature, humidity and wind speed data; The preprocessing includes realigning the running data according to timestamps using a linear interpolation method, performing denoising using a low-pass filter, identifying and deleting outliers using an interquartile range method, filling missing data using the median, and normalizing the filled running data.

3. The intelligent monitoring system for substations based on digital twin technology according to claim 2, characterized in that: The construction of the digital twin model and calculation of information entropy and mutual information include: Use ANSYS to build a digital twin model, calibrate the digital twin model parameters using the Monte Carlo method based on operational data, simulate and generate twin data, and perform preprocessing; Use the PTP protocol to synchronize the time between running data and twin data; Use a sliding window to set the time window, use the histogram method to divide the running data and twin data into K discrete intervals, count the probability density of the running data and twin data, use the information entropy formula to calculate the information entropy, and use the mutual information formula to calculate the mutual information.

4. The intelligent monitoring system for substations based on digital twin technology according to claim 3, characterized in that: The method of calculating the dynamic entropy adjustment coefficient using the Sigmoid function includes: Use the difference method to calculate the entropy change of information entropy, collect historical entropy change data, and calculate the standard deviation of entropy change; Use the Sigmoid function to calculate the dynamic entropy adjustment coefficient.

5. The intelligent monitoring system for substations based on digital twin technology according to claim 4, characterized in that: The method of using the weighted fusion method to calculate the abnormality index and perform condition monitoring on the substation includes: The anomaly index is calculated using the weighted fusion method combined with the dynamic entropy adjustment coefficient; Use statistical analysis to set the monitoring threshold, and compare the abnormal index with the monitoring threshold. If the abnormal index is greater than the monitoring threshold, it is judged as an abnormal state, otherwise it is judged as a normal state.

6. The intelligent monitoring system for substations based on digital twin technology according to claim 5, characterized in that: The classification of warning levels based on monitoring results includes: Based on the monitoring results, the abnormal state is classified into grades using the classification rules, the mean of the abnormal index is calculated as a scalar, and the abnormal deviation of the abnormal index is calculated; Use the percentile method to set the classification threshold and compare the abnormal deviation with the classification threshold. If the abnormal deviation is greater than the classification threshold, it is judged as a serious abnormality and the maintenance personnel are notified to perform repairs. Otherwise, it is judged as a minor abnormality and an early warning is issued and recorded.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the substation intelligent monitoring system based on digital twin technology described in any one of claims 1 to 6 is used.

Images