Environment-adaptive 110kV transformer neutral point intelligent protection method and system

Abstract

The invention relates to the technical field of power system overvoltage protection, and discloses an environment-adaptive 110kV transformer neutral point intelligent protection method and system. The method realizes intelligent protection through the following steps: (1) collecting discharge voltage data of different gap distances under a simulated atmosphere condition; (2) calculating 0.1% probability impulse discharge voltage and 99.9% probability power frequency discharge voltage based on normal distribution; (3) main environmental influence factors such as air pressure, temperature and humidity are screened, and a discharge voltage regression model is established; and (4) environment parameters are monitored in real time, and the gap distance is dynamically adjusted, so that the power frequency discharge voltage does not exceed the single-phase earth fault voltage, and the impact discharge voltage is not lower than the residual voltage of the lightning arrester. The system integrates an environment monitoring module, a data processing module and a gap adjustment executing mechanism. According to the invention, the dynamic optimization of the gap distance is realized, the environmental interference is effectively eliminated, and the protection precision and reliability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of neutral point overvoltage protection for power system transformers, and in particular to the technical field of an environment-adaptive 110kV transformer neutral point intelligent protection method and system. Background Art

[0002] In 110kV neutral-point effective grounding systems, some transformers operate with their neutral points ungrounded to limit single-phase grounding short-circuit currents and meet relay protection setting configuration requirements. To protect neutral-point insulation, existing technologies typically employ a parallel grounding scheme involving a protective gap and a lightning arrester. However, this scheme has the following drawbacks: 1. The gap distance setting is not accurate: The rod gap distance is selected based on the 50% discharge voltage value. However, due to the inherent dispersion of gap discharge, false discharge (accidental breakdown under non-fault conditions) and rejected discharge (failure to break down in time under fault conditions) frequently occur in actual operation, making it difficult to accurately adapt the gap distance to protection requirements.

[0003] 2. Environmental sensitivity leads to protection failure: The rod gap uses air as the insulating medium, and its breakdown voltage is significantly affected by environmental factors such as temperature, humidity, and atmospheric pressure, resulting in unstable discharge voltage. This characteristic leads to mismatched protection parameters between the gap and the arrester. For example, under power-frequency overvoltage conditions, if the gap fails to operate, the arrester will be forced to bear the entire energy, posing a risk of arrester explosion. Summary of the Invention

[0004] The purpose of the present invention is to solve the problem in the prior art that the parallel discharge gap of the lightning arrester causes malfunction of the relay protection and the gap refusal to operate during actual operation, which leads to the explosion of the lightning arrester. An environmentally adaptive 110kV transformer neutral point intelligent protection method and system are proposed, which can dynamically optimize the gap distance, eliminate environmental interference in real time, and intelligently block the protection failure chain.

[0005] To achieve the above object, the present invention proposes an environment-adaptive 110kV transformer neutral point intelligent protection method, comprising the following steps: (1) In an artificial climate chamber, simulate various atmospheric conditions and conduct lightning impulse and power frequency discharge tests on rod gap lengths with different gap distances. Repeat the test 20 times under each environment and gap distance, and record the breakdown voltage value and the corresponding environmental parameters, including air pressure, temperature, wind speed, relative humidity and illumination. (2) Based on the breakdown voltage data of step (1), calculate the impulse discharge voltage of each gap length and the 0.1% probability under the corresponding environment through normal probability distribution. and 99.9% probability power frequency discharge voltage , specifically including: Calculate the mean of the breakdown voltage data and standard deviation ; Through the cumulative distribution function of the normal distribution , solve get , get ,in is the error function; (3) Grey correlation, Pearson correlation coefficient, and Spearman correlation coefficient were used to analyze the correlation between environmental parameters and discharge voltage and screen the main influencing factors; (4) A multiple linear regression model was established with the main environmental factors screened as independent variables and discharge voltage as the dependent variable: , is the gap discharge voltage, , ,…, The main influencing factors are is the discharge voltage intercept term under standard atmospheric conditions, , ,…, is the regression coefficient, is the error term; (5) Real-time monitoring of environmental parameters, inputting the model of step (4) to calculate the current and , and judge: like If the voltage is greater than the single-phase ground fault voltage of the ground-lost system, shorten the gap distance by 10 mm; like If it is less than the residual pressure of the arrester, increase the gap distance by 10mm; (6) Repeat step (5) until the gap distance meets Single-phase ground fault voltage and Residual pressure of the lightning arrester.

[0006] Preferably, the rod gap length in step (1) is selected from 90 mm, 100 mm, 110 mm, 120 mm, 130 mm, 140 mm, and 150 mm.

[0007] Preferably, the specific method of correlation analysis in step (3) includes: Pearson correlation coefficient calculation: Where, and are the expectations of random variables X and Y, respectively, and To distinguish their standard deviations, is their covariance; Spearman rank correlation coefficient calculation: Where, It represents the difference in the rank value of the i-th data pair, and n is the total number of observation samples; Grey relational analysis: Including data normalization, correlation coefficient calculation and correlation degree calculation; The data normalization formula is: Where: is the original value of a certain feature; and are the maximum and minimum values ​​of a certain characteristic quantity respectively; It is the normalized value of a certain characteristic quantity; The correlation coefficient was calculated as Where: is the resolution coefficient, , usually take =0.5, is the minimum absolute difference between all compared sequences and the reference sequence, It is the maximum absolute difference between all compared sequences and the reference sequence; ,when <0.5, indicating a weak correlation; when 0.5≤ When <0.7, it indicates a strong correlation; When ≥ 0.7, it indicates a strong correlation; The correlation is calculated as Where: is the grey correlation degree, and its value and meaning are the same as .

[0008] Preferably, step (4) also includes model evaluation using mean absolute percentage error (MAPE), root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination ( ) as the evaluation indicator.

[0009] The present invention also proposes an environment-adaptive 110kV transformer neutral point intelligent protection system for implementing any of the above methods, characterized by comprising: an environmental monitoring module: comprising air pressure, temperature, wind speed, relative humidity and illumination sensors for real-time collection of environmental parameters; Data processing module: is configured to perform the following operations: Based on historical test data, calculate the length of each gap through normal distribution and ; Grey correlation, Pearson coefficient and Spearman coefficient were used to analyze the correlation between environmental parameters and discharge voltage; Model calculation module: storing multiple linear regression models , receive real-time environment parameters and output and ; Judgment module: comparison Single-phase ground fault voltage, Relationship with the residual voltage of the arrester; Gap adjustment module: drives the actuator to increase or decrease the gap distance of the rods according to the judgment results, and the adjustment step is 10mm.

[0010] Preferably, the gap adjustment module includes a stepping motor and a mechanical transmission mechanism, wherein the mechanical transmission mechanism connects the rod gap electrodes and responds to the displacement instruction of the stepping motor.

[0011] Preferably, the data processing module and the model calculation module are integrated into an edge computing gateway, and the edge computing gateway communicates with the environment monitoring module and the gap adjustment module through an industrial bus.

[0012] According to the method or system described above, step (5) and the adjustment logic of the judgment module meet the following requirements: single-phase grounding fault voltage and arrester residual voltage.

[0013] Beneficial effects of the present invention: (1) Improved protection accuracy: By dynamically adjusting the gap distance to adapt to environmental changes, the probability of false discharge and discharge rejection is effectively reduced; (2) Enhanced protection reliability: The voltage calculation model based on normal distribution provides a precise basis for selecting the gap distance, ensuring accurate matching with the arrester parameters; (3) Intelligent operation and maintenance: Through environmental monitoring and automatic adjustment closed loop, human intervention is reduced and the risk of protection failure is avoided.

[0014] The features and advantages of the present invention will be described in detail through embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a method flow chart of an environment-adaptive 110kV transformer neutral point intelligent protection method and system of the present invention. DETAILED DESCRIPTION

[0016] See Figure 1 The method of the present invention comprises the following steps: (1) In an artificial climate chamber, simulate various atmospheric conditions and conduct lightning impulse and power frequency discharge tests on rod gap lengths with different gap distances. Repeat the test 20 times under each environment and gap distance, and record the breakdown voltage value and the corresponding environmental parameters, including air pressure, temperature, wind speed, relative humidity and illumination. (2) Based on the breakdown voltage data of step (1), calculate the impulse discharge voltage of each gap length and the 0.1% probability under the corresponding environment through normal probability distribution. and 99.9% probability power frequency discharge voltage ; (3) Grey correlation, Pearson correlation coefficient, and Spearman correlation coefficient were used to analyze the correlation between environmental parameters and discharge voltage and screen the main influencing factors; (4) Establish a multiple linear regression model with the main environmental factors screened as independent variables and discharge voltage as the dependent variable; (5) Real-time monitoring of environmental parameters, inputting the model of step (4) to calculate the current and , and judge: like If the voltage is greater than the single-phase ground fault voltage of the ground-lost system, shorten the gap distance by 10 mm; like If it is less than the residual pressure of the arrester, increase the gap distance by 10mm; (6) Repeat step (5) until the gap distance meets Single-phase ground fault voltage and Residual pressure of the lightning arrester.

[0017] The system of the present invention comprises: an environmental monitoring module: comprising air pressure, temperature, wind speed, relative humidity and illumination sensors for collecting environmental parameters in real time; Data processing module: is configured to perform the following operations: Based on historical test data, calculate the length of each gap through normal distribution and ; Grey correlation, Pearson coefficient and Spearman coefficient were used to analyze the correlation between environmental parameters and discharge voltage; Model calculation module: storing multiple linear regression models , receive real-time environment parameters and output and ; Judgment module: comparison Single-phase ground fault voltage, Relationship with the residual voltage of the arrester; Gap adjustment module: drives the actuator to increase or decrease the gap distance of the rods according to the judgment results, and the adjustment step is 10mm.

[0018] Working process of the present invention: The working process of an environment-adaptive 110kV transformer neutral point intelligent protection method and system of the present invention is described in conjunction with the accompanying drawings.

[0019] First, an artificial climate chamber was used to simulate different atmospheric conditions, and lightning impulse and power frequency discharge tests were conducted on various gap lengths. Environmental parameters such as air pressure, temperature, wind speed, relative humidity, and illumination, as well as corresponding breakdown voltage data, were collected. Then, the normal probability distribution method was used to calculate the impulse discharge voltage with a 0.1% probability of the gap under various gap lengths and corresponding environments. , 99.9% probability power frequency discharge voltage Then, using three methods—grey correlation, Pearson coefficient, and Spearman coefficient—the correlation between discharge voltage and atmospheric conditions was analyzed to identify the main influencing factors. A discharge voltage calculation model was then established based on multiple linear regression, with environmental factors as independent variables and discharge voltage as the dependent variable. The regression coefficients were calculated by fitting the data to construct the model. Finally, the discharge voltage was calculated based on real-time atmospheric data and gap distance data, and the gap distance was determined and dynamically adjusted based on the coordination principle to achieve intelligent protection. Specific embodiment: 1. Data collection: In an artificial climate chamber, various atmospheric conditions were simulated, and lightning impulse and power frequency discharge tests were conducted at different gap distances. The tests were repeated 20 times for each environment and gap distance, and the breakdown voltage and the corresponding environment were recorded for each test. Atmospheric conditions included air pressure, temperature, wind speed, relative humidity, and illumination. According to DL / T 1848-2018, "Technical Specification for Neutral Point Overvoltage Protection of 220kV and 110kV Transformers," the neutral point gap distance for 110kV transformers ranges from 95mm to 150mm. Therefore, the rod gap lengths selected were 90mm, 100mm, 110mm, 120mm, 130mm, 140mm, and 150mm.

[0021] 2. Calculate the length of each gap and the impulse discharge voltage with a 0.1% probability of the gap under the corresponding environment by using the normal probability distribution method , 99.9% probability power frequency discharge voltage .

[0022] S21. Fit the normal probability distribution.

[0023] First, calculate the mean and standard deviation of the recorded breakdown voltage data. Then use the probability density function formula of the normal distribution: Where, is a random variable, which refers to the gap breakdown voltage value; is the mathematical expectation (mean), is the standard deviation.

[0024] S22. Calculate the target probability discharge voltage.

[0025] According to the cumulative distribution function formula of the normal distribution, the voltage value corresponding to a specific probability is calculated in, is the error function.

[0026] For impulse discharge voltage ,Pick , and get the corresponding voltage value: For power frequency discharge voltage ,Pick , and get the corresponding voltage value: 3. Determine the main factors affecting the gap discharge voltage: The three correlation calculation methods of grey correlation, Pearson coefficient and Spearman coefficient were used to analyze the relationship between gap discharge voltage and atmospheric conditions, and the main factors that significantly affected the discharge voltage were screened out, providing a basis for subsequent modeling.

[0027] The Pearson correlation coefficient is used to detect linear correlation, and the calculation formula is as follows: Where, and are the expectations of random variables X and Y, respectively, and To distinguish their standard deviations, is their covariance.

[0028] The value of the Pearson correlation coefficient ranges from -1 to 1. Values ​​closer to 1 or -1 indicate stronger linear correlation, and 0 indicates no correlation.

[0029] If the data does not conform to a normal distribution or has a nonlinear relationship, the Spearman rank correlation coefficient can be used. The calculation formula is as follows: Where, It represents the difference in the rank value of the i-th data pair, and n is the total number of observed samples.

[0030] The Spearman rank correlation coefficient also has a value range between -1 and 1. Its meaning is the same as the Pearson correlation coefficient, but it is applicable to data with non-normal distribution or nonlinear relationships.

[0031] When the data is incomplete or the information is incomplete, grey relational analysis can be used to evaluate the correlation between factors. The working process is as follows: 1) Determine the analysis sequence. According to the analysis objectives, determine the comprehensive load of the transmission line as the reference sequence, set as , , is the sample size. The influencing factors of tension are comparative sequences, set as , is the number of feature quantities.

[0032] Secondly, data normalization is performed. The order of magnitude and units of the reference sequence and the comparison sequence are usually different. To facilitate analysis, each sequence needs to be normalized. The formula is as follows: Where: is the original value of a certain feature; and are the maximum and minimum values ​​of a certain characteristic quantity respectively; It is the normalized value of a certain feature.

[0033] 2) Calculate the correlation coefficient. The correlation coefficient refers to the degree of correlation between the comparison sequence and the reference sequence at each time. and In the Correlation coefficient of time for: Where: is the resolution coefficient, , usually take =0.5, is the minimum absolute difference between all compared sequences and the reference sequence, It is the maximum absolute difference between all compared sequences and the reference sequence. ,when <0.5, indicating a weak correlation; when 0.5≤ When <0.7, it indicates a strong correlation; When ≥ 0.7, it indicates a strong correlation.

[0034] 3) Determine the degree of correlation. The grey correlation refers to the overall degree of correlation between the comparison sequence and the reference sequence, that is, taking the average value of the correlation coefficient at each moment. The calculation formula is as follows: Where: is the grey correlation degree, and its value and meaning are the same as .

[0035] 4. Construct a 0.1% probability impulse discharge voltage in the gap , 99.9% probability power frequency discharge voltage Compute the model and perform an evaluation.

[0036] S41. Use the multiple linear regression method, take the main environmental factors as independent variables and the discharge voltage as the dependent variable, and establish a calculation model. The model formula is: in, is the gap discharge voltage, , ,…, The main influencing factors are is the intercept term, which represents the expected value of the dependent variable when all independent variables are zero, and is the gap discharge voltage under standard atmospheric conditions. , ,…, is the regression coefficient, is the error term.

[0037] S42. Calculate the regression coefficient of each independent variable in the multiple linear regression model; S43: Substitute the regression coefficients of the independent variables into the multiple linear regression model to obtain the final gap discharge voltage calculation model.

[0038] S44. Evaluate the gap discharge voltage calculation model.

[0039] The mean absolute percentage error (MAPE), root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (CDR) were used. ) Four evaluation indicators are used to comprehensively evaluate the gap discharge voltage calculation model. Among them, MAPE provides a percentage of the prediction error and is sensitive to outliers; RMSE takes into account the size of the prediction error, but is not as intuitive as MAPE; MAE is similar to RMSE, but does not consider the direction of the error and is less sensitive to outliers; R 2 This measures the explanatory power of the model. The closer the value is to 1, the stronger the explanatory power of the model. The formula is as follows: 5. Determine whether the gap distance needs to be adjusted: Real-time monitoring of the main atmospheric factors affecting the gap discharge voltage, and calculation of the impulse discharge voltage with a 0.1% probability of the gap through the gap discharge voltage calculation model , 99.9% probability power frequency discharge voltage .

[0040] in accordance with Less than the single-phase ground fault voltage of the ground-lost system, The principle of greater than the residual voltage of the lightning arrester is used to determine whether the current gap distance meets the requirements.

[0041] like If the voltage is greater than the single-phase grounding fault voltage of the ground-lost system, shorten the gap distance by 10 mm and return to step 4.

[0042] like If the voltage is less than the residual voltage of the arrester, increase the gap by 10 mm and return to step 4.

[0043] 6. Intelligent protection system implementation and dynamic adjustment of gap.

[0044] The intelligent protection system integrates an environmental monitoring module, a data processing module, a model calculation module, and a gap adjustment module. The system monitors environmental parameters in real time, calculates the discharge voltage, and automatically executes the aforementioned analysis and adjustment process to achieve intelligent protection for the transformer neutral point.

[0045] The above embodiments are intended to illustrate the present invention, not to limit the present invention. Any solution that is a simple transformation of the present invention falls within the protection scope of the present invention.

Claims

1. An environmentally adaptive 110kV transformer neutral point intelligent protection method, characterized by: The following steps are involved: (1) In an artificial climate chamber, simulate various atmospheric conditions and conduct lightning impulse and power frequency discharge tests on rod gap lengths with different gap distances. Repeat the test 20 times under each environment and gap distance, and record the breakdown voltage value and the corresponding environmental parameters, including air pressure, temperature, wind speed, relative humidity and illumination. (2) Based on the breakdown voltage data of step (1), calculate the impulse discharge voltage of each gap length and the 0.1% probability under the corresponding environment through normal probability distribution. and 99.9% probability power frequency discharge voltage , specifically including: Calculate the mean of the breakdown voltage data and standard deviation ; Through the cumulative distribution function of the normal distribution , solve get , get ,in is the error function; (3) Grey correlation, Pearson correlation coefficient, and Spearman correlation coefficient were used to analyze the correlation between environmental parameters and discharge voltage and screen the main influencing factors; (4) A multiple linear regression model was established with the main environmental factors screened as independent variables and discharge voltage as the dependent variable: , is the gap discharge voltage, , ,…, The main influencing factors are is the discharge voltage intercept term under standard atmospheric conditions, , ,…, is the regression coefficient, is the error term; (5) Real-time monitoring of environmental parameters, inputting the model of step (4) to calculate the current and , and judge: like If the voltage is greater than the single-phase ground fault voltage of the ground-lost system, shorten the gap distance by 10 mm; like If it is less than the residual pressure of the arrester, increase the gap distance by 10mm; (6) Repeat step (5) until the gap distance meets Single-phase ground fault voltage and Residual pressure of the lightning arrester.

2. The method according to claim 1, characterized in that The rod gap lengths in step (1) are selected as 90 mm, 100 mm, 110 mm, 120 mm, 130 mm, 140 mm, and 150 mm.

3. The method according to claim 1, characterized in that The specific methods of correlation analysis in step (3) include: Pearson correlation coefficient calculation: Where, and are the expectations of random variables X and Y, respectively, and To distinguish their standard deviations, is their covariance; Spearman rank correlation coefficient calculation: Where, It represents the difference in the rank value of the i-th data pair, and n is the total number of observation samples; Grey relational analysis: Including data normalization, correlation coefficient calculation and correlation degree calculation; The data normalization formula is: Where: is the original value of a certain feature; and are the maximum and minimum values ​​of a certain characteristic quantity respectively; It is the normalized value of a certain characteristic quantity; The correlation coefficient was calculated as Where: is the resolution coefficient, , usually take =0.5, is the minimum absolute difference between all compared sequences and the reference sequence, It is the maximum absolute difference between all compared sequences and the reference sequence; ,when <0.5, indicating a weak correlation; when 0.5≤ When <0.7, it indicates a strong correlation; When ≥ 0.7, it indicates a strong correlation; The correlation is calculated as Where: is the grey correlation degree, and its value and meaning are the same as .

4. The method according to claim 1, wherein Step (4) also includes model evaluation using mean absolute percentage error (MAPE), root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination ( ) as the evaluation indicator.

5. An environment-adaptive 110kV transformer neutral point intelligent protection system, used to implement the method according to any one of claims 1 to 4, characterized in that: include: Environmental monitoring module: including air pressure, temperature, wind speed, relative humidity and illumination sensors for real-time collection of environmental parameters; Data processing module: is configured to perform the following operations: Based on historical test data, calculate the length of each gap through normal distribution and ; Grey correlation, Pearson coefficient and Spearman coefficient were used to analyze the correlation between environmental parameters and discharge voltage; Model calculation module: storing multiple linear regression models , receive real-time environment parameters and output and ; Judgment module: comparison Single-phase ground fault voltage, Relationship with the residual voltage of the arrester; Gap adjustment module: drives the actuator to increase or decrease the gap distance of the rods according to the judgment results, and the adjustment step is 10mm.

6. The system according to claim 5, characterized in that The gap adjustment module includes a stepping motor and a mechanical transmission mechanism, wherein the mechanical transmission mechanism connects the rod gap electrodes and responds to the displacement instruction of the stepping motor.

7. The system according to claim 5, characterized in that The data processing module and the model calculation module are integrated into an edge computing gateway, and the edge computing gateway communicates with the environment monitoring module and the gap adjustment module through an industrial bus.

8. The method or system according to claim 1 or 5, characterized in that: Step (5) and the adjustment logic of the judgment module meet the following requirements: Single-phase ground fault voltage and Residual pressure of the lightning arrester.

Images