A method for online monitoring and early warning of abnormal conditions in a distribution radio area

Abstract

This invention proposes an online monitoring and early warning method for abnormal states in distribution transformer substations. First, it obtains voltage and current sequence data of the substation from a historical database and collects three-phase voltage and current values ​​in real time. Next, it calculates the Pearson correlation coefficient between the voltage and current data and determines the connection group of the distribution transformer based on preset thresholds and judgment conditions. Then, it extracts features from the collected three-phase voltage and current values ​​to obtain voltage and current features, and obtains voltage feature enhancement values ​​based on the connection group. Finally, it constructs a total scoring function to score the voltage features, current features, and voltage feature enhancement values. By comparing these scores with preset thresholds, it determines whether a fault has occurred in the distribution transformer substation, thus achieving online monitoring and early warning of abnormal states. This invention focuses on improving the diagnostic accuracy of a specific fault—phase loss on the high-voltage side—and effectively reduces the false alarm and false negative rates of online detection in distribution transformer substations by utilizing low-frequency measurement data.

Description

Technical Field

[0001] This invention belongs to the field of power monitoring technology, specifically relating to an online monitoring and early warning method for abnormal conditions in distribution substations. Background Technology

[0002] As a crucial component of the smart grid, the safe and stable operation of the distribution network is of paramount importance. Phase loss faults on the high-voltage side of a distribution substation (such as line breaks or switch failures) can lead to three-phase voltage asymmetry, causing equipment damage, widespread power outages, and economic losses. Traditional fault handling relies on manual inspections and user reports, resulting in delayed responses and high costs. While distribution automation terminals (such as FTUs and DTUs) are used, the comprehensive deployment of high-end terminals is prohibitively expensive, and the vast amount of existing low-frequency measurement data (such as low-voltage and current data collected every 15 minutes) is not being fully utilized. Furthermore, the connection group of distribution transformers (such as Dyn11 and Yyn0) is a critical parameter, and traditional record-keeping may be inaccurate, affecting the accuracy of fault diagnosis.

[0003] Existing fault handling modes and monitoring technologies include the following categories:

[0004] 1. Manual inspection and user reports: The most traditional method, relying on manual discovery or user complaints, has a delayed response, cannot provide proactive early warning, and results in significant losses due to faults.

[0005] 2. Local intelligent terminal monitoring: Some TTUs / FTUs have a phase loss judgment function based on simple logic such as low voltage / current imbalance and voltage over-limit, which is costly, has insufficient ability to distinguish fault types (such as difficulty in distinguishing high voltage side phase loss from load imbalance), and is difficult to maintain.

[0006] 3. Direct monitoring on the high-voltage side: Installing voltage transformers, current sensors or dedicated fault indicators on the 10kV high-voltage side to directly monitor the voltage and current status has high installation and maintenance costs, high risks, and lacks universality.

[0007] 4. Fault diagnosis based on high-frequency transient data: This method utilizes the characteristics of high-frequency transient signals generated at the moment of a fault to analyze the fault type and location. It relies on high-speed sampling equipment, as existing systems cannot acquire high-frequency data.

[0008] Existing fault handling models and monitoring technologies have significant shortcomings in terms of response speed, cost, accuracy, and ease of maintenance. These shortcomings limit the power system's effective monitoring and rapid diagnosis of distribution substation faults, and fail to meet the requirements of smart grid construction for the safe and stable operation of the distribution network.

[0009] For example, Chinese patent CN116008682B proposes a method for determining phase loss faults on the high-voltage side of distribution transformers using a rule engine. Its core lies in: first, using voltage correlation coefficients and voltage difference extreme values ​​to determine the connection group; then, determining whether a phase loss has occurred based on simple logical rules; and finally, grouping transformer substations that alarm at the same time according to their respective lines to pinpoint whether the fault is on the line side or the transformer side. Furthermore, Chinese patent CN109713671B discloses a distribution transformer substation operation and maintenance method, system, storage medium, and electronic equipment. This patent aims to achieve comprehensive operation and maintenance of distribution transformer substations, with a very broad scope. It utilizes various data mining algorithms such as fuzzy clustering and linear fitting to identify multiple operating parameters, including connection group, operating tap, and capacity, and generates corresponding operation and maintenance suggestions based on the identification results of these parameters. However, the Chinese patent with publication number CN116008682B uses a fixed logic rule engine, which is a rigid and non-adaptive judgment method. Its accuracy and generalization ability are limited by the simplicity of the rules. The technical means of the Chinese patent with publication number CN109713671B are scattered. It uses fuzzy clustering to identify gear positions and linear fitting to identify capacity, but does not build a unified comprehensive diagnostic model for high-voltage phase loss faults. Summary of the Invention

[0010] To address the technical problems in existing technologies, an online monitoring and early warning method for abnormal states in distribution radio areas is provided, including:

[0011] Step S1: Obtain voltage and current sequence data of the distribution substation from the historical database; collect the three-phase voltage and three-phase current values ​​of the distribution substation in real time;

[0012] Step S2: Calculate the Pearson correlation coefficient between the voltage sequence data and the current sequence data in step S1; determine the connection group of the distribution transformer corresponding to the distribution area based on the Pearson correlation coefficient, according to the preset threshold and judgment conditions; the connection groups include Yyn0 and Dyn11;

[0013] Step S3: Obtain the three-phase voltage and three-phase current values ​​from step S1, perform feature extraction, and obtain voltage features and current features respectively; and obtain voltage feature enhancement values ​​based on the connection group obtained in step S2.

[0014] Step S4: Construct a total scoring function, and score the voltage characteristics, current characteristics and voltage characteristic enhancement values ​​based on the connection group using the total scoring function. Based on the score and the preset threshold, determine whether a fault has occurred in the distribution area.

[0015] Furthermore, step S1 specifically includes:

[0016] Step S11: Obtain measurement data of three-phase voltage and three-phase current on the low-voltage side of all distribution substations within the target monitoring range from the provincial or regional measurement data center, which serves as a historical database;

[0017] Step S12: For each distribution substation to be identified, extract voltage sequence data and current sequence data from the historical database respectively; obtain the three-phase voltage value and three-phase current value of each distribution substation at the latest acquisition time and the previous acquisition time for real-time fault identification;

[0018] Step S13: Verify the validity of the acquired voltage sequence data, current sequence data, three-phase voltage values, and three-phase current values, and remove damaged and missing data.

[0019] Furthermore, step S2 specifically involves:

[0020] Step S21: Obtain the voltage sequence data and current sequence data from step S1; calculate the correlation between the voltage sequence data, which includes... Phase voltage sequence, Phase voltage sequence and Phase voltage sequence; specifically:

[0021] calculate Phase voltage sequence With phase b voltage sequence Pearson correlation coefficient ;calculate Phase voltage sequence and Phase voltage sequence Pearson correlation coefficient ;calculate Phase voltage sequence and Phase voltage sequence Pearson correlation coefficient ;

[0022] Step S22: Calculate the correlation between voltage change and current change based on current sequence data, specifically:

[0023] The voltage change is calculated as follows:

[0024] Get Time corresponding Phase voltage change , represented as:

[0025] ;

[0026] ;

[0027] in, For a moment corresponding Phase voltage, For a moment corresponding Phase voltage;

[0028] The change in current is calculated as follows:

[0029] Get Time corresponding Phase current change , represented as:

[0030] ;

[0031] ;

[0032] in, For a moment corresponding Phase current, For a moment corresponding Phase current;

[0033] Calculate the Pearson correlation coefficient between the voltage change and current change of the corresponding phase, specifically as follows:

[0034] calculate Pearson correlation coefficient between phase voltage change and current change ;

[0035] calculate Pearson correlation coefficient between phase voltage change and current change ;

[0036] calculate Pearson correlation coefficient between phase voltage change and current change ;

[0037] Step S23: Based on the calculated Pearson correlation coefficient, set a threshold for judging the Pearson correlation coefficient between phase voltages. Threshold for determining the Pearson correlation coefficient between voltage and current changes. ;

[0038] The specific process for determining the Yyn0 connection group is as follows:

[0039] If the following conditions are met simultaneously:

[0040] ;

[0041] ;

[0042] ;

[0043] ;

[0044] Then the connection group of the distribution transformer is determined to be Yyn0;

[0045] The specific process for determining the Dyn11 connection group is as follows:

[0046] If the judgment conditions for the Yyn0 connection group are not met simultaneously, then the connection group of the distribution transformer is determined to be Dyn11.

[0047] Step S24: Associate the identified connection group information with the ID of the corresponding distribution transformer and the corresponding distribution area, and store it.

[0048] Furthermore, step S3 specifically includes:

[0049] Step S31: Obtain the voltage change Current change Voltage change rate and rate of change of current ; indicates as:

[0050] ;

[0051] ;

[0052] ;

[0053] ;

[0054] ;

[0055] in, For time, For time intervals, Indicates separation, For the sake of separation The voltage at time t For the sake of separation The amount of voltage change. For the sake of separation The current corresponding to time t, For the sake of separation The change in current, For the sake of separation The rate of change of voltage, For the sake of separation The rate of change of current; For the sake of separation exist Voltage corresponding to time; For the sake of separation In Current corresponding to time;

[0056] Step S32: Obtain voltage features through feature extraction. The voltage features include:

[0057] Negative sequence voltage components , represented as:

[0058] ;

[0059] Zero-sequence voltage component , represented as:

[0060] ;

[0061] Voltage imbalance , represented as:

[0062] ;

[0063] Maximum phase voltage sag , represented as:

[0064] ;

[0065] Current value of minimum phase voltage Specifically:

[0066] ;

[0067] in, Indicates the phase rotation operator; This represents the function that maximizes the value. This represents the minimum evaluation function; This represents the positive-sequence voltage component acquired in real time. Indicates taking the absolute value; Represents the core rotation operator;

[0068] Further current characteristics are obtained, including:

[0069] Negative sequence current components , represented as:

[0070] ;

[0071] Zero-sequence current component , represented as:

[0072] ;

[0073] Current imbalance , represented as:

[0074] ;

[0075] Maximum phase current amplification rate , represented as:

[0076] ;

[0077] in, Indicates separation The current at time t Indicates separation The current at time t Indicates separation The current at time t; This represents the positive-sequence current component acquired in real time.

[0078] Step S33: Based on the connection group obtained in step S2, obtain the voltage characteristic enhancement value, specifically:

[0079] If the connection group is Dyn11, assuming that the voltage drop occurs in two phases, calculate the voltage characteristic enhancement value under the condition that the third phase is stable;

[0080] Voltage characteristic enhancement values ​​include:

[0081] The normalized deviation of the two-phase voltage from the other phase voltage , represented as: ;

[0082] Normalized fluctuation of steady phase voltage , represented as:

[0083] ;

[0084] in, This represents the instantaneous voltage value of the first phase at time t. This represents the instantaneous voltage value of the second phase at time t. This represents the instantaneous voltage value of the third phase at time t. This is the rated phase voltage, which is 220V; This represents the instantaneous change in the voltage of the third phase.

[0085] If the connection group is Yyn0, calculate the corresponding voltage characteristic enhancement value;

[0086] The corresponding voltage characteristic enhancement values ​​include:

[0087] Ratio of minimum phase voltage to rated voltage , represented as:

[0088] ;

[0089] in, This represents the minimum phase voltage amplitude.

[0090] Average drop rate of non-lowest voltage phase That is, assuming phase X is the phase with the lowest voltage, the average voltage drop rate of the other two phases Y and Z is calculated and expressed as: .

[0091] Furthermore, the total score function in step S4 Specifically:

[0092] ;

[0093] in, A comprehensive score for voltage characteristics. A comprehensive score for current characteristics. A comprehensive score for voltage enhancement values ​​for a specific connection group;

[0094] pass Function calculation , and The rating value;

[0095] if If so, it is determined to be a phase loss fault on the high-voltage side. The threshold for determining faults in the overall score.

[0096] Furthermore, The function is represented as:

[0097] ;

[0098] in, express The input of the function, express The first threshold of the function, express The second threshold of the function, , and These represent the scores corresponding to different inputs;

[0099] The comprehensive score for voltage characteristics is expressed as follows:

[0100] ;

[0101] in, , , and These represent the scoring weights for voltage imbalance, zero-sequence voltage component, maximum phase voltage drop rate, and current value of minimum phase voltage, respectively.

[0102] The comprehensive score for current characteristics is expressed as follows:

[0103] ;

[0104] in, , and These represent the scoring weights for current imbalance, zero-sequence current component, and maximum phase current amplification rate, respectively.

[0105] The comprehensive score based on the voltage enhancement value of a specific connection group is as follows:

[0106] If the connection group is Dyn11, the corresponding comprehensive score is expressed as follows:

[0107] ;

[0108] in, The overall score for voltage enhancement value of connection group Dyn11. The scoring weights represent the normalized deviation of the two-phase voltage from the other phase voltage. The scoring weights represent the normalized fluctuations in the steady-state phase voltage.

[0109] If the connection group is Yyn0, the overall score is expressed as follows:

[0110] ;

[0111] in, The overall score representing the voltage enhancement value for connection group Dyn11. and These represent the scoring weights for the ratio of the lowest phase voltage to the rated voltage and the average drop rate of the non-lowest voltage phase, respectively.

[0112] The technical effects of this invention include:

[0113] This invention significantly improves the accuracy of high-voltage side phase loss fault diagnosis: Based on automatic identification of connection groups, it designs differentiated, refined judgment rules based on voltage change characteristics for two common distribution transformer connection groups, Dyn11 and Yyn0, and combines them with current change characteristics for further differentiation. Compared with universal unbalance criteria or simple logic that does not distinguish connection groups, this invention can more accurately identify high-voltage side phase loss faults, effectively reducing false alarm and false negative rates. Furthermore, this invention focuses on how to improve the diagnostic accuracy of high-voltage side phase loss, a specific fault, and provides a high-precision, model-based fault diagnosis and early warning method using low-frequency measurement data. Attached Figure Description

[0114] Figure 1 This is a flowchart of the steps in this application. Detailed Implementation

[0115] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention.

[0116] Reference Figure 1 A method for online monitoring and early warning of abnormal conditions in a distribution radio area, comprising:

[0117] Step S1: Obtain voltage and current sequence data of the distribution substation from the historical database; collect the three-phase voltage and three-phase current values ​​of the distribution substation in real time;

[0118] Step S2: Calculate the Pearson correlation coefficient between the voltage sequence data and the current sequence data in step S1; determine the connection group of the distribution transformer corresponding to the distribution area based on the Pearson correlation coefficient, according to the preset threshold and judgment conditions; the connection groups include Yyn0 and Dyn11;

[0119] Step S3: Obtain the three-phase voltage and three-phase current values ​​from step S1, perform feature extraction, and obtain voltage features and current features respectively; and obtain voltage feature enhancement values ​​based on the connection group obtained in step S2.

[0120] Step S4: Construct a total scoring function, and score the voltage characteristics, current characteristics and voltage characteristic enhancement values ​​based on the connection group using the total scoring function. Based on the score and the preset threshold, determine whether a fault has occurred in the distribution area.

[0121] Furthermore, step S1 specifically includes:

[0122] Step S11: Obtain measurement data of three-phase voltage and three-phase current on the low-voltage side of all distribution substations within the target monitoring range from the provincial or regional measurement data center, which serves as a historical database;

[0123] Step S12: For each distribution substation to be identified, extract voltage sequence data and current sequence data from the historical database respectively; obtain the three-phase voltage value and three-phase current value of each distribution substation at the latest acquisition time and the previous acquisition time for real-time fault identification;

[0124] Step S13: Verify the validity of the acquired voltage sequence data, current sequence data, three-phase voltage values, and three-phase current values, and remove damaged and missing data.

[0125] Furthermore, step S2 specifically involves:

[0126] Step S21: Obtain the voltage sequence data and current sequence data from step S1; calculate the correlation between the voltage sequence data, which includes... Phase voltage sequence, Phase voltage sequence and Phase voltage sequence; specifically:

[0127] calculate Phase voltage sequence With phase b voltage sequence Pearson correlation coefficient ;calculate Phase voltage sequence and Phase voltage sequence Pearson correlation coefficient ;calculate Phase voltage sequence and Phase voltage sequence Pearson correlation coefficient ;

[0128] Step S22: Calculate the correlation between voltage change and current change based on current sequence data, specifically:

[0129] The voltage change is calculated as follows:

[0130] Get Time corresponding Phase voltage change , represented as:

[0131] ;

[0132] ;

[0133] in, For a moment corresponding Phase voltage, For a moment corresponding Phase voltage;

[0134] The change in current is calculated as follows:

[0135] Get Time corresponding Phase current change , represented as:

[0136] ;

[0137] ;

[0138] in, For a moment corresponding Phase current, For a moment corresponding Phase current;

[0139] Calculate the Pearson correlation coefficient between the voltage change and current change of the corresponding phase, specifically as follows:

[0140] calculate Pearson correlation coefficient between phase voltage change and current change ;

[0141] calculate Pearson correlation coefficient between phase voltage change and current change ;

[0142] calculate Pearson correlation coefficient between phase voltage change and current change ;

[0143] Step S23: Based on the calculated Pearson correlation coefficient, set a threshold for judging the Pearson correlation coefficient between phase voltages. Threshold for determining the Pearson correlation coefficient between voltage and current changes. ;

[0144] The specific process for determining the Yyn0 connection group is as follows:

[0145] If the following conditions are met simultaneously:

[0146] ;

[0147] ;

[0148] ;

[0149] ;

[0150] Then the connection group of the distribution transformer is determined to be Yyn0;

[0151] The specific process for determining the Dyn11 connection group is as follows:

[0152] If the judgment conditions for the Yyn0 connection group are not met simultaneously, then the connection group of the distribution transformer is determined to be Dyn11.

[0153] Step S24: Associate the identified connection group information with the ID of the corresponding distribution transformer and the corresponding distribution area, and store it.

[0154] Furthermore, step S3 specifically includes:

[0155] Step S31: Obtain the voltage change Current change Voltage change rate and rate of change of current ; indicates as:

[0156] ;

[0157] ;

[0158] ;

[0159] ;

[0160] ;

[0161] in, For time, For time intervals, Indicates separation, For the sake of separation The voltage at time t For the sake of separation The amount of voltage change. For the sake of separation The current corresponding to time t, For the sake of separation The change in current, For the sake of separation The rate of change of voltage, For the sake of separation The rate of change of current; For the sake of separation exist Voltage corresponding to time; For the sake of separation In Current corresponding to time;

[0162] Step S32: Obtain voltage features through feature extraction. The voltage features include:

[0163] Negative sequence voltage components , represented as:

[0164] ;

[0165] Zero-sequence voltage component , represented as:

[0166] ;

[0167] Voltage imbalance , represented as:

[0168] ;

[0169] Maximum phase voltage sag , represented as:

[0170] ;

[0171] Current value of minimum phase voltage Specifically:

[0172] ;

[0173] in, Indicates the phase rotation operator; This represents the function that maximizes the value. This represents the minimum evaluation function; This represents the positive-sequence voltage component acquired in real time. Indicates taking the absolute value; Represents the core rotation operator;

[0174] Further current characteristics are obtained, including:

[0175] Negative sequence current components , represented as:

[0176] ;

[0177] Zero-sequence current component , represented as:

[0178] ;

[0179] Current imbalance , represented as:

[0180] ;

[0181] Maximum phase current amplification rate , represented as:

[0182] ;

[0183] in, Indicates separation The current at time t Indicates separation The current at time t Indicates separation The current at time t; This represents the positive-sequence current component acquired in real time.

[0184] Step S33: Based on the connection group obtained in step S2, obtain the voltage characteristic enhancement value, specifically:

[0185] If the connection group is Dyn11, assuming that the voltage drop occurs in two phases, calculate the voltage characteristic enhancement value under the condition that the third phase is stable;

[0186] Voltage characteristic enhancement values ​​include:

[0187] The normalized deviation of the two-phase voltage from the other phase voltage , represented as: ;

[0188] Normalized fluctuation of steady phase voltage , represented as:

[0189] ;

[0190] in, This represents the instantaneous voltage value of the first phase at time t. This represents the instantaneous voltage value of the second phase at time t. This represents the instantaneous voltage value of the third phase at time t. This is the rated phase voltage, which is 220V; This represents the instantaneous change in the voltage of the third phase.

[0191] If the connection group is Yyn0, calculate the corresponding voltage characteristic enhancement value;

[0192] The corresponding voltage characteristic enhancement values ​​include:

[0193] Ratio of minimum phase voltage to rated voltage , represented as:

[0194] ;

[0195] in, This represents the minimum phase voltage amplitude.

[0196] Average drop rate of non-lowest voltage phase That is, assuming phase X is the phase with the lowest voltage, the average voltage drop rate of the other two phases Y and Z is calculated and expressed as: .

[0197] Furthermore, the total score function in step S4 Specifically:

[0198] ;

[0199] in, A comprehensive score for voltage characteristics. A comprehensive score for current characteristics. A comprehensive score for voltage enhancement values ​​for a specific connection group;

[0200] pass Function calculation , and The rating value;

[0201] if If so, it is determined to be a phase loss fault on the high-voltage side. The threshold for determining faults in the overall score.

[0202] Furthermore, The function is represented as:

[0203] ;

[0204] in, express The input of the function, express The first threshold of the function, express The second threshold of the function, , and These represent the scores corresponding to different inputs;

[0205] The comprehensive score for voltage characteristics is expressed as follows:

[0206] ;

[0207] in, , , and These represent the scoring weights for voltage imbalance, zero-sequence voltage component, maximum phase voltage drop rate, and current value of minimum phase voltage, respectively.

[0208] The comprehensive score for current characteristics is expressed as follows:

[0209] ;

[0210] in, , and These represent the scoring weights for current imbalance, zero-sequence current component, and maximum phase current amplification rate, respectively.

[0211] The comprehensive score based on the voltage enhancement value of a specific connection group is as follows:

[0212] If the connection group is Dyn11, the corresponding comprehensive score is expressed as follows:

[0213] ;

[0214] in, The overall score for voltage enhancement value of connection group Dyn11. The scoring weights represent the normalized deviation of the two-phase voltage from the other phase voltage. The scoring weights represent the normalized fluctuations in the steady-state phase voltage.

[0215] If the connection group is Yyn0, the overall score is expressed as follows:

[0216] ;

[0217] in, The overall score representing the voltage enhancement value for connection group Dyn11. and These represent the scoring weights for the ratio of the lowest phase voltage to the rated voltage and the average drop rate of the non-lowest voltage phase, respectively.

[0218] The present invention has been described in detail above with reference to the accompanying drawings and embodiments. Those skilled in the art can make various modifications to the present invention based on the above description. Therefore, certain details in the embodiments should not be construed as limiting the present invention, and the scope of protection of the present invention shall be defined by the appended claims.

Claims

1. A method for online monitoring and early warning of abnormal conditions in a distribution radio area, characterized in that, include: Step S1: Obtain voltage and current sequence data of the distribution substation from the historical database; Real-time acquisition of three-phase voltage and three-phase current values ​​in the distribution transformer area; Step S2: Calculate the Pearson correlation coefficient between the voltage sequence data and the current sequence data in step S1; determine the connection group of the distribution transformer corresponding to the distribution area based on the Pearson correlation coefficient, according to the preset threshold and judgment conditions; the connection groups include Yyn0 and Dyn11; Step S3: Obtain the three-phase voltage and three-phase current values ​​from step S1, perform feature extraction, and obtain voltage features and current features respectively; Based on the connection group obtained in step S2, the voltage characteristic enhancement value is obtained; Step S4: Construct a total scoring function, and score the voltage characteristics, current characteristics and voltage characteristic enhancement value based on the connection group using the total scoring function. Based on the score and the preset threshold, determine whether a fault has occurred in the distribution area. Step S2 is as follows: Step S21: Obtain the voltage sequence data and current sequence data from step S1; calculate the correlation between the voltage sequence data, which includes... Phase voltage sequence, Phase voltage sequence and Phase voltage sequence; specifically: calculate Phase voltage sequence With phase b voltage sequence Pearson correlation coefficient ;calculate Phase voltage sequence and Phase voltage sequence Pearson correlation coefficient ;calculate Phase voltage sequence and Phase voltage sequence Pearson correlation coefficient ; Step S22: Calculate the correlation between voltage change and current change based on current sequence data, specifically: The voltage change is calculated as follows: Get Time corresponding Phase voltage change , represented as: ； ； in, For a moment corresponding Phase voltage, For a moment corresponding Phase voltage; The change in current is calculated as follows: Get Time corresponding Phase current change , represented as: ； ； in, For a moment corresponding Phase current, For a moment corresponding Phase current; Calculate the Pearson correlation coefficient between the voltage change and current change of the corresponding phase, specifically as follows: calculate Pearson correlation coefficient between phase voltage change and current change ; calculate Pearson correlation coefficient between phase voltage change and current change ; calculate Pearson correlation coefficient between phase voltage change and current change ; Step S23: Based on the calculated Pearson correlation coefficient, set a threshold for judging the Pearson correlation coefficient between phase voltages. Threshold for determining the Pearson correlation coefficient between voltage and current changes. ; The specific process for determining the Yyn0 connection group is as follows: If the following conditions are met simultaneously: ； ； ； ； Then the connection group of the distribution transformer is determined to be Yyn0; The specific process for determining the Dyn11 connection group is as follows: If the judgment conditions for the Yyn0 connection group are not met simultaneously, then the connection group of the distribution transformer is determined to be Dyn11. Step S24: Associate the identified connection group information with the ID of the corresponding distribution transformer and its corresponding distribution substation and store it; Step S3 is as follows: Step S31: Obtain the voltage change Current change Voltage change rate and rate of change of current ; indicates as: ； ； ； ； ； in, For time, For time intervals, Indicates separation, For the sake of separation The voltage at time t For the sake of separation The amount of voltage change. For the sake of separation The current corresponding to time t, For the sake of separation The change in current, For the sake of separation The rate of change of voltage, For the sake of separation The rate of change of current; For the sake of separation exist Voltage corresponding to time; For the sake of separation In Current corresponding to time; Step S32: Obtain voltage features through feature extraction. The voltage features include: Negative sequence voltage components , represented as: ； Zero-sequence voltage component , represented as: ； Voltage imbalance , represented as: ； Maximum phase voltage sag , represented as: ； Current value of minimum phase voltage Specifically: ； in, Represents the phase rotation operator; This represents the function that maximizes the value. This represents the minimum evaluation function; This represents the positive-sequence voltage component acquired in real time. Indicates taking the absolute value; Represents the core rotation operator; Further current characteristics are obtained, including: Negative sequence current components , is represented as: ； Zero-sequence current component , is represented as: ； Current imbalance , is represented as: ； Maximum phase current amplification rate , represented as: ； in, Indicates separation The current at time t Indicates separation The current at time t Indicates separation The current at time t; This represents the positive-sequence current component acquired in real time. Step S33: Based on the connection group obtained in step S2, obtain the voltage characteristic enhancement value, specifically: If the connection group is Dyn11, assuming that the voltage drop occurs in two phases, calculate the voltage characteristic enhancement value under the condition that the third phase is stable; Voltage characteristic enhancement values ​​include: The normalized deviation of the two-phase voltage from the other phase voltage , is represented as: ； Normalized fluctuation of steady phase voltage , represented as: ； in, This represents the instantaneous voltage value of the first phase at time t. This represents the instantaneous voltage value of the second phase at time t. This represents the instantaneous voltage value of the third phase at time t. This is the rated phase voltage, which is 220V; This represents the instantaneous change in the voltage of the third phase. If the connection group is Yyn0, calculate the corresponding voltage characteristic enhancement value; The corresponding voltage characteristic enhancement values ​​include: Ratio of minimum phase voltage to rated voltage , is represented as: ； in, This represents the minimum phase voltage amplitude. Average drop rate of non-lowest voltage phase That is, assuming phase X is the phase with the lowest voltage, the average voltage drop rate of the other two phases Y and Z is calculated and expressed as: ; Total score function in step S4 Specifically: ； in, A comprehensive score for voltage characteristics. A comprehensive score for current characteristics. A comprehensive score for voltage enhancement values ​​for a specific connection group; pass Function calculation , and The rating value; if If so, it is determined to be a phase loss fault on the high-voltage side. The threshold for determining faults in the overall score; The function is represented as: ； in, express The input of the function, express The first threshold of the function, express The second threshold of the function, , and These represent the scores corresponding to different inputs; The comprehensive score for voltage characteristics is expressed as follows: ； in, , , and These represent the scoring weights for voltage imbalance, zero-sequence voltage component, maximum phase voltage drop rate, and current value of minimum phase voltage, respectively. The comprehensive score for current characteristics is expressed as follows: ； in, , and These represent the scoring weights for current imbalance, zero-sequence current component, and maximum phase current amplification rate, respectively. The comprehensive score based on the voltage enhancement value of a specific connection group is as follows: If the connection group is Dyn11, the corresponding comprehensive score is expressed as follows: ； in, The overall score for voltage enhancement value of connection group Dyn11. The scoring weights represent the normalized deviation of the two-phase voltage from the other phase voltage. The scoring weights represent the normalized fluctuations in the steady-state phase voltage. If the connection group is Yyn0, the overall score is expressed as follows: ； in, The overall score representing the voltage enhancement value for connection group Dyn11. and These represent the scoring weights for the ratio of the lowest phase voltage to the rated voltage and the average drop rate of the non-lowest voltage phase, respectively.

2. The method for online monitoring and early warning of abnormal status in a distribution radio area according to claim 1, characterized in that, Step S1 is as follows: Step S11: Obtain measurement data of three-phase voltage and three-phase current on the low-voltage side of all distribution substations within the target monitoring range from the provincial or regional measurement data center, which serves as a historical database; Step S12: For each distribution substation to be identified, extract voltage sequence data and current sequence data from the historical database respectively; obtain the three-phase voltage value and three-phase current value of each distribution substation at the latest acquisition time and the previous acquisition time for real-time fault identification; Step S13: Verify the validity of the acquired voltage sequence data, current sequence data, three-phase voltage values, and three-phase current values, and remove damaged and missing data.

Images