A monitoring and maintenance method for a low-voltage side circuit breaker of a 35kV box-type transformer

Abstract

The present application relates to the technical field of monitoring of low-voltage side circuit breaker, and discloses a kind of 35kV box-type transformer low-voltage side circuit breaker monitoring maintenance method, comprising: according to the equipment parameter information obtained, formulating monitoring information sampling period;Based on low-voltage side circuit breaker historical data, construct low-voltage side circuit breaker maintenance model;Based on monitoring information sampling period, set monitoring node, obtain the real-time data of low-voltage side circuit breaker of current monitoring node;The operation fault risk of equipment is detected by low-voltage side circuit breaker maintenance model, and maintenance is carried out according to the detection result.The present application realizes the intelligent monitoring and automatic control of circuit breaker state, and through the evaluation of equipment health state and the detection of operation fault risk, more fine maintenance management can be realized, which helps to optimize resource allocation, reduces unnecessary maintenance activities, reduces maintenance cost, and at the same time improves the efficiency and effect of maintenance work.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of monitoring low-voltage side circuit breakers, in particular to a monitoring and maintenance method for a 35kV box-type transformer low-voltage side circuit breaker. BACKGROUND

[0002] The 35kV box-type transformer low-voltage side circuit breaker is an important component of the power system, responsible for connecting and disconnecting the circuit at the low-voltage side of the transformer, ensuring the safe and stable operation of the power system. The reliability of the low-voltage side circuit breaker directly affects the continuity of power supply and the safety of equipment, so effective monitoring and maintenance is crucial.

[0003] In summary, the technical background of the monitoring and maintenance method for the 35kV box-type transformer low-voltage side circuit breaker involves the development of automation and intelligent monitoring technology, as well as the establishment and optimization of standardized maintenance processes. The combination of these technologies and standards helps to improve the reliability and maintenance efficiency of the circuit breaker, ensuring the safe and stable operation of the power system. SUMMARY

[0004] The purpose of the present application is to use historical current, voltage, and temperature data of the circuit breaker to construct a low-voltage side circuit breaker maintenance model, generate a low-voltage side circuit breaker maintenance model by constructing a first compensation parameter based on corresponding voltage and temperature data characteristics, and control the movement of the time window and determine the emergency situation of the fault by dividing the time window, counting the peak and valley values of the current, and generating a fault prediction score.

[0005] To achieve the above purpose, the present application provides a monitoring and maintenance method for a 35kV box-type transformer low-voltage side circuit breaker, comprising:

[0006] According to the device parameters, a plurality of monitoring periods are set, and a plurality of monitoring time nodes are set, each monitoring time node representing the start of a monitoring period;

[0007] Based on the historical data of the low-voltage side circuit breaker, a low-voltage side circuit breaker maintenance model is constructed;

[0008] Obtain the real-time data of the low-voltage side circuit breaker at the current monitoring time node, and detect the operation fault risk of the device according to the low-voltage side circuit breaker maintenance model;

[0009] According to the detection result of the current monitoring time node, determine whether to perform maintenance.

[0010] In some embodiments of the present application, when the monitoring information sampling period is determined based on the obtained device parameter information, it comprises:

[0011] Obtain the parameter information P of the current device to be maintained, P = [P1, P2…P i …P m ];

[0012] wherein P i represents the parameter information value of the i-th category, and m represents the total number of categories of parameter information;

[0013] Based on the parameter information of the equipment to be repaired, a low-voltage side circuit breaker primary evaluation model is established;

[0014] A health state evaluation value of the current equipment is generated through the low-voltage side circuit breaker primary evaluation model;

[0015] According to the health state evaluation value of the current equipment, a monitoring cycle length is set.

[0016] In some embodiments of the present application, when the low-voltage side circuit breaker primary evaluation model is established, the following steps are included:

[0017] The parameter information P of n groups of historical repair equipment is obtained, and an n*m sample matrix X is constructed,

[0018] Based on the sample matrix X, a covariance matrix Σ[Y ij ] is constructed;

[0019] wherein Y ij =Cov(X i ,X j ), Y ij represents the i-th row and j-th column element in the covariance matrix;

[0020] The eigenvalues λ of the covariance matrix are calculated, λ=[λ1, λ2… λ i … λ m ];

[0021] λ i represents the i-th eigenvalue, and n represents the total number of eigenvalues;

[0022] Based on the eigenvalues λ of the covariance matrix, the contribution values R of the parameter information of each category of the current repair equipment are determined, R=[R1, R2… R i … R m ];

[0023] Based on the contribution values R of the parameter information of each category of the current repair equipment and the parameter information P of the current repair equipment, the low-voltage side circuit breaker primary evaluation model is established;

[0024]

[0025] A represents the health state evaluation value of the current equipment.

[0026] In some embodiments of the present application, when the low-voltage side circuit breaker repair model is constructed, the following steps are included:

[0027] Obtain historical monitoring data of the circuit breaker, the historical monitoring data comprising: historical current data, historical voltage data and historical temperature data;

[0028] Extract feature parameters of the historical current data, comprising: peak value of current, valley value of current;

[0029] Classify the peak value of current into grade intervals to obtain a current peak value data set IF, IF=[IF1, IF2…IF i …IF n ];

[0030] Wherein, IF i represents the i-th grade power peak interval, and n represents the total number of current peak intervals;

[0031] Classify the valley value of current into grade intervals to obtain a current valley value data set IG, IG=[IG1, IG2…IG i …IG n ];

[0032] Wherein, IG i represents the i-th grade power valley interval, and n represents the total number of current valley intervals;

[0033] Determine the state of the corresponding low-voltage side circuit breaker based on the feature parameters of the historical current data, and establish a circuit breaker state event set F, F=[F1, F2…F i …F n ];

[0034] Wherein, Fi represents the i-th type of circuit breaker state event, and n represents the total number of circuit breaker state events;

[0035] Obtain voltage historical data and temperature historical data corresponding to the occurrence of the circuit breaker state event; extract data features of the voltage historical data and the temperature historical data;

[0036] Construct a first compensation parameter C based on the data features of the voltage historical data and the temperature historical data;

[0037] Combine the feature parameters of the historical current data and the first compensation parameter C to generate a low-voltage side circuit breaker maintenance model;

[0038] In some embodiments of the present application, when the first compensation parameter C is constructed:

[0039] Calculate the change rate of the voltage historical data and the change rate of the temperature historical data;

[0040] And classify the change rate of the voltage historical data and the change rate of the temperature historical data into grades; an evaluation value is generated for each grade;

[0041] Generate the historical change rate evaluation value DV of the voltage in the sampling interval and the historical change rate evaluation value DT of the temperature;

[0042] C=k1*DV+k2*DT;

[0043] Wherein, k1 is the historical change rate evaluation value weight of the voltage, and k2 is the historical change rate evaluation value weight of the temperature.

[0044] In some embodiments of the application, when detecting the operation failure risk of the device, the following steps are included:

[0045] Obtain the real-time data of the low-voltage side circuit breaker of the current monitoring node, including current data, voltage data and temperature data;

[0046] Based on the low-voltage side circuit breaker maintenance model, generate the operation state evaluation value of the low-voltage side circuit breaker of the current monitoring node, and judge whether there is a fault based on the operation state evaluation value;

[0047] If there is a fault, generate a first control instruction to identify the type of fault occurrence;

[0048] If there is no fault, generate a second control instruction to predict the probability of fault occurrence.

[0049] In some embodiments of the application, the generation of the fault prediction instruction includes:

[0050] Divide the time window m in the monitoring information sampling period, and count the number of occurrence and the frequency of occurrence of the current valley value and the number of occurrence and the frequency of occurrence of the current peak value in each time window;

[0051] And combine the first compensation parameter C to generate the fault prediction score M;

[0052] Control the movement of the time window based on the fault prediction score M;

[0053] Generate the change value of the fault prediction score M in the whole sampling period;

[0054] Based on the change value of the fault prediction score M, judge the emergency of the fault occurrence.

[0055] In some embodiments of the application, the generation of the fault prediction score M includes:

[0056] Get the current peak value data set IF, IF=[IF1, IF2…IF i …IF n ];

[0057] M=n1*IF i +n2*IG i +C;

[0058] Among them, IF i IG represents the power valley range for the i-th level. i Let n1 represent the power trough interval of the i-th level, n2 represent the number of times the power peak interval of the i-th level occurs, and n3 represent the number of times the power trough interval of the i-th level occurs.

[0059] In some embodiments of the present invention, when the time window is moved based on the fault prediction score M, it includes:

[0060] Calculate the fault prediction score M within a single time window;

[0061] After obtaining the fault prediction score M within the current time window, the control time window is shifted to the right by m steps, with each step being a sampling time.

[0062] Based on the fault prediction score M, multi-level thresholds are generated, and the value of m is controlled based on the multi-level thresholds; the fault prediction score M is positively correlated with the number of steps to the right of the time window.

[0063] Compared with existing technologies, the monitoring and maintenance method for the low-voltage side circuit breaker of a 35kV box-type transformer according to an embodiment of the present invention has the following advantages:

[0064] Different parameters reflect the equipment's status from various perspectives, providing a rich source of data for establishing accurate evaluation models in the future.

[0065] By establishing a primary evaluation model, power maintenance personnel can predict potential equipment problems in advance based on this evaluation value, thereby avoiding sudden equipment failures and improving the reliability and stability of the power system.

[0066] Establishing a maintenance model for low-voltage circuit breakers can help maintenance personnel more accurately determine whether circuit breakers need maintenance, identify the key areas for maintenance, improve maintenance efficiency and accuracy, and reduce the risk of power system failures caused by circuit breaker malfunctions.

[0067] Judging the change value of the fault prediction score M can help maintenance personnel allocate maintenance resources more rationally and improve the reliability and security of the power system.

[0068] By moving the time window with the sampling time as the step size, we can analyze the changes in the data over time more meticulously. This allows us to explore the time periods in which faults may occur more deeply, thereby discovering potential faults more promptly and accurately, and ensuring the stable operation of the power system. Attached Figure Description

[0069] Figure 1 This is a structural diagram of a monitoring and maintenance method for a low-voltage side circuit breaker of a 35kV box-type transformer provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0070] The specific embodiments of the present application will be further described in conjunction with the drawings and examples. The following examples are used to illustrate the present application, but not to limit the scope of the present application.

[0071] In the description of the present application, it needs to be understood that the terms "center", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer" and the like indicate the orientation or positional relationship shown in the drawings, and are only for the purpose of facilitating the description of the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as a limitation on the present application.

[0072] The terms "first", "second" are only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features. In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more.

[0073] In the description of the present application, it needs to be noted that, unless otherwise explicitly specified and limited, the terms "mounting", "connecting", "connection" should be understood broadly, for example, it can be fixed connection, or detachable connection, or integral connection; it can be mechanical connection, or electrical connection; it can be direct connection, or indirect connection through intermediate medium, or internal communication of two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.

[0074] Example 1: A monitoring and maintenance method for a low-voltage side circuit breaker of a 35kV box-type transformer, as shown in Figure 1 , comprising:

[0075] According to the device parameters, a plurality of monitoring periods are set, and a plurality of monitoring time nodes are set, each monitoring time node representing the start of a monitoring period;

[0076] A low-voltage side circuit breaker maintenance model is constructed based on the historical data of the low-voltage side circuit breaker;

[0077] Obtain the real-time data of the low-voltage side circuit breaker at the current monitoring time node, and detect the operation failure risk of the device according to the low-voltage side circuit breaker maintenance model;

[0078] According to the detection result of the current monitoring time node, it is judged whether to perform maintenance.

[0079] In this embodiment, the device information collection

[0080] For a 35kV box transformer, the low-voltage side circuit breaker has a variety of available device parameter information. For example, the rated current is 500A, the rated voltage is 0.4kV, the operating environment temperature range is -20-40℃, etc.

[0081] P = [P1 = 500A, P2 = 0.4kV, P3 = -20-40℃, …]

[0082] Historical data collection

[0083] From the historical operation records of the low-voltage side circuit breaker of the transformer, the current, voltage, and temperature data of the past year (assuming) are obtained. These data are stored in a database for subsequent construction of maintenance models.

[0084] Primary evaluation model construction

[0085] Using the obtained m = 5 types of device parameter information Based on the parameter information of the past n = 100 sets of historical maintenance equipment, a sample matrix X is constructed.

[0086] By calculating the covariance matrix of the sample matrix X, for example

[0087] Cov(X), and calculating its eigenvalues Determine the contribution value of each parameter.

[0088] Establish a primary evaluation model for the low-voltage side circuit breaker, and obtain a device health status evaluation value H = 0.8. According to this evaluation value, the sampling frequency is determined to be once per hour, i.e. the monitoring information sampling period is determined to be 1 hour.

[0089] Current data feature extraction

[0090] From the historical current data, for example, the maximum current peak value is 800A and the minimum current valley value is 100A. The current peak and valley values are divided into interval sections, such as 0-200A for low current interval, 200-500A for normal interval, and 500-800A for high current interval.

[0091] Determine the circuit breaker state event set, such as the high current interval may correspond to an overload event, etc.

[0092] Combine voltage and temperature data

[0093] When an overload event (high current interval) occurs, the corresponding voltage may fluctuate, such as from 0.4kV to 0.38kV, and the temperature rises from 30℃ to 35℃. Combine these voltage and temperature data features to construct the first compensation parameter C = 0.9, and finally generate the low-voltage side circuit breaker maintenance model.

[0094] Monitoring node setting

[0095] The monitoring node is set based on the determined 1-hour sampling period. At each monitoring node, real-time current, voltage, and temperature data are obtained through sensors installed on the low-voltage side circuit breaker.

[0096] For example, the real-time current obtained at a certain monitoring node is 300 A, the voltage is 0.39 kV, and the temperature is 32℃.

[0097] The equipment operation fault risk is detected through the constructed maintenance model. The real-time obtained current, voltage, and temperature data are substituted into the maintenance model.

[0098] Suppose the operation state evaluation value generated according to the maintenance model is S = 0.9, and since S > 0.8 (previously set threshold, assume), it is determined that the equipment is not faulty at this time.

[0099] Then generate a secondary control instruction to predict the fault probability, for example, predict the fault probability within the next 24 hours as 5%.

[0100] Fault condition handling

[0101] If at another monitoring node, the operation state evaluation value S = 0.6, it is determined to be a fault.

[0102] At this time, a primary control instruction is generated to identify the fault type, and through further analysis of the current, voltage, and temperature data trends and comparison with historical fault data, it is determined to be a possible poor contact fault. Then perform corresponding maintenance operations, such as checking the connection parts, replacing the aging parts, etc.

[0103] Through the above specific embodiments, the practical application process of the 35kV box-type transformer low-voltage side circuit breaker monitoring and maintenance method is demonstrated.

[0104] In the embodiment 2, when the monitoring information sampling period is determined according to the obtained equipment parameter information, it includes:

[0105] Obtain the parameter information P of the current equipment to be maintained, P = [P1, P2…Pm]; i …P m ];

[0106] Wherein, P i represents the i-th type of parameter information value, and m represents the total number of parameter information categories;

[0107] Based on the parameter information of the equipment to be maintained, a low-voltage side circuit breaker primary evaluation model is established;

[0108] Through the low-voltage side circuit breaker primary evaluation model, the health state evaluation value of the current equipment is generated;

[0109] According to the health state evaluation value of the current device, the monitoring period length is set.

[0110] In this embodiment, the device parameter information is acquired

[0111] Suppose we want to overhaul a 35kV box-type transformer low-voltage side circuit breaker. First, acquire its parameter information P = [P1, P2, P3, P4], where m = 4.

[0112] Among them, P1 is the rated current, whose value is 400A; P2 is the rated voltage, whose value is 0.4kV; P3 is the circuit breaker contact material type (assuming it is represented by code, such as 1 for copper contact); P4 is the operating environment humidity, whose value is 50% (assuming).

[0113] Sample data preparation

[0114] Collect the parameter information of 50 groups of similar low-voltage side circuit breakers in different health states as sample data.

[0115] Construct the sample data into a sample matrix X, each row of the matrix represents a group of samples, and each column corresponds to a parameter category.

[0116] Model building process

[0117] Calculate the covariance matrix Cov(X) of the sample matrix X.

[0118] Solve the eigenvalues λi(i = 1, 2, □, 4) and the corresponding eigenvectors of the covariance matrix Cov(X). According to the eigenvalues, determine the contribution values of each parameter. For example, it is found through calculation that the contribution value of the rated current P1 is 0.3, the contribution value of the rated voltage P2 is 0.25, the contribution value of the contact material type P3 is 0.2, and the contribution value of the operating environment humidity P4 is 0.25.

[0119] Establish a low-voltage side circuit breaker primary evaluation model, which can be a weighted summation model, for example:

[0120] The device health state evaluation value is H, H = 0.3 × P1 / P1max + 0.25 × P2 / P2max + 0.2 × f(P3) + 0.25 × P4 / P4 max (here P1 max is the maximum allowable value of the rated current, assuming 500A; P2 max is the maximum allowable value of the rated voltage, assuming 0.45kV; f(P3) is the function value corresponding to the contact material type, assuming copper contact f(P3) = 1; P4max is the maximum allowable value of the operating environment humidity, assuming 80%).

[0121] Substitute the parameter value of the current device into the model to obtain H = 0.3 * 500 / 400 + 0.25 * 0.45 / 0.4 + 0.2 * 1 + 0.25 * 80 / 50

[0122] The calculation can obtain H ≈ 0.65.

[0123] Determination rule

[0124] Set the sampling frequency corresponding to the range of the health state evaluation value. For example, when H ≥ 0.8, the sampling frequency is once every 2 hours; when 0.5 ≤ H < 0.8, the sampling frequency is once every 1 hour; and when H < 0.5, the sampling frequency is once every 30 minutes.

[0125] Since the health state evaluation value H of the current device is approximately 0.65, it is determined that the sampling frequency of the detection information is once every 1 hour.

[0126] Embodiment 3: when the low-voltage side circuit breaker primary evaluation model is established, the following steps are included:

[0127] Obtain the parameter information P of n groups of historical maintenance devices, and construct an n * m sample matrix X,

[0128] Based on the sample matrix X, a covariance matrix Σ is constructed, ij ];

[0129] Wherein, Y ij = Cov(X i ,X j ), Y ij represents the element in the i-th row and the j-th column of the covariance matrix;

[0130] Calculate the eigenvalues λ of the covariance matrix, λ = [λ1, λ2…λ i …λ m ];

[0131] λ i represents the i-th eigenvalue, and n represents the total number of eigenvalues;

[0132] Based on the eigenvalues λ of the covariance matrix, the contribution values R of the parameter information of each category of the current device to be maintained are determined, R = [R1, R2…R i …R m ];

[0133] Based on the contribution values R of the parameter information of each category of the current device to be maintained and the parameter information P of the current device to be maintained, a low-voltage side circuit breaker primary evaluation model is established;

[0134]

[0135] A represents the health state evaluation value of the current device.

[0136] In this embodiment, a sample matrix is constructed using historical data

[0137] By obtaining the parameter information P of n sets of historical maintenance equipment, an n x m sample matrix X is constructed, which enables the model to fully utilize the various parameter information of past equipment. For example, in the power system, different 35kV box-type transformer low-voltage side circuit breakers may have great differences in parameters due to factors such as operating environment and service life. The integration of these historical data enables the model to cover a variety of possible situations and improve the adaptability of the model to different equipment states.

[0138] Considering the relationship between multiple parameters

[0139] A covariance matrix Σ[Yij] is constructed, where Yij = Cov(Xi, Xj), which takes into account the relationship between different categories of parameters. Taking the low-voltage side circuit breaker as an example, there may be mutual influence between parameters such as rated current, rated voltage, and contact wear degree. For example, changes in rated current may affect contact wear degree, and contact wear degree may have a certain feedback effect on rated voltage. This consideration of parameter relationships enables the model to more comprehensively assess the health status of the equipment.

[0140] Determining the contribution value based on eigenvalues

[0141] The eigenvalues λ = [λ1, λ2, □, λm] of the covariance matrix are calculated, and the contribution values R of each category of parameter information of the current equipment to be maintained are determined based on these eigenvalues. This mathematical feature-based contribution value determination method can objectively reflect the importance of each parameter in evaluating the health status of the equipment. For example, for some key parameters (such as contact wear degree having a greater impact on the overall performance of the circuit breaker), their corresponding eigenvalues may be larger, resulting in a higher proportion in the contribution value calculation, so that the model can focus on these key factors when evaluating.

[0142] Establishing a primary evaluation model based on the contribution value R and the parameter information P of the current equipment to be maintained

[0143] A primary evaluation model for the low-voltage side circuit breaker is established, and the health status evaluation value A of the current equipment is obtained. This model can comprehensively consider various parameters and their importance, accurately quantitatively evaluate the health status of the equipment. In practical applications, power maintenance personnel can predict potential problems of the equipment in advance based on this evaluation value, such as arranging maintenance work in advance when the A value is below a certain threshold, avoiding sudden equipment failure, and improving the reliability and stability of the power system.

[0144] Developing targeted maintenance plans based on the equipment's health status assessment value (A) allows for more targeted maintenance strategies. For equipment in good health (higher A value), maintenance cycles can be appropriately extended, reducing unnecessary maintenance work and thus lowering maintenance costs. Conversely, for equipment in poor health (lower A value), timely and detailed overhauls can be scheduled, focusing on components corresponding to parameters that significantly impact the equipment's health status, thereby extending the equipment's lifespan and reducing the impact of equipment failures on the entire power system.

[0145] Example 4: The construction of the low-voltage side circuit breaker maintenance model includes:

[0146] Obtain historical monitoring data of the circuit breaker, including historical current data, historical voltage data, and historical temperature data;

[0147] Extract the characteristic parameters of historical current data, including: peak current and valley current;

[0148] The peak current is divided into level intervals to obtain the peak current dataset IF, where IF = [IF1, IF2, ..., IF]. i …IF n ];

[0149] Among them, IF i This represents the peak power range of the i-th level, and n represents the total number of peak current ranges.

[0150] The valley values ​​of the current are divided into graded intervals to obtain the current valley value dataset IG, where IG = [IG1, IG2, ..., IG3]. i …IG n ];

[0151] Among them, IG i This represents the power valley range of the i-th level, and n represents the total number of current valley ranges.

[0152] The state of the corresponding low-voltage side circuit breaker is determined based on the characteristic parameters of historical current data, and a circuit breaker state event set F is established, F = [F1, F2…F…]. i …F n ];

[0153] Where Fi represents the i-th type of circuit breaker state event, and n represents the total number of circuit breaker state times;

[0154] Acquire historical voltage and temperature data corresponding to the occurrence of circuit breaker status events; extract data features from historical voltage and temperature data.

[0155] The first compensation parameter C is constructed based on the data characteristics of historical voltage and temperature data.

[0156] The characteristic parameter combined with the historical current data and the first compensation parameter C generates a low-voltage side circuit breaker maintenance model.

[0157] In embodiment 5, the first compensation parameter C is constructed as follows:

[0158] The voltage historical data change rate and the temperature historical data change rate are calculated.

[0159] The voltage historical data change rate and the temperature historical data change rate are classified into grades, and an evaluation value is generated for each grade.

[0160] The historical change rate evaluation value DV of the voltage and the historical change rate evaluation value DT of the temperature in the sampling interval are generated.

[0161] C = k1*DV + k2*DT

[0162] Wherein, k1 is the historical change rate evaluation value weight of the voltage, and k2 is the historical change rate evaluation value weight of the temperature.

[0163] This embodiment includes:

[0164] Multi-data type utilization

[0165] By obtaining the historical monitoring data of the circuit breaker, including historical current data, historical voltage data and historical temperature data, the state information of the circuit breaker in the past operation can be comprehensively understood. For example, in the power system, these three types of data reflect the working condition of the circuit breaker from different aspects. The current data reflects the load condition, the voltage data reflects the stability of the power supply, and the temperature data is related to the heat dissipation and loss of the equipment.

[0166] Accurate analysis of current characteristics

[0167] The characteristic parameters of the historical current data, such as the peak and valley values of the current, are extracted, and the current peak data set and the current valley data set are obtained by classifying the intervals. This accurate analysis can better grasp the change of the current under different working conditions. For example, for a 35kV box-type transformer low-voltage side circuit breaker, by classifying the current peak interval, different states such as normal load, overload and light load can be distinguished, providing more detailed basis for subsequent state evaluation.

[0168] Determination of associated state

[0169] Based on the feature parameters of historical current data, the state of the corresponding low-voltage side circuit breaker is determined, and a circuit breaker state event set F is established. This makes the state evaluation of the circuit breaker not a single numerical judgment, but a comprehensive judgment based on a series of related state events. For example, when the current peak value is in a certain interval, it may correspond to an overload event Fi, and this association helps to more accurately identify the operating state of the circuit breaker.

[0170] Voltage and temperature data utilization

[0171] The voltage historical data and temperature historical data corresponding to the occurrence of the circuit breaker state event are obtained, and the data features thereof are extracted. This step combines current data with voltage and temperature data, and considers the mutual influence between different physical quantities. For example, when an overload event (judged by current data) occurs, the voltage may decrease and the temperature may rise, and the comprehensive data features can more comprehensively describe the working state of the circuit breaker.

[0172] Compensation parameter construction

[0173] Based on the data features of the voltage historical data and the temperature historical data, a first compensation parameter C is constructed, which can quantitatively reflect the influence of voltage and temperature on the state evaluation of the circuit breaker to a certain extent. For example, when the temperature rises, it may accelerate the aging of the equipment, and the first compensation parameter C can adjust the evaluation weight of the equipment health state according to the amplitude of the temperature rise.

[0174] Comprehensive model construction The low-voltage side circuit breaker maintenance model is generated by combining the feature parameters of historical current data and the first compensation parameter C. This maintenance model considers multiple factors such as current, voltage, and temperature, and can more accurately evaluate the operating state of the low-voltage side circuit breaker. In practical applications, such as maintenance work in power systems, this model can help maintenance personnel more accurately determine whether the circuit breaker needs maintenance and determine the key direction of maintenance, improving the efficiency and accuracy of maintenance and reducing the risk of power system failure caused by circuit breaker failure.

[0175] In an embodiment 6, when detecting the operating failure risk of the equipment, the method comprises:

[0176] Obtaining real-time data of the low-voltage side circuit breaker of the current monitoring node, including current data, voltage data, and temperature data;

[0177] Based on the low-voltage side circuit breaker maintenance model, generating an operating state evaluation value of the low-voltage side circuit breaker of the current monitoring node, and judging whether there is a failure based on the operating state evaluation value;

[0178] If there is a failure, generating a first control instruction to identify the type of failure;

[0179] If there is no fault, a secondary control instruction is generated to predict the probability of fault occurrence.

[0180] In embodiment 7, the generated fault prediction instruction comprises:

[0181] In the monitoring information sampling period, time windows m are divided, and the number of occurrences and the frequency of occurrence of the current valley value and the number of occurrences and the frequency of occurrence of the current peak value in each time window are counted.

[0182] The fault prediction score M is generated in combination with the first compensation parameter C.

[0183] The time window is moved based on the fault prediction score M.

[0184] The change value of the fault prediction score M in the entire sampling period is generated.

[0185] Based on the change value of the fault prediction score M, the urgency of the fault occurrence is judged.

[0186] In this embodiment, time windows m are divided in the monitoring information sampling period, and the number of occurrences and the frequency of occurrence of the current valley value and the number of occurrences and the frequency of occurrence of the current peak value in each time window are counted. This statistical analysis can capture the fluctuation characteristics of the current in different time segments in detail. For example, in the power system, for the low-voltage side circuit breaker, the change of the valley and peak values of the current may imply the dynamic change of the load or the potential problem inside the device. Through detailed statistics of these data, the time window of abnormal fluctuation of the current can be found in time, providing a richer data basis for fault prediction.

[0187] The fault prediction score M is generated in combination with the first compensation parameter C. The first compensation parameter C considers the influence of voltage and temperature and other factors on the state of the device, and combines it with the statistical information of the current valley and peak values, so that the fault prediction score M can evaluate comprehensively from multiple aspects. For example, in a certain time window, although the change of the current peak and valley values is not obvious alone, considering that the voltage fluctuation (reflected by the first compensation parameter C) may amplify the risk of device failure, the fault prediction score M can more accurately reflect the actual failure risk state of the device.

[0188] The time window is moved based on the fault prediction score. This dynamic adjustment mechanism can enable the monitoring system to focus on the time area with high fault risk. For example, if the fault prediction score M of a certain time window is high, the system can slow down the moving speed of the time window, analyze the data in this area in more detail, or adjust the statistical strategy of the subsequent time window, thereby improving the accuracy of fault prediction.

[0189] Fault emergency situation judgment

[0190] The change value of the fault prediction score M in the entire sampling period is generated, and the emergency of the fault occurrence is judged based on this. By observing the change trend of the fault prediction score M in the entire sampling period, it can be judged whether the fault is gradually developed or suddenly occurred. For example, if the fault prediction score M rises sharply in a short time, it may mean that the equipment is about to have a serious fault, and immediate measures need to be taken; if the fault prediction score M rises slowly, it may mean that the fault is in the early development stage, and the maintenance can be planned. This judgment based on the change value of the fault prediction score M can help maintenance personnel more reasonably arrange maintenance resources, and improve the reliability and safety of the power system.

[0191] In embodiment 8, the fault prediction score M is generated, comprising:

[0192] Obtain the current peak value data set IF, IF = [IF1, IF2…IF i …IF n ];

[0193] M = n1*IF i +n2*IG i +C;

[0194] Wherein, IF i represents the i-th level power valley interval, IG i represents the i-th level power valley interval, n1 represents the number of occurrences of the i-th level power peak interval, and n2 represents the number of occurrences of the i-th level power valley interval.

[0195] In embodiment 9, when the time window is controlled to move based on the fault prediction score M, comprising:

[0196] Calculate the fault prediction score M in the time window;

[0197] After obtaining the fault prediction score M in the current time window, control the time window to move right by m steps, each step being a sampling time;

[0198] According to the fault prediction score M, a multi-level threshold value is generated, and the value of m is controlled based on the multi-level threshold value; the fault prediction score M is positively correlated with the number of steps of moving the time window to the right.

[0199] In this embodiment, in the monitoring of the low-voltage side circuit breaker of the power system, it means that if the fault prediction score M in the current time window is high, it indicates that the equipment may have a large fault risk, then the moving mode of the time window can be decided according to this score, so as to better track the development trend of the fault risk.

[0200] The setting of each step as a sampling time improves the accuracy of the time window movement. In the monitoring data of power equipment, the sampling time is the basic time unit for obtaining data. Moving the time window by sampling time can more carefully analyze the changes of data in the time series. For example, for rapidly changing current or voltage data, this high-precision moving method can more accurately capture the fluctuation characteristics of the data, thereby improving the accuracy of fault prediction.

[0201] According to the multi-level threshold generated by the fault prediction score M, the value of m is controlled based on the multi-level threshold. This way can flexibly adjust the moving step of the time window according to different levels of the fault prediction score M. For example, when the fault prediction score M is at a lower level, it means that the risk of equipment failure is low, at this time, the value of m can be appropriately increased to make the time window move quickly to improve the monitoring efficiency; when the fault prediction score M is at a higher level, it means that the equipment may soon fail, at this time, the value of m is reduced to make the time window move slowly to carefully analyze the data and improve the accuracy of fault prediction.

[0202] Advantages of positive correlation

[0203] The setting of the positive correlation between the fault prediction score M and the time window right-moving step number further optimizes the moving strategy of the time window. This means that as the fault prediction score M increases, the time window right-moving step number increases. In actual monitoring, when the risk of failure gradually increases, this positive correlation can prompt the time window to explore the time period where the failure may occur more deeply, so as to more timely and accurately find the hidden danger of failure and ensure the stable operation of the power system.

[0204] Finally, it should be noted that: obviously, those skilled in the art can make various modifications and changes to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and changes of the present application fall within the scope of the claims of the present application and its equivalent technology, the present application also intends to include these modifications and changes.

[0205] The above is only one embodiment of the present application, but cannot limit the scope of the present application. Any structural changes made according to the present application, as long as the essence of the present application is not lost, should be considered to fall within the scope of the present application and be restricted. Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the platform and the related description described above can refer to the corresponding process in the foregoing platform embodiment, which will not be repeated here.

[0206] The term "comprising" or any other similar term is intended to encompass the inclusion of one or more stated elements or steps but not preclude the inclusion of additional elements or steps. The term "comprising" is intended to mean that the process, platform, article, or apparatus that "comprises" one or more elements can also comprise other elements not expressly listed or inherent to such process, platform, article, or apparatus.

[0207] The technical solutions of the present application have been described in combination with the further embodiments shown in the drawings, but it is easy for those skilled in the art to understand that the protection scope of the present application is obviously not limited to these specific embodiments. Those skilled in the art can make equivalent changes or replacements to the related technical features without departing from the principles of the present application, and the technical solutions after the changes or replacements will all fall within the protection scope of the present application.

[0208] The above description is merely preferred embodiments of the present application, but not for limiting the protection scope of the present application.

Claims

1. A method of monitoring and maintenance of a low voltage side circuit breaker of a 35 kV tank transformer, characterized in that, The application relates to a low-voltage side circuit breaker maintenance method and device. The application comprises the following steps: Setting multiple monitoring periods according to device parameters and setting multiple monitoring time nodes, each of which represents the start of a monitoring period; Building a low-voltage side circuit breaker maintenance model based on historical data of the low-voltage side circuit breaker; Obtaining real-time data of the low-voltage side circuit breaker at the current monitoring time node and detecting the running fault risk of the device according to the low-voltage side circuit breaker maintenance model; Judging whether to perform maintenance according to the detection result at the current monitoring time node; The method comprises the following steps: Obtaining historical monitoring data of the circuit breaker, which comprises historical current data, historical voltage data and historical temperature data; Extracting characteristic parameters of the historical current data, which comprise the peak value of the current and the valley value of the current; Dividing the peak value of the current into grade intervals to obtain a current peak value data set IF, IF=[IF1, IF2... IFi... IFn]; Wherein, IFi represents the i-th grade power peak interval, and n represents the total number of current peak intervals; Dividing the valley value of the current into grade intervals to obtain a current valley value data set IG, IG=[IG1, IG2... IGi... IGn]; Wherein, IGi represents the i-th grade power valley interval, and n represents the total number of current valley intervals; Determining the state of the corresponding low-voltage side circuit breaker based on the characteristic parameters of the historical current data, and establishing a circuit breaker state event set F, F=[F1, F2... Fi... Fn]; Wherein, Fi represents the i-th circuit breaker state event, and n represents the total number of circuit breaker state events; Obtaining corresponding voltage historical data and temperature historical data when the circuit breaker state event occurs; and extracting data characteristics of the voltage historical data and the temperature historical data; Building a first compensation parameter C based on the data characteristics of the voltage historical data and the temperature historical data; the building of the first compensation parameter C specifically comprises: calculating the voltage historical data change rate and the temperature historical data change rate; and grade-dividing the voltage historical data change rate and the temperature historical data change rate; each grade generates an evaluation value; generating a historical change rate evaluation value DV of voltage in a sampling interval and a historical change rate evaluation value DT of temperature; C=k1*DV+k2*DT; wherein, k1 is the historical change rate evaluation value weight of voltage, and k2 is the historical change rate evaluation value weight of temperature Combining the characteristic parameters of the historical current data and the first compensation parameter C to generate a low-voltage side circuit breaker maintenance model; The detection of the running fault risk of the device comprises the following steps: Obtaining real-time data of the low-voltage side circuit breaker at the current monitoring node, which comprises current data, voltage data and temperature data; Generating a low-voltage side circuit breaker running state evaluation value of the current monitoring node based on the low-voltage side circuit breaker maintenance model, and judging whether there is a fault based on the running state evaluation value; If there is a fault, a first-level control instruction is generated to identify the type of the fault. If there is no fault, a secondary control instruction is generated to predict the probability of fault occurrence; the generation of the secondary control instruction to predict the probability of fault occurrence comprises: dividing a time window m in a monitoring information sampling period, counting the occurrence frequency of current valley value and the occurrence frequency of current peak value in each time window; and generating a fault prediction score M in combination with a first compensation parameter C; controlling the time window movement based on the fault prediction score M; generating a fault prediction score M change value of the entire sampling period; and judging the emergency of fault occurrence based on the fault prediction score M change value.

2. The method for monitoring and servicing the low voltage side circuit breaker of the 35 kV box-type transformer according to claim 1, characterized in that, The setting of the plurality of monitoring periods comprises: Obtaining parameter information P of the current equipment to be maintained, P = [P1, P2…Pi…Pm]; Wherein, Pi represents the parameter information value of the i-th category, and m represents the total number of categories of parameter information; Based on the parameter information of the equipment to be maintained, a low-voltage side circuit breaker primary evaluation model is established; Through the low-voltage side circuit breaker primary evaluation model, the health state evaluation value of the current equipment is generated; According to the health state evaluation value of the current equipment, the monitoring period length is set.

3. The method for monitoring and servicing the low voltage side circuit breaker of the 35 kV box-type transformer according to claim 2, characterized in that, The establishment of the low-voltage side circuit breaker primary evaluation model comprises: Obtaining n groups of historical maintenance equipment parameter information P, constructing an n×m sample matrix X, and constructing a covariance matrix Σ[Yij] based on the sample matrix X; Wherein, Yij = Cov(Xi, Xj), Yij represents the i-th row and j-th column element in the covariance matrix; Calculate the eigenvalue λ of the covariance matrix, λ = [λ1, λ2…λi…λm]; λi represents the i-th eigenvalue, and n represents the total number of eigenvalues; Based on the eigenvalue λ of the covariance matrix, the contribution value R of each category of parameter information of the current equipment to be maintained is determined, R = [R1, R2…Ri…Rm]; Based on the contribution value R of each category of parameter information of the current equipment to be maintained and the parameter information P of the current equipment to be maintained, a low-voltage side circuit breaker primary evaluation model is established; ； A represents the health state evaluation value of the current equipment.

4. The method for monitoring and servicing the low voltage side circuit breaker of the 35 kV box-type transformer according to claim 3, characterized in that, The generation of the fault prediction score M comprises: Obtaining a current peak value data set IF, IF = [IF1, IF2…IFi…IFn]; M = n1*IFi + n2*IGi + C; Wherein, IFi represents the i-th level power valley interval, IGi represents the i-th level power valley interval, n1 represents the number of times of occurrence of the i-th level power peak interval, and n2 represents the number of times of occurrence of the i-th level power valley interval.

5. The method for monitoring and servicing the low voltage side circuit breaker of the 35 kV box-type transformer as claimed in claim 4, wherein, The control of the time window movement based on the fault prediction score M comprises: Calculate the fault prediction score M in a time window; After obtaining the fault prediction score M in the current time window, control the time window to move right by m steps, each step being a sampling time; According to the fault prediction score M, a multi-level threshold value is generated, and the value of m is controlled based on the multi-level threshold value; the fault prediction score M is positively correlated with the number of steps of the time window moving right.

Images