Monitoring and overhauling method for low-voltage side circuit breaker of 35kV box-type transformer

Abstract

The invention relates to the technical field of monitoring of low-voltage side circuit breakers, and discloses a monitoring and overhauling method of a 35kV box-type transformer low-voltage side circuit breaker, which comprises the following steps of: formulating a monitoring information sampling period according to acquired equipment parameter information; constructing a low-voltage side circuit breaker maintenance model based on the historical data of the low-voltage side circuit breaker; setting a monitoring node based on the monitoring information sampling period, and obtaining low-voltage side circuit breaker real-time data of the current monitoring node; and detecting the operation fault risk of the equipment through the low-voltage side circuit breaker maintenance model, and carrying out maintenance according to the detection result. According to the invention, intelligent monitoring and automatic control of the state of the circuit breaker are realized, more refined maintenance management can be realized through evaluation of the health state of equipment and detection of operation fault risks, optimization of resource allocation is facilitated, unnecessary maintenance activities are reduced, the maintenance cost is reduced, and the efficiency and effect of maintenance work are improved at the same time.

Description

Technical Field

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

[0002] The low-voltage side circuit breaker of a 35kV box-type transformer is a crucial component of the power system. It connects and disconnects circuits on the transformer's low-voltage side, ensuring safe and stable operation of the power system. The reliability of the low-voltage side circuit breaker is directly related to power supply continuity and equipment safety, making effective monitoring and maintenance crucial.

[0003] In summary, the technical background for monitoring and maintenance methods for circuit breakers on the low-voltage side of 35kV box-type transformers involves the development of automated and intelligent monitoring technologies, as well as the establishment and optimization of standardized maintenance processes. The combination of these technologies and standards helps improve circuit breaker reliability and maintenance efficiency, ensuring the safe and stable operation of power systems. Summary of the Invention

[0004] The purpose of the present invention is to use the historical current, voltage and temperature data of the circuit breaker to construct a first compensation parameter in combination with the corresponding voltage and temperature data characteristics to generate a low-voltage side circuit breaker maintenance model; by dividing the time window, statistically analyzing the current peak and valley values ​​and generating a fault prediction score, the time window movement is controlled and the fault emergency situation is judged.

[0005] In order to achieve the above object, the present invention provides a monitoring and maintenance method for a 35kV box-type transformer low-voltage side circuit breaker, comprising:

[0006] Set multiple monitoring cycles according to equipment parameters and set multiple monitoring time nodes, each monitoring time node represents the start of a monitoring cycle;

[0007] Build a low-voltage side circuit breaker maintenance model based on the historical data of the low-voltage side circuit breaker;

[0008] Obtain real-time data of the low-voltage side circuit breaker at the current monitoring time node, and detect the operational failure risk of the equipment based on the low-voltage side circuit breaker maintenance model;

[0009] Determine whether to perform maintenance based on the detection results of the current monitoring time node.

[0010] In some embodiments of the present invention, it is characterized in that the step of formulating a monitoring information sampling period based on the acquired device parameter information includes:

[0011] Get the parameter information P of the equipment to be repaired, P=[P1,P2…P i …P m ];

[0012] Among them, 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 first-level evaluation model for the low-voltage side circuit breaker is established;

[0014] Generate the health status evaluation value of the current equipment through the first-level evaluation model of the low-voltage side circuit breaker;

[0015] Set the monitoring cycle duration based on the current device health status evaluation value.

[0016] In some embodiments of the present invention, the establishment of the first-level evaluation model for the low-voltage side circuit breaker includes:

[0017] Obtain parameter information P of n sets of historical maintenance equipment and construct an n×m sample matrix X.

[0018] Based on the sample matrix X, construct the covariance matrix Σ[Y ij ];

[0019] Among them, Y ij =Cov(X i ,X j ),Y ij Represents the element in row i and column j of the covariance matrix;

[0020] Calculate the eigenvalues ​​λ of the covariance matrix, 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 eigenvalue λ of the covariance matrix, the contribution value R of each category of parameter information of the equipment to be repaired is determined, R=[R1,R2…R i …R m ];

[0023] Based on the contribution value R of each category of parameter information of the equipment to be repaired and the parameter information P of the equipment to be repaired, a first-level evaluation model for the low-voltage side circuit breaker is established;

[0024]

[0025] A represents the current health status evaluation value of the device.

[0026] In some embodiments of the present invention, the construction of the low-voltage side circuit breaker maintenance model includes:

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

[0028] Extract characteristic parameters of historical current data, including current peak value and current valley value;

[0029] The peak value of the current is divided into level intervals to obtain the current peak data set IF, IF=[IF1, IF2…IF i …IF n ];

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

[0031] The valley value of the current is divided into level intervals to obtain the current valley value data set IG, IG = [IG1, IG2…IG i …IG n ];

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

[0033] The state of the corresponding low-voltage side circuit breaker is determined based on the characteristic parameters of the historical current data, and the circuit breaker state event set F is established, F = [F1, F2…F i …F n ];

[0034] Where Fi represents the i-th type of circuit breaker status event, and n represents the total number of circuit breaker status times;

[0035] Obtaining the voltage history data and temperature history data corresponding to the occurrence of the circuit breaker status event; extracting the data features of the voltage history data and temperature history data;

[0036] Constructing a first compensation parameter C based on data characteristics of the voltage history data and the temperature history data;

[0037] Combining the characteristic parameters of the historical current data with the first compensation parameter C, a low-voltage side circuit breaker maintenance model is generated;

[0038] In some embodiments of the present invention, when constructing the first compensation parameter C:

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

[0040] The voltage history data change rate and the temperature history data change rate are divided into grades; each grade generates an evaluation value;

[0041] Generate a historical voltage change rate evaluation value DV and a historical temperature change rate evaluation value DT within a sampling interval;

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

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

[0044] In some embodiments of the present invention, the detecting of the risk of an operational failure of the device includes:

[0045] Obtain 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 low-voltage side circuit breaker operation status evaluation value of the current monitoring node, and determine whether there is a fault based on the operation status evaluation value;

[0047] If a fault exists, a first-level control instruction is generated to identify the type of fault that occurred;

[0048] If there is no fault, a secondary control instruction is generated to predict the probability of a fault occurring.

[0049] In some embodiments of the present invention, generating a fault prediction instruction includes:

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

[0051] Combined with the first compensation parameter C, a fault prediction score M is generated;

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

[0053] Generate the fault prediction score M change value for the entire sampling period;

[0054] Based on the change value of the fault prediction score M, the emergency situation of the fault is judged.

[0055] In some embodiments of the present invention, generating a fault prediction score M includes:

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

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

[0058] Among them, IF i Indicates the i-th level power valley interval, IG i represents the i-th level power valley interval, n1 represents the number of times the i-th level power peak interval occurs, and n2 represents the number of times the i-th level power valley interval occurs;

[0059] In some embodiments of the present invention, controlling the movement of the time window based on the fault prediction score M includes:

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

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

[0062] According to the fault prediction score M, a multi-level threshold is generated, and the value of m is controlled based on the multi-level threshold. The fault prediction score M is positively correlated with the number of steps to the right of the time window.

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

[0064] Different parameters reflect the status of the equipment from different aspects, providing a rich source of data for the subsequent establishment of an accurate evaluation model

[0065] By establishing a first-level evaluation model, power maintenance personnel can predict possible equipment problems in advance based on this evaluation value, avoid sudden equipment failures, and improve the reliability and stability of the power system.

[0066] By establishing a low-voltage side circuit breaker maintenance model, maintenance personnel can more accurately determine whether the circuit breaker needs maintenance and determine the focus of maintenance, thereby improving the efficiency and accuracy of maintenance and reducing the risk of power system failure caused by circuit breaker failure.

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

[0068] By moving the time window with the sampling moment as the step size, the changes in the data in the time series can be analyzed more carefully, which can enable the time window to more deeply explore the time period when faults may occur, thereby discovering potential faults more timely and accurately and ensuring the stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[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 by an embodiment of the present invention. DETAILED DESCRIPTION

[0070] The following embodiments of the present invention are described in further detail with reference to the accompanying drawings and examples. The following embodiments are used to illustrate the present invention but are not intended to limit the scope of the present invention.

[0071] In the description of the present invention, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention.

[0072] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, "plurality" means two or more.

[0073] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0074] Example 1: A monitoring and maintenance method for a 35kV box-type transformer low-voltage side circuit breaker, such as Figure 1 Shown, including:

[0075] Set multiple monitoring cycles according to equipment parameters and set multiple monitoring time nodes, each monitoring time node represents the start of a monitoring cycle;

[0076] Build a low-voltage side circuit breaker maintenance model based on the historical data of the low-voltage side circuit breaker;

[0077] Obtain real-time data of the low-voltage side circuit breaker at the current monitoring time node, and detect the operational failure risk of the equipment based on the low-voltage side circuit breaker maintenance model;

[0078] Determine whether to perform maintenance based on the detection results of the current monitoring time node.

[0079] In this embodiment, device information collection

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

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

[0082] Historical data collection

[0083] The current, voltage, and temperature data for the past year (hypothetically) are obtained from the historical operation records of the transformer's low-voltage side circuit breaker. This data is stored in a database for subsequent use in building a maintenance model.

[0084] Construction of the first-level evaluation model

[0085] Using the acquired m=5 type equipment parameter information The sample matrix X is constructed based on the parameter information of n=100 groups of historical maintenance equipment in the past.

[0086] By calculating the covariance matrix of the sample matrix X, such as

[0087] Cov(X) and calculate its eigenvalue Determine the contribution of each parameter.

[0088] A first-level evaluation model for the low-voltage side circuit breaker is established, and the equipment health status evaluation value is obtained as H=0.8. Based on this evaluation value, the sampling frequency is determined to be once per hour, that is, the monitoring information sampling period is determined to be 1 hour.

[0089] Current data feature extraction

[0090] For example, the maximum current peak value extracted from historical current data is 800 A, and the minimum current valley value is 100 A. The current peak and valley values ​​are divided into graded intervals, such as 0-200 A for low current, 200-500 A for normal current, and 500-800 A for high current.

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

[0092] Combined voltage and temperature data

[0093] When an overload event (high current range) occurs, the corresponding voltage may fluctuate, such as dropping from 0.4 kV to 0.38 kV or increasing the temperature from 30°C to 35°C. Combining these voltage and temperature data features, a first compensation parameter C = 0.9 is constructed, ultimately generating a low-voltage circuit breaker maintenance model.

[0094] Monitoring node settings

[0095] Monitoring nodes are set up based on a predetermined 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 300A, the voltage is 0.39kV, and the temperature is 32°C.

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

[0098] Assume that the operating status evaluation value generated by the maintenance model is S=0.9. Since S>0.8 (the threshold value set previously, assumption), it is determined that the equipment has no fault at this time.

[0099] Then a secondary control instruction is generated to predict the failure probability, for example, predicting that the failure probability within the next 24 hours is 5%.

[0100] Troubleshooting

[0101] If the operating status evaluation value S=0.6 at another monitoring node, it is judged as a fault.

[0102] At this point, a first-level control command is generated to identify the fault type. Further analysis of current, voltage, and temperature data trends, as well as comparison with historical fault data, identifies a possible poor contact fault. Appropriate maintenance actions are then performed, such as checking connections and replacing aging components.

[0103] The above specific embodiments demonstrate the practical application of the method for monitoring and repairing the low-voltage side circuit breaker of a 35kV box-type transformer.

[0104] Example 2: The step of formulating a monitoring information sampling period based on the acquired device parameter information includes:

[0105] Get the parameter information P of the equipment to be repaired, P=[P1,P2…P i …P m ];

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

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

[0108] Generate the health status evaluation value of the current equipment through the first-level evaluation model of the low-voltage side circuit breaker;

[0109] Set the monitoring cycle duration based on the current device health status evaluation value.

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

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

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

[0113] Sample data preparation

[0114] The parameter information of the past 50 groups (n=50) of similar low-voltage side circuit breakers in different health states is collected as sample data.

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

[0116] Model building process

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

[0118] Calculate the eigenvalues ​​λi (i = 1, 2, □, 4) and corresponding eigenvectors of the covariance matrix Cov(X). Determine the contribution of each parameter based on the eigenvalues. For example, calculations show that the contribution of rated current P1 is 0.3, the contribution of rated voltage P2 is 0.25, the contribution of contact material type P3 is 0.2, and the contribution of operating environment humidity P4 is 0.25.

[0119] Establish a first-level evaluation model for low-voltage side circuit breakers. The model can be a weighted sum model, for example:

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

[0121] Substituting the current device parameter values ​​into the model calculation, we get H = 0.3 × 500 / 400 + 0.25 × 0.45 / 0.4 + 0.2 × 1 + 0.25 × 80 / 50

[0122] Calculation shows that H≈0.65.

[0123] Determine the rules

[0124] Set the sampling frequency for different health status evaluation value ranges. 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 hour; when H<0.5, the sampling frequency is once every 30 minutes.

[0125] Since the current health status evaluation value of the device H≈0.65, the sampling frequency of the detection information is determined to be once every hour.

[0126] Example 3: The establishment of the first-level evaluation model for the low-voltage side circuit breaker includes:

[0127] Obtain parameter information P of n sets of historical maintenance equipment and construct an n×m sample matrix X.

[0128] Based on the sample matrix X, construct the covariance matrix Σ[Y ij ];

[0129] Among them, Y ij =Cov(X i ,X j ),Y ij Represents the element in row i and column j 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 eigenvalue λ of the covariance matrix, the contribution value R of each category of parameter information of the equipment to be repaired is determined, R=[R1,R2…R i …R m ];

[0133] Based on the contribution value R of each category of parameter information of the equipment to be repaired and the parameter information P of the equipment to be repaired, a first-level evaluation model for the low-voltage side circuit breaker is established;

[0134]

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

[0136] In this embodiment, the sample matrix is ​​constructed using historical data.

[0137] By acquiring parameter information P from n sets of historically maintained equipment and constructing an n×m sample matrix X, the model can fully utilize the diverse parameter information of past equipment. For example, in a power system, the parameters of different 35kV box-type transformer low-voltage side circuit breakers may vary significantly due to factors such as operating environment and age. Integrating this historical data allows the model to cover a wide range of possible scenarios and improve its adaptability to different equipment conditions.

[0138] Considering multiple parameter relationships

[0139] The covariance matrix Σ[Yij], where Yij = Cov(Xi,Xj), is constructed. This process considers the relationships between different parameter categories. For example, for a low-voltage circuit breaker, parameters such as rated current, rated voltage, and contact wear may interact with each other. For example, changes in rated current may affect contact wear, which in turn may have a certain feedback effect on the rated voltage. This consideration of parameter relationships enables the model to more comprehensively assess the health of the equipment.

[0140] Determine contribution value based on eigenvalue

[0141] The eigenvalues ​​of the covariance matrix, λ = [λ1,λ2,□,λm], are calculated, and based on these eigenvalues, the contribution value R of each parameter category of the equipment under maintenance is determined. This mathematically-based contribution value determination method objectively reflects the importance of each parameter in assessing the health status of the equipment. For example, certain key parameters (such as contact wear, which significantly affects the overall performance of the circuit breaker) may have large eigenvalues, resulting in a higher proportion in the contribution value calculation, allowing the model to focus on these key factors during the assessment.

[0142] Establish a first-level evaluation model based on the contribution value R and the parameter information P of the equipment to be repaired

[0143] A first-level evaluation model for low-voltage circuit breakers was established to derive a health status evaluation value, A, for the current equipment. This model comprehensively considers various parameters and their importance, accurately and quantitatively assessing the health status of the equipment. In practical applications, power maintenance personnel can use this evaluation value to predict potential equipment problems in advance. For example, if the A value falls below a certain threshold, maintenance work can be scheduled in advance to avoid sudden equipment failures and improve the reliability and stability of the power system.

[0144] Developing targeted maintenance plans based on the equipment's health evaluation value, A, allows for the development of more targeted maintenance strategies. For equipment in good health (higher A values), maintenance cycles can be appropriately extended, reducing unnecessary maintenance work and thus lowering maintenance costs. Conversely, for equipment in poor health (lower A values), detailed inspections can be promptly scheduled, focusing on components with parameters that significantly impact equipment health. This can extend equipment life and minimize 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 characteristic parameters of historical current data, including current peak value and current valley value;

[0148] The peak value of the current is divided into level intervals to obtain the current peak data set IF, IF=[IF1, IF2…IF i …IF n ];

[0149] Among them, IF i represents the i-th level power peak interval, and n represents the total number of current peak intervals;

[0150] The valley value of the current is divided into level intervals to obtain the current valley value data set IG, IG = [IG1, IG2…IG i …IG n ];

[0151] Among them, IG i represents the i-th level power valley interval, and n represents the total number of current valley intervals;

[0152] The state of the corresponding low-voltage side circuit breaker is determined based on the characteristic parameters of the historical current data, and the 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 status event, and n represents the total number of circuit breaker status times;

[0154] Obtaining the voltage history data and temperature history data corresponding to the occurrence of the circuit breaker status event; extracting the data features of the voltage history data and temperature history data;

[0155] Constructing a first compensation parameter C based on data characteristics of the voltage history data and the temperature history data;

[0156] Combining the characteristic parameters of the historical current data with the first compensation parameter C, a low-voltage side circuit breaker maintenance model is generated;

[0157] Example 5: When constructing the first compensation parameter C:

[0158] Calculate the change rate of voltage history data and the change rate of temperature history data;

[0159] The voltage history data change rate and the temperature history data change rate are divided into grades; each grade generates an evaluation value;

[0160] Generate a historical voltage change rate evaluation value DV and a historical temperature change rate evaluation value DT within a sampling interval;

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

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

[0163] This embodiment includes:

[0164] Multiple data type utilization

[0165] By acquiring historical monitoring data for circuit breakers, including historical current, voltage, and temperature data, we can gain a comprehensive understanding of the circuit breaker's past operating status. For example, in a power system, these three data types reflect the circuit breaker's operating conditions from different perspectives: current data reflects load conditions, voltage data reflects power supply stability, and temperature data is related to equipment heat dissipation and losses.

[0166] Accurate analysis of current characteristics

[0167] Characteristic parameters of historical current data, such as peak and valley current values, are extracted and divided into graded intervals to produce current peak and valley current datasets. This precise analysis allows for a better understanding of current variations under different operating conditions. For example, for a 35kV box-type transformer's low-voltage side circuit breaker, by dividing the current peak intervals, it is possible to distinguish between normal load, overload, and light load conditions, providing a more detailed basis for subsequent condition assessment.

[0168] Association status determination

[0169] The status of the corresponding low-voltage circuit breaker is determined based on the characteristic parameters of historical current data, and a set of circuit breaker status events, F, is established. This eliminates the need for a single numerical judgment when assessing the circuit breaker's status, and instead allows for a comprehensive assessment based on a series of related status events. For example, when the current peak falls within a specific range, it may correspond to an overload event, Fi. This correlation helps more accurately identify the circuit breaker's operating status.

[0170] Voltage and temperature data utilization

[0171] The historical voltage and temperature data corresponding to the circuit breaker status event is obtained and their data features are extracted. This step combines the current data with the voltage and temperature data, taking into account the mutual influence of different physical quantities. For example, when an overload event (indicated by current data) occurs, the voltage may drop and the temperature may rise. Combining these data features can provide a more comprehensive description of the circuit breaker's operating status.

[0172] Compensation parameter construction

[0173] A first compensation parameter, C, is constructed based on the data characteristics of historical voltage and temperature data. This parameter can, to a certain extent, quantify the impact of voltage and temperature on circuit breaker health assessment. For example, when temperature increases, equipment aging may be accelerated. The first compensation parameter, C, can adjust the assessment weight of the equipment health status based on the magnitude of the temperature increase.

[0174] The comprehensive model combines the characteristic parameters of historical current data with the first compensation parameter C to generate a low-voltage circuit breaker maintenance model. This maintenance model integrates multiple factors, such as current, voltage, and temperature, to more accurately assess the operating status of the low-voltage circuit breaker. In practical applications, such as during power system maintenance, this model can help maintenance personnel more accurately determine whether a circuit breaker requires maintenance and determine the key areas for maintenance. This improves maintenance efficiency and accuracy, and reduces the risk of power system failures caused by circuit breaker failures.

[0175] Example 6: The detection of the risk of an operational failure of the device includes:

[0176] Obtain 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, generate the low-voltage side circuit breaker operation status evaluation value of the current monitoring node, and determine whether there is a fault based on the operation status evaluation value;

[0178] If a fault exists, a first-level control instruction is generated to identify the type of fault that occurred;

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

[0180] Embodiment 7: The generating of the fault prediction instruction includes:

[0181] Divide the monitoring information sampling period into a time window m, and count the number and frequency of occurrence of current valley values ​​and the number and frequency of occurrence of current peak values ​​in each time window;

[0182] Combined with the first compensation parameter C, a fault prediction score M is generated;

[0183] Control the movement of the time window based on the fault prediction score M;

[0184] Generate the fault prediction score M change value for the entire sampling period;

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

[0186] In this embodiment, a time window m is divided within the monitoring information sampling period, and the number and frequency of occurrence of current valley values, and the number and frequency of occurrence of current peak values ​​within each time window are counted. This statistical analysis can carefully capture the fluctuation characteristics of current in different time segments. For example, in a power system, for a low-voltage side circuit breaker, changes in the valley and peak values ​​of the current may indicate dynamic changes in the load or potential problems within the equipment. By using detailed statistics on these data, the time window of abnormal current fluctuations can be discovered in a timely manner, providing a richer data basis for fault prediction.

[0187] The first compensation parameter C is combined to generate a fault prediction score M. The first compensation parameter C takes into account the impact of factors such as voltage and temperature on the device state. Combining this with statistical information about current valley and peak values ​​allows the fault prediction score M to comprehensively assess multiple factors. For example, within a certain time window, while changes in current peak and valley values ​​alone may not appear significant, given that voltage fluctuations (reflected by the first compensation parameter C) may amplify the risk of device failure, the fault prediction score M can more accurately reflect the device's actual fault risk status.

[0188] Time window movement control controls the movement of time windows based on the fault prediction score. This dynamic adjustment mechanism allows the monitoring system to focus on time zones with higher fault risks. For example, if the fault prediction score M for a time window is high, the system can slow down the movement of the time window to analyze the data in that zone in more detail, or adjust the statistical strategy for subsequent time windows, thereby improving fault prediction accuracy.

[0189] Fault emergency judgment

[0190] The change in the fault prediction score M over the entire sampling period is generated and used to determine the urgency of the fault. By observing the changing trend of the fault prediction score M throughout the sampling period, it is possible to determine whether the fault develops gradually or suddenly. For example, if the fault prediction score M rises sharply over a short period of time, it may mean that the equipment is about to experience a serious failure and immediate action is required. On the other hand, if the fault prediction score M rises slowly, it may indicate that the fault is in the early stages of development and maintenance can be scheduled in a planned manner. This judgment based on the change in the fault prediction score M can help maintenance personnel more effectively allocate maintenance resources and improve the reliability and safety of the power system.

[0191] Example 8: Generating a fault prediction score M includes:

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

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

[0194] Among them, IF i Indicates the i-th level power valley interval, IG i represents the i-th level power valley interval, n1 represents the number of times the i-th level power peak interval occurs, and n2 represents the number of times the i-th level power valley interval occurs;

[0195] Embodiment 9: The control of the time window movement based on the fault prediction score M includes:

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

[0197] After obtaining the fault prediction score M within the current time window, the control time window is shifted right by m steps, with each step being a sampling moment;

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

[0199] In this embodiment, in the monitoring of the low-voltage side circuit breaker of the power system, this means that if the fault prediction score M in the current time window is high, indicating that the equipment may have a greater failure risk, then the movement of the time window can be determined based on this score to better track the development trend of the fault risk.

[0200] Setting each step to a sampling moment improves the precision of time window movement. For power equipment monitoring data, the sampling moment is the fundamental unit of time for data acquisition. Moving the time window in steps of sampling moments allows for more detailed analysis of data changes over time. For example, for rapidly changing current or voltage data, this high-precision movement method can more accurately capture the data's fluctuations, thereby improving the accuracy of fault prediction.

[0201] Based on the fault prediction score M, a multi-level threshold is generated, and the value of m is controlled based on the multi-level threshold. This approach allows for flexible adjustment of the time window's moving step size based on the different levels of the fault prediction score M. For example, when the fault prediction score M is low, indicating a low risk of equipment failure, the value of m can be appropriately increased to move the time window quickly, improving monitoring efficiency. Conversely, when the fault prediction score M is high, indicating an imminent equipment failure, the value of m can be reduced, allowing the time window to move more slowly, allowing for more detailed data analysis and improving fault prediction accuracy.

[0202] Advantages of positive correlation

[0203] The positive correlation between the fault prediction score M and the number of right-shift steps in the time window further optimizes the time window movement strategy. This means that as the fault prediction score M increases, the number of right-shift steps in the time window increases. In actual monitoring, when the fault risk gradually increases, this positive correlation can prompt the time window to more deeply explore the time period when faults may occur, thereby more promptly and accurately detecting potential faults and ensuring the stable operation of the power system.

[0204] Finally, it should be noted that it is apparent that those skilled in the art may make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, to the extent such modifications and variations fall within the scope of the present invention and its equivalents, the present invention is intended to include such modifications and variations.

[0205] The above description is only an example of an embodiment of the present invention, but it does not limit the scope of the present invention. Any structural changes made according to the present invention, as long as they do not lose the essence of the present invention, should be considered to fall within the scope of protection of the present invention and be subject to restrictions. Those skilled in the art will clearly understand that for the convenience and simplicity of description, the specific working process and related instructions of the platform described above can refer to the corresponding process in the aforementioned platform embodiment, and will not be repeated here.

[0206] The term "comprise," "comprises," or any other similar term is intended to cover a non-exclusive inclusion such that a process, platform, article, or apparatus / platform that comprises a list of elements includes not only those elements but also other elements not expressly listed or inherent to such process, platform, article, or apparatus / platform.

[0207] Thus far, the technical solutions of the present invention have been described in conjunction with the further embodiments shown in the accompanying drawings. However, it is readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

[0208] The above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention.

Claims

1. A monitoring and maintenance method for a 35kV box-type transformer low-voltage side circuit breaker, characterized in that: include: Set multiple monitoring cycles according to equipment parameters, and set multiple monitoring time nodes, each monitoring time node represents the beginning of a monitoring cycle; Construct a maintenance model for low-voltage circuit breakers based on historical data of low-voltage circuit breakers; Obtain the real-time data of the low-voltage side circuit breaker at the current monitoring time node, and detect the operating failure risk of the equipment based on the low-voltage side circuit breaker maintenance model; Determine whether to perform maintenance based on the detection results of the current monitoring time node.

2. The monitoring and maintenance method for the low-voltage side circuit breaker of a 35kV box-type transformer according to claim 1 is characterized in that: The setting of multiple monitoring cycles includes: Get the parameter information P of the equipment to be repaired, P = [P1, P2…P i …P m ]; Among them, P i 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 repaired, a first-level evaluation model for the low-voltage side circuit breaker is established; Generate the health status evaluation value of the current equipment through the first-level evaluation model of the low-voltage side circuit breaker; Set the monitoring cycle duration based on the current device health status evaluation value.

3. The monitoring and maintenance method for the low-voltage side circuit breaker of a 35kV box-type transformer according to claim 2 is characterized in that: The establishment of the first-level evaluation model of the low-voltage side circuit breaker includes: Obtain parameter information P of n sets of historical maintenance equipment and construct an n×m sample matrix X. Based on the sample matrix X, construct the covariance matrix Σ[Y ij ]; Among them, Y ij = Cov(X i ,X j ),Y ij Represents the element in the i-th row and j-th column of the covariance matrix; Calculate the eigenvalues ​​λ of the covariance matrix, λ=[λ1,λ2…λ i …λ m ]; λ i 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 equipment to be repaired is determined, R=[R1,R2…R i …R m ]; Based on the contribution value R of each category of parameter information of the equipment to be repaired and the parameter information P of the equipment to be repaired, a primary evaluation model of the low-voltage side circuit breaker is established; A represents the health status evaluation value of the current device.

4. The monitoring and maintenance method for the low-voltage side circuit breaker of a 35kV box-type transformer according to claim 1 is characterized in that: The construction of the low-voltage side circuit breaker maintenance model includes: Obtain historical monitoring data of the circuit breaker, the historical monitoring data includes: historical current data, historical voltage data and historical temperature data; Extract characteristic parameters of historical current data, including: current peak value and current valley value; The peak value of the current is divided into level intervals to obtain the current peak data set IF, IF = [IF1, IF2…IF i …IF n ]; Among them, IF i represents the i-th level power peak interval, and n represents the total number of current peak intervals; The valley value of the current is divided into level intervals to obtain the current valley value data set IG, IG = [IG1, IG2…IG i …IG n ]; Among them, IG i represents the i-th level power valley interval, and n represents the total number of current valley intervals; Based on the characteristic 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, where F = [F1, F2…F i …F n ]; Where Fi represents the i-th type of circuit breaker status event, and n represents the total number of circuit breaker status time; Obtaining voltage history data and temperature history data corresponding to when a circuit breaker status event occurs; extracting data features of the voltage history data and temperature history data; Constructing a first compensation parameter C based on data characteristics of voltage history data and temperature history data; The characteristic parameters of the historical current data are combined with the first compensation parameter C to generate a maintenance model for the low-voltage side circuit breaker.

5. The monitoring and maintenance method for the low-voltage side circuit breaker of a 35kV box-type transformer according to claim 1 is characterized in that: The step of constructing the first compensation parameter C includes: Calculate the change rate of voltage history data and the change rate of temperature history data; The voltage history data change rate and the temperature history data change rate are classified into grades; each grade generates an evaluation value; Generate a historical change rate evaluation value DV of voltage and a historical change rate evaluation value DT of temperature within a sampling interval; C = k1*DV+k2*DT; Among them, k1 is the historical change rate evaluation value weight of voltage, and k2 is the historical change rate evaluation value weight of temperature.

6. The monitoring and maintenance method for the low-voltage side circuit breaker of a 35kV box-type transformer according to claim 5 is characterized in that: The detection of the risk of equipment operation failure includes: Obtain real-time data of the low-voltage side circuit breaker of the current monitoring node, including current data, voltage data and temperature data; Based on the low-voltage side circuit breaker maintenance model, generate the low-voltage side circuit breaker operation status evaluation value of the current monitoring node, and judge whether there is a fault at present based on the operation status evaluation value; If there is a fault, a first-level control instruction is generated to identify the type of fault that occurred; If there is no fault, a secondary control instruction is generated to predict the probability of a fault occurring.

7. The monitoring and maintenance method for the low-voltage side circuit breaker of a 35kV box-type transformer according to claim 6 is characterized in that: The generating of the fault prediction instruction comprises: Divide the time window m within the monitoring information sampling period, and count the number of occurrences and frequency of the current valley value and the number of occurrences and frequency of the current peak value in each time window; And combined with the first compensation parameter C, a fault prediction score M is generated; Control the movement of the time window based on the fault prediction score M; Generate the fault prediction score M change value of the entire sampling period; Based on the change value of the fault prediction score M, the emergency situation of the fault is determined.

8. The monitoring and maintenance method for the low-voltage side circuit breaker of a 35kV box-type transformer according to claim 7 is characterized in that: The generating of the fault prediction score M comprises: Get the current peak data set IF, IF = [IF1, IF2…IF i …IF n ]; M=n1*IF i +n2*IG i +C; Among them, IF i Indicates the i-th level power valley interval, IG i represents the i-th level power valley interval, n1 represents the number of times the i-th level power peak interval occurs, and n2 represents the number of times the i-th level power valley interval occurs.

9. The monitoring and maintenance method for the low-voltage side circuit breaker of a 35kV box-type transformer according to claim 8 is characterized in that: The control of the time window movement based on the fault prediction score M includes: Calculate the fault prediction score M within a time window; After obtaining the fault prediction score M in the current time window, the control time window is shifted right by m steps, where each step is a sampling moment; According to the fault prediction score M, a multi-level threshold is generated, and the value of m is controlled based on the multi-level threshold; the fault prediction score M is positively correlated with the number of steps of the time window rightward shift.

Images