Device and method for converting 35kV incoming line circuit into power supply circuit of transformer substation

Abstract

The invention relates to a substation 35kV incoming line power supply switching device and method, and belongs to the technical field of power supply switching. The substation 35kV incoming line power supply switching device comprises a circuit breaker installed on a bearing trolley and a terminal box installed on the front side of the bearing trolley. The circuit breaker is connected with a 35kV incoming line power supply and a main transformer of a transformer substation, an intelligent controller is installed in the terminal box, and the intelligent controller is connected with the circuit breaker and an in-station protection system through the terminal box. The power supply switching method comprises the steps of a preparation stage, equipment isolation and maintenance, power supply line switching, monitoring operation, equipment maintenance, maintenance completion, original power supply state recovery and the like. An operator can monitor parameters such as current and voltage of a power supply line in real time through the intelligent controller, and stable power supply in the whole power supply conversion process is ensured. The intelligent controller is further integrated with a data acquisition unit which can acquire operation data such as current, voltage, temperature, pressure and vibration in real time, and machine learning and a deep learning model are adopted for data analysis and prediction.

Description

Technical Field

[0001] The present invention relates to the technical field of power transfer, and in particular to a 35kV incoming line power transfer device and method for a transformer substation. Background Art

[0002] In the process of ensuring the healthy and stable operation of power equipment, periodic maintenance is crucial for substation equipment. These maintenance works cover multiple links such as inspection, testing, maintenance and repair, and usually require the equipment to be shut down and converted to maintenance status. However, due to the dual factors of power supply reliability and the limited number of users during power outages, the implementation of power outages has become increasingly difficult.

[0003] Taking the region as an example, many 35kV substations still use single incoming line or single busbar power supply, which makes equipment maintenance more challenging. In addition, the 10kV line is also affected by many factors in terms of power transfer and cannot be fully transferred. In this case, two main power supply guarantee technologies are provided for equipment maintenance needs:

[0004] Power supply by high-power generator trucks: This technology uses high-power generator trucks to directly supply power to 10kV lines and end users. Although this method can solve the power supply problem during power outages and maintenance to a certain extent, it has some obvious disadvantages. First, the load capacity of high-power generator trucks is limited and it is difficult to meet the power needs of all users; secondly, due to its high fuel consumption and relatively high operating costs, it may increase the operating burden of power companies in long-term use.

[0005] Power supply from mobile substations: Another solution is to use mobile substations for power transfer. This method can improve the flexibility of power supply to a certain extent, but it also has its limitations. First, the length of the mobile substation can reach 17 meters, which limits its ability to pass through some narrow or traffic-congested areas; second, each time a mobile substation is connected and put into operation, a full set of inspections is required to ensure the safety and reliability of the equipment, which is not only time-consuming and labor-intensive, but also further increases the complexity of the maintenance process.

[0006] In summary, although there have been some explorations in the technology of power supply guarantee during equipment maintenance, its convenience and economy of operation still need to be considered to ensure the healthy operation of the equipment and the electricity demand of users. Summary of the invention

[0007] In order to solve the above problems, the present invention provides a 35kV incoming line power transfer device and method for a substation, which utilizes the smallest unit equipment to isolate the equipment that needs to be repaired to achieve the power transfer effect.

[0008] The technical solution adopted by the present invention is:

[0009] A 35kV incoming line power transfer device for a substation, comprising a carrying trolley, a circuit breaker installed on the carrying trolley, and a terminal box installed on the front side of the carrying trolley; the circuit breaker is connected to a 35kV incoming power supply and a main transformer of the substation, an intelligent controller is installed in the terminal box, and the intelligent controller is connected to the circuit breaker and a protection system in the station through the terminal box.

[0010] Furthermore, the circuit breaker includes a box body, an operating mechanism located in the box body, three groups of integrated sealed poles located on the upper part of the box body and electrically connected to the operating mechanism, and current transformers installed on the three groups of integrated sealed poles; the three groups of integrated sealed poles are provided with high-voltage input terminals and high-voltage output terminals, and the outside of the box body is also provided with a closing and opening operating handle and an energy storage handle connected to the operating mechanism.

[0011] A method for transferring power supply of a 35kV incoming line of a substation, the method for transferring power supply is based on the above-mentioned 35kV incoming line of a substation and comprises the following steps:

[0012] Step 1, preparation phase: confirm the equipment to be repaired and the corresponding lines; evaluate the load and operating status of the power supply lines to ensure that there will be no power outage during the power supply transfer process;

[0013] Step 2, Isolate the equipment to be repaired: Use the opening function of the circuit breaker to send out an opening signal to isolate the equipment to be repaired from the main power supply line; confirm that the opening operation is successful to ensure that the maintenance area is safe and without electricity;

[0014] Step 3, switch the power supply line: On the power supply line that needs to be switched, use the intelligent controller to perform the closing operation through on-site operation or remote control; send a closing signal to ensure that the circuit breaker is closed normally and connected to the backup power supply line;

[0015] Step 4, monitoring operation: confirm that the reconnected line is in good condition, monitor the current and voltage operating parameters through the intelligent controller; use the communication interface to feed back the information to the protection system in the station and monitor the operation effect in real time;

[0016] Step 5, equipment maintenance: In an isolated state, conduct detailed inspection and maintenance of the equipment to be repaired; according to the maintenance plan, perform equipment replacement, overhaul or maintenance operations;

[0017] Step 6, complete the maintenance: After the maintenance is completed, check all equipment and lines to ensure that they are in normal working condition; reconnect the equipment to be repaired to the main power supply line;

[0018] Step 7, restore the original power supply status: send a trip signal, use the circuit breaker's trip solenoid operation or manual method to isolate the backup power supply line and switch back to the main power supply line; perform a closing operation to ensure that everything is restored to a normal power supply state.

[0019] Furthermore, the intelligent controller is connected to a data acquisition unit, which includes three groups of current transformers integrated on the sealed poles, and voltage sensors, temperature sensors, pressure sensors, and vibration sensors for real-time collection of operating data in the station protection system; the intelligent controller uses an embedded database to store historical data to provide support for predictive analysis. Its high-performance embedded computing chip runs machine learning and deep learning models, supports GPRS, 4G / 5G, and NB-IoT communication methods, and remotely transmits and monitors data with the station protection system. It can also judge the equipment status in real time during the power transfer process, triggering local sound and light alarms or remote alarm signals.

[0020] Furthermore, the process of real-time prediction and alarm by the intelligent controller includes the following steps:

[0021] Step 1, data acquisition and preprocessing: The data acquisition unit collects the following parameters in real time through sensors, including: current signal I(t), voltage signal V(t), temperature parameter T(t), pressure parameter P(t), vibration parameter a(t), number of switch operations N op , Closing duration t close , and the opening response time t open ;

[0022] Perform data preprocessing and use sliding window filtering to eliminate noise; normalize the preprocessed data for subsequent analysis;

[0023] Step 2, feature extraction: calculate time domain features, including mean, variance, and skewness; extract the main frequency component through Fourier transform; use wavelet transform to obtain local features of the signal;

[0024] Step 3: Establish and train the fault prediction model: Use the traditional machine learning model and input the feature matrix; use the cross entropy loss function to calculate the loss of the classification problem; use the historical fault data set to train the model and optimize the hyperparameters;

[0025] Step 4, real-time prediction and alarm: input the collected features into the prediction model to calculate the fault probability; compare the set fault threshold with the fault probability, and trigger an alarm when the fault probability is greater than the fault threshold; the intelligent controller sends the alarm information to the protection system in the station.

[0026] Furthermore, in step 1, the calculation formula for eliminating noise using sliding window filtering is as follows:

[0027]

[0028] Where, X filtered (t) represents the data value after filtering at time point t; w is the window size; tw / 2 is the starting position of the window; t+w / 2 is the ending position of the window; X(i) represents the value of the data point in the original data sequence at time i;

[0029] In step 1, the calculation formula for normalizing the preprocessed data is as follows:

[0030]

[0031] Where, X norm (t) represents the normalized data value at time point t; X(t) represents the value of the original data sequence at time t; μ and σ are the mean and standard deviation of the historical data, respectively.

[0032] Furthermore, in step 2, the calculation formula of the mean is as follows:

[0033]

[0034] In the formula, μ represents the mean; N represents the total number of data points in the data set, that is, the sample size; X(i) represents the value of the data point in the original data sequence at time i;

[0035] The formula for calculating variance is as follows:

[0036]

[0037] In the formula, σ 2 represents variance; N represents the total number of data points in the data set, that is, the sample size; X(i) represents the value of the data point in the original data sequence at time i; μ represents the mean;

[0038] The calculation formula for skewness is as follows:

[0039]

[0040] In the formula, Skewness represents skewness; N represents the total number of data points in the data set, that is, the sample size; X(i) represents the value of the data point in the original data sequence at time i; μ represents the mean; σ represents the standard deviation of the data set;

[0041] The calculation formula for extracting the main frequency component through Fourier transform is as follows:

[0042]

[0043] In the formula, F(ω) represents the result after Fourier transform; ω is the angular frequency; X(t) represents the value of the original data sequence at time t; e is the base of the natural logarithm; j is the imaginary unit; ωt represents the product of angular frequency and time; dt represents the differential element, which represents the process of integrating over time t;

[0044] The calculation formula for obtaining the local characteristics of the signal using wavelet transform is as follows:

[0045]

[0046] Where WT(τ,s) represents the result of wavelet transform; X(t) represents the value of the original data sequence at time t; ψ is the wavelet basis function; t is the time variable; τ is the time displacement; s is the scale; dt represents the differential element, which represents the process of integrating over time t.

[0047] Furthermore, in step 3, the input feature matrix is:

[0048] X=[μ,σ,Skewness,F(ω),WT(τ,s)]

[0049] Where X is the feature matrix; μ represents the mean; σ represents the standard deviation of the data set; Skewness represents the skewness; F(ω) represents the result after Fourier transform; WT(τ,s) represents the result of wavelet transform;

[0050] The cross entropy loss function calculation formula is as follows:

[0051]

[0052] In the formula, L represents the cross entropy loss value; N represents the total number of data points in the data set, that is, the sample size; y i is the actual label of the i-th sample; y i is the predicted value of the model for the i-th sample.

[0053] Furthermore, in step 4, the calculation formula of the failure probability is as follows:

[0054] Pf=f(X)=P(y=1|X)

[0055] Where Pf is the failure probability; f(X) represents a function that accepts input X and outputs the failure probability; P(y=1|X) represents the conditional probability of failure y=1 given the feature set X; y is a binary output variable; and X is the input feature set.

[0056] The beneficial effects of the substation 35kV incoming line power supply device and method are mainly reflected in the following aspects:

[0057] 1. Improve power supply reliability: The device and method can quickly switch power supply lines when equipment needs to be repaired to ensure uninterrupted power supply, greatly improving the reliability and continuity of power supply in substations. This is crucial to ensure the stable operation of the power grid.

[0058] 2. Improve operational safety: Through the effective cooperation of intelligent controllers and circuit breakers, the equipment status can be monitored and fed back in real time when isolating the equipment to be repaired, ensuring the safety of the maintenance area. Operators can control remotely or on-site, reducing the risk of operational errors.

[0059] 3. Realize intelligent monitoring: The intelligent controller can monitor current, voltage, temperature, pressure, vibration and other parameters in real time through the data acquisition unit, providing real-time data support for the health status of the equipment. At the same time, the embedded database stores historical data, which is helpful for predictive analysis and risk assessment of equipment status.

[0060] 4. Reduce labor costs and operational complexity: The intelligent control of the device reduces the reliance on manual operation, and operators can easily complete line conversion and equipment monitoring through the interface. This not only reduces labor costs, but also improves operational efficiency.

[0061] 5. Promote equipment maintenance optimization: Through the analysis of operating data and the accumulation of historical records, the operating status of the equipment can be effectively evaluated, thereby optimizing the maintenance plan, improving the service life and reliability of the equipment, and reducing the failure rate.

[0062] 6. Support modern communication technology: Intelligent controllers support a variety of modern communication methods, making remote data transmission and monitoring possible. This ensures that the data of the equipment can be obtained at any time and potential problems can be responded to in a timely manner.

[0063] 7. Improve emergency response capabilities: In the event of an emergency, the intelligent controller can respond quickly and quickly switch power supply lines through automated control, effectively improving emergency response capabilities and reducing accident risks.

[0064] In summary, the 35kV incoming line power supply transfer device and method of the substation not only achieved technical innovation, but also improved the operational efficiency and safety of the substation from multiple aspects such as safety, intelligence, and economy. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0066] Figure 1This is a schematic diagram of the overall structure of the 35kV incoming line power supply transfer device of the substation of the present invention;

[0067] Figure 2 It is a schematic structural diagram of the circuit breaker of the present invention;

[0068] Figure 3 This is a flow chart of the power supply transfer method for the 35kV incoming line of a substation of the present invention;

[0069] Figure 4 This is a flow chart of the present invention's real-time prediction and alarm of the power transfer process based on the intelligent controller;

[0070] In the figure, 1 is a carrying trolley; 2 is a circuit breaker; 3 is a terminal box; 4 is an integrated sealed pole; 5 is a high voltage input terminal; 6 is a high voltage output terminal; 7 is a box; 8 is a current transformer; 9 is a closing and opening operating handle; 10 is an energy storage handle; 11 is a vacuum arc extinguishing chamber. DETAILED DESCRIPTION

[0071] The following will be combined with the drawings of the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without creative work are within the scope of protection of the present invention.

[0072] Example 1

[0073] This embodiment provides a 35kV incoming line power supply device for a substation, such as Figure 1 As shown, the 35kV incoming line power supply device of the substation includes a carrying trolley 1, a circuit breaker 2 installed on the carrying trolley 1, and a terminal box 3 installed on the front side of the carrying trolley 1. The circuit breaker 2 can be connected to the 35kV incoming power supply and the main transformer of the substation; an intelligent controller is installed in the terminal box 3, and the intelligent controller can adopt the Schneider MT16N1 Micrologic 2.0 intelligent controller, and the intelligent controller is connected to the circuit breaker 2 and the protection system in the station through the terminal box 3.

[0074] Further, such as Figure 2As shown, the circuit breaker 2 in this embodiment includes a box body 7, an operating mechanism located in the box body 7, three sets of integrated sealed poles 4 located on the upper part of the box body 7 and electrically connected to the operating mechanism, and a current transformer 8 installed on the three sets of integrated sealed poles 4; the three sets of integrated sealed poles 4 are provided with a high-voltage input terminal 5 and a high-voltage output terminal 6, and the outside of the box body 7 is also provided with a closing and opening operating handle 9 and an energy storage handle connected to the operating mechanism. The circuit breaker 2 is of miniaturized design, and the outer shell is made of high-quality steel box. The current transformer 8 can be selected according to user needs. The circuit breaker 2 is combined with a matching intelligent controller to realize the opening and closing operations of the switch on-site, and can also be remotely controlled through a communication interface. Other information of the circuit breaker 2 can also be transmitted to the protection system within the station.

[0075] The sealed pole of the circuit breaker adopts a vacuum arc extinguishing chamber 11, which uses vacuum as the arc extinguishing and insulating medium and has an extremely high vacuum degree. When the moving and static contacts are energized and opened under the action of the operating mechanism, a vacuum arc will be generated between the contacts. At the same time, due to the special structure of the contacts, an appropriate longitudinal magnetic field will be generated in the gap between the contacts, which will cause the vacuum arc to remain diffuse and evenly distribute the arc on the contact surface to burn, maintaining a low arc voltage. When the current naturally passes through zero, the residual ions, electrons and metal vapors can be compounded or condensed on the contact surface and the shielding cover within a microsecond. The dielectric insulation strength of the arc extinguishing chamber break is quickly restored, so that the arc is extinguished to achieve the purpose of breaking. Since the longitudinal magnetic field is used to control the vacuum arc, the vacuum circuit breaker has a strong and stable current breaking capacity.

[0076] The motor in the operating mechanism applies the output torque to the pinion of the mechanism, which is then transmitted to the large sprocket on the main shaft, thereby driving the crank arm to rotate and storing energy in the closing spring. When the screw on the crank arm presses down the travel switch, the power supply to the motor is cut off and the spring is electrically charged. The energy storage handle connected to the operating mechanism transmits the rotational torque to the large gear that is fully meshed with the pinion through the pinion on the output shaft, thereby driving the crank arm to rotate and manually storing energy in the closing spring.

[0077] After the operating mechanism receives the closing signal, the moving iron core of the closing electromagnet moves upward, pushing the closing trip rod upward, causing the closing half shaft to rotate counterclockwise. The constraint on the closing latch is released. At the same time, the closing latch rotates counterclockwise due to the pressure of the roller, releasing the energy storage maintenance. The cam on the main shaft generates an impact force due to the contraction force of the closing spring, hitting the rocker arm on the manual energy storage shaft (i.e., the output shaft), and is transmitted to the switch through the connecting rod, thereby completing the closing operation. The closing and opening operating handle connected to the operating mechanism can drive the shift fork on the closing half shaft to rotate counterclockwise, driving the closing half shaft to rotate counterclockwise, thereby producing the same effect as the closing electromagnet operation.

[0078] After the operating mechanism receives the opening signal, the moving iron core of the opening electromagnet moves upward, pushing the opening trip rod to move upward, causing the opening half shaft to rotate counterclockwise, releasing the constraint on the opening latch. At the same time, the opening latch rotates counterclockwise due to the pressure of the roller, and the rocker arm rotates counterclockwise due to the thrust of the opening spring inside the switch, thus completing the opening operation. The closing and opening operating handle connected to the operating mechanism can drive the fork on the opening half shaft to rotate counterclockwise, driving the opening half shaft to rotate counterclockwise, thereby producing the same effect as the opening electromagnet operation.

[0079] Through the 35kV incoming line power transfer device of the substation, when the 35kV equipment needs to be shut down for operation, the incoming power directly enters the main transformer of the substation through this device, and the 35kV equipment is separated from the power grid, thereby realizing the power outage. For a single-incoming substation, the 35kV equipment can be shut down after the power transfer; for a single-busbar power supply substation, the incoming line can be directly connected to the main transformer, and the busbar can be vacated for maintenance; through one withdrawal and one input, non-sensing switching can be achieved; through the intelligent controller to adjust the set value, 10kV line power transfer can be achieved. This device is mainly used in medium-voltage overhead line power grids for the purpose of dividing and combining load current, overload current, and short-circuit current; it has extremely high reliability, is completely maintenance-free throughout its life, has high mechanical and electrical life, is small in size, light in weight, and easy to install.

[0080] Further based on the substation 35kV incoming line power supply transfer device, this embodiment also proposes a substation 35kV incoming line power supply transfer method, such as Figure 3 As shown, the specific steps include:

[0081] Step 1, preparation phase: confirm the equipment to be repaired and the corresponding lines; evaluate the load and operating status of the power supply lines to ensure that there will be no power outage during the power supply transfer process;

[0082] Step 2, Isolate the equipment to be repaired: Use the opening function of the circuit breaker to send out an opening signal to isolate the equipment to be repaired from the main power supply line; confirm that the opening operation is successful to ensure that the maintenance area is safe and without electricity;

[0083] Step 3, switch the power supply line: On the power supply line that needs to be switched, use the intelligent controller to perform the closing operation through on-site operation or remote control; send a closing signal to ensure that the circuit breaker is closed normally and connected to the backup power supply line;

[0084] Step 4, monitoring operation: confirm that the reconnected line is in good condition, monitor the current and voltage operating parameters through the intelligent controller; use the communication interface to feed back the information to the protection system in the station and monitor the operation effect in real time;

[0085] Step 5, equipment maintenance: In an isolated state, conduct detailed inspection and maintenance of the equipment to be repaired; according to the maintenance plan, perform equipment replacement, overhaul or maintenance operations;

[0086] Step 6, complete the maintenance: After the maintenance is completed, check all equipment and lines to ensure that they are in normal working condition; reconnect the equipment to be repaired to the main power supply line;

[0087] Step 7, restore the original power supply status: send a trip signal, use the circuit breaker's trip solenoid operation or manual method to isolate the backup power supply line and switch back to the main power supply line; perform a closing operation to ensure that everything is restored to a normal power supply state.

[0088] Example 2

[0089] On the basis of Example 1, it is further improved; specifically, the intelligent controller in this embodiment is connected to a data acquisition unit; the data acquisition unit includes three sets of current transformers integrated on the sealed poles, and voltage sensors, temperature sensors, pressure sensors, and vibration sensors for real-time collection of operating data in the station protection system. The intelligent controller uses an embedded database to store historical data to provide support for predictive analysis. The intelligent controller has built-in high-performance embedded computing chips such as the ARM Cortex A series to run machine learning and deep learning models. The intelligent controller supports GPRS, 4G / 5G, and NB-IoT communication methods, remote data transmission and monitoring with the station protection system, and real-time judgment of the equipment status during the power transfer process, triggering local sound and light alarms or remote alarm signals.

[0090] Based on the intelligent controller, the above-mentioned power transfer process can be predicted and warned in real time, such as Figure 4 As shown in the figure, the real-time prediction and warning process includes the following steps:

[0091] Step 1, data acquisition and preprocessing: The data acquisition unit collects the following parameters in real time through sensors, including: current signal I(t), voltage signal V(t), temperature parameter T(t), pressure parameter P(t), vibration parameter a(t), number of switch operations N op , Closing duration t close , and the opening response time t open ;

[0092] Perform data preprocessing and use sliding window filtering to eliminate noise;

[0093]

[0094] Where, X filtered(t) represents the data value after filtering at time point t; w is the window size; tw / 2 is the starting position of the window; t+w / 2 is the ending position of the window; X(i) represents the value of the data point in the original data sequence at time i.

[0095] Normalize the preprocessed data for subsequent analysis;

[0096]

[0097] Where, X norm (t) represents the normalized data value at time point t; X(t) represents the value of the original data sequence at time t; μ and σ are the mean and standard deviation of the historical data, respectively.

[0098] Step 2, feature extraction: calculate time domain features, including mean, variance, and skewness;

[0099] The mean is calculated as follows:

[0100]

[0101] In the formula, μ represents the mean; N represents the total number of data points in the data set, that is, the sample size; X(i) represents the value of the data point in the original data sequence at time i.

[0102] The formula for calculating variance is as follows:

[0103]

[0104] In the formula, σ 2 represents variance; N represents the total number of data points in the data set, that is, the sample size; X(i) represents the value of the data point in the original data sequence at time i; μ represents the mean.

[0105] The calculation formula for skewness is as follows:

[0106]

[0107] In the formula, Skewness represents skewness; N represents the total number of data points in the data set, that is, the sample size; X(i) represents the value of the data point in the original data sequence at time i; μ represents the mean; σ represents the standard deviation of the data set.

[0108] Extract the main frequency component through Fourier transform;

[0109]

[0110] Wherein, F(ω) represents the result after Fourier transform; ω is the angular frequency; X(t) represents the value of the original data sequence at time t; e is the base of the natural logarithm; j is the imaginary unit; ωt represents the product of angular frequency and time; dt represents the differential element, which represents the process of integrating over time t.

[0111] Use wavelet transform to obtain local features of the signal;

[0112]

[0113] Where WT(τ,s) represents the result of wavelet transform; X(t) represents the value of the original data sequence at time t; ψ is the wavelet basis function; t is the time variable; τ is the time displacement; s is the scale; dt represents the differential element, which represents the process of integrating over time t.

[0114] Step 3: Establishment and training of fault prediction model:

[0115] Model selection: Use traditional machine learning models such as random forest and SVM; random forest is an ensemble learning method based on decision trees, which can build multiple decision tree models on training data and obtain the final prediction results by voting. It has good robustness. SVM is suitable for binary classification tasks, which separates data by finding a hyperplane that maximizes the interval, and is particularly suitable for high-dimensional and small sample data.

[0116] Input feature matrix:

[0117] X=[μ,σ,Skewness,F(ω),WT(τ,s)]

[0118] Where X is the feature matrix; μ represents the mean; σ represents the standard deviation of the data set; Skewness represents the skewness; F(ω) represents the result after Fourier transform; WT(τ,s) represents the result of wavelet transform.

[0119] Use the cross entropy loss function to calculate the loss for classification problems;

[0120] The cross entropy loss function calculation formula is as follows:

[0121]

[0122] In the formula, L represents the cross entropy loss value; N represents the total number of data points in the data set, that is, the sample size; y i is the actual label of the i-th sample; y i is the predicted value of the model for the i-th sample.

[0123] Use historical failure datasets to train the model and optimize hyperparameters such as learning rate and regularization parameters.

[0124] Step 4: Real-time prediction and warning:

[0125] The collected features are input into the prediction model to calculate the probability of failure;

[0126] The failure probability is calculated as follows:

[0127] Pf=f(X)=P(y=1|X)

[0128] Where Pf is the failure probability; f(X) represents a function that accepts input X and outputs the failure probability; P(y=1|X) represents the conditional probability of failure y=1 given the feature set X; y is a binary output variable; and X is the input feature set.

[0129] A fault threshold α is set in the intelligent controller, and α is 0.8; the set fault threshold Pf is compared with the fault probability threshold α; when the fault probability is greater than the fault threshold, that is, Pf>α, an alarm is triggered; the intelligent controller sends an alarm message to the protection system in the station.

[0130] Obviously, many modifications and changes can be made according to the content of this specification. This specification selects and describes these embodiments in detail in order to better explain the principles and practical applications of the present invention, so that those skilled in the art can understand and use the present invention well. The present invention is limited only by the claims and their full scope and equivalents.

Claims

1. A 35kV incoming line power supply device for a substation, characterized in that: The 35kV incoming line power supply device of the substation includes a carrying trolley, a circuit breaker installed on the carrying trolley, and a terminal box installed on the front side of the carrying trolley; the circuit breaker is connected to the 35kV incoming power supply and the main transformer of the substation, and an intelligent controller is installed in the terminal box, which is connected to the circuit breaker and the protection system in the station through the terminal box.

2. The 35kV incoming line power supply device for a substation according to claim 1 is characterized in that: The circuit breaker includes a box body, an operating mechanism located in the box body, three groups of integrated sealed poles located on the upper part of the box body and electrically connected to the operating mechanism, and current transformers installed on the three groups of integrated sealed poles; the three groups of integrated sealed poles are provided with high-voltage input terminals and high-voltage output terminals, and the outside of the box body is also provided with a closing and opening operating handle and an energy storage handle connected to the operating mechanism.

3. A method for transferring power from a 35kV incoming line of a substation, the method for transferring power is based on the 35kV incoming line of a substation according to any one of claims 1 to 2, characterized in that: The following steps are involved: Step 1, preparation phase: confirm the equipment to be repaired and the corresponding lines; evaluate the load and operating status of the power supply lines to ensure that there will be no power outage during the power supply transfer process; Step 2, Isolate the equipment to be repaired: Use the opening function of the circuit breaker to send out an opening signal to isolate the equipment to be repaired from the main power supply line; confirm that the opening operation is successful to ensure that the maintenance area is safe and without electricity; Step 3, switch the power supply line: On the power supply line that needs to be switched, use the intelligent controller to perform the closing operation through on-site operation or remote control; send a closing signal to ensure that the circuit breaker is closed normally and connected to the backup power supply line; Step 4, monitoring operation: confirm that the reconnected line is in good condition, monitor the current and voltage operating parameters through the intelligent controller; use the communication interface to feed back the information to the protection system in the station and monitor the operation effect in real time; Step 5, equipment maintenance: In an isolated state, conduct detailed inspection and maintenance of the equipment to be repaired; according to the maintenance plan, perform equipment replacement, overhaul or maintenance operations; Step 6, complete the maintenance: After the maintenance is completed, check all equipment and lines to ensure that they are in normal working condition; reconnect the equipment to be repaired to the main power supply line; Step 7, restore the original power supply status: send a trip signal, use the circuit breaker's trip solenoid operation or manual method to isolate the backup power supply line and switch back to the main power supply line; perform a closing operation to ensure that everything is restored to a normal power supply state.

4. The method for transferring power supply from a 35kV incoming line of a substation according to claim 3 is characterized in that: The intelligent controller is connected to a data acquisition unit, which includes three groups of current transformers integrated on the sealed poles, and voltage sensors, temperature sensors, pressure sensors, and vibration sensors for real-time collection of operating data in the station protection system; the intelligent controller uses an embedded database to store historical data to provide support for predictive analysis. Its high-performance embedded computing chip runs machine learning and deep learning models, supports GPRS, 4G / 5G, and NB-IoT communication methods, and remotely transmits and monitors data with the station protection system. It also judges the equipment status in real time during the power transfer process, triggering local sound and light alarms or remote alarm signals.

5. The method for transferring power supply from a 35kV incoming line of a substation according to claim 4 is characterized in that: The process of real-time prediction and alarm by the intelligent controller includes the following steps: Step 1, data acquisition and preprocessing: The data acquisition unit collects the following parameters in real time through sensors, including: current signal I(t), voltage signal V(t), temperature parameter T(t), pressure parameter P(t), vibration parameter a(t), number of switch operations N op , Closing duration t close , and the opening response time t open ; Perform data preprocessing and use sliding window filtering to eliminate noise; normalize the preprocessed data for subsequent analysis; Step 2, feature extraction: calculate time domain features, including mean, variance, and skewness; extract the main frequency component through Fourier transform; use wavelet transform to obtain local features of the signal; Step 3: Establish and train the fault prediction model: Use the traditional machine learning model and input the feature matrix; use the cross entropy loss function to calculate the loss of the classification problem; use the historical fault data set to train the model and optimize the hyperparameters; Step 4, real-time prediction and alarm: input the collected features into the prediction model to calculate the fault probability; compare the set fault threshold with the fault probability, and trigger an alarm when the fault probability is greater than the fault threshold; the intelligent controller sends the alarm information to the protection system in the station.

6. The method for transferring power supply from a 35kV incoming line of a substation according to claim 5, characterized in that: In step 1, the calculation formula for eliminating noise using sliding window filtering is as follows: Where, X filtered (t) represents the data value after filtering at time point t; w is the window size; tw / 2 is the starting position of the window; t+w / 2 is the ending position of the window; X(i) represents the value of the data point in the original data sequence at time i; In step 1, the calculation formula for normalizing the preprocessed data is as follows: Where, X norm (t) represents the normalized data value at time point t; X(t) represents the value of the original data sequence at time t; μ and σ are the mean and standard deviation of the historical data, respectively.

7. The method for transferring power supply from a 35kV incoming line of a substation according to claim 5, characterized in that: In step 2, the mean is calculated as follows: In the formula, μ represents the mean; N represents the total number of data points in the data set, that is, the sample size; X(i) represents the value of the data point in the original data sequence at time i; The formula for calculating variance is as follows: In the formula, σ 2 represents variance; N represents the total number of data points in the data set, that is, the sample size; X(i) represents the value of the data point in the original data sequence at time i; μ represents the mean; The calculation formula for skewness is as follows: In the formula, Skewness represents skewness; N represents the total number of data points in the data set, that is, the sample size; X(i) represents the value of the data point in the original data sequence at time i; μ represents the mean; σ represents the standard deviation of the data set; The calculation formula for extracting the main frequency component through Fourier transform is as follows: In the formula, F(ω) represents the result after Fourier transform; ω is the angular frequency; X(t) represents the value of the original data sequence at time t; e is the base of the natural logarithm; j is the imaginary unit; ωt represents the product of angular frequency and time; dt represents the differential element, which represents the process of integrating over time t; The calculation formula for obtaining the local characteristics of the signal using wavelet transform is as follows: Where WT(τ,s) represents the result of wavelet transform; X(t) represents the value of the original data sequence at time t; ψ is the wavelet basis function; t is the time variable; τ is the time displacement; s is the scale; dt represents the differential element, which represents the process of integrating over time t.

8. The method for transferring power supply from a 35kV incoming line of a substation according to claim 7, characterized in that: In step 3, the input feature matrix is: X=[μ,σ,Skewness,F(ω),WT(τ,s)] Where X is the feature matrix; μ represents the mean; σ represents the standard deviation of the data set; Skewness represents the skewness; F(ω) represents the result after Fourier transform; WT(τ,s) represents the result of wavelet transform; The cross entropy loss function calculation formula is as follows: In the formula, L represents the cross entropy loss value; N represents the total number of data points in the data set, that is, the sample size; y i is the actual label of the i-th sample; y i is the predicted value of the model for the i-th sample.

9. The method for transferring power from a 35kV incoming line of a substation according to claim 5, characterized in that: In step 4, the failure probability is calculated as follows: Pf=f(X)=P(y=1X) Where Pf is the failure probability; f(X) represents a function that accepts input X and outputs the failure probability; P(y=1X) represents the conditional probability of failure y=1 given a feature set X; y is a binary output variable; and X is the input feature set.

Images